summaryrefslogtreecommitdiff
path: root/arch/mips/kvm/mmu.c
blob: 6d1f68cf4edfca4a81da207bc1db5ffb2f794d41 (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
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * KVM/MIPS MMU handling in the KVM module.
 *
 * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
 * Authors: Sanjay Lal <sanjayl@kymasys.com>
 */

#include <linux/highmem.h>
#include <linux/kvm_host.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>

/*
 * KVM_MMU_CACHE_MIN_PAGES is the number of GPA page table translation levels
 * for which pages need to be cached.
 */
#if defined(__PAGETABLE_PMD_FOLDED)
#define KVM_MMU_CACHE_MIN_PAGES 1
#else
#define KVM_MMU_CACHE_MIN_PAGES 2
#endif

void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
{
	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
}

/**
 * kvm_pgd_init() - Initialise KVM GPA page directory.
 * @page:	Pointer to page directory (PGD) for KVM GPA.
 *
 * Initialise a KVM GPA page directory with pointers to the invalid table, i.e.
 * representing no mappings. This is similar to pgd_init(), however it
 * initialises all the page directory pointers, not just the ones corresponding
 * to the userland address space (since it is for the guest physical address
 * space rather than a virtual address space).
 */
static void kvm_pgd_init(void *page)
{
	unsigned long *p, *end;
	unsigned long entry;

#ifdef __PAGETABLE_PMD_FOLDED
	entry = (unsigned long)invalid_pte_table;
#else
	entry = (unsigned long)invalid_pmd_table;
#endif

	p = (unsigned long *)page;
	end = p + PTRS_PER_PGD;

	do {
		p[0] = entry;
		p[1] = entry;
		p[2] = entry;
		p[3] = entry;
		p[4] = entry;
		p += 8;
		p[-3] = entry;
		p[-2] = entry;
		p[-1] = entry;
	} while (p != end);
}

/**
 * kvm_pgd_alloc() - Allocate and initialise a KVM GPA page directory.
 *
 * Allocate a blank KVM GPA page directory (PGD) for representing guest physical
 * to host physical page mappings.
 *
 * Returns:	Pointer to new KVM GPA page directory.
 *		NULL on allocation failure.
 */
pgd_t *kvm_pgd_alloc(void)
{
	pgd_t *ret;

	ret = (pgd_t *)__get_free_pages(GFP_KERNEL, PGD_ORDER);
	if (ret)
		kvm_pgd_init(ret);

	return ret;
}

/**
 * kvm_mips_walk_pgd() - Walk page table with optional allocation.
 * @pgd:	Page directory pointer.
 * @addr:	Address to index page table using.
 * @cache:	MMU page cache to allocate new page tables from, or NULL.
 *
 * Walk the page tables pointed to by @pgd to find the PTE corresponding to the
 * address @addr. If page tables don't exist for @addr, they will be created
 * from the MMU cache if @cache is not NULL.
 *
 * Returns:	Pointer to pte_t corresponding to @addr.
 *		NULL if a page table doesn't exist for @addr and !@cache.
 *		NULL if a page table allocation failed.
 */
static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache,
				unsigned long addr)
{
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;

	pgd += pgd_index(addr);
	if (pgd_none(*pgd)) {
		/* Not used on MIPS yet */
		BUG();
		return NULL;
	}
	p4d = p4d_offset(pgd, addr);
	pud = pud_offset(p4d, addr);
	if (pud_none(*pud)) {
		pmd_t *new_pmd;

		if (!cache)
			return NULL;
		new_pmd = kvm_mmu_memory_cache_alloc(cache);
		pmd_init((unsigned long)new_pmd,
			 (unsigned long)invalid_pte_table);
		pud_populate(NULL, pud, new_pmd);
	}
	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd)) {
		pte_t *new_pte;

		if (!cache)
			return NULL;
		new_pte = kvm_mmu_memory_cache_alloc(cache);
		clear_page(new_pte);
		pmd_populate_kernel(NULL, pmd, new_pte);
	}
	return pte_offset_kernel(pmd, addr);
}

/* Caller must hold kvm->mm_lock */
static pte_t *kvm_mips_pte_for_gpa(struct kvm *kvm,
				   struct kvm_mmu_memory_cache *cache,
				   unsigned long addr)
{
	return kvm_mips_walk_pgd(kvm->arch.gpa_mm.pgd, cache, addr);
}

/*
 * kvm_mips_flush_gpa_{pte,pmd,pud,pgd,pt}.
 * Flush a range of guest physical address space from the VM's GPA page tables.
 */

static bool kvm_mips_flush_gpa_pte(pte_t *pte, unsigned long start_gpa,
				   unsigned long end_gpa)
{
	int i_min = pte_index(start_gpa);
	int i_max = pte_index(end_gpa);
	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PTE - 1);
	int i;

	for (i = i_min; i <= i_max; ++i) {
		if (!pte_present(pte[i]))
			continue;

		set_pte(pte + i, __pte(0));
	}
	return safe_to_remove;
}

static bool kvm_mips_flush_gpa_pmd(pmd_t *pmd, unsigned long start_gpa,
				   unsigned long end_gpa)
{
	pte_t *pte;
	unsigned long end = ~0ul;
	int i_min = pmd_index(start_gpa);
	int i_max = pmd_index(end_gpa);
	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PMD - 1);
	int i;

	for (i = i_min; i <= i_max; ++i, start_gpa = 0) {
		if (!pmd_present(pmd[i]))
			continue;

		pte = pte_offset_kernel(pmd + i, 0);
		if (i == i_max)
			end = end_gpa;

		if (kvm_mips_flush_gpa_pte(pte, start_gpa, end)) {
			pmd_clear(pmd + i);
			pte_free_kernel(NULL, pte);
		} else {
			safe_to_remove = false;
		}
	}
	return safe_to_remove;
}

static bool kvm_mips_flush_gpa_pud(pud_t *pud, unsigned long start_gpa,
				   unsigned long end_gpa)
{
	pmd_t *pmd;
	unsigned long end = ~0ul;
	int i_min = pud_index(start_gpa);
	int i_max = pud_index(end_gpa);
	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PUD - 1);
	int i;

	for (i = i_min; i <= i_max; ++i, start_gpa = 0) {
		if (!pud_present(pud[i]))
			continue;

		pmd = pmd_offset(pud + i, 0);
		if (i == i_max)
			end = end_gpa;

		if (kvm_mips_flush_gpa_pmd(pmd, start_gpa, end)) {
			pud_clear(pud + i);
			pmd_free(NULL, pmd);
		} else {
			safe_to_remove = false;
		}
	}
	return safe_to_remove;
}

static bool kvm_mips_flush_gpa_pgd(pgd_t *pgd, unsigned long start_gpa,
				   unsigned long end_gpa)
{
	p4d_t *p4d;
	pud_t *pud;
	unsigned long end = ~0ul;
	int i_min = pgd_index(start_gpa);
	int i_max = pgd_index(end_gpa);
	bool safe_to_remove = (i_min == 0 && i_max == PTRS_PER_PGD - 1);
	int i;

	for (i = i_min; i <= i_max; ++i, start_gpa = 0) {
		if (!pgd_present(pgd[i]))
			continue;

		p4d = p4d_offset(pgd, 0);
		pud = pud_offset(p4d + i, 0);
		if (i == i_max)
			end = end_gpa;

		if (kvm_mips_flush_gpa_pud(pud, start_gpa, end)) {
			pgd_clear(pgd + i);
			pud_free(NULL, pud);
		} else {
			safe_to_remove = false;
		}
	}
	return safe_to_remove;
}

/**
 * kvm_mips_flush_gpa_pt() - Flush a range of guest physical addresses.
 * @kvm:	KVM pointer.
 * @start_gfn:	Guest frame number of first page in GPA range to flush.
 * @end_gfn:	Guest frame number of last page in GPA range to flush.
 *
 * Flushes a range of GPA mappings from the GPA page tables.
 *
 * The caller must hold the @kvm->mmu_lock spinlock.
 *
 * Returns:	Whether its safe to remove the top level page directory because
 *		all lower levels have been removed.
 */
bool kvm_mips_flush_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn)
{
	return kvm_mips_flush_gpa_pgd(kvm->arch.gpa_mm.pgd,
				      start_gfn << PAGE_SHIFT,
				      end_gfn << PAGE_SHIFT);
}

#define BUILD_PTE_RANGE_OP(name, op)					\
static int kvm_mips_##name##_pte(pte_t *pte, unsigned long start,	\
				 unsigned long end)			\
{									\
	int ret = 0;							\
	int i_min = pte_index(start);				\
	int i_max = pte_index(end);					\
	int i;								\
	pte_t old, new;							\
									\
	for (i = i_min; i <= i_max; ++i) {				\
		if (!pte_present(pte[i]))				\
			continue;					\
									\
		old = pte[i];						\
		new = op(old);						\
		if (pte_val(new) == pte_val(old))			\
			continue;					\
		set_pte(pte + i, new);					\
		ret = 1;						\
	}								\
	return ret;							\
}									\
									\
/* returns true if anything was done */					\
static int kvm_mips_##name##_pmd(pmd_t *pmd, unsigned long start,	\
				 unsigned long end)			\
{									\
	int ret = 0;							\
	pte_t *pte;							\
	unsigned long cur_end = ~0ul;					\
	int i_min = pmd_index(start);				\
	int i_max = pmd_index(end);					\
	int i;								\
									\
	for (i = i_min; i <= i_max; ++i, start = 0) {			\
		if (!pmd_present(pmd[i]))				\
			continue;					\
									\
		pte = pte_offset_kernel(pmd + i, 0);				\
		if (i == i_max)						\
			cur_end = end;					\
									\
		ret |= kvm_mips_##name##_pte(pte, start, cur_end);	\
	}								\
	return ret;							\
}									\
									\
static int kvm_mips_##name##_pud(pud_t *pud, unsigned long start,	\
				 unsigned long end)			\
{									\
	int ret = 0;							\
	pmd_t *pmd;							\
	unsigned long cur_end = ~0ul;					\
	int i_min = pud_index(start);				\
	int i_max = pud_index(end);					\
	int i;								\
									\
	for (i = i_min; i <= i_max; ++i, start = 0) {			\
		if (!pud_present(pud[i]))				\
			continue;					\
									\
		pmd = pmd_offset(pud + i, 0);				\
		if (i == i_max)						\
			cur_end = end;					\
									\
		ret |= kvm_mips_##name##_pmd(pmd, start, cur_end);	\
	}								\
	return ret;							\
}									\
									\
static int kvm_mips_##name##_pgd(pgd_t *pgd, unsigned long start,	\
				 unsigned long end)			\
{									\
	int ret = 0;							\
	p4d_t *p4d;							\
	pud_t *pud;							\
	unsigned long cur_end = ~0ul;					\
	int i_min = pgd_index(start);					\
	int i_max = pgd_index(end);					\
	int i;								\
									\
	for (i = i_min; i <= i_max; ++i, start = 0) {			\
		if (!pgd_present(pgd[i]))				\
			continue;					\
									\
		p4d = p4d_offset(pgd, 0);				\
		pud = pud_offset(p4d + i, 0);				\
		if (i == i_max)						\
			cur_end = end;					\
									\
		ret |= kvm_mips_##name##_pud(pud, start, cur_end);	\
	}								\
	return ret;							\
}

/*
 * kvm_mips_mkclean_gpa_pt.
 * Mark a range of guest physical address space clean (writes fault) in the VM's
 * GPA page table to allow dirty page tracking.
 */

BUILD_PTE_RANGE_OP(mkclean, pte_mkclean)

/**
 * kvm_mips_mkclean_gpa_pt() - Make a range of guest physical addresses clean.
 * @kvm:	KVM pointer.
 * @start_gfn:	Guest frame number of first page in GPA range to flush.
 * @end_gfn:	Guest frame number of last page in GPA range to flush.
 *
 * Make a range of GPA mappings clean so that guest writes will fault and
 * trigger dirty page logging.
 *
 * The caller must hold the @kvm->mmu_lock spinlock.
 *
 * Returns:	Whether any GPA mappings were modified, which would require
 *		derived mappings (GVA page tables & TLB enties) to be
 *		invalidated.
 */
int kvm_mips_mkclean_gpa_pt(struct kvm *kvm, gfn_t start_gfn, gfn_t end_gfn)
{
	return kvm_mips_mkclean_pgd(kvm->arch.gpa_mm.pgd,
				    start_gfn << PAGE_SHIFT,
				    end_gfn << PAGE_SHIFT);
}

/**
 * kvm_arch_mmu_enable_log_dirty_pt_masked() - write protect dirty pages
 * @kvm:	The KVM pointer
 * @slot:	The memory slot associated with mask
 * @gfn_offset:	The gfn offset in memory slot
 * @mask:	The mask of dirty pages at offset 'gfn_offset' in this memory
 *		slot to be write protected
 *
 * Walks bits set in mask write protects the associated pte's. Caller must
 * acquire @kvm->mmu_lock.
 */
void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
		struct kvm_memory_slot *slot,
		gfn_t gfn_offset, unsigned long mask)
{
	gfn_t base_gfn = slot->base_gfn + gfn_offset;
	gfn_t start = base_gfn +  __ffs(mask);
	gfn_t end = base_gfn + __fls(mask);

	kvm_mips_mkclean_gpa_pt(kvm, start, end);
}

/*
 * kvm_mips_mkold_gpa_pt.
 * Mark a range of guest physical address space old (all accesses fault) in the
 * VM's GPA page table to allow detection of commonly used pages.
 */

BUILD_PTE_RANGE_OP(mkold, pte_mkold)

static int kvm_mips_mkold_gpa_pt(struct kvm *kvm, gfn_t start_gfn,
				 gfn_t end_gfn)
{
	return kvm_mips_mkold_pgd(kvm->arch.gpa_mm.pgd,
				  start_gfn << PAGE_SHIFT,
				  end_gfn << PAGE_SHIFT);
}

bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
	kvm_mips_flush_gpa_pt(kvm, range->start, range->end);
	return 1;
}

bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	gpa_t gpa = range->start << PAGE_SHIFT;
	pte_t hva_pte = range->pte;
	pte_t *gpa_pte = kvm_mips_pte_for_gpa(kvm, NULL, gpa);
	pte_t old_pte;

	if (!gpa_pte)
		return false;

	/* Mapping may need adjusting depending on memslot flags */
	old_pte = *gpa_pte;
	if (range->slot->flags & KVM_MEM_LOG_DIRTY_PAGES && !pte_dirty(old_pte))
		hva_pte = pte_mkclean(hva_pte);
	else if (range->slot->flags & KVM_MEM_READONLY)
		hva_pte = pte_wrprotect(hva_pte);

	set_pte(gpa_pte, hva_pte);

	/* Replacing an absent or old page doesn't need flushes */
	if (!pte_present(old_pte) || !pte_young(old_pte))
		return false;

	/* Pages swapped, aged, moved, or cleaned require flushes */
	return !pte_present(hva_pte) ||
	       !pte_young(hva_pte) ||
	       pte_pfn(old_pte) != pte_pfn(hva_pte) ||
	       (pte_dirty(old_pte) && !pte_dirty(hva_pte));
}

bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	return kvm_mips_mkold_gpa_pt(kvm, range->start, range->end);
}

bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	gpa_t gpa = range->start << PAGE_SHIFT;
	pte_t *gpa_pte = kvm_mips_pte_for_gpa(kvm, NULL, gpa);

	if (!gpa_pte)
		return 0;
	return pte_young(*gpa_pte);
}

/**
 * _kvm_mips_map_page_fast() - Fast path GPA fault handler.
 * @vcpu:		VCPU pointer.
 * @gpa:		Guest physical address of fault.
 * @write_fault:	Whether the fault was due to a write.
 * @out_entry:		New PTE for @gpa (written on success unless NULL).
 * @out_buddy:		New PTE for @gpa's buddy (written on success unless
 *			NULL).
 *
 * Perform fast path GPA fault handling, doing all that can be done without
 * calling into KVM. This handles marking old pages young (for idle page
 * tracking), and dirtying of clean pages (for dirty page logging).
 *
 * Returns:	0 on success, in which case we can update derived mappings and
 *		resume guest execution.
 *		-EFAULT on failure due to absent GPA mapping or write to
 *		read-only page, in which case KVM must be consulted.
 */
static int _kvm_mips_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa,
				   bool write_fault,
				   pte_t *out_entry, pte_t *out_buddy)
{
	struct kvm *kvm = vcpu->kvm;
	gfn_t gfn = gpa >> PAGE_SHIFT;
	pte_t *ptep;
	kvm_pfn_t pfn = 0;	/* silence bogus GCC warning */
	bool pfn_valid = false;
	int ret = 0;

	spin_lock(&kvm->mmu_lock);

	/* Fast path - just check GPA page table for an existing entry */
	ptep = kvm_mips_pte_for_gpa(kvm, NULL, gpa);
	if (!ptep || !pte_present(*ptep)) {
		ret = -EFAULT;
		goto out;
	}

	/* Track access to pages marked old */
	if (!pte_young(*ptep)) {
		set_pte(ptep, pte_mkyoung(*ptep));
		pfn = pte_pfn(*ptep);
		pfn_valid = true;
		/* call kvm_set_pfn_accessed() after unlock */
	}
	if (write_fault && !pte_dirty(*ptep)) {
		if (!pte_write(*ptep)) {
			ret = -EFAULT;
			goto out;
		}

		/* Track dirtying of writeable pages */
		set_pte(ptep, pte_mkdirty(*ptep));
		pfn = pte_pfn(*ptep);
		mark_page_dirty(kvm, gfn);
		kvm_set_pfn_dirty(pfn);
	}

	if (out_entry)
		*out_entry = *ptep;
	if (out_buddy)
		*out_buddy = *ptep_buddy(ptep);

out:
	spin_unlock(&kvm->mmu_lock);
	if (pfn_valid)
		kvm_set_pfn_accessed(pfn);
	return ret;
}

/**
 * kvm_mips_map_page() - Map a guest physical page.
 * @vcpu:		VCPU pointer.
 * @gpa:		Guest physical address of fault.
 * @write_fault:	Whether the fault was due to a write.
 * @out_entry:		New PTE for @gpa (written on success unless NULL).
 * @out_buddy:		New PTE for @gpa's buddy (written on success unless
 *			NULL).
 *
 * Handle GPA faults by creating a new GPA mapping (or updating an existing
 * one).
 *
 * This takes care of marking pages young or dirty (idle/dirty page tracking),
 * asking KVM for the corresponding PFN, and creating a mapping in the GPA page
 * tables. Derived mappings (GVA page tables and TLBs) must be handled by the
 * caller.
 *
 * Returns:	0 on success, in which case the caller may use the @out_entry
 *		and @out_buddy PTEs to update derived mappings and resume guest
 *		execution.
 *		-EFAULT if there is no memory region at @gpa or a write was
 *		attempted to a read-only memory region. This is usually handled
 *		as an MMIO access.
 */
static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa,
			     bool write_fault,
			     pte_t *out_entry, pte_t *out_buddy)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
	gfn_t gfn = gpa >> PAGE_SHIFT;
	int srcu_idx, err;
	kvm_pfn_t pfn;
	pte_t *ptep, entry, old_pte;
	bool writeable;
	unsigned long prot_bits;
	unsigned long mmu_seq;

	/* Try the fast path to handle old / clean pages */
	srcu_idx = srcu_read_lock(&kvm->srcu);
	err = _kvm_mips_map_page_fast(vcpu, gpa, write_fault, out_entry,
				      out_buddy);
	if (!err)
		goto out;

	/* We need a minimum of cached pages ready for page table creation */
	err = kvm_mmu_topup_memory_cache(memcache, KVM_MMU_CACHE_MIN_PAGES);
	if (err)
		goto out;

retry:
	/*
	 * Used to check for invalidations in progress, of the pfn that is
	 * returned by pfn_to_pfn_prot below.
	 */
	mmu_seq = kvm->mmu_notifier_seq;
	/*
	 * Ensure the read of mmu_notifier_seq isn't reordered with PTE reads in
	 * gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
	 * risk the page we get a reference to getting unmapped before we have a
	 * chance to grab the mmu_lock without mmu_notifier_retry() noticing.
	 *
	 * This smp_rmb() pairs with the effective smp_wmb() of the combination
	 * of the pte_unmap_unlock() after the PTE is zapped, and the
	 * spin_lock() in kvm_mmu_notifier_invalidate_<page|range_end>() before
	 * mmu_notifier_seq is incremented.
	 */
	smp_rmb();

	/* Slow path - ask KVM core whether we can access this GPA */
	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writeable);
	if (is_error_noslot_pfn(pfn)) {
		err = -EFAULT;
		goto out;
	}

	spin_lock(&kvm->mmu_lock);
	/* Check if an invalidation has taken place since we got pfn */
	if (mmu_notifier_retry(kvm, mmu_seq)) {
		/*
		 * This can happen when mappings are changed asynchronously, but
		 * also synchronously if a COW is triggered by
		 * gfn_to_pfn_prot().
		 */
		spin_unlock(&kvm->mmu_lock);
		kvm_release_pfn_clean(pfn);
		goto retry;
	}

	/* Ensure page tables are allocated */
	ptep = kvm_mips_pte_for_gpa(kvm, memcache, gpa);

	/* Set up the PTE */
	prot_bits = _PAGE_PRESENT | __READABLE | _page_cachable_default;
	if (writeable) {
		prot_bits |= _PAGE_WRITE;
		if (write_fault) {
			prot_bits |= __WRITEABLE;
			mark_page_dirty(kvm, gfn);
			kvm_set_pfn_dirty(pfn);
		}
	}
	entry = pfn_pte(pfn, __pgprot(prot_bits));

	/* Write the PTE */
	old_pte = *ptep;
	set_pte(ptep, entry);

	err = 0;
	if (out_entry)
		*out_entry = *ptep;
	if (out_buddy)
		*out_buddy = *ptep_buddy(ptep);

	spin_unlock(&kvm->mmu_lock);
	kvm_release_pfn_clean(pfn);
	kvm_set_pfn_accessed(pfn);
out:
	srcu_read_unlock(&kvm->srcu, srcu_idx);
	return err;
}

int kvm_mips_handle_vz_root_tlb_fault(unsigned long badvaddr,
				      struct kvm_vcpu *vcpu,
				      bool write_fault)
{
	int ret;

	ret = kvm_mips_map_page(vcpu, badvaddr, write_fault, NULL, NULL);
	if (ret)
		return ret;

	/* Invalidate this entry in the TLB */
	return kvm_vz_host_tlb_inv(vcpu, badvaddr);
}

/**
 * kvm_mips_migrate_count() - Migrate timer.
 * @vcpu:	Virtual CPU.
 *
 * Migrate CP0_Count hrtimer to the current CPU by cancelling and restarting it
 * if it was running prior to being cancelled.
 *
 * Must be called when the VCPU is migrated to a different CPU to ensure that
 * timer expiry during guest execution interrupts the guest and causes the
 * interrupt to be delivered in a timely manner.
 */
static void kvm_mips_migrate_count(struct kvm_vcpu *vcpu)
{
	if (hrtimer_cancel(&vcpu->arch.comparecount_timer))
		hrtimer_restart(&vcpu->arch.comparecount_timer);
}

/* Restore ASID once we are scheduled back after preemption */
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	unsigned long flags;

	kvm_debug("%s: vcpu %p, cpu: %d\n", __func__, vcpu, cpu);

	local_irq_save(flags);

	vcpu->cpu = cpu;
	if (vcpu->arch.last_sched_cpu != cpu) {
		kvm_debug("[%d->%d]KVM VCPU[%d] switch\n",
			  vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
		/*
		 * Migrate the timer interrupt to the current CPU so that it
		 * always interrupts the guest and synchronously triggers a
		 * guest timer interrupt.
		 */
		kvm_mips_migrate_count(vcpu);
	}

	/* restore guest state to registers */
	kvm_mips_callbacks->vcpu_load(vcpu, cpu);

	local_irq_restore(flags);
}

/* ASID can change if another task is scheduled during preemption */
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	unsigned long flags;
	int cpu;

	local_irq_save(flags);

	cpu = smp_processor_id();
	vcpu->arch.last_sched_cpu = cpu;
	vcpu->cpu = -1;

	/* save guest state in registers */
	kvm_mips_callbacks->vcpu_put(vcpu, cpu);

	local_irq_restore(flags);
}