summaryrefslogtreecommitdiff
path: root/arch/riscv/kvm/mmu.c
blob: 9af67dbdc66af7ce351df1146987cf0e1187216b (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2019 Western Digital Corporation or its affiliates.
 *
 * Authors:
 *     Anup Patel <anup.patel@wdc.com>
 */

#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/hugetlb.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/kvm_host.h>
#include <linux/sched/signal.h>
#include <asm/csr.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/sbi.h>

#ifdef CONFIG_64BIT
static unsigned long stage2_mode = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT);
static unsigned long stage2_pgd_levels = 3;
#define stage2_index_bits	9
#else
static unsigned long stage2_mode = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT);
static unsigned long stage2_pgd_levels = 2;
#define stage2_index_bits	10
#endif

#define stage2_pgd_xbits	2
#define stage2_pgd_size	(1UL << (HGATP_PAGE_SHIFT + stage2_pgd_xbits))
#define stage2_gpa_bits	(HGATP_PAGE_SHIFT + \
			 (stage2_pgd_levels * stage2_index_bits) + \
			 stage2_pgd_xbits)
#define stage2_gpa_size	((gpa_t)(1ULL << stage2_gpa_bits))

#define stage2_pte_leaf(__ptep)	\
	(pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC))

static inline unsigned long stage2_pte_index(gpa_t addr, u32 level)
{
	unsigned long mask;
	unsigned long shift = HGATP_PAGE_SHIFT + (stage2_index_bits * level);

	if (level == (stage2_pgd_levels - 1))
		mask = (PTRS_PER_PTE * (1UL << stage2_pgd_xbits)) - 1;
	else
		mask = PTRS_PER_PTE - 1;

	return (addr >> shift) & mask;
}

static inline unsigned long stage2_pte_page_vaddr(pte_t pte)
{
	return (unsigned long)pfn_to_virt(pte_val(pte) >> _PAGE_PFN_SHIFT);
}

static int stage2_page_size_to_level(unsigned long page_size, u32 *out_level)
{
	u32 i;
	unsigned long psz = 1UL << 12;

	for (i = 0; i < stage2_pgd_levels; i++) {
		if (page_size == (psz << (i * stage2_index_bits))) {
			*out_level = i;
			return 0;
		}
	}

	return -EINVAL;
}

static int stage2_level_to_page_size(u32 level, unsigned long *out_pgsize)
{
	if (stage2_pgd_levels < level)
		return -EINVAL;

	*out_pgsize = 1UL << (12 + (level * stage2_index_bits));

	return 0;
}

static bool stage2_get_leaf_entry(struct kvm *kvm, gpa_t addr,
				  pte_t **ptepp, u32 *ptep_level)
{
	pte_t *ptep;
	u32 current_level = stage2_pgd_levels - 1;

	*ptep_level = current_level;
	ptep = (pte_t *)kvm->arch.pgd;
	ptep = &ptep[stage2_pte_index(addr, current_level)];
	while (ptep && pte_val(*ptep)) {
		if (stage2_pte_leaf(ptep)) {
			*ptep_level = current_level;
			*ptepp = ptep;
			return true;
		}

		if (current_level) {
			current_level--;
			*ptep_level = current_level;
			ptep = (pte_t *)stage2_pte_page_vaddr(*ptep);
			ptep = &ptep[stage2_pte_index(addr, current_level)];
		} else {
			ptep = NULL;
		}
	}

	return false;
}

static void stage2_remote_tlb_flush(struct kvm *kvm, u32 level, gpa_t addr)
{
	struct cpumask hmask;
	unsigned long size = PAGE_SIZE;
	struct kvm_vmid *vmid = &kvm->arch.vmid;

	if (stage2_level_to_page_size(level, &size))
		return;
	addr &= ~(size - 1);

	/*
	 * TODO: Instead of cpu_online_mask, we should only target CPUs
	 * where the Guest/VM is running.
	 */
	preempt_disable();
	riscv_cpuid_to_hartid_mask(cpu_online_mask, &hmask);
	sbi_remote_hfence_gvma_vmid(cpumask_bits(&hmask), addr, size,
				    READ_ONCE(vmid->vmid));
	preempt_enable();
}

static int stage2_set_pte(struct kvm *kvm, u32 level,
			   struct kvm_mmu_memory_cache *pcache,
			   gpa_t addr, const pte_t *new_pte)
{
	u32 current_level = stage2_pgd_levels - 1;
	pte_t *next_ptep = (pte_t *)kvm->arch.pgd;
	pte_t *ptep = &next_ptep[stage2_pte_index(addr, current_level)];

	if (current_level < level)
		return -EINVAL;

	while (current_level != level) {
		if (stage2_pte_leaf(ptep))
			return -EEXIST;

		if (!pte_val(*ptep)) {
			if (!pcache)
				return -ENOMEM;
			next_ptep = kvm_mmu_memory_cache_alloc(pcache);
			if (!next_ptep)
				return -ENOMEM;
			*ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)),
					__pgprot(_PAGE_TABLE));
		} else {
			if (stage2_pte_leaf(ptep))
				return -EEXIST;
			next_ptep = (pte_t *)stage2_pte_page_vaddr(*ptep);
		}

		current_level--;
		ptep = &next_ptep[stage2_pte_index(addr, current_level)];
	}

	*ptep = *new_pte;
	if (stage2_pte_leaf(ptep))
		stage2_remote_tlb_flush(kvm, current_level, addr);

	return 0;
}

static int stage2_map_page(struct kvm *kvm,
			   struct kvm_mmu_memory_cache *pcache,
			   gpa_t gpa, phys_addr_t hpa,
			   unsigned long page_size,
			   bool page_rdonly, bool page_exec)
{
	int ret;
	u32 level = 0;
	pte_t new_pte;
	pgprot_t prot;

	ret = stage2_page_size_to_level(page_size, &level);
	if (ret)
		return ret;

	/*
	 * A RISC-V implementation can choose to either:
	 * 1) Update 'A' and 'D' PTE bits in hardware
	 * 2) Generate page fault when 'A' and/or 'D' bits are not set
	 *    PTE so that software can update these bits.
	 *
	 * We support both options mentioned above. To achieve this, we
	 * always set 'A' and 'D' PTE bits at time of creating stage2
	 * mapping. To support KVM dirty page logging with both options
	 * mentioned above, we will write-protect stage2 PTEs to track
	 * dirty pages.
	 */

	if (page_exec) {
		if (page_rdonly)
			prot = PAGE_READ_EXEC;
		else
			prot = PAGE_WRITE_EXEC;
	} else {
		if (page_rdonly)
			prot = PAGE_READ;
		else
			prot = PAGE_WRITE;
	}
	new_pte = pfn_pte(PFN_DOWN(hpa), prot);
	new_pte = pte_mkdirty(new_pte);

	return stage2_set_pte(kvm, level, pcache, gpa, &new_pte);
}

enum stage2_op {
	STAGE2_OP_NOP = 0,	/* Nothing */
	STAGE2_OP_CLEAR,	/* Clear/Unmap */
	STAGE2_OP_WP,		/* Write-protect */
};

static void stage2_op_pte(struct kvm *kvm, gpa_t addr,
			  pte_t *ptep, u32 ptep_level, enum stage2_op op)
{
	int i, ret;
	pte_t *next_ptep;
	u32 next_ptep_level;
	unsigned long next_page_size, page_size;

	ret = stage2_level_to_page_size(ptep_level, &page_size);
	if (ret)
		return;

	BUG_ON(addr & (page_size - 1));

	if (!pte_val(*ptep))
		return;

	if (ptep_level && !stage2_pte_leaf(ptep)) {
		next_ptep = (pte_t *)stage2_pte_page_vaddr(*ptep);
		next_ptep_level = ptep_level - 1;
		ret = stage2_level_to_page_size(next_ptep_level,
						&next_page_size);
		if (ret)
			return;

		if (op == STAGE2_OP_CLEAR)
			set_pte(ptep, __pte(0));
		for (i = 0; i < PTRS_PER_PTE; i++)
			stage2_op_pte(kvm, addr + i * next_page_size,
					&next_ptep[i], next_ptep_level, op);
		if (op == STAGE2_OP_CLEAR)
			put_page(virt_to_page(next_ptep));
	} else {
		if (op == STAGE2_OP_CLEAR)
			set_pte(ptep, __pte(0));
		else if (op == STAGE2_OP_WP)
			set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
		stage2_remote_tlb_flush(kvm, ptep_level, addr);
	}
}

static void stage2_unmap_range(struct kvm *kvm, gpa_t start,
			       gpa_t size, bool may_block)
{
	int ret;
	pte_t *ptep;
	u32 ptep_level;
	bool found_leaf;
	unsigned long page_size;
	gpa_t addr = start, end = start + size;

	while (addr < end) {
		found_leaf = stage2_get_leaf_entry(kvm, addr,
						   &ptep, &ptep_level);
		ret = stage2_level_to_page_size(ptep_level, &page_size);
		if (ret)
			break;

		if (!found_leaf)
			goto next;

		if (!(addr & (page_size - 1)) && ((end - addr) >= page_size))
			stage2_op_pte(kvm, addr, ptep,
				      ptep_level, STAGE2_OP_CLEAR);

next:
		addr += page_size;

		/*
		 * If the range is too large, release the kvm->mmu_lock
		 * to prevent starvation and lockup detector warnings.
		 */
		if (may_block && addr < end)
			cond_resched_lock(&kvm->mmu_lock);
	}
}

static void stage2_wp_range(struct kvm *kvm, gpa_t start, gpa_t end)
{
	int ret;
	pte_t *ptep;
	u32 ptep_level;
	bool found_leaf;
	gpa_t addr = start;
	unsigned long page_size;

	while (addr < end) {
		found_leaf = stage2_get_leaf_entry(kvm, addr,
						   &ptep, &ptep_level);
		ret = stage2_level_to_page_size(ptep_level, &page_size);
		if (ret)
			break;

		if (!found_leaf)
			goto next;

		if (!(addr & (page_size - 1)) && ((end - addr) >= page_size))
			stage2_op_pte(kvm, addr, ptep,
				      ptep_level, STAGE2_OP_WP);

next:
		addr += page_size;
	}
}

static void stage2_wp_memory_region(struct kvm *kvm, int slot)
{
	struct kvm_memslots *slots = kvm_memslots(kvm);
	struct kvm_memory_slot *memslot = id_to_memslot(slots, slot);
	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;

	spin_lock(&kvm->mmu_lock);
	stage2_wp_range(kvm, start, end);
	spin_unlock(&kvm->mmu_lock);
	kvm_flush_remote_tlbs(kvm);
}

static int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
			  unsigned long size, bool writable)
{
	pte_t pte;
	int ret = 0;
	unsigned long pfn;
	phys_addr_t addr, end;
	struct kvm_mmu_memory_cache pcache;

	memset(&pcache, 0, sizeof(pcache));
	pcache.gfp_zero = __GFP_ZERO;

	end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
	pfn = __phys_to_pfn(hpa);

	for (addr = gpa; addr < end; addr += PAGE_SIZE) {
		pte = pfn_pte(pfn, PAGE_KERNEL);

		if (!writable)
			pte = pte_wrprotect(pte);

		ret = kvm_mmu_topup_memory_cache(&pcache, stage2_pgd_levels);
		if (ret)
			goto out;

		spin_lock(&kvm->mmu_lock);
		ret = stage2_set_pte(kvm, 0, &pcache, addr, &pte);
		spin_unlock(&kvm->mmu_lock);
		if (ret)
			goto out;

		pfn++;
	}

out:
	kvm_mmu_free_memory_cache(&pcache);
	return ret;
}

void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
					     struct kvm_memory_slot *slot,
					     gfn_t gfn_offset,
					     unsigned long mask)
{
	phys_addr_t base_gfn = slot->base_gfn + gfn_offset;
	phys_addr_t start = (base_gfn +  __ffs(mask)) << PAGE_SHIFT;
	phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT;

	stage2_wp_range(kvm, start, end);
}

void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
}

void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
					const struct kvm_memory_slot *memslot)
{
	kvm_flush_remote_tlbs(kvm);
}

void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free)
{
}

void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
{
}

void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
	kvm_riscv_stage2_free_pgd(kvm);
}

void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
				   struct kvm_memory_slot *slot)
{
	gpa_t gpa = slot->base_gfn << PAGE_SHIFT;
	phys_addr_t size = slot->npages << PAGE_SHIFT;

	spin_lock(&kvm->mmu_lock);
	stage2_unmap_range(kvm, gpa, size, false);
	spin_unlock(&kvm->mmu_lock);
}

void kvm_arch_commit_memory_region(struct kvm *kvm,
				struct kvm_memory_slot *old,
				const struct kvm_memory_slot *new,
				enum kvm_mr_change change)
{
	/*
	 * At this point memslot has been committed and there is an
	 * allocated dirty_bitmap[], dirty pages will be tracked while
	 * the memory slot is write protected.
	 */
	if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES)
		stage2_wp_memory_region(kvm, new->id);
}

int kvm_arch_prepare_memory_region(struct kvm *kvm,
				const struct kvm_memory_slot *old,
				struct kvm_memory_slot *new,
				enum kvm_mr_change change)
{
	hva_t hva, reg_end, size;
	gpa_t base_gpa;
	bool writable;
	int ret = 0;

	if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
			change != KVM_MR_FLAGS_ONLY)
		return 0;

	/*
	 * Prevent userspace from creating a memory region outside of the GPA
	 * space addressable by the KVM guest GPA space.
	 */
	if ((new->base_gfn + new->npages) >=
	    (stage2_gpa_size >> PAGE_SHIFT))
		return -EFAULT;

	hva = new->userspace_addr;
	size = new->npages << PAGE_SHIFT;
	reg_end = hva + size;
	base_gpa = new->base_gfn << PAGE_SHIFT;
	writable = !(new->flags & KVM_MEM_READONLY);

	mmap_read_lock(current->mm);

	/*
	 * A memory region could potentially cover multiple VMAs, and
	 * any holes between them, so iterate over all of them to find
	 * out if we can map any of them right now.
	 *
	 *     +--------------------------------------------+
	 * +---------------+----------------+   +----------------+
	 * |   : VMA 1     |      VMA 2     |   |    VMA 3  :    |
	 * +---------------+----------------+   +----------------+
	 *     |               memory region                |
	 *     +--------------------------------------------+
	 */
	do {
		struct vm_area_struct *vma = find_vma(current->mm, hva);
		hva_t vm_start, vm_end;

		if (!vma || vma->vm_start >= reg_end)
			break;

		/*
		 * Mapping a read-only VMA is only allowed if the
		 * memory region is configured as read-only.
		 */
		if (writable && !(vma->vm_flags & VM_WRITE)) {
			ret = -EPERM;
			break;
		}

		/* Take the intersection of this VMA with the memory region */
		vm_start = max(hva, vma->vm_start);
		vm_end = min(reg_end, vma->vm_end);

		if (vma->vm_flags & VM_PFNMAP) {
			gpa_t gpa = base_gpa + (vm_start - hva);
			phys_addr_t pa;

			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
			pa += vm_start - vma->vm_start;

			/* IO region dirty page logging not allowed */
			if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) {
				ret = -EINVAL;
				goto out;
			}

			ret = stage2_ioremap(kvm, gpa, pa,
					     vm_end - vm_start, writable);
			if (ret)
				break;
		}
		hva = vm_end;
	} while (hva < reg_end);

	if (change == KVM_MR_FLAGS_ONLY)
		goto out;

	spin_lock(&kvm->mmu_lock);
	if (ret)
		stage2_unmap_range(kvm, base_gpa, size, false);
	spin_unlock(&kvm->mmu_lock);

out:
	mmap_read_unlock(current->mm);
	return ret;
}

bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
	if (!kvm->arch.pgd)
		return false;

	stage2_unmap_range(kvm, range->start << PAGE_SHIFT,
			   (range->end - range->start) << PAGE_SHIFT,
			   range->may_block);
	return false;
}

bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	int ret;
	kvm_pfn_t pfn = pte_pfn(range->pte);

	if (!kvm->arch.pgd)
		return false;

	WARN_ON(range->end - range->start != 1);

	ret = stage2_map_page(kvm, NULL, range->start << PAGE_SHIFT,
			      __pfn_to_phys(pfn), PAGE_SIZE, true, true);
	if (ret) {
		kvm_debug("Failed to map stage2 page (error %d)\n", ret);
		return true;
	}

	return false;
}

bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	pte_t *ptep;
	u32 ptep_level = 0;
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	if (!kvm->arch.pgd)
		return false;

	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE);

	if (!stage2_get_leaf_entry(kvm, range->start << PAGE_SHIFT,
				   &ptep, &ptep_level))
		return false;

	return ptep_test_and_clear_young(NULL, 0, ptep);
}

bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
	pte_t *ptep;
	u32 ptep_level = 0;
	u64 size = (range->end - range->start) << PAGE_SHIFT;

	if (!kvm->arch.pgd)
		return false;

	WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE);

	if (!stage2_get_leaf_entry(kvm, range->start << PAGE_SHIFT,
				   &ptep, &ptep_level))
		return false;

	return pte_young(*ptep);
}

int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu,
			 struct kvm_memory_slot *memslot,
			 gpa_t gpa, unsigned long hva, bool is_write)
{
	int ret;
	kvm_pfn_t hfn;
	bool writeable;
	short vma_pageshift;
	gfn_t gfn = gpa >> PAGE_SHIFT;
	struct vm_area_struct *vma;
	struct kvm *kvm = vcpu->kvm;
	struct kvm_mmu_memory_cache *pcache = &vcpu->arch.mmu_page_cache;
	bool logging = (memslot->dirty_bitmap &&
			!(memslot->flags & KVM_MEM_READONLY)) ? true : false;
	unsigned long vma_pagesize, mmu_seq;

	mmap_read_lock(current->mm);

	vma = find_vma_intersection(current->mm, hva, hva + 1);
	if (unlikely(!vma)) {
		kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
		mmap_read_unlock(current->mm);
		return -EFAULT;
	}

	if (is_vm_hugetlb_page(vma))
		vma_pageshift = huge_page_shift(hstate_vma(vma));
	else
		vma_pageshift = PAGE_SHIFT;
	vma_pagesize = 1ULL << vma_pageshift;
	if (logging || (vma->vm_flags & VM_PFNMAP))
		vma_pagesize = PAGE_SIZE;

	if (vma_pagesize == PMD_SIZE || vma_pagesize == PGDIR_SIZE)
		gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;

	mmap_read_unlock(current->mm);

	if (vma_pagesize != PGDIR_SIZE &&
	    vma_pagesize != PMD_SIZE &&
	    vma_pagesize != PAGE_SIZE) {
		kvm_err("Invalid VMA page size 0x%lx\n", vma_pagesize);
		return -EFAULT;
	}

	/* We need minimum second+third level pages */
	ret = kvm_mmu_topup_memory_cache(pcache, stage2_pgd_levels);
	if (ret) {
		kvm_err("Failed to topup stage2 cache\n");
		return ret;
	}

	mmu_seq = kvm->mmu_notifier_seq;

	hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writeable);
	if (hfn == KVM_PFN_ERR_HWPOISON) {
		send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva,
				vma_pageshift, current);
		return 0;
	}
	if (is_error_noslot_pfn(hfn))
		return -EFAULT;

	/*
	 * If logging is active then we allow writable pages only
	 * for write faults.
	 */
	if (logging && !is_write)
		writeable = false;

	spin_lock(&kvm->mmu_lock);

	if (mmu_notifier_retry(kvm, mmu_seq))
		goto out_unlock;

	if (writeable) {
		kvm_set_pfn_dirty(hfn);
		mark_page_dirty(kvm, gfn);
		ret = stage2_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
				      vma_pagesize, false, true);
	} else {
		ret = stage2_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
				      vma_pagesize, true, true);
	}

	if (ret)
		kvm_err("Failed to map in stage2\n");

out_unlock:
	spin_unlock(&kvm->mmu_lock);
	kvm_set_pfn_accessed(hfn);
	kvm_release_pfn_clean(hfn);
	return ret;
}

int kvm_riscv_stage2_alloc_pgd(struct kvm *kvm)
{
	struct page *pgd_page;

	if (kvm->arch.pgd != NULL) {
		kvm_err("kvm_arch already initialized?\n");
		return -EINVAL;
	}

	pgd_page = alloc_pages(GFP_KERNEL | __GFP_ZERO,
				get_order(stage2_pgd_size));
	if (!pgd_page)
		return -ENOMEM;
	kvm->arch.pgd = page_to_virt(pgd_page);
	kvm->arch.pgd_phys = page_to_phys(pgd_page);

	return 0;
}

void kvm_riscv_stage2_free_pgd(struct kvm *kvm)
{
	void *pgd = NULL;

	spin_lock(&kvm->mmu_lock);
	if (kvm->arch.pgd) {
		stage2_unmap_range(kvm, 0UL, stage2_gpa_size, false);
		pgd = READ_ONCE(kvm->arch.pgd);
		kvm->arch.pgd = NULL;
		kvm->arch.pgd_phys = 0;
	}
	spin_unlock(&kvm->mmu_lock);

	if (pgd)
		free_pages((unsigned long)pgd, get_order(stage2_pgd_size));
}

void kvm_riscv_stage2_update_hgatp(struct kvm_vcpu *vcpu)
{
	unsigned long hgatp = stage2_mode;
	struct kvm_arch *k = &vcpu->kvm->arch;

	hgatp |= (READ_ONCE(k->vmid.vmid) << HGATP_VMID_SHIFT) &
		 HGATP_VMID_MASK;
	hgatp |= (k->pgd_phys >> PAGE_SHIFT) & HGATP_PPN;

	csr_write(CSR_HGATP, hgatp);

	if (!kvm_riscv_stage2_vmid_bits())
		__kvm_riscv_hfence_gvma_all();
}

void kvm_riscv_stage2_mode_detect(void)
{
#ifdef CONFIG_64BIT
	/* Try Sv48x4 stage2 mode */
	csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT);
	if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV48X4) {
		stage2_mode = (HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT);
		stage2_pgd_levels = 4;
	}
	csr_write(CSR_HGATP, 0);

	__kvm_riscv_hfence_gvma_all();
#endif
}

unsigned long kvm_riscv_stage2_mode(void)
{
	return stage2_mode >> HGATP_MODE_SHIFT;
}

int kvm_riscv_stage2_gpa_bits(void)
{
	return stage2_gpa_bits;
}