summaryrefslogtreecommitdiff
path: root/arch/riscv/kvm/mmu.c
blob: a1c3b2ec1dde54c65bd72e64bc2e3b252cbf5f6d (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2019 Western Digital Corporation or its affiliates.
 *
 * Authors:
 *     Anup Patel <anup.patel@wdc.com>
 */

#include <linux/errno.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/kvm_mmu.h>
#include <asm/kvm_nacl.h>

static void mmu_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;
	struct kvm_gstage gstage;

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;

	spin_lock(&kvm->mmu_lock);
	kvm_riscv_gstage_wp_range(&gstage, start, end);
	spin_unlock(&kvm->mmu_lock);
	kvm_flush_remote_tlbs_memslot(kvm, memslot);
}

int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
			  unsigned long size, bool writable, bool in_atomic)
{
	int ret = 0;
	unsigned long pfn;
	phys_addr_t addr, end;
	struct kvm_mmu_memory_cache pcache = {
		.gfp_custom = (in_atomic) ? GFP_ATOMIC | __GFP_ACCOUNT : 0,
		.gfp_zero = __GFP_ZERO,
	};
	struct kvm_gstage_mapping map;
	struct kvm_gstage gstage;

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;

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

	for (addr = gpa; addr < end; addr += PAGE_SIZE) {
		map.addr = addr;
		map.pte = pfn_pte(pfn, PAGE_KERNEL_IO);
		map.level = 0;

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

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

		spin_lock(&kvm->mmu_lock);
		ret = kvm_riscv_gstage_set_pte(&gstage, &pcache, &map);
		spin_unlock(&kvm->mmu_lock);
		if (ret)
			goto out;

		pfn++;
	}

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

void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size)
{
	struct kvm_gstage gstage;

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;

	spin_lock(&kvm->mmu_lock);
	kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false);
	spin_unlock(&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)
{
	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;
	struct kvm_gstage gstage;

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;

	kvm_riscv_gstage_wp_range(&gstage, start, end);
}

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

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_mmu_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;
	struct kvm_gstage gstage;

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;

	spin_lock(&kvm->mmu_lock);
	kvm_riscv_gstage_unmap_range(&gstage, 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)
		mmu_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) >=
	    (kvm_riscv_gstage_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;
		hva_t vm_start, vm_end;

		vma = find_vma_intersection(current->mm, hva, reg_end);
		if (!vma)
			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 = kvm_riscv_mmu_ioremap(kvm, gpa, pa, vm_end - vm_start,
						    writable, false);
			if (ret)
				break;
		}
		hva = vm_end;
	} while (hva < reg_end);

	if (change == KVM_MR_FLAGS_ONLY)
		goto out;

	if (ret)
		kvm_riscv_mmu_iounmap(kvm, base_gpa, size);

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

bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
{
	struct kvm_gstage gstage;

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

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;
	kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT,
				     (range->end - range->start) << PAGE_SHIFT,
				     range->may_block);
	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;
	struct kvm_gstage gstage;

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

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

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;
	if (!kvm_riscv_gstage_get_leaf(&gstage, 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;
	struct kvm_gstage gstage;

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

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

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;
	if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT,
				       &ptep, &ptep_level))
		return false;

	return pte_young(ptep_get(ptep));
}

int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
		      gpa_t gpa, unsigned long hva, bool is_write,
		      struct kvm_gstage_mapping *out_map)
{
	int ret;
	kvm_pfn_t hfn;
	bool writable;
	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;
	struct kvm_gstage gstage;
	struct page *page;

	gstage.kvm = kvm;
	gstage.flags = 0;
	gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
	gstage.pgd = kvm->arch.pgd;

	/* Setup initial state of output mapping */
	memset(out_map, 0, sizeof(*out_map));

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

	mmap_read_lock(current->mm);

	vma = vma_lookup(current->mm, hva);
	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 == PUD_SIZE)
		gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;

	/*
	 * Read mmu_invalidate_seq so that KVM can detect if the results of
	 * vma_lookup() or __kvm_faultin_pfn() become stale prior to acquiring
	 * kvm->mmu_lock.
	 *
	 * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
	 * with the smp_wmb() in kvm_mmu_invalidate_end().
	 */
	mmu_seq = kvm->mmu_invalidate_seq;
	mmap_read_unlock(current->mm);

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

	hfn = __kvm_faultin_pfn(memslot, gfn, is_write ? FOLL_WRITE : 0,
				&writable, &page);
	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)
		writable = false;

	spin_lock(&kvm->mmu_lock);

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

	if (writable) {
		mark_page_dirty_in_slot(kvm, memslot, gfn);
		ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT,
						vma_pagesize, false, true, out_map);
	} else {
		ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT,
						vma_pagesize, true, true, out_map);
	}

	if (ret)
		kvm_err("Failed to map in G-stage\n");

out_unlock:
	kvm_release_faultin_page(kvm, page, ret && ret != -EEXIST, writable);
	spin_unlock(&kvm->mmu_lock);
	return ret;
}

int kvm_riscv_mmu_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(kvm_riscv_gstage_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_mmu_free_pgd(struct kvm *kvm)
{
	struct kvm_gstage gstage;
	void *pgd = NULL;

	spin_lock(&kvm->mmu_lock);
	if (kvm->arch.pgd) {
		gstage.kvm = kvm;
		gstage.flags = 0;
		gstage.vmid = READ_ONCE(kvm->arch.vmid.vmid);
		gstage.pgd = kvm->arch.pgd;
		kvm_riscv_gstage_unmap_range(&gstage, 0UL, kvm_riscv_gstage_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(kvm_riscv_gstage_pgd_size));
}

void kvm_riscv_mmu_update_hgatp(struct kvm_vcpu *vcpu)
{
	unsigned long hgatp = kvm_riscv_gstage_mode << HGATP_MODE_SHIFT;
	struct kvm_arch *k = &vcpu->kvm->arch;

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

	ncsr_write(CSR_HGATP, hgatp);

	if (!kvm_riscv_gstage_vmid_bits())
		kvm_riscv_local_hfence_gvma_all();
}