aboutsummaryrefslogtreecommitdiff
path: root/arch/arm64/include/asm/kvm_mmu.h
blob: 61f1c0bfabd052400f8975ea69a3ac9ffa1fd24a (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
/*
 * Copyright (C) 2012,2013 - ARM Ltd
 * Author: Marc Zyngier <marc.zyngier@arm.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#ifndef __ARM64_KVM_MMU_H__
#define __ARM64_KVM_MMU_H__

#include <asm/page.h>
#include <asm/memory.h>

/*
 * As we only have the TTBR0_EL2 register, we cannot express
 * "negative" addresses. This makes it impossible to directly share
 * mappings with the kernel.
 *
 * Instead, give the HYP mode its own VA region at a fixed offset from
 * the kernel by just masking the top bits (which are all ones for a
 * kernel address).
 */
#define HYP_PAGE_OFFSET_SHIFT	VA_BITS
#define HYP_PAGE_OFFSET_MASK	((UL(1) << HYP_PAGE_OFFSET_SHIFT) - 1)
#define HYP_PAGE_OFFSET		(PAGE_OFFSET & HYP_PAGE_OFFSET_MASK)

/*
 * Our virtual mapping for the idmap-ed MMU-enable code. Must be
 * shared across all the page-tables. Conveniently, we use the last
 * possible page, where no kernel mapping will ever exist.
 */
#define TRAMPOLINE_VA		(HYP_PAGE_OFFSET_MASK & PAGE_MASK)

/*
 * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
 * levels in addition to the PGD and potentially the PUD which are
 * pre-allocated (we pre-allocate the fake PGD and the PUD when the Stage-2
 * tables use one level of tables less than the kernel.
 */
#ifdef CONFIG_ARM64_64K_PAGES
#define KVM_MMU_CACHE_MIN_PAGES	1
#else
#define KVM_MMU_CACHE_MIN_PAGES	2
#endif

#ifdef __ASSEMBLY__

/*
 * Convert a kernel VA into a HYP VA.
 * reg: VA to be converted.
 */
.macro kern_hyp_va	reg
	and	\reg, \reg, #HYP_PAGE_OFFSET_MASK
.endm

#else

#include <asm/pgalloc.h>
#include <asm/cachetype.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>

#define KERN_TO_HYP(kva)	((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)

/*
 * We currently only support a 40bit IPA.
 */
#define KVM_PHYS_SHIFT	(40)
#define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)

int create_hyp_mappings(void *from, void *to);
int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
void free_boot_hyp_pgd(void);
void free_hyp_pgds(void);

void stage2_unmap_vm(struct kvm *kvm);
int kvm_alloc_stage2_pgd(struct kvm *kvm);
void kvm_free_stage2_pgd(struct kvm *kvm);
int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
			  phys_addr_t pa, unsigned long size, bool writable);

int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);

void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);

phys_addr_t kvm_mmu_get_httbr(void);
phys_addr_t kvm_mmu_get_boot_httbr(void);
phys_addr_t kvm_get_idmap_vector(void);
phys_addr_t kvm_get_idmap_start(void);
int kvm_mmu_init(void);
void kvm_clear_hyp_idmap(void);

#define	kvm_set_pte(ptep, pte)		set_pte(ptep, pte)
#define	kvm_set_pmd(pmdp, pmd)		set_pmd(pmdp, pmd)

static inline void kvm_clean_pgd(pgd_t *pgd) {}
static inline void kvm_clean_pmd(pmd_t *pmd) {}
static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
static inline void kvm_clean_pte(pte_t *pte) {}
static inline void kvm_clean_pte_entry(pte_t *pte) {}

static inline void kvm_set_s2pte_writable(pte_t *pte)
{
	pte_val(*pte) |= PTE_S2_RDWR;
}

static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
{
	pmd_val(*pmd) |= PMD_S2_RDWR;
}

static inline void kvm_set_s2pte_readonly(pte_t *pte)
{
	pte_val(*pte) = (pte_val(*pte) & ~PTE_S2_RDWR) | PTE_S2_RDONLY;
}

static inline bool kvm_s2pte_readonly(pte_t *pte)
{
	return (pte_val(*pte) & PTE_S2_RDWR) == PTE_S2_RDONLY;
}

static inline void kvm_set_s2pmd_readonly(pmd_t *pmd)
{
	pmd_val(*pmd) = (pmd_val(*pmd) & ~PMD_S2_RDWR) | PMD_S2_RDONLY;
}

static inline bool kvm_s2pmd_readonly(pmd_t *pmd)
{
	return (pmd_val(*pmd) & PMD_S2_RDWR) == PMD_S2_RDONLY;
}


#define kvm_pgd_addr_end(addr, end)	pgd_addr_end(addr, end)
#define kvm_pud_addr_end(addr, end)	pud_addr_end(addr, end)
#define kvm_pmd_addr_end(addr, end)	pmd_addr_end(addr, end)

/*
 * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address
 * the entire IPA input range with a single pgd entry, and we would only need
 * one pgd entry.  Note that in this case, the pgd is actually not used by
 * the MMU for Stage-2 translations, but is merely a fake pgd used as a data
 * structure for the kernel pgtable macros to work.
 */
#if PGDIR_SHIFT > KVM_PHYS_SHIFT
#define PTRS_PER_S2_PGD_SHIFT	0
#else
#define PTRS_PER_S2_PGD_SHIFT	(KVM_PHYS_SHIFT - PGDIR_SHIFT)
#endif
#define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)

#define kvm_pgd_index(addr)	(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))

/*
 * If we are concatenating first level stage-2 page tables, we would have less
 * than or equal to 16 pointers in the fake PGD, because that's what the
 * architecture allows.  In this case, (4 - CONFIG_PGTABLE_LEVELS)
 * represents the first level for the host, and we add 1 to go to the next
 * level (which uses contatenation) for the stage-2 tables.
 */
#if PTRS_PER_S2_PGD <= 16
#define KVM_PREALLOC_LEVEL	(4 - CONFIG_PGTABLE_LEVELS + 1)
#else
#define KVM_PREALLOC_LEVEL	(0)
#endif

static inline void *kvm_get_hwpgd(struct kvm *kvm)
{
	pgd_t *pgd = kvm->arch.pgd;
	pud_t *pud;

	if (KVM_PREALLOC_LEVEL == 0)
		return pgd;

	pud = pud_offset(pgd, 0);
	if (KVM_PREALLOC_LEVEL == 1)
		return pud;

	BUG_ON(KVM_PREALLOC_LEVEL != 2);
	return pmd_offset(pud, 0);
}

static inline unsigned int kvm_get_hwpgd_size(void)
{
	if (KVM_PREALLOC_LEVEL > 0)
		return PTRS_PER_S2_PGD * PAGE_SIZE;
	return PTRS_PER_S2_PGD * sizeof(pgd_t);
}

static inline bool kvm_page_empty(void *ptr)
{
	struct page *ptr_page = virt_to_page(ptr);
	return page_count(ptr_page) == 1;
}

#define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep)

#ifdef __PAGETABLE_PMD_FOLDED
#define kvm_pmd_table_empty(kvm, pmdp) (0)
#else
#define kvm_pmd_table_empty(kvm, pmdp) \
	(kvm_page_empty(pmdp) && (!(kvm) || KVM_PREALLOC_LEVEL < 2))
#endif

#ifdef __PAGETABLE_PUD_FOLDED
#define kvm_pud_table_empty(kvm, pudp) (0)
#else
#define kvm_pud_table_empty(kvm, pudp) \
	(kvm_page_empty(pudp) && (!(kvm) || KVM_PREALLOC_LEVEL < 1))
#endif


struct kvm;

#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))

static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
{
	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
}

static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
					       unsigned long size,
					       bool ipa_uncached)
{
	void *va = page_address(pfn_to_page(pfn));

	if (!vcpu_has_cache_enabled(vcpu) || ipa_uncached)
		kvm_flush_dcache_to_poc(va, size);

	if (!icache_is_aliasing()) {		/* PIPT */
		flush_icache_range((unsigned long)va,
				   (unsigned long)va + size);
	} else if (!icache_is_aivivt()) {	/* non ASID-tagged VIVT */
		/* any kind of VIPT cache */
		__flush_icache_all();
	}
}

static inline void __kvm_flush_dcache_pte(pte_t pte)
{
	struct page *page = pte_page(pte);
	kvm_flush_dcache_to_poc(page_address(page), PAGE_SIZE);
}

static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
{
	struct page *page = pmd_page(pmd);
	kvm_flush_dcache_to_poc(page_address(page), PMD_SIZE);
}

static inline void __kvm_flush_dcache_pud(pud_t pud)
{
	struct page *page = pud_page(pud);
	kvm_flush_dcache_to_poc(page_address(page), PUD_SIZE);
}

#define kvm_virt_to_phys(x)		__virt_to_phys((unsigned long)(x))

void kvm_set_way_flush(struct kvm_vcpu *vcpu);
void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);

static inline bool __kvm_cpu_uses_extended_idmap(void)
{
	return __cpu_uses_extended_idmap();
}

static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
				       pgd_t *hyp_pgd,
				       pgd_t *merged_hyp_pgd,
				       unsigned long hyp_idmap_start)
{
	int idmap_idx;

	/*
	 * Use the first entry to access the HYP mappings. It is
	 * guaranteed to be free, otherwise we wouldn't use an
	 * extended idmap.
	 */
	VM_BUG_ON(pgd_val(merged_hyp_pgd[0]));
	merged_hyp_pgd[0] = __pgd(__pa(hyp_pgd) | PMD_TYPE_TABLE);

	/*
	 * Create another extended level entry that points to the boot HYP map,
	 * which contains an ID mapping of the HYP init code. We essentially
	 * merge the boot and runtime HYP maps by doing so, but they don't
	 * overlap anyway, so this is fine.
	 */
	idmap_idx = hyp_idmap_start >> VA_BITS;
	VM_BUG_ON(pgd_val(merged_hyp_pgd[idmap_idx]));
	merged_hyp_pgd[idmap_idx] = __pgd(__pa(boot_hyp_pgd) | PMD_TYPE_TABLE);
}

#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */