summaryrefslogtreecommitdiffstats
path: root/arch/arm64/include/asm/kvm_mmu.h
blob: fbe4ddd9da09d7bb9ce267d4a4a8d86cdc0a7ff1 (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
/*
 * 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>
#include <asm/cpufeature.h>

/*
 * As ARMv8.0 only has 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). We need to find out how many bits to mask.
 *
 * We want to build a set of page tables that cover both parts of the
 * idmap (the trampoline page used to initialize EL2), and our normal
 * runtime VA space, at the same time.
 *
 * Given that the kernel uses VA_BITS for its entire address space,
 * and that half of that space (VA_BITS - 1) is used for the linear
 * mapping, we can also limit the EL2 space to (VA_BITS - 1).
 *
 * The main question is "Within the VA_BITS space, does EL2 use the
 * top or the bottom half of that space to shadow the kernel's linear
 * mapping?". As we need to idmap the trampoline page, this is
 * determined by the range in which this page lives.
 *
 * If the page is in the bottom half, we have to use the top half. If
 * the page is in the top half, we have to use the bottom half:
 *
 * T = __pa_symbol(__hyp_idmap_text_start)
 * if (T & BIT(VA_BITS - 1))
 *	HYP_VA_MIN = 0  //idmap in upper half
 * else
 *	HYP_VA_MIN = 1 << (VA_BITS - 1)
 * HYP_VA_MAX = HYP_VA_MIN + (1 << (VA_BITS - 1)) - 1
 *
 * This of course assumes that the trampoline page exists within the
 * VA_BITS range. If it doesn't, then it means we're in the odd case
 * where the kernel idmap (as well as HYP) uses more levels than the
 * kernel runtime page tables (as seen when the kernel is configured
 * for 4k pages, 39bits VA, and yet memory lives just above that
 * limit, forcing the idmap to use 4 levels of page tables while the
 * kernel itself only uses 3). In this particular case, it doesn't
 * matter which side of VA_BITS we use, as we're guaranteed not to
 * conflict with anything.
 *
 * When using VHE, there are no separate hyp mappings and all KVM
 * functionality is already mapped as part of the main kernel
 * mappings, and none of this applies in that case.
 */

#ifdef __ASSEMBLY__

#include <asm/alternative.h>

/*
 * Convert a kernel VA into a HYP VA.
 * reg: VA to be converted.
 *
 * The actual code generation takes place in kvm_update_va_mask, and
 * the instructions below are only there to reserve the space and
 * perform the register allocation (kvm_update_va_mask uses the
 * specific registers encoded in the instructions).
 */
.macro kern_hyp_va	reg
alternative_cb kvm_update_va_mask
	and     \reg, \reg, #1		/* mask with va_mask */
	ror	\reg, \reg, #1		/* rotate to the first tag bit */
	add	\reg, \reg, #0		/* insert the low 12 bits of the tag */
	add	\reg, \reg, #0, lsl 12	/* insert the top 12 bits of the tag */
	ror	\reg, \reg, #63		/* rotate back */
alternative_cb_end
.endm

#else

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

void kvm_update_va_mask(struct alt_instr *alt,
			__le32 *origptr, __le32 *updptr, int nr_inst);

static inline unsigned long __kern_hyp_va(unsigned long v)
{
	asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n"
				    "ror %0, %0, #1\n"
				    "add %0, %0, #0\n"
				    "add %0, %0, #0, lsl 12\n"
				    "ror %0, %0, #63\n",
				    kvm_update_va_mask)
		     : "+r" (v));
	return v;
}

#define kern_hyp_va(v) 	((typeof(v))(__kern_hyp_va((unsigned long)(v))))

/*
 * Obtain the PC-relative address of a kernel symbol
 * s: symbol
 *
 * The goal of this macro is to return a symbol's address based on a
 * PC-relative computation, as opposed to a loading the VA from a
 * constant pool or something similar. This works well for HYP, as an
 * absolute VA is guaranteed to be wrong. Only use this if trying to
 * obtain the address of a symbol (i.e. not something you obtained by
 * following a pointer).
 */
#define hyp_symbol_addr(s)						\
	({								\
		typeof(s) *addr;					\
		asm("adrp	%0, %1\n"				\
		    "add	%0, %0, :lo12:%1\n"			\
		    : "=r" (addr) : "S" (&s));				\
		addr;							\
	})

/*
 * 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)

#include <asm/stage2_pgtable.h>

int create_hyp_mappings(void *from, void *to, pgprot_t prot);
int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
			   void __iomem **kaddr,
			   void __iomem **haddr);
int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
			     void **haddr);
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_get_idmap_vector(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 pte_t kvm_s2pte_mkwrite(pte_t pte)
{
	pte_val(pte) |= PTE_S2_RDWR;
	return pte;
}

static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
{
	pmd_val(pmd) |= PMD_S2_RDWR;
	return pmd;
}

static inline pte_t kvm_s2pte_mkexec(pte_t pte)
{
	pte_val(pte) &= ~PTE_S2_XN;
	return pte;
}

static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd)
{
	pmd_val(pmd) &= ~PMD_S2_XN;
	return pmd;
}

static inline void kvm_set_s2pte_readonly(pte_t *ptep)
{
	pteval_t old_pteval, pteval;

	pteval = READ_ONCE(pte_val(*ptep));
	do {
		old_pteval = pteval;
		pteval &= ~PTE_S2_RDWR;
		pteval |= PTE_S2_RDONLY;
		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
	} while (pteval != old_pteval);
}

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

static inline bool kvm_s2pte_exec(pte_t *ptep)
{
	return !(READ_ONCE(pte_val(*ptep)) & PTE_S2_XN);
}

static inline void kvm_set_s2pmd_readonly(pmd_t *pmdp)
{
	kvm_set_s2pte_readonly((pte_t *)pmdp);
}

static inline bool kvm_s2pmd_readonly(pmd_t *pmdp)
{
	return kvm_s2pte_readonly((pte_t *)pmdp);
}

static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
{
	return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
}

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

#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)

#ifdef __PAGETABLE_PMD_FOLDED
#define hyp_pmd_table_empty(pmdp) (0)
#else
#define hyp_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
#endif

#ifdef __PAGETABLE_PUD_FOLDED
#define hyp_pud_table_empty(pudp) (0)
#else
#define hyp_pud_table_empty(pudp) kvm_page_empty(pudp)
#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_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
}

static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
{
	void *va = page_address(pfn_to_page(pfn));

	kvm_flush_dcache_to_poc(va, size);
}

static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
						  unsigned long size)
{
	if (icache_is_aliasing()) {
		/* any kind of VIPT cache */
		__flush_icache_all();
	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
		void *va = page_address(pfn_to_page(pfn));

		invalidate_icache_range((unsigned long)va,
					(unsigned long)va + size);
	}
}

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)		__pa_symbol(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_level();
}

static inline unsigned long __kvm_idmap_ptrs_per_pgd(void)
{
	return idmap_ptrs_per_pgd;
}

/*
 * Can't use pgd_populate here, because the extended idmap adds an extra level
 * above CONFIG_PGTABLE_LEVELS (which is 2 or 3 if we're using the extended
 * idmap), and pgd_populate is only available if CONFIG_PGTABLE_LEVELS = 4.
 */
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;
	u64 pgd_addr;

	/*
	 * 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]));
	pgd_addr = __phys_to_pgd_val(__pa(hyp_pgd));
	merged_hyp_pgd[0] = __pgd(pgd_addr | 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]));
	pgd_addr = __phys_to_pgd_val(__pa(boot_hyp_pgd));
	merged_hyp_pgd[idmap_idx] = __pgd(pgd_addr | PMD_TYPE_TABLE);
}

static inline unsigned int kvm_get_vmid_bits(void)
{
	int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);

	return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
}

#ifdef CONFIG_KVM_INDIRECT_VECTORS
/*
 * EL2 vectors can be mapped and rerouted in a number of ways,
 * depending on the kernel configuration and CPU present:
 *
 * - If the CPU has the ARM64_HARDEN_BRANCH_PREDICTOR cap, the
 *   hardening sequence is placed in one of the vector slots, which is
 *   executed before jumping to the real vectors.
 *
 * - If the CPU has both the ARM64_HARDEN_EL2_VECTORS cap and the
 *   ARM64_HARDEN_BRANCH_PREDICTOR cap, the slot containing the
 *   hardening sequence is mapped next to the idmap page, and executed
 *   before jumping to the real vectors.
 *
 * - If the CPU only has the ARM64_HARDEN_EL2_VECTORS cap, then an
 *   empty slot is selected, mapped next to the idmap page, and
 *   executed before jumping to the real vectors.
 *
 * Note that ARM64_HARDEN_EL2_VECTORS is somewhat incompatible with
 * VHE, as we don't have hypervisor-specific mappings. If the system
 * is VHE and yet selects this capability, it will be ignored.
 */
#include <asm/mmu.h>

extern void *__kvm_bp_vect_base;
extern int __kvm_harden_el2_vector_slot;

static inline void *kvm_get_hyp_vector(void)
{
	struct bp_hardening_data *data = arm64_get_bp_hardening_data();
	void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
	int slot = -1;

	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start));
		slot = data->hyp_vectors_slot;
	}

	if (this_cpu_has_cap(ARM64_HARDEN_EL2_VECTORS) && !has_vhe()) {
		vect = __kvm_bp_vect_base;
		if (slot == -1)
			slot = __kvm_harden_el2_vector_slot;
	}

	if (slot != -1)
		vect += slot * SZ_2K;

	return vect;
}

/*  This is only called on a !VHE system */
static inline int kvm_map_vectors(void)
{
	/*
	 * HBP  = ARM64_HARDEN_BRANCH_PREDICTOR
	 * HEL2 = ARM64_HARDEN_EL2_VECTORS
	 *
	 * !HBP + !HEL2 -> use direct vectors
	 *  HBP + !HEL2 -> use hardened vectors in place
	 * !HBP +  HEL2 -> allocate one vector slot and use exec mapping
	 *  HBP +  HEL2 -> use hardened vertors and use exec mapping
	 */
	if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start);
		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
	}

	if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
		phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start);
		unsigned long size = (__bp_harden_hyp_vecs_end -
				      __bp_harden_hyp_vecs_start);

		/*
		 * Always allocate a spare vector slot, as we don't
		 * know yet which CPUs have a BP hardening slot that
		 * we can reuse.
		 */
		__kvm_harden_el2_vector_slot = atomic_inc_return(&arm64_el2_vector_last_slot);
		BUG_ON(__kvm_harden_el2_vector_slot >= BP_HARDEN_EL2_SLOTS);
		return create_hyp_exec_mappings(vect_pa, size,
						&__kvm_bp_vect_base);
	}

	return 0;
}
#else
static inline void *kvm_get_hyp_vector(void)
{
	return kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
}

static inline int kvm_map_vectors(void)
{
	return 0;
}
#endif

#ifdef CONFIG_ARM64_SSBD
DECLARE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);

static inline int hyp_map_aux_data(void)
{
	int cpu, err;

	for_each_possible_cpu(cpu) {
		u64 *ptr;

		ptr = per_cpu_ptr(&arm64_ssbd_callback_required, cpu);
		err = create_hyp_mappings(ptr, ptr + 1, PAGE_HYP);
		if (err)
			return err;
	}
	return 0;
}
#else
static inline int hyp_map_aux_data(void)
{
	return 0;
}
#endif

#define kvm_phys_to_vttbr(addr)		phys_to_ttbr(addr)

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