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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 ARM Ltd.
* Author: Marc Zyngier <marc.zyngier@arm.com>
*/
#include <linux/kvm_host.h>
#include <linux/random.h>
#include <linux/memblock.h>
#include <asm/alternative.h>
#include <asm/debug-monitors.h>
#include <asm/insn.h>
#include <asm/kvm_mmu.h>
#include <asm/memory.h>
/*
* The LSB of the HYP VA tag
*/
static u8 tag_lsb;
/*
* The HYP VA tag value with the region bit
*/
static u64 tag_val;
static u64 va_mask;
/*
* Compute HYP VA by using the same computation as kern_hyp_va().
*/
static u64 __early_kern_hyp_va(u64 addr)
{
addr &= va_mask;
addr |= tag_val << tag_lsb;
return addr;
}
/*
* Store a hyp VA <-> PA offset into a hyp-owned variable.
*/
static void init_hyp_physvirt_offset(void)
{
extern s64 kvm_nvhe_sym(hyp_physvirt_offset);
u64 kern_va, hyp_va;
/* Compute the offset from the hyp VA and PA of a random symbol. */
kern_va = (u64)kvm_ksym_ref(__hyp_text_start);
hyp_va = __early_kern_hyp_va(kern_va);
CHOOSE_NVHE_SYM(hyp_physvirt_offset) = (s64)__pa(kern_va) - (s64)hyp_va;
}
/*
* We want to generate a hyp VA with the following format (with V ==
* vabits_actual):
*
* 63 ... V | V-1 | V-2 .. tag_lsb | tag_lsb - 1 .. 0
* ---------------------------------------------------------
* | 0000000 | hyp_va_msb | random tag | kern linear VA |
* |--------- tag_val -----------|----- va_mask ---|
*
* which does not conflict with the idmap regions.
*/
__init void kvm_compute_layout(void)
{
phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
u64 hyp_va_msb;
/* Where is my RAM region? */
hyp_va_msb = idmap_addr & BIT(vabits_actual - 1);
hyp_va_msb ^= BIT(vabits_actual - 1);
tag_lsb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^
(u64)(high_memory - 1));
va_mask = GENMASK_ULL(tag_lsb - 1, 0);
tag_val = hyp_va_msb;
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && tag_lsb != (vabits_actual - 1)) {
/* We have some free bits to insert a random tag. */
tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
}
tag_val >>= tag_lsb;
init_hyp_physvirt_offset();
}
static u32 compute_instruction(int n, u32 rd, u32 rn)
{
u32 insn = AARCH64_BREAK_FAULT;
switch (n) {
case 0:
insn = aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_AND,
AARCH64_INSN_VARIANT_64BIT,
rn, rd, va_mask);
break;
case 1:
/* ROR is a variant of EXTR with Rm = Rn */
insn = aarch64_insn_gen_extr(AARCH64_INSN_VARIANT_64BIT,
rn, rn, rd,
tag_lsb);
break;
case 2:
insn = aarch64_insn_gen_add_sub_imm(rd, rn,
tag_val & GENMASK(11, 0),
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_ADSB_ADD);
break;
case 3:
insn = aarch64_insn_gen_add_sub_imm(rd, rn,
tag_val & GENMASK(23, 12),
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_ADSB_ADD);
break;
case 4:
/* ROR is a variant of EXTR with Rm = Rn */
insn = aarch64_insn_gen_extr(AARCH64_INSN_VARIANT_64BIT,
rn, rn, rd, 64 - tag_lsb);
break;
}
return insn;
}
void __init kvm_update_va_mask(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
int i;
BUG_ON(nr_inst != 5);
for (i = 0; i < nr_inst; i++) {
u32 rd, rn, insn, oinsn;
/*
* VHE doesn't need any address translation, let's NOP
* everything.
*
* Alternatively, if the tag is zero (because the layout
* dictates it and we don't have any spare bits in the
* address), NOP everything after masking the kernel VA.
*/
if (has_vhe() || (!tag_val && i > 0)) {
updptr[i] = cpu_to_le32(aarch64_insn_gen_nop());
continue;
}
oinsn = le32_to_cpu(origptr[i]);
rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, oinsn);
rn = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RN, oinsn);
insn = compute_instruction(i, rd, rn);
BUG_ON(insn == AARCH64_BREAK_FAULT);
updptr[i] = cpu_to_le32(insn);
}
}
void kvm_patch_vector_branch(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
u64 addr;
u32 insn;
BUG_ON(nr_inst != 4);
if (!cpus_have_const_cap(ARM64_SPECTRE_V3A) || WARN_ON_ONCE(has_vhe()))
return;
/*
* Compute HYP VA by using the same computation as kern_hyp_va()
*/
addr = __early_kern_hyp_va((u64)kvm_ksym_ref(__kvm_hyp_vector));
/* Use PC[10:7] to branch to the same vector in KVM */
addr |= ((u64)origptr & GENMASK_ULL(10, 7));
/*
* Branch over the preamble in order to avoid the initial store on
* the stack (which we already perform in the hardening vectors).
*/
addr += KVM_VECTOR_PREAMBLE;
/* movz x0, #(addr & 0xffff) */
insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
(u16)addr,
0,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_ZERO);
*updptr++ = cpu_to_le32(insn);
/* movk x0, #((addr >> 16) & 0xffff), lsl #16 */
insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
(u16)(addr >> 16),
16,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_KEEP);
*updptr++ = cpu_to_le32(insn);
/* movk x0, #((addr >> 32) & 0xffff), lsl #32 */
insn = aarch64_insn_gen_movewide(AARCH64_INSN_REG_0,
(u16)(addr >> 32),
32,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_KEEP);
*updptr++ = cpu_to_le32(insn);
/* br x0 */
insn = aarch64_insn_gen_branch_reg(AARCH64_INSN_REG_0,
AARCH64_INSN_BRANCH_NOLINK);
*updptr++ = cpu_to_le32(insn);
}
static void generate_mov_q(u64 val, __le32 *origptr, __le32 *updptr, int nr_inst)
{
u32 insn, oinsn, rd;
BUG_ON(nr_inst != 4);
/* Compute target register */
oinsn = le32_to_cpu(*origptr);
rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, oinsn);
/* movz rd, #(val & 0xffff) */
insn = aarch64_insn_gen_movewide(rd,
(u16)val,
0,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_ZERO);
*updptr++ = cpu_to_le32(insn);
/* movk rd, #((val >> 16) & 0xffff), lsl #16 */
insn = aarch64_insn_gen_movewide(rd,
(u16)(val >> 16),
16,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_KEEP);
*updptr++ = cpu_to_le32(insn);
/* movk rd, #((val >> 32) & 0xffff), lsl #32 */
insn = aarch64_insn_gen_movewide(rd,
(u16)(val >> 32),
32,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_KEEP);
*updptr++ = cpu_to_le32(insn);
/* movk rd, #((val >> 48) & 0xffff), lsl #48 */
insn = aarch64_insn_gen_movewide(rd,
(u16)(val >> 48),
48,
AARCH64_INSN_VARIANT_64BIT,
AARCH64_INSN_MOVEWIDE_KEEP);
*updptr++ = cpu_to_le32(insn);
}
void kvm_update_kimg_phys_offset(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
generate_mov_q(kimage_voffset + PHYS_OFFSET, origptr, updptr, nr_inst);
}
void kvm_get_kimage_voffset(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst)
{
generate_mov_q(kimage_voffset, origptr, updptr, nr_inst);
}
|
