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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2020 SiFive
*/
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <linux/memory.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/stop_machine.h>
#include <asm/kprobes.h>
#include <asm/cacheflush.h>
#include <asm/fixmap.h>
#include <asm/ftrace.h>
#include <asm/patch.h>
#include <asm/sections.h>
struct patch_insn {
void *addr;
u32 *insns;
int ninsns;
atomic_t cpu_count;
};
int riscv_patch_in_stop_machine = false;
#ifdef CONFIG_MMU
static inline bool is_kernel_exittext(uintptr_t addr)
{
return system_state < SYSTEM_RUNNING &&
addr >= (uintptr_t)__exittext_begin &&
addr < (uintptr_t)__exittext_end;
}
/*
* The fix_to_virt(, idx) needs a const value (not a dynamic variable of
* reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses".
* So use '__always_inline' and 'const unsigned int fixmap' here.
*/
static __always_inline void *patch_map(void *addr, const unsigned int fixmap)
{
uintptr_t uintaddr = (uintptr_t) addr;
struct page *page;
if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr))
page = phys_to_page(__pa_symbol(addr));
else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
page = vmalloc_to_page(addr);
else
return addr;
BUG_ON(!page);
return (void *)set_fixmap_offset(fixmap, page_to_phys(page) +
(uintaddr & ~PAGE_MASK));
}
static void patch_unmap(int fixmap)
{
clear_fixmap(fixmap);
}
NOKPROBE_SYMBOL(patch_unmap);
static int __patch_insn_set(void *addr, u8 c, size_t len)
{
void *waddr = addr;
bool across_pages = (((uintptr_t)addr & ~PAGE_MASK) + len) > PAGE_SIZE;
/*
* Only two pages can be mapped at a time for writing.
*/
if (len + offset_in_page(addr) > 2 * PAGE_SIZE)
return -EINVAL;
/*
* Before reaching here, it was expected to lock the text_mutex
* already, so we don't need to give another lock here and could
* ensure that it was safe between each cores.
*/
lockdep_assert_held(&text_mutex);
preempt_disable();
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
waddr = patch_map(addr, FIX_TEXT_POKE0);
memset(waddr, c, len);
/*
* We could have just patched a function that is about to be
* called so make sure we don't execute partially patched
* instructions by flushing the icache as soon as possible.
*/
local_flush_icache_range((unsigned long)waddr,
(unsigned long)waddr + len);
patch_unmap(FIX_TEXT_POKE0);
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
preempt_enable();
return 0;
}
NOKPROBE_SYMBOL(__patch_insn_set);
static int __patch_insn_write(void *addr, const void *insn, size_t len)
{
void *waddr = addr;
bool across_pages = (((uintptr_t) addr & ~PAGE_MASK) + len) > PAGE_SIZE;
int ret;
/*
* Only two pages can be mapped at a time for writing.
*/
if (len + offset_in_page(addr) > 2 * PAGE_SIZE)
return -EINVAL;
/*
* Before reaching here, it was expected to lock the text_mutex
* already, so we don't need to give another lock here and could
* ensure that it was safe between each cores.
*
* We're currently using stop_machine() for ftrace & kprobes, and while
* that ensures text_mutex is held before installing the mappings it
* does not ensure text_mutex is held by the calling thread. That's
* safe but triggers a lockdep failure, so just elide it for that
* specific case.
*/
if (!riscv_patch_in_stop_machine)
lockdep_assert_held(&text_mutex);
preempt_disable();
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
waddr = patch_map(addr, FIX_TEXT_POKE0);
ret = copy_to_kernel_nofault(waddr, insn, len);
/*
* We could have just patched a function that is about to be
* called so make sure we don't execute partially patched
* instructions by flushing the icache as soon as possible.
*/
local_flush_icache_range((unsigned long)waddr,
(unsigned long)waddr + len);
patch_unmap(FIX_TEXT_POKE0);
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
preempt_enable();
return ret;
}
NOKPROBE_SYMBOL(__patch_insn_write);
#else
static int __patch_insn_set(void *addr, u8 c, size_t len)
{
memset(addr, c, len);
return 0;
}
NOKPROBE_SYMBOL(__patch_insn_set);
static int __patch_insn_write(void *addr, const void *insn, size_t len)
{
return copy_to_kernel_nofault(addr, insn, len);
}
NOKPROBE_SYMBOL(__patch_insn_write);
#endif /* CONFIG_MMU */
static int patch_insn_set(void *addr, u8 c, size_t len)
{
size_t patched = 0;
size_t size;
int ret = 0;
/*
* __patch_insn_set() can only work on 2 pages at a time so call it in a
* loop with len <= 2 * PAGE_SIZE.
*/
while (patched < len && !ret) {
size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched);
ret = __patch_insn_set(addr + patched, c, size);
patched += size;
}
return ret;
}
NOKPROBE_SYMBOL(patch_insn_set);
int patch_text_set_nosync(void *addr, u8 c, size_t len)
{
u32 *tp = addr;
int ret;
ret = patch_insn_set(tp, c, len);
return ret;
}
NOKPROBE_SYMBOL(patch_text_set_nosync);
int patch_insn_write(void *addr, const void *insn, size_t len)
{
size_t patched = 0;
size_t size;
int ret = 0;
/*
* Copy the instructions to the destination address, two pages at a time
* because __patch_insn_write() can only handle len <= 2 * PAGE_SIZE.
*/
while (patched < len && !ret) {
size = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(addr + patched), len - patched);
ret = __patch_insn_write(addr + patched, insn + patched, size);
patched += size;
}
return ret;
}
NOKPROBE_SYMBOL(patch_insn_write);
int patch_text_nosync(void *addr, const void *insns, size_t len)
{
u32 *tp = addr;
int ret;
ret = patch_insn_write(tp, insns, len);
return ret;
}
NOKPROBE_SYMBOL(patch_text_nosync);
static int patch_text_cb(void *data)
{
struct patch_insn *patch = data;
unsigned long len;
int i, ret = 0;
if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) {
for (i = 0; ret == 0 && i < patch->ninsns; i++) {
len = GET_INSN_LENGTH(patch->insns[i]);
ret = patch_insn_write(patch->addr + i * len, &patch->insns[i], len);
}
/*
* Make sure the patching store is effective *before* we
* increment the counter which releases all waiting CPUs
* by using the release variant of atomic increment. The
* release pairs with the call to local_flush_icache_all()
* on the waiting CPU.
*/
atomic_inc_return_release(&patch->cpu_count);
} else {
while (atomic_read(&patch->cpu_count) <= num_online_cpus())
cpu_relax();
local_flush_icache_all();
}
return ret;
}
NOKPROBE_SYMBOL(patch_text_cb);
int patch_text(void *addr, u32 *insns, int ninsns)
{
int ret;
struct patch_insn patch = {
.addr = addr,
.insns = insns,
.ninsns = ninsns,
.cpu_count = ATOMIC_INIT(0),
};
/*
* kprobes takes text_mutex, before calling patch_text(), but as we call
* calls stop_machine(), the lockdep assertion in patch_insn_write()
* gets confused by the context in which the lock is taken.
* Instead, ensure the lock is held before calling stop_machine(), and
* set riscv_patch_in_stop_machine to skip the check in
* patch_insn_write().
*/
lockdep_assert_held(&text_mutex);
riscv_patch_in_stop_machine = true;
ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask);
riscv_patch_in_stop_machine = false;
return ret;
}
NOKPROBE_SYMBOL(patch_text);
|