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
|
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2019 Facebook */
#include <linux/hash.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/ftrace.h>
#include <linux/rbtree_latch.h>
#include <linux/perf_event.h>
#include <linux/btf.h>
#include <linux/rcupdate_trace.h>
#include <linux/rcupdate_wait.h>
/* dummy _ops. The verifier will operate on target program's ops. */
const struct bpf_verifier_ops bpf_extension_verifier_ops = {
};
const struct bpf_prog_ops bpf_extension_prog_ops = {
};
/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
#define TRAMPOLINE_HASH_BITS 10
#define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS)
static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];
/* serializes access to trampoline_table */
static DEFINE_MUTEX(trampoline_mutex);
void *bpf_jit_alloc_exec_page(void)
{
void *image;
image = bpf_jit_alloc_exec(PAGE_SIZE);
if (!image)
return NULL;
set_vm_flush_reset_perms(image);
/* Keep image as writeable. The alternative is to keep flipping ro/rw
* everytime new program is attached or detached.
*/
set_memory_x((long)image, 1);
return image;
}
void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym)
{
ksym->start = (unsigned long) data;
ksym->end = ksym->start + PAGE_SIZE;
bpf_ksym_add(ksym);
perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
PAGE_SIZE, false, ksym->name);
}
void bpf_image_ksym_del(struct bpf_ksym *ksym)
{
bpf_ksym_del(ksym);
perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start,
PAGE_SIZE, true, ksym->name);
}
static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
{
struct bpf_ksym *ksym = &tr->ksym;
snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key);
bpf_image_ksym_add(tr->image, ksym);
}
static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
{
struct bpf_trampoline *tr;
struct hlist_head *head;
void *image;
int i;
mutex_lock(&trampoline_mutex);
head = &trampoline_table[hash_64(key, TRAMPOLINE_HASH_BITS)];
hlist_for_each_entry(tr, head, hlist) {
if (tr->key == key) {
refcount_inc(&tr->refcnt);
goto out;
}
}
tr = kzalloc(sizeof(*tr), GFP_KERNEL);
if (!tr)
goto out;
/* is_root was checked earlier. No need for bpf_jit_charge_modmem() */
image = bpf_jit_alloc_exec_page();
if (!image) {
kfree(tr);
tr = NULL;
goto out;
}
tr->key = key;
INIT_HLIST_NODE(&tr->hlist);
hlist_add_head(&tr->hlist, head);
refcount_set(&tr->refcnt, 1);
mutex_init(&tr->mutex);
for (i = 0; i < BPF_TRAMP_MAX; i++)
INIT_HLIST_HEAD(&tr->progs_hlist[i]);
tr->image = image;
INIT_LIST_HEAD_RCU(&tr->ksym.lnode);
bpf_trampoline_ksym_add(tr);
out:
mutex_unlock(&trampoline_mutex);
return tr;
}
static int is_ftrace_location(void *ip)
{
long addr;
addr = ftrace_location((long)ip);
if (!addr)
return 0;
if (WARN_ON_ONCE(addr != (long)ip))
return -EFAULT;
return 1;
}
static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr)
{
void *ip = tr->func.addr;
int ret;
if (tr->func.ftrace_managed)
ret = unregister_ftrace_direct((long)ip, (long)old_addr);
else
ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
return ret;
}
static int modify_fentry(struct bpf_trampoline *tr, void *old_addr, void *new_addr)
{
void *ip = tr->func.addr;
int ret;
if (tr->func.ftrace_managed)
ret = modify_ftrace_direct((long)ip, (long)old_addr, (long)new_addr);
else
ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, new_addr);
return ret;
}
/* first time registering */
static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
{
void *ip = tr->func.addr;
int ret;
ret = is_ftrace_location(ip);
if (ret < 0)
return ret;
tr->func.ftrace_managed = ret;
if (tr->func.ftrace_managed)
ret = register_ftrace_direct((long)ip, (long)new_addr);
else
ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
return ret;
}
static struct bpf_tramp_progs *
bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total)
{
const struct bpf_prog_aux *aux;
struct bpf_tramp_progs *tprogs;
struct bpf_prog **progs;
int kind;
*total = 0;
tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
if (!tprogs)
return ERR_PTR(-ENOMEM);
for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
tprogs[kind].nr_progs = tr->progs_cnt[kind];
*total += tr->progs_cnt[kind];
progs = tprogs[kind].progs;
hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist)
*progs++ = aux->prog;
}
return tprogs;
}
static int bpf_trampoline_update(struct bpf_trampoline *tr)
{
void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2;
void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2;
struct bpf_tramp_progs *tprogs;
u32 flags = BPF_TRAMP_F_RESTORE_REGS;
int err, total;
tprogs = bpf_trampoline_get_progs(tr, &total);
if (IS_ERR(tprogs))
return PTR_ERR(tprogs);
if (total == 0) {
err = unregister_fentry(tr, old_image);
tr->selector = 0;
goto out;
}
if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
/* Though the second half of trampoline page is unused a task could be
* preempted in the middle of the first half of trampoline and two
* updates to trampoline would change the code from underneath the
* preempted task. Hence wait for tasks to voluntarily schedule or go
* to userspace.
* The same trampoline can hold both sleepable and non-sleepable progs.
* synchronize_rcu_tasks_trace() is needed to make sure all sleepable
* programs finish executing.
* Wait for these two grace periods together.
*/
synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace);
err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
&tr->func.model, flags, tprogs,
tr->func.addr);
if (err < 0)
goto out;
if (tr->selector)
/* progs already running at this address */
err = modify_fentry(tr, old_image, new_image);
else
/* first time registering */
err = register_fentry(tr, new_image);
if (err)
goto out;
tr->selector++;
out:
kfree(tprogs);
return err;
}
static
|