aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/unwind_orc.c
blob: 2701b370e58fef1973ccb7cdfdabb489a537eed1 (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
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
#include <linux/module.h>
#include <linux/sort.h>
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
#include <asm/orc_types.h>
#include <asm/orc_lookup.h>

#define orc_warn(fmt, ...) \
	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)

extern int __start_orc_unwind_ip[];
extern int __stop_orc_unwind_ip[];
extern struct orc_entry __start_orc_unwind[];
extern struct orc_entry __stop_orc_unwind[];

static DEFINE_MUTEX(sort_mutex);
int *cur_orc_ip_table = __start_orc_unwind_ip;
struct orc_entry *cur_orc_table = __start_orc_unwind;

unsigned int lookup_num_blocks;
bool orc_init;

static inline unsigned long orc_ip(const int *ip)
{
	return (unsigned long)ip + *ip;
}

static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
				    unsigned int num_entries, unsigned long ip)
{
	int *first = ip_table;
	int *last = ip_table + num_entries - 1;
	int *mid = first, *found = first;

	if (!num_entries)
		return NULL;

	/*
	 * Do a binary range search to find the rightmost duplicate of a given
	 * starting address.  Some entries are section terminators which are
	 * "weak" entries for ensuring there are no gaps.  They should be
	 * ignored when they conflict with a real entry.
	 */
	while (first <= last) {
		mid = first + ((last - first) / 2);

		if (orc_ip(mid) <= ip) {
			found = mid;
			first = mid + 1;
		} else
			last = mid - 1;
	}

	return u_table + (found - ip_table);
}

#ifdef CONFIG_MODULES
static struct orc_entry *orc_module_find(unsigned long ip)
{
	struct module *mod;

	mod = __module_address(ip);
	if (!mod || !mod->arch.orc_unwind || !mod->arch.orc_unwind_ip)
		return NULL;
	return __orc_find(mod->arch.orc_unwind_ip, mod->arch.orc_unwind,
			  mod->arch.num_orcs, ip);
}
#else
static struct orc_entry *orc_module_find(unsigned long ip)
{
	return NULL;
}
#endif

#ifdef CONFIG_DYNAMIC_FTRACE
static struct orc_entry *orc_find(unsigned long ip);

/*
 * Ftrace dynamic trampolines do not have orc entries of their own.
 * But they are copies of the ftrace entries that are static and
 * defined in ftrace_*.S, which do have orc entries.
 *
 * If the undwinder comes across a ftrace trampoline, then find the
 * ftrace function that was used to create it, and use that ftrace
 * function's orc entrie, as the placement of the return code in
 * the stack will be identical.
 */
static struct orc_entry *orc_ftrace_find(unsigned long ip)
{
	struct ftrace_ops *ops;
	unsigned long caller;

	ops = ftrace_ops_trampoline(ip);
	if (!ops)
		return NULL;

	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
		caller = (unsigned long)ftrace_regs_call;
	else
		caller = (unsigned long)ftrace_call;

	/* Prevent unlikely recursion */
	if (ip == caller)
		return NULL;

	return orc_find(caller);
}
#else
static struct orc_entry *orc_ftrace_find(unsigned long ip)
{
	return NULL;
}
#endif

/*
 * If we crash with IP==0, the last successfully executed instruction
 * was probably an indirect function call with a NULL function pointer,
 * and we don't have unwind information for NULL.
 * This hardcoded ORC entry for IP==0 allows us to unwind from a NULL function
 * pointer into its parent and then continue normally from there.
 */
static struct orc_entry null_orc_entry = {
	.sp_offset = sizeof(long),
	.sp_reg = ORC_REG_SP,
	.bp_reg = ORC_REG_UNDEFINED,
	.type = ORC_TYPE_CALL
};

static struct orc_entry *orc_find(unsigned long ip)
{
	static struct orc_entry *orc;

	if (ip == 0)
		return &null_orc_entry;

	/* For non-init vmlinux addresses, use the fast lookup table: */
	if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) {
		unsigned int idx, start, stop;

		idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE;

		if (unlikely((idx >= lookup_num_blocks-1))) {
			orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%pB\n",
				 idx, lookup_num_blocks, (void *)ip);
			return NULL;
		}

		start = orc_lookup[idx];
		stop = orc_lookup[idx + 1] + 1;

		if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) ||
			     (__start_orc_unwind + stop > __stop_orc_unwind))) {
			orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%pB\n",
				 idx, lookup_num_blocks, start, stop, (void *)ip);
			return NULL;
		}

		return __orc_find(__start_orc_unwind_ip + start,
				  __start_orc_unwind + start, stop - start, ip);
	}

	/* vmlinux .init slow lookup: */
	if (init_kernel_text(ip))
		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);

	/* Module lookup: */
	orc = orc_module_find(ip);
	if (orc)
		return orc;

	return orc_ftrace_find(ip);
}

static void orc_sort_swap(void *_a, void *_b, int size)
{
	struct orc_entry *orc_a, *orc_b;
	struct orc_entry orc_tmp;
	int *a = _a, *b = _b, tmp;
	int delta = _b - _a;

	/* Swap the .orc_unwind_ip entries: */
	tmp = *a;
	*a = *b + delta;
	*b = tmp - delta;

	/* Swap the corresponding .orc_unwind entries: */
	orc_a = cur_orc_table + (a - cur_orc_ip_table);
	orc_b = cur_orc_table + (b - cur_orc_ip_table);
	orc_tmp = *orc_a;
	*orc_a = *orc_b;
	*orc_b = orc_tmp;
}

static int orc_sort_cmp(const void *_a, const void *_b)
{
	struct orc_entry *orc_a;
	const int *a = _a, *b = _b;
	unsigned long a_val = orc_ip(a);
	unsigned long b_val = orc_ip(b);

	if (a_val > b_val)
		return 1;
	if (a_val < b_val)
		return -1;

	/*
	 * The "weak" section terminator entries need to always be on the left
	 * to ensure the lookup code skips them in favor of real entries.
	 * These terminator entries exist to handle any gaps created by
	 * whitelisted .o files which didn't get objtool generation.
	 */
	orc_a = cur_orc_table + (a - cur_orc_ip_table);
	return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1;
}

#ifdef CONFIG_MODULES
void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size,
			void *_orc, size_t orc_size)
{
	int *orc_ip = _orc_ip;
	struct orc_entry *orc = _orc;
	unsigned int num_entries = orc_ip_size / sizeof(int);

	WARN_ON_ONCE(orc_ip_size % sizeof(int) != 0 ||
		     orc_size % sizeof(*orc) != 0 ||
		     num_entries != orc_size / sizeof(*orc));

	/*
	 * The 'cur_orc_*' globals allow the orc_sort_swap() callback to
	 * associate an .orc_unwind_ip table entry with its corresponding
	 * .orc_unwind entry so they can both be swapped.
	 */
	mutex_lock(&sort_mutex);
	cur_orc_ip_table = orc_ip;
	cur_orc_table = orc;
	sort(orc_ip, num_entries, sizeof(int), orc_sort_cmp, orc_sort_swap);
	mutex_unlock(&sort_mutex);

	mod->arch.orc_unwind_ip = orc_ip;
	mod->arch.orc_unwind = orc;
	mod->arch.num_orcs = num_entries;
}
#endif

void __init unwind_init(void)
{
	size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip;
	size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind;
	size_t num_entries = orc_ip_size / sizeof(int);
	struct orc_entry *orc;
	int i;

	if (!num_entries || orc_ip_size % sizeof(int) != 0 ||
	    orc_size % sizeof(struct orc_entry) != 0 ||
	    num_entries != orc_size / sizeof(struct orc_entry)) {
		orc_warn("WARNING: Bad or missing .orc_unwind table.  Disabling unwinder.\n");
		return;
	}

	/* Sort the .orc_unwind and .orc_unwind_ip tables: */
	sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp,
	     orc_sort_swap);

	/* Initialize the fast lookup table: */
	lookup_num_blocks = orc_lookup_end - orc_lookup;
	for (i = 0; i < lookup_num_blocks-1; i++) {
		orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
				 num_entries,
				 LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i));
		if (!orc) {
			orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
			return;
		}

		orc_lookup[i] = orc - __start_orc_unwind;
	}

	/* Initialize the ending block: */
	orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries,
			 LOOKUP_STOP_IP);
	if (!orc) {
		orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
		return;
	}
	orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind;

	orc_init = true;
}

unsigned long unwind_get_return_address(struct unwind_state *state)
{
	if (unwind_done(state))
		return 0;

	return __kernel_text_address(state->ip) ? state->ip : 0;
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);

unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
{
	struct task_struct *task = state->task;

	if (unwind_done(state))
		return NULL;

	if (state->regs)
		return &state->regs->ip;

	if (task != current && state->sp == task->thread.sp) {
		struct inactive_task_frame *frame = (void *)task->thread.sp;
		return &frame->ret_addr;
	}

	if (state->sp)
		return (unsigned long *)state->sp - 1;

	return NULL;
}

static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
			    size_t len)
{
	struct stack_info *info = &state->stack_info;
	void *addr = (void *)_addr;

	if (!on_stack(info, addr, len) &&
	    (get_stack_info(addr, state->task, info, &state->stack_mask)))
		return false;

	return true;
}

static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
			    unsigned long *val)
{
	if (!stack_access_ok(state, addr, sizeof(long)))
		return false;

	*val = READ_ONCE_NOCHECK(*(unsigned long *)addr);
	return true;
}

static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
			     unsigned long *ip, unsigned long *sp)
{
	struct pt_regs *regs = (struct pt_regs *)addr;

	/* x86-32 support will be more complicated due to the &regs->sp hack */
	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32));

	if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
		return false;

	*ip = regs->ip;
	*sp = regs->sp;
	return true;
}

static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr,
				  unsigned long *ip, unsigned long *sp)
{
	struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET;

	if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
		return false;

	*ip = regs->ip;
	*sp = regs->sp;
	return true;
}

/*
 * If state->regs is non-NULL, and points to a full pt_regs, just get the reg
 * value from state->regs.
 *
 * Otherwise, if state->regs just points to IRET regs, and the previous frame
 * had full regs, it's safe to get the value from the previous regs.  This can
 * happen when early/late IRQ entry code gets interrupted by an NMI.
 */
static bool get_reg(struct unwind_state *state, unsigned int reg_off,
		    unsigned long *val)
{
	unsigned int reg = reg_off/8;

	if (!state->regs)
		return false;

	if (state->full_regs) {
		*val = ((unsigned long *)state->regs)[reg];
		return true;
	}

	if (state->prev_regs) {
		*val = ((unsigned long *)state->prev_regs)[reg];
		return true;
	}

	return false;
}

bool unwind_next_frame(struct unwind_state *state)
{
	unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp;
	enum stack_type prev_type = state->stack_info.type;
	struct orc_entry *orc;
	bool indirect = false;

	if (unwind_done(state))
		return false;

	/* Don't let modules unload while we're reading their ORC data. */
	preempt_disable();

	/* End-of-stack check for user tasks: */
	if (state->regs && user_mode(state->regs))
		goto the_end;

	/*
	 * Find the orc_entry associated with the text address.
	 *
	 * Decrement call return addresses by one so they work for sibling
	 * calls and calls to noreturn functions.
	 */
	orc = orc_find(state->signal ? state->ip : state->ip - 1);
	if (!orc)
		goto err;

	/* End-of-stack check for kernel threads: */
	if (orc->sp_reg == ORC_REG_UNDEFINED) {
		if (!orc->end)
			goto err;

		goto the_end;
	}

	/* Find the previous frame's stack: */
	switch (orc->sp_reg) {
	case ORC_REG_SP:
		sp = state->sp + orc->sp_offset;
		break;

	case ORC_REG_BP:
		sp = state->bp + orc->sp_offset;
		break;

	case ORC_REG_SP_INDIRECT:
		sp = state->sp + orc->sp_offset;
		indirect = true;
		break;

	case ORC_REG_BP_INDIRECT:
		sp = state->bp + orc->sp_offset;
		indirect = true;
		break;

	case ORC_REG_R10:
		if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) {
			orc_warn("missing regs for base reg R10 at ip %pB\n",
				 (void *)state->ip);
			goto err;
		}
		break;

	case ORC_REG_R13:
		if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) {
			orc_warn("missing regs for base reg R13 at ip %pB\n",
				 (void *)state->ip);
			goto err;
		}
		break;

	case ORC_REG_DI:
		if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) {
			orc_warn("missing regs for base reg DI at ip %pB\n",
				 (void *)state->ip);
			goto err;
		}
		break;

	case ORC_REG_DX:
		if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) {
			orc_warn("missing regs for base reg DX at ip %pB\n",
				 (void *)state->ip);
			goto err;
		}
		break;

	default:
		orc_warn("unknown SP base reg %d for ip %pB\n",
			 orc->sp_reg, (void *)state->ip);
		goto err;
	}

	if (indirect) {
		if (!deref_stack_reg(state, sp, &sp))
			goto err;
	}

	/* Find IP, SP and possibly regs: */
	switch (orc->type) {
	case ORC_TYPE_CALL:
		ip_p = sp - sizeof(long);

		if (!deref_stack_reg(state, ip_p, &state->ip))
			goto err;

		state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
						  state->ip, (void *)ip_p);

		state->sp = sp;
		state->regs = NULL;
		state->prev_regs = NULL;
		state->signal = false;
		break;

	case ORC_TYPE_REGS:
		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
			orc_warn("can't dereference registers at %p for ip %pB\n",
				 (void *)sp, (void *)orig_ip);
			goto err;
		}

		state->regs = (struct pt_regs *)sp;
		state->prev_regs = NULL;
		state->full_regs = true;
		state->signal = true;
		break;

	case ORC_TYPE_REGS_IRET:
		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
			orc_warn("can't dereference iret registers at %p for ip %pB\n",
				 (void *)sp, (void *)orig_ip);
			goto err;
		}

		if (state->full_regs)
			state->prev_regs = state->regs;
		state->regs = (void *)sp - IRET_FRAME_OFFSET;
		state->full_regs = false;
		state->signal = true;
		break;

	default:
		orc_warn("unknown .orc_unwind entry type %d for ip %pB\n",
			 orc->type, (void *)orig_ip);
		goto err;
	}

	/* Find BP: */
	switch (orc->bp_reg) {
	case ORC_REG_UNDEFINED:
		if (get_reg(state, offsetof(struct pt_regs, bp), &tmp))
			state->bp = tmp;
		break;

	case ORC_REG_PREV_SP:
		if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp))
			goto err;
		break;

	case ORC_REG_BP:
		if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp))
			goto err;
		break;

	default:
		orc_warn("unknown BP base reg %d for ip %pB\n",
			 orc->bp_reg, (void *)orig_ip);
		goto err;
	}

	/* Prevent a recursive loop due to bad ORC data: */
	if (state->stack_info.type == prev_type &&
	    on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) &&
	    state->sp <= prev_sp) {
		orc_warn("stack going in the wrong direction? ip=%pB\n",
			 (void *)orig_ip);
		goto err;
	}

	preempt_enable();
	return true;

err:
	state->error = true;

the_end:
	preempt_enable();
	state->stack_info.type = STACK_TYPE_UNKNOWN;
	return false;
}
EXPORT_SYMBOL_GPL(unwind_next_frame);

void __unwind_start(struct unwind_state *state, struct task_struct *task,
		    struct pt_regs *regs, unsigned long *first_frame)
{
	memset(state, 0, sizeof(*state));
	state->task = task;

	if (!orc_init)
		goto err;

	/*
	 * Refuse to unwind the stack of a task while it's executing on another
	 * CPU.  This check is racy, but that's ok: the unwinder has other
	 * checks to prevent it from going off the rails.
	 */
	if (task_on_another_cpu(task))
		goto err;

	if (regs) {
		if (user_mode(regs))
			goto the_end;

		state->ip = regs->ip;
		state->sp = kernel_stack_pointer(regs);
		state->bp = regs->bp;
		state->regs = regs;
		state->full_regs = true;
		state->signal = true;

	} else if (task == current) {
		asm volatile("lea (%%rip), %0\n\t"
			     "mov %%rsp, %1\n\t"
			     "mov %%rbp, %2\n\t"
			     : "=r" (state->ip), "=r" (state->sp),
			       "=r" (state->bp));

	} else {
		struct inactive_task_frame *frame = (void *)task->thread.sp;

		state->sp = task->thread.sp;
		state->bp = READ_ONCE_NOCHECK(frame->bp);
		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
	}

	if (get_stack_info((unsigned long *)state->sp, state->task,
			   &state->stack_info, &state->stack_mask)) {
		/*
		 * We weren't on a valid stack.  It's possible that
		 * we overflowed a valid stack into a guard page.
		 * See if the next page up is valid so that we can
		 * generate some kind of backtrace if this happens.
		 */
		void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp);
		state->error = true;
		if (get_stack_info(next_page, state->task, &state->stack_info,
				   &state->stack_mask))
			return;
	}

	/*
	 * The caller can provide the address of the first frame directly
	 * (first_frame) or indirectly (regs->sp) to indicate which stack frame
	 * to start unwinding at.  Skip ahead until we reach it.
	 */

	/* When starting from regs, skip the regs frame: */
	if (regs) {
		unwind_next_frame(state);
		return;
	}

	/* Otherwise, skip ahead to the user-specified starting frame: */
	while (!unwind_done(state) &&
	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
			state->sp < (unsigned long)first_frame))
		unwind_next_frame(state);

	return;

err:
	state->error = true;
the_end:
	state->stack_info.type = STACK_TYPE_UNKNOWN;
}
EXPORT_SYMBOL_GPL(__unwind_start);