summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/ftrace.c
blob: 3386dc9aa3330ac032523032a72e22fc9066c40b (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
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
/*
 * Code for replacing ftrace calls with jumps.
 *
 * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
 *
 * Thanks goes to Ingo Molnar, for suggesting the idea.
 * Mathieu Desnoyers, for suggesting postponing the modifications.
 * Arjan van de Ven, for keeping me straight, and explaining to me
 * the dangers of modifying code on the run.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/spinlock.h>
#include <linux/hardirq.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/module.h>

#include <trace/syscall.h>

#include <asm/cacheflush.h>
#include <asm/kprobes.h>
#include <asm/ftrace.h>
#include <asm/nops.h>

#ifdef CONFIG_DYNAMIC_FTRACE

int ftrace_arch_code_modify_prepare(void)
{
	set_kernel_text_rw();
	set_all_modules_text_rw();
	return 0;
}

int ftrace_arch_code_modify_post_process(void)
{
	set_all_modules_text_ro();
	set_kernel_text_ro();
	return 0;
}

union ftrace_code_union {
	char code[MCOUNT_INSN_SIZE];
	struct {
		char e8;
		int offset;
	} __attribute__((packed));
};

static int ftrace_calc_offset(long ip, long addr)
{
	return (int)(addr - ip);
}

static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
{
	static union ftrace_code_union calc;

	calc.e8		= 0xe8;
	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);

	/*
	 * No locking needed, this must be called via kstop_machine
	 * which in essence is like running on a uniprocessor machine.
	 */
	return calc.code;
}

static inline int
within(unsigned long addr, unsigned long start, unsigned long end)
{
	return addr >= start && addr < end;
}

static unsigned long text_ip_addr(unsigned long ip)
{
	/*
	 * On x86_64, kernel text mappings are mapped read-only with
	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
	 * of the kernel text mapping to modify the kernel text.
	 *
	 * For 32bit kernels, these mappings are same and we can use
	 * kernel identity mapping to modify code.
	 */
	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
		ip = (unsigned long)__va(__pa_symbol(ip));

	return ip;
}

static const unsigned char *ftrace_nop_replace(void)
{
	return ideal_nops[NOP_ATOMIC5];
}

static int
ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
		   unsigned const char *new_code)
{
	unsigned char replaced[MCOUNT_INSN_SIZE];

	/*
	 * Note: Due to modules and __init, code can
	 *  disappear and change, we need to protect against faulting
	 *  as well as code changing. We do this by using the
	 *  probe_kernel_* functions.
	 *
	 * No real locking needed, this code is run through
	 * kstop_machine, or before SMP starts.
	 */

	/* read the text we want to modify */
	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
		return -EFAULT;

	/* Make sure it is what we expect it to be */
	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
		return -EINVAL;

	ip = text_ip_addr(ip);

	/* replace the text with the new text */
	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
		return -EPERM;

	sync_core();

	return 0;
}

int ftrace_make_nop(struct module *mod,
		    struct dyn_ftrace *rec, unsigned long addr)
{
	unsigned const char *new, *old;
	unsigned long ip = rec->ip;

	old = ftrace_call_replace(ip, addr);
	new = ftrace_nop_replace();

	/*
	 * On boot up, and when modules are loaded, the MCOUNT_ADDR
	 * is converted to a nop, and will never become MCOUNT_ADDR
	 * again. This code is either running before SMP (on boot up)
	 * or before the code will ever be executed (module load).
	 * We do not want to use the breakpoint version in this case,
	 * just modify the code directly.
	 */
	if (addr == MCOUNT_ADDR)
		return ftrace_modify_code_direct(rec->ip, old, new);

	/* Normal cases use add_brk_on_nop */
	WARN_ONCE(1, "invalid use of ftrace_make_nop");
	return -EINVAL;
}

int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
	unsigned const char *new, *old;
	unsigned long ip = rec->ip;

	old = ftrace_nop_replace();
	new = ftrace_call_replace(ip, addr);

	/* Should only be called when module is loaded */
	return ftrace_modify_code_direct(rec->ip, old, new);
}

/*
 * The modifying_ftrace_code is used to tell the breakpoint
 * handler to call ftrace_int3_handler(). If it fails to
 * call this handler for a breakpoint added by ftrace, then
 * the kernel may crash.
 *
 * As atomic_writes on x86 do not need a barrier, we do not
 * need to add smp_mb()s for this to work. It is also considered
 * that we can not read the modifying_ftrace_code before
 * executing the breakpoint. That would be quite remarkable if
 * it could do that. Here's the flow that is required:
 *
 *   CPU-0                          CPU-1
 *
 * atomic_inc(mfc);
 * write int3s
 *				<trap-int3> // implicit (r)mb
 *				if (atomic_read(mfc))
 *					call ftrace_int3_handler()
 *
 * Then when we are finished:
 *
 * atomic_dec(mfc);
 *
 * If we hit a breakpoint that was not set by ftrace, it does not
 * matter if ftrace_int3_handler() is called or not. It will
 * simply be ignored. But it is crucial that a ftrace nop/caller
 * breakpoint is handled. No other user should ever place a
 * breakpoint on an ftrace nop/caller location. It must only
 * be done by this code.
 */
atomic_t modifying_ftrace_code __read_mostly;

static int
ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
		   unsigned const char *new_code);

/*
 * Should never be called:
 *  As it is only called by __ftrace_replace_code() which is called by
 *  ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
 *  which is called to turn mcount into nops or nops into function calls
 *  but not to convert a function from not using regs to one that uses
 *  regs, which ftrace_modify_call() is for.
 */
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
				 unsigned long addr)
{
	WARN_ON(1);
	return -EINVAL;
}

static unsigned long ftrace_update_func;

static int update_ftrace_func(unsigned long ip, void *new)
{
	unsigned char old[MCOUNT_INSN_SIZE];
	int ret;

	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);

	ftrace_update_func = ip;
	/* Make sure the breakpoints see the ftrace_update_func update */
	smp_wmb();

	/* See comment above by declaration of modifying_ftrace_code */
	atomic_inc(&modifying_ftrace_code);

	ret = ftrace_modify_code(ip, old, new);

	atomic_dec(&modifying_ftrace_code);

	return ret;
}

int ftrace_update_ftrace_func(ftrace_func_t func)
{
	unsigned long ip = (unsigned long)(&ftrace_call);
	unsigned char *new;
	int ret;

	new = ftrace_call_replace(ip, (unsigned long)func);
	ret = update_ftrace_func(ip, new);

	/* Also update the regs callback function */
	if (!ret) {
		ip = (unsigned long)(&ftrace_regs_call);
		new = ftrace_call_replace(ip, (unsigned long)func);
		ret = update_ftrace_func(ip, new);
	}

	return ret;
}

static int is_ftrace_caller(unsigned long ip)
{
	if (ip == ftrace_update_func)
		return 1;

	return 0;
}

/*
 * A breakpoint was added to the code address we are about to
 * modify, and this is the handle that will just skip over it.
 * We are either changing a nop into a trace call, or a trace
 * call to a nop. While the change is taking place, we treat
 * it just like it was a nop.
 */
int ftrace_int3_handler(struct pt_regs *regs)
{
	unsigned long ip;

	if (WARN_ON_ONCE(!regs))
		return 0;

	ip = regs->ip - 1;
	if (!ftrace_location(ip) && !is_ftrace_caller(ip))
		return 0;

	regs->ip += MCOUNT_INSN_SIZE - 1;

	return 1;
}

static int ftrace_write(unsigned long ip, const char *val, int size)
{
	ip = text_ip_addr(ip);

	if (probe_kernel_write((void *)ip, val, size))
		return -EPERM;

	return 0;
}

static int add_break(unsigned long ip, const char *old)
{
	unsigned char replaced[MCOUNT_INSN_SIZE];
	unsigned char brk = BREAKPOINT_INSTRUCTION;

	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
		return -EFAULT;

	/* Make sure it is what we expect it to be */
	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
		return -EINVAL;

	return ftrace_write(ip, &brk, 1);
}

static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
{
	unsigned const char *old;
	unsigned long ip = rec->ip;

	old = ftrace_call_replace(ip, addr);

	return add_break(rec->ip, old);
}


static int add_brk_on_nop(struct dyn_ftrace *rec)
{
	unsigned const char *old;

	old = ftrace_nop_replace();

	return add_break(rec->ip, old);
}

static int add_breakpoints(struct dyn_ftrace *rec, int enable)
{
	unsigned long ftrace_addr;
	int ret;

	ftrace_addr = ftrace_get_addr_curr(rec);

	ret = ftrace_test_record(rec, enable);

	switch (ret) {
	case FTRACE_UPDATE_IGNORE:
		return 0;

	case FTRACE_UPDATE_MAKE_CALL:
		/* converting nop to call */
		return add_brk_on_nop(rec);

	case FTRACE_UPDATE_MODIFY_CALL:
	case FTRACE_UPDATE_MAKE_NOP:
		/* converting a call to a nop */
		return add_brk_on_call(rec, ftrace_addr);
	}
	return 0;
}

/*
 * On error, we need to remove breakpoints. This needs to
 * be done caefully. If the address does not currently have a
 * breakpoint, we know we are done. Otherwise, we look at the
 * remaining 4 bytes of the instruction. If it matches a nop
 * we replace the breakpoint with the nop. Otherwise we replace
 * it with the call instruction.
 */
static int remove_breakpoint(struct dyn_ftrace *rec)
{
	unsigned char ins[MCOUNT_INSN_SIZE];
	unsigned char brk = BREAKPOINT_INSTRUCTION;
	const unsigned char *nop;
	unsigned long ftrace_addr;
	unsigned long ip = rec->ip;

	/* If we fail the read, just give up */
	if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE))
		return -EFAULT;

	/* If this does not have a breakpoint, we are done */
	if (ins[0] != brk)
		return 0;

	nop = ftrace_nop_replace();

	/*
	 * If the last 4 bytes of the instruction do not match
	 * a nop, then we assume that this is a call to ftrace_addr.
	 */
	if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) {
		/*
		 * For extra paranoidism, we check if the breakpoint is on
		 * a call that would actually jump to the ftrace_addr.
		 * If not, don't touch the breakpoint, we make just create
		 * a disaster.
		 */
		ftrace_addr = ftrace_get_addr_new(rec);
		nop = ftrace_call_replace(ip, ftrace_addr);

		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
			goto update;

		/* Check both ftrace_addr and ftrace_old_addr */
		ftrace_addr = ftrace_get_addr_curr(rec);
		nop = ftrace_call_replace(ip, ftrace_addr);

		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
			return -EINVAL;
	}

 update:
	return ftrace_write(ip, nop, 1);
}

static int add_update_code(unsigned long ip, unsigned const char *new)
{
	/* skip breakpoint */
	ip++;
	new++;
	return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1);
}

static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
{
	unsigned long ip = rec->ip;
	unsigned const char *new;

	new = ftrace_call_replace(ip, addr);
	return add_update_code(ip, new);
}

static int add_update_nop(struct dyn_ftrace *rec)
{
	unsigned long ip = rec->ip;
	unsigned const char *new;

	new = ftrace_nop_replace();
	return add_update_code(ip, new);
}

static int add_update(struct dyn_ftrace *rec, int enable)
{
	unsigned long ftrace_addr;
	int ret;

	ret = ftrace_test_record(rec, enable);

	ftrace_addr  = ftrace_get_addr_new(rec);

	switch (ret) {
	case FTRACE_UPDATE_IGNORE:
		return 0;

	case FTRACE_UPDATE_MODIFY_CALL:
	case FTRACE_UPDATE_MAKE_CALL:
		/* converting nop to call */
		return add_update_call(rec, ftrace_addr);

	case FTRACE_UPDATE_MAKE_NOP:
		/* converting a call to a nop */
		return add_update_nop(rec);
	}

	return 0;
}

static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
{
	unsigned long ip = rec->ip;
	unsigned const char *new;

	new = ftrace_call_replace(ip, addr);

	return ftrace_write(ip, new, 1);
}

static int finish_update_nop(struct dyn_ftrace *rec)
{
	unsigned long ip = rec->ip;
	unsigned const char *new;

	new = ftrace_nop_replace();

	return ftrace_write(ip, new, 1);
}

static int finish_update(struct dyn_ftrace *rec, int enable)
{
	unsigned long ftrace_addr;
	int ret;

	ret = ftrace_update_record(rec, enable);

	ftrace_addr = ftrace_get_addr_new(rec);

	switch (ret) {
	case FTRACE_UPDATE_IGNORE:
		return 0;

	case FTRACE_UPDATE_MODIFY_CALL:
	case FTRACE_UPDATE_MAKE_CALL:
		/* converting nop to call */
		return finish_update_call(rec, ftrace_addr);

	case FTRACE_UPDATE_MAKE_NOP:
		/* converting a call to a nop */
		return finish_update_nop(rec);
	}

	return 0;
}

static void do_sync_core(void *data)
{
	sync_core();
}

static void run_sync(void)
{
	int enable_irqs = irqs_disabled();

	/* We may be called with interrupts disbled (on bootup). */
	if (enable_irqs)
		local_irq_enable();
	on_each_cpu(do_sync_core, NULL, 1);
	if (enable_irqs)
		local_irq_disable();
}

void ftrace_replace_code(int enable)
{
	struct ftrace_rec_iter *iter;
	struct dyn_ftrace *rec;
	const char *report = "adding breakpoints";
	int count = 0;
	int ret;

	for_ftrace_rec_iter(iter) {
		rec = ftrace_rec_iter_record(iter);

		ret = add_breakpoints(rec, enable);
		if (ret)
			goto remove_breakpoints;
		count++;
	}

	run_sync();

	report = "updating code";

	for_ftrace_rec_iter(iter) {
		rec = ftrace_rec_iter_record(iter);

		ret = add_update(rec, enable);
		if (ret)
			goto remove_breakpoints;
	}

	run_sync();

	report = "removing breakpoints";

	for_ftrace_rec_iter(iter) {
		rec = ftrace_rec_iter_record(iter);

		ret = finish_update(rec, enable);
		if (ret)
			goto remove_breakpoints;
	}

	run_sync();

	return;

 remove_breakpoints:
	pr_warn("Failed on %s (%d):\n", report, count);
	ftrace_bug(ret, rec ? rec->ip : 0);
	for_ftrace_rec_iter(iter) {
		rec = ftrace_rec_iter_record(iter);
		/*
		 * Breakpoints are handled only when this function is in
		 * progress. The system could not work with them.
		 */
		if (remove_breakpoint(rec))
			BUG();
	}
	run_sync();
}

static int
ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
		   unsigned const char *new_code)
{
	int ret;

	ret = add_break(ip, old_code);
	if (ret)
		goto out;

	run_sync();

	ret = add_update_code(ip, new_code);
	if (ret)
		goto fail_update;

	run_sync();

	ret = ftrace_write(ip, new_code, 1);
	/*
	 * The breakpoint is handled only when this function is in progress.
	 * The system could not work if we could not remove it.
	 */
	BUG_ON(ret);
 out:
	run_sync();
	return ret;

 fail_update:
	/* Also here the system could not work with the breakpoint */
	if (ftrace_write(ip, old_code, 1))
		BUG();
	goto out;
}

void arch_ftrace_update_code(int command)
{
	/* See comment above by declaration of modifying_ftrace_code */
	atomic_inc(&modifying_ftrace_code);

	ftrace_modify_all_code(command);

	atomic_dec(&modifying_ftrace_code);
}

int __init ftrace_dyn_arch_init(void)
{
	return 0;
}
#endif

#ifdef CONFIG_FUNCTION_GRAPH_TRACER

#ifdef CONFIG_DYNAMIC_FTRACE
extern void ftrace_graph_call(void);

static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
{
	static union ftrace_code_union calc;

	/* Jmp not a call (ignore the .e8) */
	calc.e8		= 0xe9;
	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);

	/*
	 * ftrace external locks synchronize the access to the static variable.
	 */
	return calc.code;
}

static int ftrace_mod_jmp(unsigned long ip, void *func)
{
	unsigned char *new;

	new = ftrace_jmp_replace(ip, (unsigned long)func);

	return update_ftrace_func(ip, new);
}

int ftrace_enable_ftrace_graph_caller(void)
{
	unsigned long ip = (unsigned long)(&ftrace_graph_call);

	return ftrace_mod_jmp(ip, &ftrace_graph_caller);
}

int ftrace_disable_ftrace_graph_caller(void)
{
	unsigned long ip = (unsigned long)(&ftrace_graph_call);

	return ftrace_mod_jmp(ip, &ftrace_stub);
}

#endif /* !CONFIG_DYNAMIC_FTRACE */

/*
 * Hook the return address and push it in the stack of return addrs
 * in current thread info.
 */
void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
			   unsigned long frame_pointer)
{
	unsigned long old;
	int faulted;
	struct ftrace_graph_ent trace;
	unsigned long return_hooker = (unsigned long)
				&return_to_handler;

	if (unlikely(ftrace_graph_is_dead()))
		return;

	if (unlikely(atomic_read(&current->tracing_graph_pause)))
		return;

	/*
	 * Protect against fault, even if it shouldn't
	 * happen. This tool is too much intrusive to
	 * ignore such a protection.
	 */
	asm volatile(
		"1: " _ASM_MOV " (%[parent]), %[old]\n"
		"2: " _ASM_MOV " %[return_hooker], (%[parent])\n"
		"   movl $0, %[faulted]\n"
		"3:\n"

		".section .fixup, \"ax\"\n"
		"4: movl $1, %[faulted]\n"
		"   jmp 3b\n"
		".previous\n"

		_ASM_EXTABLE(1b, 4b)
		_ASM_EXTABLE(2b, 4b)

		: [old] "=&r" (old), [faulted] "=r" (faulted)
		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
		: "memory"
	);

	if (unlikely(faulted)) {
		ftrace_graph_stop();
		WARN_ON(1);
		return;
	}

	trace.func = self_addr;
	trace.depth = current->curr_ret_stack + 1;

	/* Only trace if the calling function expects to */
	if (!ftrace_graph_entry(&trace)) {
		*parent = old;
		return;
	}

	if (ftrace_push_return_trace(old, self_addr, &trace.depth,
		    frame_pointer) == -EBUSY) {
		*parent = old;
		return;
	}
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */