aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/alternative.c
blob: 15e8563e5c244e0712c9696a3367067044a300b3 (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
#define pr_fmt(fmt) "SMP alternatives: " fmt

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/stringify.h>
#include <linux/kprobes.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/memory.h>
#include <linux/stop_machine.h>
#include <linux/slab.h>
#include <linux/kdebug.h>
#include <asm/alternative.h>
#include <asm/sections.h>
#include <asm/pgtable.h>
#include <asm/mce.h>
#include <asm/nmi.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
#include <asm/fixmap.h>

#define MAX_PATCH_LEN (255-1)

static int __initdata_or_module debug_alternative;

static int __init debug_alt(char *str)
{
	debug_alternative = 1;
	return 1;
}
__setup("debug-alternative", debug_alt);

static int noreplace_smp;

static int __init setup_noreplace_smp(char *str)
{
	noreplace_smp = 1;
	return 1;
}
__setup("noreplace-smp", setup_noreplace_smp);

#ifdef CONFIG_PARAVIRT
static int __initdata_or_module noreplace_paravirt = 0;

static int __init setup_noreplace_paravirt(char *str)
{
	noreplace_paravirt = 1;
	return 1;
}
__setup("noreplace-paravirt", setup_noreplace_paravirt);
#endif

#define DPRINTK(fmt, ...)				\
do {							\
	if (debug_alternative)				\
		printk(KERN_DEBUG fmt, ##__VA_ARGS__);	\
} while (0)

/*
 * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
 * that correspond to that nop. Getting from one nop to the next, we
 * add to the array the offset that is equal to the sum of all sizes of
 * nops preceding the one we are after.
 *
 * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
 * nice symmetry of sizes of the previous nops.
 */
#if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
static const unsigned char intelnops[] =
{
	GENERIC_NOP1,
	GENERIC_NOP2,
	GENERIC_NOP3,
	GENERIC_NOP4,
	GENERIC_NOP5,
	GENERIC_NOP6,
	GENERIC_NOP7,
	GENERIC_NOP8,
	GENERIC_NOP5_ATOMIC
};
static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
{
	NULL,
	intelnops,
	intelnops + 1,
	intelnops + 1 + 2,
	intelnops + 1 + 2 + 3,
	intelnops + 1 + 2 + 3 + 4,
	intelnops + 1 + 2 + 3 + 4 + 5,
	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif

#ifdef K8_NOP1
static const unsigned char k8nops[] =
{
	K8_NOP1,
	K8_NOP2,
	K8_NOP3,
	K8_NOP4,
	K8_NOP5,
	K8_NOP6,
	K8_NOP7,
	K8_NOP8,
	K8_NOP5_ATOMIC
};
static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
{
	NULL,
	k8nops,
	k8nops + 1,
	k8nops + 1 + 2,
	k8nops + 1 + 2 + 3,
	k8nops + 1 + 2 + 3 + 4,
	k8nops + 1 + 2 + 3 + 4 + 5,
	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif

#if defined(K7_NOP1) && !defined(CONFIG_X86_64)
static const unsigned char k7nops[] =
{
	K7_NOP1,
	K7_NOP2,
	K7_NOP3,
	K7_NOP4,
	K7_NOP5,
	K7_NOP6,
	K7_NOP7,
	K7_NOP8,
	K7_NOP5_ATOMIC
};
static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
{
	NULL,
	k7nops,
	k7nops + 1,
	k7nops + 1 + 2,
	k7nops + 1 + 2 + 3,
	k7nops + 1 + 2 + 3 + 4,
	k7nops + 1 + 2 + 3 + 4 + 5,
	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif

#ifdef P6_NOP1
static const unsigned char p6nops[] =
{
	P6_NOP1,
	P6_NOP2,
	P6_NOP3,
	P6_NOP4,
	P6_NOP5,
	P6_NOP6,
	P6_NOP7,
	P6_NOP8,
	P6_NOP5_ATOMIC
};
static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
{
	NULL,
	p6nops,
	p6nops + 1,
	p6nops + 1 + 2,
	p6nops + 1 + 2 + 3,
	p6nops + 1 + 2 + 3 + 4,
	p6nops + 1 + 2 + 3 + 4 + 5,
	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
};
#endif

/* Initialize these to a safe default */
#ifdef CONFIG_X86_64
const unsigned char * const *ideal_nops = p6_nops;
#else
const unsigned char * const *ideal_nops = intel_nops;
#endif

void __init arch_init_ideal_nops(void)
{
	switch (boot_cpu_data.x86_vendor) {
	case X86_VENDOR_INTEL:
		/*
		 * Due to a decoder implementation quirk, some
		 * specific Intel CPUs actually perform better with
		 * the "k8_nops" than with the SDM-recommended NOPs.
		 */
		if (boot_cpu_data.x86 == 6 &&
		    boot_cpu_data.x86_model >= 0x0f &&
		    boot_cpu_data.x86_model != 0x1c &&
		    boot_cpu_data.x86_model != 0x26 &&
		    boot_cpu_data.x86_model != 0x27 &&
		    boot_cpu_data.x86_model < 0x30) {
			ideal_nops = k8_nops;
		} else if (boot_cpu_has(X86_FEATURE_NOPL)) {
			   ideal_nops = p6_nops;
		} else {
#ifdef CONFIG_X86_64
			ideal_nops = k8_nops;
#else
			ideal_nops = intel_nops;
#endif
		}
		break;
	default:
#ifdef CONFIG_X86_64
		ideal_nops = k8_nops;
#else
		if (boot_cpu_has(X86_FEATURE_K8))
			ideal_nops = k8_nops;
		else if (boot_cpu_has(X86_FEATURE_K7))
			ideal_nops = k7_nops;
		else
			ideal_nops = intel_nops;
#endif
	}
}

/* Use this to add nops to a buffer, then text_poke the whole buffer. */
static void __init_or_module add_nops(void *insns, unsigned int len)
{
	while (len > 0) {
		unsigned int noplen = len;
		if (noplen > ASM_NOP_MAX)
			noplen = ASM_NOP_MAX;
		memcpy(insns, ideal_nops[noplen], noplen);
		insns += noplen;
		len -= noplen;
	}
}

extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
void *text_poke_early(void *addr, const void *opcode, size_t len);

/* Replace instructions with better alternatives for this CPU type.
   This runs before SMP is initialized to avoid SMP problems with
   self modifying code. This implies that asymmetric systems where
   APs have less capabilities than the boot processor are not handled.
   Tough. Make sure you disable such features by hand. */

void __init_or_module apply_alternatives(struct alt_instr *start,
					 struct alt_instr *end)
{
	struct alt_instr *a;
	u8 *instr, *replacement;
	u8 insnbuf[MAX_PATCH_LEN];

	DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
	/*
	 * The scan order should be from start to end. A later scanned
	 * alternative code can overwrite a previous scanned alternative code.
	 * Some kernel functions (e.g. memcpy, memset, etc) use this order to
	 * patch code.
	 *
	 * So be careful if you want to change the scan order to any other
	 * order.
	 */
	for (a = start; a < end; a++) {
		instr = (u8 *)&a->instr_offset + a->instr_offset;
		replacement = (u8 *)&a->repl_offset + a->repl_offset;
		BUG_ON(a->replacementlen > a->instrlen);
		BUG_ON(a->instrlen > sizeof(insnbuf));
		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
		if (!boot_cpu_has(a->cpuid))
			continue;

		memcpy(insnbuf, replacement, a->replacementlen);

		/* 0xe8 is a relative jump; fix the offset. */
		if (*insnbuf == 0xe8 && a->replacementlen == 5)
		    *(s32 *)(insnbuf + 1) += replacement - instr;

		add_nops(insnbuf + a->replacementlen,
			 a->instrlen - a->replacementlen);

		text_poke_early(instr, insnbuf, a->instrlen);
	}
}

#ifdef CONFIG_SMP

static void alternatives_smp_lock(const s32 *start, const s32 *end,
				  u8 *text, u8 *text_end)
{
	const s32 *poff;

	mutex_lock(&text_mutex);
	for (poff = start; poff < end; poff++) {
		u8 *ptr = (u8 *)poff + *poff;

		if (!*poff || ptr < text || ptr >= text_end)
			continue;
		/* turn DS segment override prefix into lock prefix */
		if (*ptr == 0x3e)
			text_poke(ptr, ((unsigned char []){0xf0}), 1);
	}
	mutex_unlock(&text_mutex);
}

static void alternatives_smp_unlock(const s32 *start, const s32 *end,
				    u8 *text, u8 *text_end)
{
	const s32 *poff;

	mutex_lock(&text_mutex);
	for (poff = start; poff < end; poff++) {
		u8 *ptr = (u8 *)poff + *poff;

		if (!*poff || ptr < text || ptr >= text_end)
			continue;
		/* turn lock prefix into DS segment override prefix */
		if (*ptr == 0xf0)
			text_poke(ptr, ((unsigned char []){0x3E}), 1);
	}
	mutex_unlock(&text_mutex);
}

struct smp_alt_module {
	/* what is this ??? */
	struct module	*mod;
	char		*name;

	/* ptrs to lock prefixes */
	const s32	*locks;
	const s32	*locks_end;

	/* .text segment, needed to avoid patching init code ;) */
	u8		*text;
	u8		*text_end;

	struct list_head next;
};
static LIST_HEAD(smp_alt_modules);
static DEFINE_MUTEX(smp_alt);
static bool uniproc_patched = false;	/* protected by smp_alt */

void __init_or_module alternatives_smp_module_add(struct module *mod,
						  char *name,
						  void *locks, void *locks_end,
						  void *text,  void *text_end)
{
	struct smp_alt_module *smp;

	mutex_lock(&smp_alt);
	if (!uniproc_patched)
		goto unlock;

	if (num_possible_cpus() == 1)
		/* Don't bother remembering, we'll never have to undo it. */
		goto smp_unlock;

	smp = kzalloc(sizeof(*smp), GFP_KERNEL);
	if (NULL == smp)
		/* we'll run the (safe but slow) SMP code then ... */
		goto unlock;

	smp->mod	= mod;
	smp->name	= name;
	smp->locks	= locks;
	smp->locks_end	= locks_end;
	smp->text	= text;
	smp->text_end	= text_end;
	DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n",
		__func__, smp->locks, smp->locks_end,
		smp->text, smp->text_end, smp->name);

	list_add_tail(&smp->next, &smp_alt_modules);
smp_unlock:
	alternatives_smp_unlock(locks, locks_end, text, text_end);
unlock:
	mutex_unlock(&smp_alt);
}

void __init_or_module alternatives_smp_module_del(struct module *mod)
{
	struct smp_alt_module *item;

	mutex_lock(&smp_alt);
	list_for_each_entry(item, &smp_alt_modules, next) {
		if (mod != item->mod)
			continue;
		list_del(&item->next);
		kfree(item);
		break;
	}
	mutex_unlock(&smp_alt);
}

void alternatives_enable_smp(void)
{
	struct smp_alt_module *mod;

#ifdef CONFIG_LOCKDEP
	/*
	 * Older binutils section handling bug prevented
	 * alternatives-replacement from working reliably.
	 *
	 * If this still occurs then you should see a hang
	 * or crash shortly after this line:
	 */
	pr_info("lockdep: fixing up alternatives\n");
#endif

	/* Why bother if there are no other CPUs? */
	BUG_ON(num_possible_cpus() == 1);

	mutex_lock(&smp_alt);

	if (uniproc_patched) {
		pr_info("switching to SMP code\n");
		BUG_ON(num_online_cpus() != 1);
		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
		clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
		list_for_each_entry(mod, &smp_alt_modules, next)
			alternatives_smp_lock(mod->locks, mod->locks_end,
					      mod->text, mod->text_end);
		uniproc_patched = false;
	}
	mutex_unlock(&smp_alt);
}

/* Return 1 if the address range is reserved for smp-alternatives */
int alternatives_text_reserved(void *start, void *end)
{
	struct smp_alt_module *mod;
	const s32 *poff;
	u8 *text_start = start;
	u8 *text_end = end;

	list_for_each_entry(mod, &smp_alt_modules, next) {
		if (mod->text > text_end || mod->text_end < text_start)
			continue;
		for (poff = mod->locks; poff < mod->locks_end; poff++) {
			const u8 *ptr = (const u8 *)poff + *poff;

			if (text_start <= ptr && text_end > ptr)
				return 1;
		}
	}

	return 0;
}
#endif

#ifdef CONFIG_PARAVIRT
void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
				     struct paravirt_patch_site *end)
{
	struct paravirt_patch_site *p;
	char insnbuf[MAX_PATCH_LEN];

	if (noreplace_paravirt)
		return;

	for (p = start; p < end; p++) {
		unsigned int used;

		BUG_ON(p->len > MAX_PATCH_LEN);
		/* prep the buffer with the original instructions */
		memcpy(insnbuf, p->instr, p->len);
		used = pv_init_ops.patch(p->instrtype, p->clobbers, insnbuf,
					 (unsigned long)p->instr, p->len);

		BUG_ON(used > p->len);

		/* Pad the rest with nops */
		add_nops(insnbuf + used, p->len - used);
		text_poke_early(p->instr, insnbuf, p->len);
	}
}
extern struct paravirt_patch_site __start_parainstructions[],
	__stop_parainstructions[];
#endif	/* CONFIG_PARAVIRT */

void __init alternative_instructions(void)
{
	/* The patching is not fully atomic, so try to avoid local interruptions
	   that might execute the to be patched code.
	   Other CPUs are not running. */
	stop_nmi();

	/*
	 * Don't stop machine check exceptions while patching.
	 * MCEs only happen when something got corrupted and in this
	 * case we must do something about the corruption.
	 * Ignoring it is worse than a unlikely patching race.
	 * Also machine checks tend to be broadcast and if one CPU
	 * goes into machine check the others follow quickly, so we don't
	 * expect a machine check to cause undue problems during to code
	 * patching.
	 */

	apply_alternatives(__alt_instructions, __alt_instructions_end);

#ifdef CONFIG_SMP
	/* Patch to UP if other cpus not imminent. */
	if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
		uniproc_patched = true;
		alternatives_smp_module_add(NULL, "core kernel",
					    __smp_locks, __smp_locks_end,
					    _text, _etext);
	}

	if (!uniproc_patched || num_possible_cpus() == 1)
		free_init_pages("SMP alternatives",
				(unsigned long)__smp_locks,
				(unsigned long)__smp_locks_end);
#endif

	apply_paravirt(__parainstructions, __parainstructions_end);

	restart_nmi();
}

/**
 * text_poke_early - Update instructions on a live kernel at boot time
 * @addr: address to modify
 * @opcode: source of the copy
 * @len: length to copy
 *
 * When you use this code to patch more than one byte of an instruction
 * you need to make sure that other CPUs cannot execute this code in parallel.
 * Also no thread must be currently preempted in the middle of these
 * instructions. And on the local CPU you need to be protected again NMI or MCE
 * handlers seeing an inconsistent instruction while you patch.
 */
void *__init_or_module text_poke_early(void *addr, const void *opcode,
					      size_t len)
{
	unsigned long flags;
	local_irq_save(flags);
	memcpy(addr, opcode, len);
	sync_core();
	local_irq_restore(flags);
	/* Could also do a CLFLUSH here to speed up CPU recovery; but
	   that causes hangs on some VIA CPUs. */
	return addr;
}

/**
 * text_poke - Update instructions on a live kernel
 * @addr: address to modify
 * @opcode: source of the copy
 * @len: length to copy
 *
 * Only atomic text poke/set should be allowed when not doing early patching.
 * It means the size must be writable atomically and the address must be aligned
 * in a way that permits an atomic write. It also makes sure we fit on a single
 * page.
 *
 * Note: Must be called under text_mutex.
 */
void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
{
	unsigned long flags;
	char *vaddr;
	struct page *pages[2];
	int i;

	if (!core_kernel_text((unsigned long)addr)) {
		pages[0] = vmalloc_to_page(addr);
		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
	} else {
		pages[0] = virt_to_page(addr);
		WARN_ON(!PageReserved(pages[0]));
		pages[1] = virt_to_page(addr + PAGE_SIZE);
	}
	BUG_ON(!pages[0]);
	local_irq_save(flags);
	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
	if (pages[1])
		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
	clear_fixmap(FIX_TEXT_POKE0);
	if (pages[1])
		clear_fixmap(FIX_TEXT_POKE1);
	local_flush_tlb();
	sync_core();
	/* Could also do a CLFLUSH here to speed up CPU recovery; but
	   that causes hangs on some VIA CPUs. */
	for (i = 0; i < len; i++)
		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
	local_irq_restore(flags);
	return addr;
}

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

static bool bp_patching_in_progress;
static void *bp_int3_handler, *bp_int3_addr;

int poke_int3_handler(struct pt_regs *regs)
{
	/* bp_patching_in_progress */
	smp_rmb();

	if (likely(!bp_patching_in_progress))
		return 0;

	if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr)
		return 0;

	/* set up the specified breakpoint handler */
	regs->ip = (unsigned long) bp_int3_handler;

	return 1;

}

/**
 * text_poke_bp() -- update instructions on live kernel on SMP
 * @addr:	address to patch
 * @opcode:	opcode of new instruction
 * @len:	length to copy
 * @handler:	address to jump to when the temporary breakpoint is hit
 *
 * Modify multi-byte instruction by using int3 breakpoint on SMP.
 * We completely avoid stop_machine() here, and achieve the
 * synchronization using int3 breakpoint.
 *
 * The way it is done:
 *	- add a int3 trap to the address that will be patched
 *	- sync cores
 *	- update all but the first byte of the patched range
 *	- sync cores
 *	- replace the first byte (int3) by the first byte of
 *	  replacing opcode
 *	- sync cores
 *
 * Note: must be called under text_mutex.
 */
void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
{
	unsigned char int3 = 0xcc;

	bp_int3_handler = handler;
	bp_int3_addr = (u8 *)addr + sizeof(int3);
	bp_patching_in_progress = true;
	/*
	 * Corresponding read barrier in int3 notifier for
	 * making sure the in_progress flags is correctly ordered wrt.
	 * patching
	 */
	smp_wmb();

	text_poke(addr, &int3, sizeof(int3));

	on_each_cpu(do_sync_core, NULL, 1);

	if (len - sizeof(int3) > 0) {
		/* patch all but the first byte */
		text_poke((char *)addr + sizeof(int3),
			  (const char *) opcode + sizeof(int3),
			  len - sizeof(int3));
		/*
		 * According to Intel, this core syncing is very likely
		 * not necessary and we'd be safe even without it. But
		 * better safe than sorry (plus there's not only Intel).
		 */
		on_each_cpu(do_sync_core, NULL, 1);
	}

	/* patch the first byte */
	text_poke(addr, opcode, sizeof(int3));

	on_each_cpu(do_sync_core, NULL, 1);

	bp_patching_in_progress = false;
	smp_wmb();

	return addr;
}