about summary refs log tree commit diff
path: root/sysdeps/x86_64/dl-trampoline.h
blob: b90836ab137faf13266c641cf34cbd4f087687bb (plain) (blame)
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
/* PLT trampolines.  x86-64 version.
   Copyright (C) 2009-2016 Free Software Foundation, Inc.
   This file is part of the GNU C Library.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <http://www.gnu.org/licenses/>.  */

#undef REGISTER_SAVE_AREA_RAW
#ifdef __ILP32__
/* X32 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as VEC0 to
   VEC7.  */
# define REGISTER_SAVE_AREA_RAW	(8 * 7 + VEC_SIZE * 8)
#else
/* X86-64 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as
   BND0, BND1, BND2, BND3 and VEC0 to VEC7. */
# define REGISTER_SAVE_AREA_RAW	(8 * 7 + 16 * 4 + VEC_SIZE * 8)
#endif

#undef REGISTER_SAVE_AREA
#undef LOCAL_STORAGE_AREA
#undef BASE
#if DL_RUNTIME_RESOLVE_REALIGN_STACK
# define REGISTER_SAVE_AREA	(REGISTER_SAVE_AREA_RAW + 8)
/* Local stack area before jumping to function address: RBX.  */
# define LOCAL_STORAGE_AREA	8
# define BASE			rbx
# if (REGISTER_SAVE_AREA % VEC_SIZE) != 0
#  error REGISTER_SAVE_AREA must be multples of VEC_SIZE
# endif
#else
# define REGISTER_SAVE_AREA	REGISTER_SAVE_AREA_RAW
/* Local stack area before jumping to function address:  All saved
   registers.  */
# define LOCAL_STORAGE_AREA	REGISTER_SAVE_AREA
# define BASE			rsp
# if (REGISTER_SAVE_AREA % 16) != 8
#  error REGISTER_SAVE_AREA must be odd multples of 8
# endif
#endif

	.text
	.globl _dl_runtime_resolve
	.hidden _dl_runtime_resolve
	.type _dl_runtime_resolve, @function
	.align 16
	cfi_startproc
_dl_runtime_resolve:
	cfi_adjust_cfa_offset(16) # Incorporate PLT
#if DL_RUNTIME_RESOLVE_REALIGN_STACK
# if LOCAL_STORAGE_AREA != 8
#  error LOCAL_STORAGE_AREA must be 8
# endif
	pushq %rbx			# push subtracts stack by 8.
	cfi_adjust_cfa_offset(8)
	cfi_rel_offset(%rbx, 0)
	mov %RSP_LP, %RBX_LP
	cfi_def_cfa_register(%rbx)
	and $-VEC_SIZE, %RSP_LP
#endif
	sub $REGISTER_SAVE_AREA, %RSP_LP
	cfi_adjust_cfa_offset(REGISTER_SAVE_AREA)
	# Preserve registers otherwise clobbered.
	movq %rax, REGISTER_SAVE_RAX(%rsp)
	movq %rcx, REGISTER_SAVE_RCX(%rsp)
	movq %rdx, REGISTER_SAVE_RDX(%rsp)
	movq %rsi, REGISTER_SAVE_RSI(%rsp)
	movq %rdi, REGISTER_SAVE_RDI(%rsp)
	movq %r8, REGISTER_SAVE_R8(%rsp)
	movq %r9, REGISTER_SAVE_R9(%rsp)
	VMOV %VEC(0), (REGISTER_SAVE_VEC_OFF)(%rsp)
	VMOV %VEC(1), (REGISTER_SAVE_VEC_OFF + VEC_SIZE)(%rsp)
	VMOV %VEC(2), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 2)(%rsp)
	VMOV %VEC(3), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 3)(%rsp)
	VMOV %VEC(4), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 4)(%rsp)
	VMOV %VEC(5), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 5)(%rsp)
	VMOV %VEC(6), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 6)(%rsp)
	VMOV %VEC(7), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 7)(%rsp)
#ifndef __ILP32__
	# We also have to preserve bound registers.  These are nops if
	# Intel MPX isn't available or disabled.
# ifdef HAVE_MPX_SUPPORT
	bndmov %bnd0, REGISTER_SAVE_BND0(%rsp)
	bndmov %bnd1, REGISTER_SAVE_BND1(%rsp)
	bndmov %bnd2, REGISTER_SAVE_BND2(%rsp)
	bndmov %bnd3, REGISTER_SAVE_BND3(%rsp)
# else
#  if REGISTER_SAVE_BND0 == 0
	.byte 0x66,0x0f,0x1b,0x04,0x24
#  else
	.byte 0x66,0x0f,0x1b,0x44,0x24,REGISTER_SAVE_BND0
#  endif
	.byte 0x66,0x0f,0x1b,0x4c,0x24,REGISTER_SAVE_BND1
	.byte 0x66,0x0f,0x1b,0x54,0x24,REGISTER_SAVE_BND2
	.byte 0x66,0x0f,0x1b,0x5c,0x24,REGISTER_SAVE_BND3
# endif
#endif
	# Copy args pushed by PLT in register.
	# %rdi: link_map, %rsi: reloc_index
	mov (LOCAL_STORAGE_AREA + 8)(%BASE), %RSI_LP
	mov LOCAL_STORAGE_AREA(%BASE), %RDI_LP
	call _dl_fixup		# Call resolver.
	mov %RAX_LP, %R11_LP	# Save return value
#ifndef __ILP32__
	# Restore bound registers.  These are nops if Intel MPX isn't
	# avaiable or disabled.
# ifdef HAVE_MPX_SUPPORT
	bndmov REGISTER_SAVE_BND3(%rsp), %bnd3
	bndmov REGISTER_SAVE_BND2(%rsp), %bnd2
	bndmov REGISTER_SAVE_BND1(%rsp), %bnd1
	bndmov REGISTER_SAVE_BND0(%rsp), %bnd0
# else
	.byte 0x66,0x0f,0x1a,0x5c,0x24,REGISTER_SAVE_BND3
	.byte 0x66,0x0f,0x1a,0x54,0x24,REGISTER_SAVE_BND2
	.byte 0x66,0x0f,0x1a,0x4c,0x24,REGISTER_SAVE_BND1
#  if REGISTER_SAVE_BND0 == 0
	.byte 0x66,0x0f,0x1a,0x04,0x24
#  else
	.byte 0x66,0x0f,0x1a,0x44,0x24,REGISTER_SAVE_BND0
#  endif
# endif
#endif
	# Get register content back.
	movq REGISTER_SAVE_R9(%rsp), %r9
	movq REGISTER_SAVE_R8(%rsp), %r8
	movq REGISTER_SAVE_RDI(%rsp), %rdi
	movq REGISTER_SAVE_RSI(%rsp), %rsi
	movq REGISTER_SAVE_RDX(%rsp), %rdx
	movq REGISTER_SAVE_RCX(%rsp), %rcx
	movq REGISTER_SAVE_RAX(%rsp), %rax
	VMOV (REGISTER_SAVE_VEC_OFF)(%rsp), %VEC(0)
	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE)(%rsp), %VEC(1)
	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 2)(%rsp), %VEC(2)
	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 3)(%rsp), %VEC(3)
	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 4)(%rsp), %VEC(4)
	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 5)(%rsp), %VEC(5)
	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 6)(%rsp), %VEC(6)
	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 7)(%rsp), %VEC(7)
#if DL_RUNTIME_RESOLVE_REALIGN_STACK
	mov %RBX_LP, %RSP_LP
	cfi_def_cfa_register(%rsp)
	movq (%rsp), %rbx
	cfi_restore(%rbx)
#endif
	# Adjust stack(PLT did 2 pushes)
	add $(LOCAL_STORAGE_AREA + 16), %RSP_LP
	cfi_adjust_cfa_offset(-(LOCAL_STORAGE_AREA + 16))
	# Preserve bound registers.
	PRESERVE_BND_REGS_PREFIX
	jmp *%r11		# Jump to function address.
	cfi_endproc
	.size _dl_runtime_resolve, .-_dl_runtime_resolve


#ifndef PROF
# if (LR_VECTOR_OFFSET % VEC_SIZE) != 0
#  error LR_VECTOR_OFFSET must be multples of VEC_SIZE
# endif

	.globl _dl_runtime_profile
	.hidden _dl_runtime_profile
	.type _dl_runtime_profile, @function
	.align 16
_dl_runtime_profile:
	cfi_startproc
	cfi_adjust_cfa_offset(16) # Incorporate PLT
	/* The La_x86_64_regs data structure pointed to by the
	   fourth paramater must be VEC_SIZE-byte aligned.  This must
	   be explicitly enforced.  We have the set up a dynamically
	   sized stack frame.  %rbx points to the top half which
	   has a fixed size and preserves the original stack pointer.  */

	sub $32, %RSP_LP	# Allocate the local storage.
	cfi_adjust_cfa_offset(32)
	movq %rbx, (%rsp)
	cfi_rel_offset(%rbx, 0)

	/* On the stack:
		56(%rbx)	parameter #1
		48(%rbx)	return address

		40(%rbx)	reloc index
		32(%rbx)	link_map

		24(%rbx)	La_x86_64_regs pointer
		16(%rbx)	framesize
		 8(%rbx)	rax
		  (%rbx)	rbx
	*/

	movq %rax, 8(%rsp)
	mov %RSP_LP, %RBX_LP
	cfi_def_cfa_register(%rbx)

	/* Actively align the La_x86_64_regs structure.  */
	and $-VEC_SIZE, %RSP_LP
	/* sizeof(La_x86_64_regs).  Need extra space for 8 SSE registers
	   to detect if any xmm0-xmm7 registers are changed by audit
	   module.  */
	sub $(LR_SIZE + XMM_SIZE*8), %RSP_LP
	movq %rsp, 24(%rbx)

	/* Fill the La_x86_64_regs structure.  */
	movq %rdx, LR_RDX_OFFSET(%rsp)
	movq %r8,  LR_R8_OFFSET(%rsp)
	movq %r9,  LR_R9_OFFSET(%rsp)
	movq %rcx, LR_RCX_OFFSET(%rsp)
	movq %rsi, LR_RSI_OFFSET(%rsp)
	movq %rdi, LR_RDI_OFFSET(%rsp)
	movq %rbp, LR_RBP_OFFSET(%rsp)

	lea 48(%rbx), %RAX_LP
	movq %rax, LR_RSP_OFFSET(%rsp)

	/* We always store the XMM registers even if AVX is available.
	   This is to provide backward binary compatibility for existing
	   audit modules.  */
	movaps %xmm0,		   (LR_XMM_OFFSET)(%rsp)
	movaps %xmm1, (LR_XMM_OFFSET +   XMM_SIZE)(%rsp)
	movaps %xmm2, (LR_XMM_OFFSET + XMM_SIZE*2)(%rsp)
	movaps %xmm3, (LR_XMM_OFFSET + XMM_SIZE*3)(%rsp)
	movaps %xmm4, (LR_XMM_OFFSET + XMM_SIZE*4)(%rsp)
	movaps %xmm5, (LR_XMM_OFFSET + XMM_SIZE*5)(%rsp)
	movaps %xmm6, (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp)
	movaps %xmm7, (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp)

# ifndef __ILP32__
#  ifdef HAVE_MPX_SUPPORT
	bndmov %bnd0, 		   (LR_BND_OFFSET)(%rsp)  # Preserve bound
	bndmov %bnd1, (LR_BND_OFFSET +   BND_SIZE)(%rsp)  # registers. Nops if
	bndmov %bnd2, (LR_BND_OFFSET + BND_SIZE*2)(%rsp)  # MPX not available
	bndmov %bnd3, (LR_BND_OFFSET + BND_SIZE*3)(%rsp)  # or disabled.
#  else
	.byte 0x66,0x0f,0x1b,0x84,0x24;.long (LR_BND_OFFSET)
	.byte 0x66,0x0f,0x1b,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE)
	.byte 0x66,0x0f,0x1b,0x94,0x24;.long (LR_BND_OFFSET + BND_SIZE*2)
	.byte 0x66,0x0f,0x1b,0x9c,0x24;.long (LR_BND_OFFSET + BND_SIZE*3)
#  endif
# endif

# ifdef RESTORE_AVX
	/* This is to support AVX audit modules.  */
	VMOVA %VEC(0),		      (LR_VECTOR_OFFSET)(%rsp)
	VMOVA %VEC(1), (LR_VECTOR_OFFSET +   VECTOR_SIZE)(%rsp)
	VMOVA %VEC(2), (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp)
	VMOVA %VEC(3), (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp)
	VMOVA %VEC(4), (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp)
	VMOVA %VEC(5), (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp)
	VMOVA %VEC(6), (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp)
	VMOVA %VEC(7), (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp)

	/* Save xmm0-xmm7 registers to detect if any of them are
	   changed by audit module.  */
	vmovdqa %xmm0,		    (LR_SIZE)(%rsp)
	vmovdqa %xmm1, (LR_SIZE +   XMM_SIZE)(%rsp)
	vmovdqa %xmm2, (LR_SIZE + XMM_SIZE*2)(%rsp)
	vmovdqa %xmm3, (LR_SIZE + XMM_SIZE*3)(%rsp)
	vmovdqa %xmm4, (LR_SIZE + XMM_SIZE*4)(%rsp)
	vmovdqa %xmm5, (LR_SIZE + XMM_SIZE*5)(%rsp)
	vmovdqa %xmm6, (LR_SIZE + XMM_SIZE*6)(%rsp)
	vmovdqa %xmm7, (LR_SIZE + XMM_SIZE*7)(%rsp)
# endif

	mov %RSP_LP, %RCX_LP	# La_x86_64_regs pointer to %rcx.
	mov 48(%rbx), %RDX_LP	# Load return address if needed.
	mov 40(%rbx), %RSI_LP	# Copy args pushed by PLT in register.
	mov 32(%rbx), %RDI_LP	# %rdi: link_map, %rsi: reloc_index
	lea 16(%rbx), %R8_LP	# Address of framesize
	call _dl_profile_fixup	# Call resolver.

	mov %RAX_LP, %R11_LP	# Save return value.

	movq 8(%rbx), %rax	# Get back register content.
	movq LR_RDX_OFFSET(%rsp), %rdx
	movq  LR_R8_OFFSET(%rsp), %r8
	movq  LR_R9_OFFSET(%rsp), %r9

	movaps		    (LR_XMM_OFFSET)(%rsp), %xmm0
	movaps	 (LR_XMM_OFFSET + XMM_SIZE)(%rsp), %xmm1
	movaps (LR_XMM_OFFSET + XMM_SIZE*2)(%rsp), %xmm2
	movaps (LR_XMM_OFFSET + XMM_SIZE*3)(%rsp), %xmm3
	movaps (LR_XMM_OFFSET + XMM_SIZE*4)(%rsp), %xmm4
	movaps (LR_XMM_OFFSET + XMM_SIZE*5)(%rsp), %xmm5
	movaps (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp), %xmm6
	movaps (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp), %xmm7

# ifdef RESTORE_AVX
	/* Check if any xmm0-xmm7 registers are changed by audit
	   module.  */
	vpcmpeqq (LR_SIZE)(%rsp), %xmm0, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm0, (LR_VECTOR_OFFSET)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET)(%rsp), %VEC(0)
	vmovdqa	%xmm0, (LR_XMM_OFFSET)(%rsp)

1:	vpcmpeqq (LR_SIZE + XMM_SIZE)(%rsp), %xmm1, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm1, (LR_VECTOR_OFFSET + VECTOR_SIZE)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE)(%rsp), %VEC(1)
	vmovdqa	%xmm1, (LR_XMM_OFFSET + XMM_SIZE)(%rsp)

1:	vpcmpeqq (LR_SIZE + XMM_SIZE*2)(%rsp), %xmm2, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm2, (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*2)(%rsp), %VEC(2)
	vmovdqa	%xmm2, (LR_XMM_OFFSET + XMM_SIZE*2)(%rsp)

1:	vpcmpeqq (LR_SIZE + XMM_SIZE*3)(%rsp), %xmm3, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm3, (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*3)(%rsp), %VEC(3)
	vmovdqa	%xmm3, (LR_XMM_OFFSET + XMM_SIZE*3)(%rsp)

1:	vpcmpeqq (LR_SIZE + XMM_SIZE*4)(%rsp), %xmm4, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm4, (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*4)(%rsp), %VEC(4)
	vmovdqa	%xmm4, (LR_XMM_OFFSET + XMM_SIZE*4)(%rsp)

1:	vpcmpeqq (LR_SIZE + XMM_SIZE*5)(%rsp), %xmm5, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm5, (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*5)(%rsp), %VEC(5)
	vmovdqa	%xmm5, (LR_XMM_OFFSET + XMM_SIZE*5)(%rsp)

1:	vpcmpeqq (LR_SIZE + XMM_SIZE*6)(%rsp), %xmm6, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm6, (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*6)(%rsp), %VEC(6)
	vmovdqa	%xmm6, (LR_XMM_OFFSET + XMM_SIZE*6)(%rsp)

1:	vpcmpeqq (LR_SIZE + XMM_SIZE*7)(%rsp), %xmm7, %xmm8
	vpmovmskb %xmm8, %esi
	cmpl $0xffff, %esi
	je 2f
	vmovdqa	%xmm7, (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp)
	jmp 1f
2:	VMOVA (LR_VECTOR_OFFSET + VECTOR_SIZE*7)(%rsp), %VEC(7)
	vmovdqa	%xmm7, (LR_XMM_OFFSET + XMM_SIZE*7)(%rsp)

1:
# endif

# ifndef __ILP32__
#  ifdef HAVE_MPX_SUPPORT
	bndmov              (LR_BND_OFFSET)(%rsp), %bnd0  # Restore bound
	bndmov (LR_BND_OFFSET +   BND_SIZE)(%rsp), %bnd1  # registers.
	bndmov (LR_BND_OFFSET + BND_SIZE*2)(%rsp), %bnd2
	bndmov (LR_BND_OFFSET + BND_SIZE*3)(%rsp), %bnd3
#  else
	.byte 0x66,0x0f,0x1a,0x84,0x24;.long (LR_BND_OFFSET)
	.byte 0x66,0x0f,0x1a,0x8c,0x24;.long (LR_BND_OFFSET + BND_SIZE)
	.byte 0x66,0x0f,0x1a,0x94,0x24;.long (LR_BND_OFFSET + BND_SIZE*2)
	.byte 0x66,0x0f,0x1a,0x9c,0x24;.long (LR_BND_OFFSET + BND_SIZE*3)
#  endif
# endif

	mov  16(%rbx), %R10_LP	# Anything in framesize?
	test %R10_LP, %R10_LP
	PRESERVE_BND_REGS_PREFIX
	jns 3f

	/* There's nothing in the frame size, so there
	   will be no call to the _dl_call_pltexit. */

	/* Get back registers content.  */
	movq LR_RCX_OFFSET(%rsp), %rcx
	movq LR_RSI_OFFSET(%rsp), %rsi
	movq LR_RDI_OFFSET(%rsp), %rdi

	mov %RBX_LP, %RSP_LP
	movq (%rsp), %rbx
	cfi_restore(%rbx)
	cfi_def_cfa_register(%rsp)

	add $48, %RSP_LP	# Adjust the stack to the return value
				# (eats the reloc index and link_map)
	cfi_adjust_cfa_offset(-48)
	PRESERVE_BND_REGS_PREFIX
	jmp *%r11		# Jump to function address.

3:
	cfi_adjust_cfa_offset(48)
	cfi_rel_offset(%rbx, 0)
	cfi_def_cfa_register(%rbx)

	/* At this point we need to prepare new stack for the function
	   which has to be called.  We copy the original stack to a
	   temporary buffer of the size specified by the 'framesize'
	   returned from _dl_profile_fixup */

	lea LR_RSP_OFFSET(%rbx), %RSI_LP # stack
	add $8, %R10_LP
	and $-16, %R10_LP
	mov %R10_LP, %RCX_LP
	sub %R10_LP, %RSP_LP
	mov %RSP_LP, %RDI_LP
	shr $3, %RCX_LP
	rep
	movsq

	movq 24(%rdi), %rcx	# Get back register content.
	movq 32(%rdi), %rsi
	movq 40(%rdi), %rdi

	PRESERVE_BND_REGS_PREFIX
	call *%r11

	mov 24(%rbx), %RSP_LP	# Drop the copied stack content

	/* Now we have to prepare the La_x86_64_retval structure for the
	   _dl_call_pltexit.  The La_x86_64_regs is being pointed by rsp now,
	   so we just need to allocate the sizeof(La_x86_64_retval) space on
	   the stack, since the alignment has already been taken care of. */
# ifdef RESTORE_AVX
	/* sizeof(La_x86_64_retval).  Need extra space for 2 SSE
	   registers to detect if xmm0/xmm1 registers are changed
	   by audit module.  */
	sub $(LRV_SIZE + XMM_SIZE*2), %RSP_LP
# else
	sub $LRV_SIZE, %RSP_LP	# sizeof(La_x86_64_retval)
# endif
	mov %RSP_LP, %RCX_LP	# La_x86_64_retval argument to %rcx.

	/* Fill in the La_x86_64_retval structure.  */
	movq %rax, LRV_RAX_OFFSET(%rcx)
	movq %rdx, LRV_RDX_OFFSET(%rcx)

	movaps %xmm0, LRV_XMM0_OFFSET(%rcx)
	movaps %xmm1, LRV_XMM1_OFFSET(%rcx)

# ifdef RESTORE_AVX
	/* This is to support AVX audit modules.  */
	VMOVA %VEC(0), LRV_VECTOR0_OFFSET(%rcx)
	VMOVA %VEC(1), LRV_VECTOR1_OFFSET(%rcx)

	/* Save xmm0/xmm1 registers to detect if they are changed
	   by audit module.  */
	vmovdqa %xmm0,		  (LRV_SIZE)(%rcx)
	vmovdqa %xmm1, (LRV_SIZE + XMM_SIZE)(%rcx)
# endif

# ifndef __ILP32__
#  ifdef HAVE_MPX_SUPPORT
	bndmov %bnd0, LRV_BND0_OFFSET(%rcx)  # Preserve returned bounds.
	bndmov %bnd1, LRV_BND1_OFFSET(%rcx)
#  else
	.byte  0x66,0x0f,0x1b,0x81;.long (LRV_BND0_OFFSET)
	.byte  0x66,0x0f,0x1b,0x89;.long (LRV_BND1_OFFSET)
#  endif
# endif

	fstpt LRV_ST0_OFFSET(%rcx)
	fstpt LRV_ST1_OFFSET(%rcx)

	movq 24(%rbx), %rdx	# La_x86_64_regs argument to %rdx.
	movq 40(%rbx), %rsi	# Copy args pushed by PLT in register.
	movq 32(%rbx), %rdi	# %rdi: link_map, %rsi: reloc_index
	call _dl_call_pltexit

	/* Restore return registers.  */
	movq LRV_RAX_OFFSET(%rsp), %rax
	movq LRV_RDX_OFFSET(%rsp), %rdx

	movaps LRV_XMM0_OFFSET(%rsp), %xmm0
	movaps LRV_XMM1_OFFSET(%rsp), %xmm1

# ifdef RESTORE_AVX
	/* Check if xmm0/xmm1 registers are changed by audit module.  */
	vpcmpeqq (LRV_SIZE)(%rsp), %xmm0, %xmm2
	vpmovmskb %xmm2, %esi
	cmpl $0xffff, %esi
	jne 1f
	VMOVA LRV_VECTOR0_OFFSET(%rsp), %VEC(0)

1:	vpcmpeqq (LRV_SIZE + XMM_SIZE)(%rsp), %xmm1, %xmm2
	vpmovmskb %xmm2, %esi
	cmpl $0xffff, %esi
	jne 1f
	VMOVA LRV_VECTOR1_OFFSET(%rsp), %VEC(1)

1:
# endif

# ifndef __ILP32__
#  ifdef HAVE_MPX_SUPPORT
	bndmov LRV_BND0_OFFSET(%rsp), %bnd0  # Restore bound registers.
	bndmov LRV_BND1_OFFSET(%rsp), %bnd1
#  else
	.byte  0x66,0x0f,0x1a,0x84,0x24;.long (LRV_BND0_OFFSET)
	.byte  0x66,0x0f,0x1a,0x8c,0x24;.long (LRV_BND1_OFFSET)
#  endif
# endif

	fldt LRV_ST1_OFFSET(%rsp)
	fldt LRV_ST0_OFFSET(%rsp)

	mov %RBX_LP, %RSP_LP
	movq (%rsp), %rbx
	cfi_restore(%rbx)
	cfi_def_cfa_register(%rsp)

	add $48, %RSP_LP	# Adjust the stack to the return value
				# (eats the reloc index and link_map)
	cfi_adjust_cfa_offset(-48)
	PRESERVE_BND_REGS_PREFIX
	retq

	cfi_endproc
	.size _dl_runtime_profile, .-_dl_runtime_profile
#endif