aboutsummaryrefslogtreecommitdiff
path: root/lib/libc/arm/string/memmove.S
blob: 8f961470076cfe6cc260d9a8ac0699f00d2ebc32 (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
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
/*	$NetBSD: memmove.S,v 1.4 2003/10/14 07:51:45 scw Exp $	*/

/*-
 * Copyright (c) 1997 The NetBSD Foundation, Inc.
 * All rights reserved.
 *
 * This code is derived from software contributed to The NetBSD Foundation
 * by Neil A. Carson and Mark Brinicombe
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include <machine/asm.h>
__FBSDID("$FreeBSD$");

.syntax	unified

#ifndef _BCOPY
/* LINTSTUB: Func: void *memmove(void *, const void *, size_t) */
ENTRY(memmove)
#else
/* bcopy = memcpy/memmove with arguments reversed. */
/* LINTSTUB: Func: void bcopy(void *, void *, size_t) */
ENTRY(bcopy)
	/* switch the source and destination registers */
	eor     r0, r1, r0 
	eor     r1, r0, r1 
	eor     r0, r1, r0 
#endif
	/* Do the buffers overlap? */
	cmp	r0, r1
	it	eq
	RETeq		/* Bail now if src/dst are the same */
	ite	cc
	subcc	r3, r0, r1	/* if (dst > src) r3 = dst - src */
	subcs	r3, r1, r0	/* if (src > dsr) r3 = src - dst */
	cmp	r3, r2		/* if (r3 < len) we have an overlap */
	bcc	PIC_SYM(_C_LABEL(memcpy), PLT)

	/* Determine copy direction */
	cmp	r1, r0
	it	cc
	bcc	.Lmemmove_backwards

	itt	eq
	moveq	r0, #0			/* Quick abort for len=0 */
	RETeq

	stmdb	sp!, {r0, lr}		/* memmove() returns dest addr */
	subs	r2, r2, #4
	blt	.Lmemmove_fl4		/* less than 4 bytes */
	ands	r12, r0, #3
	bne	.Lmemmove_fdestul	/* oh unaligned destination addr */
	ands	r12, r1, #3
	bne	.Lmemmove_fsrcul		/* oh unaligned source addr */

.Lmemmove_ft8:
	/* We have aligned source and destination */
	subs	r2, r2, #8
	blt	.Lmemmove_fl12		/* less than 12 bytes (4 from above) */
	subs	r2, r2, #0x14         
	blt	.Lmemmove_fl32		/* less than 32 bytes (12 from above) */
	stmdb	sp!, {r4}		/* borrow r4 */

	/* blat 32 bytes at a time */
	/* XXX for really big copies perhaps we should use more registers */
.Lmemmove_floop32:	
	ldmia	r1!, {r3, r4, r12, lr}
	stmia	r0!, {r3, r4, r12, lr}
	ldmia	r1!, {r3, r4, r12, lr}
	stmia	r0!, {r3, r4, r12, lr}
	subs	r2, r2, #0x20         
	bge	.Lmemmove_floop32

	cmn	r2, #0x10
	ittt	ge
	ldmiage	r1!, {r3, r4, r12, lr}	/* blat a remaining 16 bytes */
	stmiage	r0!, {r3, r4, r12, lr}
	subge	r2, r2, #0x10         
	ldmia	sp!, {r4}		/* return r4 */

.Lmemmove_fl32:
	adds	r2, r2, #0x14         

	/* blat 12 bytes at a time */
.Lmemmove_floop12:
	ittt	ge
	ldmiage	r1!, {r3, r12, lr}
	stmiage	r0!, {r3, r12, lr}
	subsge	r2, r2, #0x0c         
	bge	.Lmemmove_floop12

.Lmemmove_fl12:
	adds	r2, r2, #8
	blt	.Lmemmove_fl4

	subs	r2, r2, #4
	itt	lt
	ldrlt	r3, [r1], #4
	strlt	r3, [r0], #4
	ittt	ge
	ldmiage	r1!, {r3, r12}
	stmiage	r0!, {r3, r12}
	subge	r2, r2, #4

.Lmemmove_fl4:
	/* less than 4 bytes to go */
	adds	r2, r2, #4
	it	eq
	ldmiaeq	sp!, {r0, pc}		/* done */

	/* copy the crud byte at a time */
	cmp	r2, #2
	ldrb	r3, [r1], #1
	strb	r3, [r0], #1
	itt	ge
	ldrbge	r3, [r1], #1
	strbge	r3, [r0], #1
	itt	gt
	ldrbgt	r3, [r1], #1
	strbgt	r3, [r0], #1
	ldmia	sp!, {r0, pc}

	/* erg - unaligned destination */
.Lmemmove_fdestul:
	rsb	r12, r12, #4
	cmp	r12, #2

	/* align destination with byte copies */
	ldrb	r3, [r1], #1
	strb	r3, [r0], #1
	itt	ge
	ldrbge	r3, [r1], #1
	strbge	r3, [r0], #1
	itt	gt
	ldrbgt	r3, [r1], #1
	strbgt	r3, [r0], #1
	subs	r2, r2, r12
	blt	.Lmemmove_fl4		/* less the 4 bytes */

	ands	r12, r1, #3
	beq	.Lmemmove_ft8		/* we have an aligned source */

	/* erg - unaligned source */
	/* This is where it gets nasty ... */
.Lmemmove_fsrcul:
	bic	r1, r1, #3
	ldr	lr, [r1], #4
	cmp	r12, #2
	bgt	.Lmemmove_fsrcul3
	beq	.Lmemmove_fsrcul2
	cmp	r2, #0x0c            
	blt	.Lmemmove_fsrcul1loop4
	sub	r2, r2, #0x0c         
	stmdb	sp!, {r4, r5}

.Lmemmove_fsrcul1loop16:
#ifdef __ARMEB__
	mov	r3, lr, lsl #8
#else
	mov	r3, lr, lsr #8
#endif
	ldmia	r1!, {r4, r5, r12, lr}
#ifdef __ARMEB__
	orr	r3, r3, r4, lsr #24
	mov	r4, r4, lsl #8
	orr	r4, r4, r5, lsr #24
	mov	r5, r5, lsl #8
	orr	r5, r5, r12, lsr #24
	mov	r12, r12, lsl #8
	orr	r12, r12, lr, lsr #24
#else
	orr	r3, r3, r4, lsl #24
	mov	r4, r4, lsr #8
	orr	r4, r4, r5, lsl #24
	mov	r5, r5, lsr #8
	orr	r5, r5, r12, lsl #24
	mov	r12, r12, lsr #8
	orr	r12, r12, lr, lsl #24
#endif
	stmia	r0!, {r3-r5, r12}
	subs	r2, r2, #0x10         
	bge	.Lmemmove_fsrcul1loop16
	ldmia	sp!, {r4, r5}
	adds	r2, r2, #0x0c         
	blt	.Lmemmove_fsrcul1l4

.Lmemmove_fsrcul1loop4:
#ifdef __ARMEB__
	mov	r12, lr, lsl #8
#else
	mov	r12, lr, lsr #8
#endif
	ldr	lr, [r1], #4
#ifdef __ARMEB__
	orr	r12, r12, lr, lsr #24
#else
	orr	r12, r12, lr, lsl #24
#endif
	str	r12, [r0], #4
	subs	r2, r2, #4
	bge	.Lmemmove_fsrcul1loop4

.Lmemmove_fsrcul1l4:
	sub	r1, r1, #3
	b	.Lmemmove_fl4

.Lmemmove_fsrcul2:
	cmp	r2, #0x0c            
	blt	.Lmemmove_fsrcul2loop4
	sub	r2, r2, #0x0c         
	stmdb	sp!, {r4, r5}

.Lmemmove_fsrcul2loop16:
#ifdef __ARMEB__
	mov	r3, lr, lsl #16
#else
	mov	r3, lr, lsr #16
#endif
	ldmia	r1!, {r4, r5, r12, lr}
#ifdef __ARMEB__
	orr	r3, r3, r4, lsr #16
	mov	r4, r4, lsl #16
	orr	r4, r4, r5, lsr #16
	mov	r5, r5, lsl #16
	orr	r5, r5, r12, lsr #16
	mov	r12, r12, lsl #16
	orr	r12, r12, lr, lsr #16
#else
	orr	r3, r3, r4, lsl #16
	mov	r4, r4, lsr #16
	orr	r4, r4, r5, lsl #16
	mov	r5, r5, lsr #16
	orr	r5, r5, r12, lsl #16
	mov	r12, r12, lsr #16
	orr	r12, r12, lr, lsl #16
#endif
	stmia	r0!, {r3-r5, r12}
	subs	r2, r2, #0x10         
	bge	.Lmemmove_fsrcul2loop16
	ldmia	sp!, {r4, r5}
	adds	r2, r2, #0x0c         
	blt	.Lmemmove_fsrcul2l4

.Lmemmove_fsrcul2loop4:
#ifdef __ARMEB__
	mov	r12, lr, lsl #16
#else
	mov	r12, lr, lsr #16
#endif
	ldr	lr, [r1], #4
#ifdef __ARMEB__
	orr	r12, r12, lr, lsr #16
#else
	orr	r12, r12, lr, lsl #16
#endif
	str	r12, [r0], #4
	subs	r2, r2, #4
	bge	.Lmemmove_fsrcul2loop4

.Lmemmove_fsrcul2l4:
	sub	r1, r1, #2
	b	.Lmemmove_fl4

.Lmemmove_fsrcul3:
	cmp	r2, #0x0c            
	blt	.Lmemmove_fsrcul3loop4
	sub	r2, r2, #0x0c         
	stmdb	sp!, {r4, r5}

.Lmemmove_fsrcul3loop16:
#ifdef __ARMEB__
	mov	r3, lr, lsl #24
#else
	mov	r3, lr, lsr #24
#endif
	ldmia	r1!, {r4, r5, r12, lr}
#ifdef __ARMEB__
	orr	r3, r3, r4, lsr #8
	mov	r4, r4, lsl #24
	orr	r4, r4, r5, lsr #8
	mov	r5, r5, lsl #24
	orr	r5, r5, r12, lsr #8
	mov	r12, r12, lsl #24
	orr	r12, r12, lr, lsr #8
#else
	orr	r3, r3, r4, lsl #8
	mov	r4, r4, lsr #24
	orr	r4, r4, r5, lsl #8
	mov	r5, r5, lsr #24
	orr	r5, r5, r12, lsl #8
	mov	r12, r12, lsr #24
	orr	r12, r12, lr, lsl #8
#endif
	stmia	r0!, {r3-r5, r12}
	subs	r2, r2, #0x10         
	bge	.Lmemmove_fsrcul3loop16
	ldmia	sp!, {r4, r5}
	adds	r2, r2, #0x0c         
	blt	.Lmemmove_fsrcul3l4

.Lmemmove_fsrcul3loop4:
#ifdef __ARMEB__
	mov	r12, lr, lsl #24
#else
	mov	r12, lr, lsr #24
#endif
	ldr	lr, [r1], #4
#ifdef __ARMEB__
	orr	r12, r12, lr, lsr #8
#else
	orr	r12, r12, lr, lsl #8
#endif
	str	r12, [r0], #4
	subs	r2, r2, #4
	bge	.Lmemmove_fsrcul3loop4

.Lmemmove_fsrcul3l4:
	sub	r1, r1, #1
	b	.Lmemmove_fl4

.Lmemmove_backwards:
	add	r1, r1, r2
	add	r0, r0, r2
	subs	r2, r2, #4
	blt	.Lmemmove_bl4		/* less than 4 bytes */
	ands	r12, r0, #3
	bne	.Lmemmove_bdestul	/* oh unaligned destination addr */
	ands	r12, r1, #3
	bne	.Lmemmove_bsrcul		/* oh unaligned source addr */

.Lmemmove_bt8:
	/* We have aligned source and destination */
	subs	r2, r2, #8
	blt	.Lmemmove_bl12		/* less than 12 bytes (4 from above) */
	stmdb	sp!, {r4, lr}
	subs	r2, r2, #0x14		/* less than 32 bytes (12 from above) */
	blt	.Lmemmove_bl32

	/* blat 32 bytes at a time */
	/* XXX for really big copies perhaps we should use more registers */
.Lmemmove_bloop32:
	ldmdb	r1!, {r3, r4, r12, lr}
	stmdb	r0!, {r3, r4, r12, lr}
	ldmdb	r1!, {r3, r4, r12, lr}
	stmdb	r0!, {r3, r4, r12, lr}
	subs	r2, r2, #0x20         
	bge	.Lmemmove_bloop32

.Lmemmove_bl32:
	cmn	r2, #0x10            
	ittt	ge
	ldmdbge	r1!, {r3, r4, r12, lr}	/* blat a remaining 16 bytes */
	stmdbge	r0!, {r3, r4, r12, lr}
	subge	r2, r2, #0x10         
	adds	r2, r2, #0x14         
	ittt	ge
	ldmdbge	r1!, {r3, r12, lr}	/* blat a remaining 12 bytes */
	stmdbge	r0!, {r3, r12, lr}
	subge	r2, r2, #0x0c         
	ldmia	sp!, {r4, lr}

.Lmemmove_bl12:
	adds	r2, r2, #8
	blt	.Lmemmove_bl4
	subs	r2, r2, #4
	itt	lt
	ldrlt	r3, [r1, #-4]!
	strlt	r3, [r0, #-4]!
	ittt	ge
	ldmdbge	r1!, {r3, r12}
	stmdbge	r0!, {r3, r12}
	subge	r2, r2, #4

.Lmemmove_bl4:
	/* less than 4 bytes to go */
	adds	r2, r2, #4
	it	eq
	RETeq			/* done */

	/* copy the crud byte at a time */
	cmp	r2, #2
	ldrb	r3, [r1, #-1]!
	strb	r3, [r0, #-1]!
	itt	ge
	ldrbge	r3, [r1, #-1]!
	strbge	r3, [r0, #-1]!
	itt	gt
	ldrbgt	r3, [r1, #-1]!
	strbgt	r3, [r0, #-1]!
	RET

	/* erg - unaligned destination */
.Lmemmove_bdestul:
	cmp	r12, #2

	/* align destination with byte copies */
	ldrb	r3, [r1, #-1]!
	strb	r3, [r0, #-1]!
	itt	ge
	ldrbge	r3, [r1, #-1]!
	strbge	r3, [r0, #-1]!
	itt	gt
	ldrbgt	r3, [r1, #-1]!
	strbgt	r3, [r0, #-1]!
	subs	r2, r2, r12
	blt	.Lmemmove_bl4		/* less than 4 bytes to go */
	ands	r12, r1, #3
	beq	.Lmemmove_bt8		/* we have an aligned source */

	/* erg - unaligned source */
	/* This is where it gets nasty ... */
.Lmemmove_bsrcul:
	bic	r1, r1, #3
	ldr	r3, [r1, #0]
	cmp	r12, #2
	blt	.Lmemmove_bsrcul1
	beq	.Lmemmove_bsrcul2
	cmp	r2, #0x0c            
	blt	.Lmemmove_bsrcul3loop4
	sub	r2, r2, #0x0c         
	stmdb	sp!, {r4, r5, lr}

.Lmemmove_bsrcul3loop16:
#ifdef __ARMEB__
	mov	lr, r3, lsr #8
#else
	mov	lr, r3, lsl #8
#endif
	ldmdb	r1!, {r3-r5, r12}
#ifdef __ARMEB__
	orr	lr, lr, r12, lsl #24
	mov	r12, r12, lsr #8
	orr	r12, r12, r5, lsl #24
	mov	r5, r5, lsr #8
	orr	r5, r5, r4, lsl #24
	mov	r4, r4, lsr #8
	orr	r4, r4, r3, lsl #24
#else
	orr	lr, lr, r12, lsr #24
	mov	r12, r12, lsl #8
	orr	r12, r12, r5, lsr #24
	mov	r5, r5, lsl #8
	orr	r5, r5, r4, lsr #24
	mov	r4, r4, lsl #8
	orr	r4, r4, r3, lsr #24
#endif
	stmdb	r0!, {r4, r5, r12, lr}
	subs	r2, r2, #0x10         
	bge	.Lmemmove_bsrcul3loop16
	ldmia	sp!, {r4, r5, lr}
	adds	r2, r2, #0x0c         
	blt	.Lmemmove_bsrcul3l4

.Lmemmove_bsrcul3loop4:
#ifdef __ARMEB__
	mov	r12, r3, lsr #8
#else
	mov	r12, r3, lsl #8
#endif
	ldr	r3, [r1, #-4]!
#ifdef __ARMEB__
	orr	r12, r12, r3, lsl #24
#else
	orr	r12, r12, r3, lsr #24
#endif
	str	r12, [r0, #-4]!
	subs	r2, r2, #4
	bge	.Lmemmove_bsrcul3loop4

.Lmemmove_bsrcul3l4:
	add	r1, r1, #3
	b	.Lmemmove_bl4

.Lmemmove_bsrcul2:
	cmp	r2, #0x0c            
	blt	.Lmemmove_bsrcul2loop4
	sub	r2, r2, #0x0c         
	stmdb	sp!, {r4, r5, lr}

.Lmemmove_bsrcul2loop16:
#ifdef __ARMEB__
	mov	lr, r3, lsr #16
#else
	mov	lr, r3, lsl #16
#endif
	ldmdb	r1!, {r3-r5, r12}
#ifdef __ARMEB__
	orr	lr, lr, r12, lsl #16
	mov	r12, r12, lsr #16
	orr	r12, r12, r5, lsl #16
	mov	r5, r5, lsr #16
	orr	r5, r5, r4, lsl #16
	mov	r4, r4, lsr #16
	orr	r4, r4, r3, lsl #16
#else
	orr	lr, lr, r12, lsr #16
	mov	r12, r12, lsl #16
	orr	r12, r12, r5, lsr #16
	mov	r5, r5, lsl #16
	orr	r5, r5, r4, lsr #16
	mov	r4, r4, lsl #16
	orr	r4, r4, r3, lsr #16
#endif
	stmdb	r0!, {r4, r5, r12, lr}
	subs	r2, r2, #0x10         
	bge	.Lmemmove_bsrcul2loop16
	ldmia	sp!, {r4, r5, lr}
	adds	r2, r2, #0x0c         
	blt	.Lmemmove_bsrcul2l4

.Lmemmove_bsrcul2loop4:
#ifdef __ARMEB__
	mov	r12, r3, lsr #16
#else
	mov	r12, r3, lsl #16
#endif
	ldr	r3, [r1, #-4]!
#ifdef __ARMEB__
	orr	r12, r12, r3, lsl #16
#else
	orr	r12, r12, r3, lsr #16
#endif
	str	r12, [r0, #-4]!
	subs	r2, r2, #4
	bge	.Lmemmove_bsrcul2loop4

.Lmemmove_bsrcul2l4:
	add	r1, r1, #2
	b	.Lmemmove_bl4

.Lmemmove_bsrcul1:
	cmp	r2, #0x0c            
	blt	.Lmemmove_bsrcul1loop4
	sub	r2, r2, #0x0c         
	stmdb	sp!, {r4, r5, lr}

.Lmemmove_bsrcul1loop32:
#ifdef __ARMEB__
	mov	lr, r3, lsr #24
#else
	mov	lr, r3, lsl #24
#endif
	ldmdb	r1!, {r3-r5, r12}
#ifdef __ARMEB__
	orr	lr, lr, r12, lsl #8
	mov	r12, r12, lsr #24
	orr	r12, r12, r5, lsl #8
	mov	r5, r5, lsr #24
	orr	r5, r5, r4, lsl #8
	mov	r4, r4, lsr #24
	orr	r4, r4, r3, lsl #8
#else
	orr	lr, lr, r12, lsr #8
	mov	r12, r12, lsl #24
	orr	r12, r12, r5, lsr #8
	mov	r5, r5, lsl #24
	orr	r5, r5, r4, lsr #8
	mov	r4, r4, lsl #24
	orr	r4, r4, r3, lsr #8
#endif
	stmdb	r0!, {r4, r5, r12, lr}
	subs	r2, r2, #0x10         
	bge	.Lmemmove_bsrcul1loop32
	ldmia	sp!, {r4, r5, lr}
	adds	r2, r2, #0x0c         
	blt	.Lmemmove_bsrcul1l4

.Lmemmove_bsrcul1loop4:
#ifdef __ARMEB__
	mov	r12, r3, lsr #24
#else
	mov	r12, r3, lsl #24
#endif
	ldr	r3, [r1, #-4]!
#ifdef __ARMEB__
	orr	r12, r12, r3, lsl #8
#else
	orr	r12, r12, r3, lsr #8
#endif
	str	r12, [r0, #-4]!
	subs	r2, r2, #4
	bge	.Lmemmove_bsrcul1loop4

.Lmemmove_bsrcul1l4:
	add	r1, r1, #1
	b	.Lmemmove_bl4
#ifndef _BCOPY
END(memmove)
#else
END(bcopy)
#endif

	.section .note.GNU-stack,"",%progbits