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
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Author: Anton Blanchard <anton@au.ibm.com>
* Copyright 2015 IBM Corporation.
*/
#include <asm/ppc_asm.h>
#include <asm/export.h>
#include <asm/ppc-opcode.h>
#define off8 r6
#define off16 r7
#define off24 r8
#define rA r9
#define rB r10
#define rC r11
#define rD r27
#define rE r28
#define rF r29
#define rG r30
#define rH r31
#ifdef __LITTLE_ENDIAN__
#define LH lhbrx
#define LW lwbrx
#define LD ldbrx
#define LVS lvsr
#define VPERM(_VRT,_VRA,_VRB,_VRC) \
vperm _VRT,_VRB,_VRA,_VRC
#else
#define LH lhzx
#define LW lwzx
#define LD ldx
#define LVS lvsl
#define VPERM(_VRT,_VRA,_VRB,_VRC) \
vperm _VRT,_VRA,_VRB,_VRC
#endif
#define VMX_THRESH 4096
#define ENTER_VMX_OPS \
mflr r0; \
std r3,-STACKFRAMESIZE+STK_REG(R31)(r1); \
std r4,-STACKFRAMESIZE+STK_REG(R30)(r1); \
std r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \
std r0,16(r1); \
stdu r1,-STACKFRAMESIZE(r1); \
bl enter_vmx_ops; \
cmpwi cr1,r3,0; \
ld r0,STACKFRAMESIZE+16(r1); \
ld r3,STK_REG(R31)(r1); \
ld r4,STK_REG(R30)(r1); \
ld r5,STK_REG(R29)(r1); \
addi r1,r1,STACKFRAMESIZE; \
mtlr r0
#define EXIT_VMX_OPS \
mflr r0; \
std r3,-STACKFRAMESIZE+STK_REG(R31)(r1); \
std r4,-STACKFRAMESIZE+STK_REG(R30)(r1); \
std r5,-STACKFRAMESIZE+STK_REG(R29)(r1); \
std r0,16(r1); \
stdu r1,-STACKFRAMESIZE(r1); \
bl exit_vmx_ops; \
ld r0,STACKFRAMESIZE+16(r1); \
ld r3,STK_REG(R31)(r1); \
ld r4,STK_REG(R30)(r1); \
ld r5,STK_REG(R29)(r1); \
addi r1,r1,STACKFRAMESIZE; \
mtlr r0
/*
* LD_VSR_CROSS16B load the 2nd 16 bytes for _vaddr which is unaligned with
* 16 bytes boundary and permute the result with the 1st 16 bytes.
* | y y y y y y y y y y y y y 0 1 2 | 3 4 5 6 7 8 9 a b c d e f z z z |
* ^ ^ ^
* 0xbbbb10 0xbbbb20 0xbbb30
* ^
* _vaddr
*
*
* _vmask is the mask generated by LVS
* _v1st_qw is the 1st aligned QW of current addr which is already loaded.
* for example: 0xyyyyyyyyyyyyy012 for big endian
* _v2nd_qw is the 2nd aligned QW of cur _vaddr to be loaded.
* for example: 0x3456789abcdefzzz for big endian
* The permute result is saved in _v_res.
* for example: 0x0123456789abcdef for big endian.
*/
#define LD_VSR_CROSS16B(_vaddr,_vmask,_v1st_qw,_v2nd_qw,_v_res) \
lvx _v2nd_qw,_vaddr,off16; \
VPERM(_v_res,_v1st_qw,_v2nd_qw,_vmask)
/*
* There are 2 categories for memcmp:
* 1) src/dst has the same offset to the 8 bytes boundary. The handlers
* are named like .Lsameoffset_xxxx
* 2) src/dst has different offset to the 8 bytes boundary. The handlers
* are named like .Ldiffoffset_xxxx
*/
_GLOBAL_TOC(memcmp)
cmpdi cr1,r5,0
/* Use the short loop if the src/dst addresses are not
* with the same offset of 8 bytes align boundary.
*/
xor r6,r3,r4
andi. r6,r6,7
/* Fall back to short loop if compare at aligned addrs
* with less than 8 bytes.
*/
cmpdi cr6,r5,7
beq cr1,.Lzero
bgt cr6,.Lno_short
.Lshort:
mtctr r5
1: lbz rA,0(r3)
lbz rB,0(r4)
subf. rC,rB,rA
bne .Lnon_zero
bdz .Lzero
lbz rA,1(r3)
lbz rB,1(r4)
subf. rC,rB,rA
bne .Lnon_zero
bdz .Lzero
lbz rA,2(r3)
lbz rB,2(r4)
subf. rC,rB,rA
bne .Lnon_zero
bdz .Lzero
lbz rA,3(r3)
lbz rB,3(r4)
subf. rC,rB,rA
bne .Lnon_zero
addi r3,r3,4
addi r4,r4,4
bdnz 1b
.Lzero:
li r3,0
blr
.Lno_short:
dcbt 0,r3
dcbt 0,r4
bne .Ldiffoffset_8bytes_make_align_start
.Lsameoffset_8bytes_make_align_start:
/* attempt to compare bytes not aligned with 8 bytes so that
* rest comparison can run based on 8 bytes alignment.
*/
andi. r6,r3,7
/* Try to compare the first double word which is not 8 bytes aligned:
* load the first double word at (src & ~7UL) and shift left appropriate
* bits before comparision.
*/
rlwinm r6,r3,3,26,28
beq .Lsameoffset_8bytes_aligned
clrrdi r3,r3,3
clrrdi r4,r4,3
LD rA,0,r3
LD rB,0,r4
sld rA,rA,r6
sld rB,rB,r6
cmpld cr0,rA,rB
srwi r6,r6,3
bne cr0,.LcmpAB_lightweight
subfic r6,r6,8
subf. r5,r6,r5
addi r3,r3,8
addi r4,r4,8
beq .Lzero
.Lsameoffset_8bytes_aligned:
/* now we are aligned with 8 bytes.
* Use .Llong loop if left cmp bytes are equal or greater than 32B.
*/
cmpdi cr6,r5,31
bgt cr6,.Llong
.Lcmp_lt32bytes:
/* compare 1 ~ 31 bytes, at least r3 addr is 8 bytes aligned now */
cmpdi cr5,r5,7
srdi r0,r5,3
ble cr5,.Lcmp_rest_lt8bytes
/* handle 8 ~ 31 bytes */
clrldi r5,r5,61
mtctr r0
2:
LD rA,0,r3
LD rB,0,r4
cmpld cr0,rA,rB
addi r3,r3,8
addi r4,r4,8
bne cr0,.LcmpAB_lightweight
bdnz 2b
cmpwi r5,0
beq .Lzero
.Lcmp_rest_lt8bytes:
/*
* Here we have less than 8 bytes to compare. At least s1 is aligned to
* 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a
* page boundary, otherwise we might read past the end of the buffer and
* trigger a page fault. We use 4K as the conservative minimum page
* size. If we detect that case we go to the byte-by-byte loop.
*
* Otherwise the next double word is loaded from s1 and s2, and shifted
* right to compare the appropriate bits.
*/
clrldi r6,r4,(64-12) // r6 = r4 & 0xfff
cmpdi r6,0xff8
bgt .Lshort
subfic r6,r5,8
slwi r6,r6,3
LD rA,0,r3
LD rB,0,r4
srd rA,rA,r6
srd rB,rB,r6
cmpld cr0,rA,rB
bne cr0,.LcmpAB_lightweight
b .Lzero
.Lnon_zero:
mr r3,rC
blr
.Llong:
#ifdef CONFIG_ALTIVEC
BEGIN_FTR_SECTION
/* Try to use vmx loop if length is equal or greater than 4K */
cmpldi cr6,r5,VMX_THRESH
bge cr6,.Lsameoffset_vmx_cmp
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
.Llong_novmx_cmp:
#endif
/* At least s1 addr is aligned with 8 bytes */
li off8,8
li off16,16
li off24,24
std r31,-8(r1)
std r30,-16(r1)
std r29,-24(r1)
std r28,-32(r1)
std r27,-40(r1)
srdi r0,r5,5
mtctr r0
andi. r5,r5,31
LD rA,0,r3
LD rB,0,r4
LD rC,off8,r3
LD rD,off8,r4
LD rE,off16,r3
LD rF,off16,r4
LD rG,off24,r3
LD rH,off24,r4
cmpld cr0,rA,rB
addi r3,r3,32
addi r4,r4,32
bdz .Lfirst32
LD rA,0,r3
LD rB,0,r4
cmpld cr1,rC,rD
LD rC,off8,r3
LD rD,off8,r4
cmpld
|