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
|
/* $NetBSD: bcopyinout.S,v 1.11 2003/10/13 21:22:40 scw Exp $ */
/*-
* Copyright (c) 2002 Wasabi Systems, Inc.
* All rights reserved.
*
* Written by Allen Briggs for Wasabi Systems, Inc.
*
* 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.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed for the NetBSD Project by
* Wasabi Systems, Inc.
* 4. The name of Wasabi Systems, Inc. may not be used to endorse
* or promote products derived from this software without specific prior
* written permission.
*
* THIS SOFTWARE IS PROVIDED BY WASABI SYSTEMS, INC. ``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 WASABI SYSTEMS, INC
* 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 "assym.s"
#include <machine/asm.h>
#include <sys/errno.h>
.L_arm_memcpy:
.word _C_LABEL(_arm_memcpy)
.L_min_memcpy_size:
.word _C_LABEL(_min_memcpy_size)
__FBSDID("$FreeBSD$");
#ifdef _ARM_ARCH_5E
#include <arm/arm/bcopyinout_xscale.S>
#else
.text
.align 2
#ifdef _ARM_ARCH_6
#define GET_PCB(tmp) \
mrc p15, 0, tmp, c13, c0, 4; \
add tmp, tmp, #(TD_PCB)
#else
.Lcurpcb:
.word _C_LABEL(__pcpu) + PC_CURPCB
#define GET_PCB(tmp) \
ldr tmp, .Lcurpcb
#endif
#define SAVE_REGS stmfd sp!, {r4-r11}
#define RESTORE_REGS ldmfd sp!, {r4-r11}
#if defined(_ARM_ARCH_5E)
#define HELLOCPP #
#define PREFETCH(rx,o) pld [ rx , HELLOCPP (o) ]
#else
#define PREFETCH(rx,o)
#endif
/*
* r0 = user space address
* r1 = kernel space address
* r2 = length
*
* Copies bytes from user space to kernel space
*
* We save/restore r4-r11:
* r4-r11 are scratch
*/
ENTRY(copyin)
/* Quick exit if length is zero */
teq r2, #0
moveq r0, #0
RETeq
ldr r3, .L_arm_memcpy
ldr r3, [r3]
cmp r3, #0
beq .Lnormal
ldr r3, .L_min_memcpy_size
ldr r3, [r3]
cmp r2, r3
blt .Lnormal
stmfd sp!, {r0-r2, r4, lr}
mov r3, r0
mov r0, r1
mov r1, r3
mov r3, #2 /* SRC_IS_USER */
ldr r4, .L_arm_memcpy
mov lr, pc
ldr pc, [r4]
cmp r0, #0
ldmfd sp!, {r0-r2, r4, lr}
moveq r0, #0
RETeq
.Lnormal:
SAVE_REGS
GET_PCB(r4)
ldr r4, [r4]
ldr r5, [r4, #PCB_ONFAULT]
adr r3, .Lcopyfault
str r3, [r4, #PCB_ONFAULT]
PREFETCH(r0, 0)
PREFETCH(r1, 0)
/*
* If not too many bytes, take the slow path.
*/
cmp r2, #0x08
blt .Licleanup
/*
* Align destination to word boundary.
*/
and r6, r1, #0x3
ldr pc, [pc, r6, lsl #2]
b .Lialend
.word .Lialend
.word .Lial3
.word .Lial2
.word .Lial1
.Lial3: ldrbt r6, [r0], #1
sub r2, r2, #1
strb r6, [r1], #1
.Lial2: ldrbt r7, [r0], #1
sub r2, r2, #1
strb r7, [r1], #1
.Lial1: ldrbt r6, [r0], #1
sub r2, r2, #1
strb r6, [r1], #1
.Lialend:
/*
* If few bytes left, finish slow.
*/
cmp r2, #0x08
blt .Licleanup
/*
* If source is not aligned, finish slow.
*/
ands r3, r0, #0x03
bne .Licleanup
cmp r2, #0x60 /* Must be > 0x5f for unrolled cacheline */
blt .Licleanup8
/*
* Align destination to cacheline boundary.
* If source and destination are nicely aligned, this can be a big
* win. If not, it's still cheaper to copy in groups of 32 even if
* we don't get the nice cacheline alignment.
*/
and r6, r1, #0x1f
ldr pc, [pc, r6]
b .Licaligned
.word .Licaligned
.word .Lical28
.word .Lical24
.word .Lical20
.word .Lical16
.word .Lical12
.word .Lical8
.word .Lical4
.Lical28:ldrt r6, [r0], #4
sub r2, r2, #4
str r6, [r1], #4
.Lical24:ldrt r7, [r0], #4
sub r2, r2, #4
str r7, [r1], #4
.Lical20:ldrt r6, [r0], #4
sub r2, r2, #4
str r6, [r1], #4
.Lical16:ldrt r7, [r0], #4
sub r2, r2, #4
str r7, [r1], #4
.Lical12:ldrt r6, [r0], #4
sub r2, r2, #4
str r6, [r1], #4
.Lical8:ldrt r7, [r0], #4
sub r2, r2, #4
str r7, [r1], #4
.Lical4:ldrt r6, [r0], #4
sub r2, r2, #4
str r6, [r1], #4
/*
* We start with > 0x40 bytes to copy (>= 0x60 got us into this
* part of the code, and we may have knocked that down by as much
* as 0x1c getting aligned).
*
* This loop basically works out to:
* do {
* prefetch-next-cacheline(s)
* bytes -= 0x20;
* copy cacheline
* } while (bytes >= 0x40);
* bytes -= 0x20;
* copy cacheline
*/
.Licaligned:
PREFETCH(r0, 32)
PREFETCH(r1, 32)
sub r2, r2, #0x20
/* Copy a cacheline */
ldrt r10, [r0], #4
ldrt r11, [r0], #4
ldrt r6, [r0], #4
ldrt r7, [r0], #4
ldrt r8, [r0], #4
ldrt r9, [r0], #4
stmia r1!, {r10-r11}
ldrt r10, [r0], #4
ldrt r11, [r0], #4
stmia r1!, {r6-r11}
cmp r2, #0x40
bge .Licaligned
sub r2, r2, #0x20
/* Copy a cacheline */
ldrt r10, [r0], #4
ldrt r11, [r0], #4
ldrt r6, [r0], #4
ldrt r7, [r0], #4
ldrt r8, [r0], #4
ldrt r9, [r0], #4
stmia r1!, {r10-r11}
ldrt r10, [r0], #4
ldrt r11, [r0], #4
stmia r1!, {r6-r11}
cmp r2, #0x08
blt .Liprecleanup
.Licleanup8:
ldrt r8, [r0], #4
ldrt r9, [r0], #4
sub r2, r2, #8
stmia r1!, {r8, r9}
cmp r2, #8
bge .Licleanup8
.Liprecleanup:
/*
* If we're done, bail.
*/
cmp r2, #0
beq .Lout
.Licleanup:
and r6, r2, #0x3
ldr pc, [pc, r6, lsl #2]
b .Licend
.word .Lic4
.word .Lic1
.word .Lic2
.word .Lic3
.Lic4: ldrbt r6, [r0], #1
sub r2, r2, #1
strb r6, [r1], #1
.Lic3: ldrbt r7, [r0], #1
sub r2, r2, #1
strb r7, [r1], #1
.Lic2: ldrbt r6, [r0], #1
sub r2, r2, #1
strb r6, [r1], #1
.Lic1: ldrbt r7, [r0], #1
subs r2, r2, #1
strb r7, [r1], #1
.Licend:
bne .Licleanup
.Liout:
mov r0, #0
str r5, [r4, #PCB_ONFAULT]
RESTORE_REGS
RET
.Lcopyfault:
ldr r0, =EFAULT
str r5, [r4, #PCB_ONFAULT]
RESTORE_REGS
RET
END(copyin)
/*
* r0 = kernel space address
* r1 = user space address
* r2 = length
*
* Copies bytes from kernel space to user space
*
* We save/restore r4-r11:
* r4-r11 are scratch
*/
ENTRY(copyout)
/* Quick exit if length is zero */
teq r2, #0
moveq r0, #0
RETeq
ldr r3, .L_arm_memcpy
ldr r3, [r3]
cmp r3, #0
beq .Lnormale
ldr r3, .L_min_memcpy_size
ldr r3, [r3]
cmp r2, r3
blt .Lnormale
stmfd sp!, {r0-r2, r4, lr}
mov r3, r0
mov r0, r1
mov r1, r3
mov r3, #1 /* DST_IS_USER */
ldr r4, .L_arm_memcpy
mov lr, pc
ldr pc, [r4]
cmp r0, #0
ldmfd sp!, {r0-r2, r4, lr}
moveq r0, #0
RETeq
.Lnormale:
SAVE_REGS
GET_PCB(r4)
ldr r4, [r4]
ldr r5, [r4, #PCB_ONFAULT]
adr r3, .Lcopyfault
str r3, [r4, #PCB_ONFAULT]
PREFETCH(r0, 0)
PREFETCH(r1, 0)
/*
* If not too many bytes, take the slow path.
*/
cmp r2, #0x08
blt .Lcleanup
/*
* Align destination to word boundary.
*/
and r6, r1, #0x3
ldr pc, [pc, r6, lsl #2]
b .Lalend
.word .Lalend
.word .Lal3
.word .Lal2
.word .Lal1
.Lal3: ldrb r6, [r0], #1
sub r2, r2, #1
strbt r6, [r1], #1
.Lal2: ldrb r7, [r0], #1
sub r2, r2, #1
strbt r7, [r1], #1
.Lal1: ldrb r6, [r0], #1
sub r2, r2, #1
strbt r6, [r1], #1
.Lalend:
/*
* If few bytes left, finish slow.
*/
cmp r2, #0x08
blt .Lcleanup
/*
* If source is not aligned, finish slow.
*/
ands r3, r0, #0x03
bne .Lcleanup
cmp r2, #0x60 /* Must be > 0x5f for unrolled cacheline */
blt .Lcleanup8
/*
* Align source & destination to cacheline boundary.
*/
and r6, r1, #0x1f
ldr pc, [pc, r6]
b .Lcaligned
.word .Lcaligned
.word .Lcal28
.word .Lcal24
.word .Lcal20
.word .Lcal16
.word .Lcal12
.word .Lcal8
.word .Lcal4
.Lcal28:ldr r6, [r0], #4
sub r2, r2, #4
strt r6, [r1], #4
.Lcal24:ldr r7, [r0], #4
sub r2, r2, #4
strt r7, [r1], #4
.Lcal20:ldr r6, [r0], #4
sub r2, r2, #4
strt r6, [r1], #4
.Lcal16:ldr r7, [r0], #4
sub r2, r2, #4
strt r7, [r1], #4
.Lcal12:ldr r6, [r0], #4
sub r2, r2, #4
strt r6, [r1], #4
.Lcal8: ldr r7, [r0], #4
sub r2, r2, #4
strt r7, [r1], #4
.Lcal4: ldr r6, [r0], #4
sub r2, r2, #4
strt r6, [r1], #4
/*
* We start with > 0x40 bytes to copy (>= 0x60 got us into this
* part of the code, and we may have knocked that down by as much
* as 0x1c getting aligned).
*
* This loop basically works out to:
* do {
* prefetch-next-cacheline(s)
* bytes -= 0x20;
* copy cacheline
* } while (bytes >= 0x40);
* bytes -= 0x20;
* copy cacheline
*/
.Lcaligned:
PREFETCH(r0, 32)
PREFETCH(r1, 32)
sub r2, r2, #0x20
/* Copy a cacheline */
ldmia r0!, {r6-r11}
strt r6, [r1], #4
strt r7, [r1], #4
ldmia r0!, {r6-r7}
strt r8, [r1], #4
strt r9, [r1], #4
strt r10, [r1], #4
strt r11, [r1], #4
strt r6, [r1], #4
strt r7, [r1], #4
cmp r2, #0x40
bge .Lcaligned
sub r2, r2, #0x20
/* Copy a cacheline */
ldmia r0!, {r6-r11}
strt r6, [r1], #4
strt r7, [r1], #4
ldmia r0!, {r6-r7}
strt r8, [r1], #4
strt r9, [r1], #4
strt r10, [r1], #4
strt r11, [r1], #4
strt r6, [r1], #4
strt r7, [r1], #4
cmp r2, #0x08
blt .Lprecleanup
.Lcleanup8:
ldmia r0!, {r8-r9}
sub r2, r2, #8
strt r8, [r1], #4
strt r9, [r1], #4
cmp r2, #8
bge .Lcleanup8
.Lprecleanup:
/*
* If we're done, bail.
*/
cmp r2, #0
beq .Lout
.Lcleanup:
and r6, r2, #0x3
ldr pc, [pc, r6, lsl #2]
b .Lcend
.word .Lc4
.word .Lc1
.word .Lc2
.word .Lc3
.Lc4: ldrb r6, [r0], #1
sub r2, r2, #1
strbt r6, [r1], #1
.Lc3: ldrb r7, [r0], #1
sub r2, r2, #1
strbt r7, [r1], #1
.Lc2: ldrb r6, [r0], #1
sub r2, r2, #1
strbt r6, [r1], #1
.Lc1: ldrb r7, [r0], #1
subs r2, r2, #1
strbt r7, [r1], #1
.Lcend:
bne .Lcleanup
.Lout:
mov r0, #0
str r5, [r4, #PCB_ONFAULT]
RESTORE_REGS
RET
END(copyout)
#endif
/*
* int badaddr_read_1(const uint8_t *src, uint8_t *dest)
*
* Copies a single 8-bit value from src to dest, returning 0 on success,
* else EFAULT if a page fault occurred.
*/
ENTRY(badaddr_read_1)
GET_PCB(r2)
ldr r2, [r2]
ldr ip, [r2, #PCB_ONFAULT]
adr r3, 1f
str r3, [r2, #PCB_ONFAULT]
nop
nop
nop
ldrb r3, [r0]
nop
nop
nop
strb r3, [r1]
mov r0, #0 /* No fault */
1: str ip, [r2, #PCB_ONFAULT]
RET
END(badaddr_read_1)
/*
* int badaddr_read_2(const uint16_t *src, uint16_t *dest)
*
* Copies a single 16-bit value from src to dest, returning 0 on success,
* else EFAULT if a page fault occurred.
*/
ENTRY(badaddr_read_2)
GET_PCB(r2)
ldr r2, [r2]
ldr ip, [r2, #PCB_ONFAULT]
adr r3, 1f
str r3, [r2, #PCB_ONFAULT]
nop
nop
nop
ldrh r3, [r0]
nop
nop
nop
strh r3, [r1]
mov r0, #0 /* No fault */
1: str ip, [r2, #PCB_ONFAULT]
RET
END(badaddr_read_2)
/*
* int badaddr_read_4(const uint32_t *src, uint32_t *dest)
*
* Copies a single 32-bit value from src to dest, returning 0 on success,
* else EFAULT if a page fault occurred.
*/
ENTRY(badaddr_read_4)
GET_PCB(r2)
ldr r2, [r2]
ldr ip, [r2, #PCB_ONFAULT]
adr r3, 1f
str r3, [r2, #PCB_ONFAULT]
nop
nop
nop
ldr r3, [r0]
nop
nop
nop
str r3, [r1]
mov r0, #0 /* No fault */
1: str ip, [r2, #PCB_ONFAULT]
RET
END(badaddr_read_4)
|