summaryrefslogtreecommitdiff
path: root/arch/metag/lib/usercopy.c
blob: 2792fc621088bcd1c3d7bfe58b8560ec32e6f880 (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
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
/*
 * User address space access functions.
 * The non-inlined parts of asm-metag/uaccess.h are here.
 *
 * Copyright (C) 2006, Imagination Technologies.
 * Copyright (C) 2000, Axis Communications AB.
 *
 * Written by Hans-Peter Nilsson.
 * Pieces used from memcpy, originally by Kenny Ranerup long time ago.
 * Modified for Meta by Will Newton.
 */

#include <linux/export.h>
#include <linux/uaccess.h>
#include <asm/cache.h>			/* def of L1_CACHE_BYTES */

#define USE_RAPF
#define RAPF_MIN_BUF_SIZE	(3*L1_CACHE_BYTES)


/* The "double write" in this code is because the Meta will not fault
 * immediately unless the memory pipe is forced to by e.g. a data stall or
 * another memory op. The second write should be discarded by the write
 * combiner so should have virtually no cost.
 */

#define __asm_copy_user_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	asm volatile (						 \
		COPY						 \
		"1:\n"						 \
		"	.section .fixup,\"ax\"\n"		 \
		FIXUP						 \
		"	MOVT    D1Ar1,#HI(1b)\n"		 \
		"	JUMP    D1Ar1,#LO(1b)\n"		 \
		"	.previous\n"				 \
		"	.section __ex_table,\"a\"\n"		 \
		TENTRY						 \
		"	.previous\n"				 \
		: "=r" (to), "=r" (from), "=r" (ret)		 \
		: "0" (to), "1" (from), "2" (ret)		 \
		: "D1Ar1", "memory")


#define __asm_copy_to_user_1(to, from, ret)	\
	__asm_copy_user_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"	\
		"	SETB [%0],D1Ar1\n"	\
		"2:	SETB [%0++],D1Ar1\n",	\
		"3:	ADD  %2,%2,#1\n",	\
		"	.long 2b,3b\n")

#define __asm_copy_to_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_user_cont(to, from, ret,		\
		"	GETW D1Ar1,[%1++]\n"		\
		"	SETW [%0],D1Ar1\n"		\
		"2:	SETW [%0++],D1Ar1\n" COPY,	\
		"3:	ADD  %2,%2,#2\n" FIXUP,		\
		"	.long 2b,3b\n" TENTRY)

#define __asm_copy_to_user_2(to, from, ret) \
	__asm_copy_to_user_2x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_3(to, from, ret) \
	__asm_copy_to_user_2x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"	SETB [%0],D1Ar1\n"		\
		"4:	SETB [%0++],D1Ar1\n",		\
		"5:	ADD  %2,%2,#1\n",		\
		"	.long 4b,5b\n")

#define __asm_copy_to_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_user_cont(to, from, ret,		\
		"	GETD D1Ar1,[%1++]\n"		\
		"	SETD [%0],D1Ar1\n"		\
		"2:	SETD [%0++],D1Ar1\n" COPY,	\
		"3:	ADD  %2,%2,#4\n" FIXUP,		\
		"	.long 2b,3b\n" TENTRY)

#define __asm_copy_to_user_4(to, from, ret) \
	__asm_copy_to_user_4x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_5(to, from, ret) \
	__asm_copy_to_user_4x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"	SETB [%0],D1Ar1\n"		\
		"4:	SETB [%0++],D1Ar1\n",		\
		"5:	ADD  %2,%2,#1\n",		\
		"	.long 4b,5b\n")

#define __asm_copy_to_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_to_user_4x_cont(to, from, ret,	\
		"	GETW D1Ar1,[%1++]\n"		\
		"	SETW [%0],D1Ar1\n"		\
		"4:	SETW [%0++],D1Ar1\n" COPY,	\
		"5:	ADD  %2,%2,#2\n" FIXUP,		\
		"	.long 4b,5b\n" TENTRY)

#define __asm_copy_to_user_6(to, from, ret) \
	__asm_copy_to_user_6x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_7(to, from, ret) \
	__asm_copy_to_user_6x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"	SETB [%0],D1Ar1\n"		\
		"6:	SETB [%0++],D1Ar1\n",		\
		"7:	ADD  %2,%2,#1\n",		\
		"	.long 6b,7b\n")

#define __asm_copy_to_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_to_user_4x_cont(to, from, ret,	\
		"	GETD D1Ar1,[%1++]\n"		\
		"	SETD [%0],D1Ar1\n"		\
		"4:	SETD [%0++],D1Ar1\n" COPY,	\
		"5:	ADD  %2,%2,#4\n"  FIXUP,	\
		"	.long 4b,5b\n" TENTRY)

#define __asm_copy_to_user_8(to, from, ret) \
	__asm_copy_to_user_8x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_9(to, from, ret) \
	__asm_copy_to_user_8x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"	SETB [%0],D1Ar1\n"		\
		"6:	SETB [%0++],D1Ar1\n",		\
		"7:	ADD  %2,%2,#1\n",		\
		"	.long 6b,7b\n")

#define __asm_copy_to_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_to_user_8x_cont(to, from, ret,	\
		"	GETW D1Ar1,[%1++]\n"		\
		"	SETW [%0],D1Ar1\n"		\
		"6:	SETW [%0++],D1Ar1\n" COPY,	\
		"7:	ADD  %2,%2,#2\n" FIXUP,		\
		"	.long 6b,7b\n" TENTRY)

#define __asm_copy_to_user_10(to, from, ret) \
	__asm_copy_to_user_10x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_11(to, from, ret) \
	__asm_copy_to_user_10x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"	SETB [%0],D1Ar1\n"		\
		"8:	SETB [%0++],D1Ar1\n",		\
		"9:	ADD  %2,%2,#1\n",		\
		"	.long 8b,9b\n")

#define __asm_copy_to_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_to_user_8x_cont(to, from, ret,	\
		"	GETD D1Ar1,[%1++]\n"		\
		"	SETD [%0],D1Ar1\n"		\
		"6:	SETD [%0++],D1Ar1\n" COPY,	\
		"7:	ADD  %2,%2,#4\n" FIXUP,		\
		"	.long 6b,7b\n" TENTRY)
#define __asm_copy_to_user_12(to, from, ret) \
	__asm_copy_to_user_12x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_13(to, from, ret) \
	__asm_copy_to_user_12x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"	SETB [%0],D1Ar1\n"		\
		"8:	SETB [%0++],D1Ar1\n",		\
		"9:	ADD  %2,%2,#1\n",		\
		"	.long 8b,9b\n")

#define __asm_copy_to_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_to_user_12x_cont(to, from, ret,	\
		"	GETW D1Ar1,[%1++]\n"		\
		"	SETW [%0],D1Ar1\n"		\
		"8:	SETW [%0++],D1Ar1\n" COPY,	\
		"9:	ADD  %2,%2,#2\n" FIXUP,		\
		"	.long 8b,9b\n" TENTRY)

#define __asm_copy_to_user_14(to, from, ret) \
	__asm_copy_to_user_14x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_15(to, from, ret) \
	__asm_copy_to_user_14x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"	SETB [%0],D1Ar1\n"		\
		"10:	SETB [%0++],D1Ar1\n",		\
		"11:	ADD  %2,%2,#1\n",		\
		"	.long 10b,11b\n")

#define __asm_copy_to_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_to_user_12x_cont(to, from, ret,	\
		"	GETD D1Ar1,[%1++]\n"		\
		"	SETD [%0],D1Ar1\n"		\
		"8:	SETD [%0++],D1Ar1\n" COPY,	\
		"9:	ADD  %2,%2,#4\n" FIXUP,		\
		"	.long 8b,9b\n" TENTRY)

#define __asm_copy_to_user_16(to, from, ret) \
		__asm_copy_to_user_16x_cont(to, from, ret, "", "", "")

#define __asm_copy_to_user_8x64(to, from, ret) \
	asm volatile (					\
		"	GETL D0Ar2,D1Ar1,[%1++]\n"	\
		"	SETL [%0],D0Ar2,D1Ar1\n"	\
		"2:	SETL [%0++],D0Ar2,D1Ar1\n"	\
		"1:\n"					\
		"	.section .fixup,\"ax\"\n"	\
		"3:	ADD  %2,%2,#8\n"		\
		"	MOVT    D0Ar2,#HI(1b)\n"	\
		"	JUMP    D0Ar2,#LO(1b)\n"	\
		"	.previous\n"			\
		"	.section __ex_table,\"a\"\n"	\
		"	.long 2b,3b\n"			\
		"	.previous\n"			\
		: "=r" (to), "=r" (from), "=r" (ret)	\
		: "0" (to), "1" (from), "2" (ret)	\
		: "D1Ar1", "D0Ar2", "memory")

/*
 *	optimized copying loop using RAPF when 64 bit aligned
 *
 *	n		will be automatically decremented inside the loop
 *	ret		will be left intact. if error occurs we will rewind
 *			so that the original non optimized code will fill up
 *			this value correctly.
 *
 *	on fault:
 *		>	n will hold total number of uncopied bytes
 *
 *		>	{'to','from'} will be rewind back so that
 *			the non-optimized code will do the proper fix up
 *
 *	DCACHE drops the cacheline which helps in reducing cache
 *	pollution.
 *
 *	We introduce an extra SETL at the end of the loop to
 *	ensure we don't fall off the loop before we catch all
 *	erros.
 *
 *	NOTICE:
 *		LSM_STEP in TXSTATUS must be cleared in fix up code.
 *		since we're using M{S,G}ETL, a fault might happen at
 *		any address in the middle of M{S,G}ETL causing
 *		the value of LSM_STEP to be incorrect which can
 *		cause subsequent use of M{S,G}ET{L,D} to go wrong.
 *		ie: if LSM_STEP was 1 when a fault occurs, the
 *		next call to M{S,G}ET{L,D} will skip the first
 *		copy/getting as it think that the first 1 has already
 *		been done.
 *
 */
#define __asm_copy_user_64bit_rapf_loop(				\
		to, from, ret, n, id, FIXUP)				\
	asm volatile (							\
		".balign 8\n"						\
		"MOV	RAPF, %1\n"					\
		"MSETL	[A0StP++], D0Ar6, D0FrT, D0.5, D0.6, D0.7\n"	\
		"MOV	D0Ar6, #0\n"					\
		"LSR	D1Ar5, %3, #6\n"				\
		"SUB	TXRPT, D1Ar5, #2\n"				\
		"MOV	RAPF, %1\n"					\
		"$Lloop"id":\n"						\
		"ADD	RAPF, %1, #64\n"				\
		"21:\n"							\
		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"22:\n"							\
		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"23:\n"							\
		"SUB	%3, %3, #32\n"					\
		"24:\n"							\
		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"25:\n"							\
		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"26:\n"							\
		"SUB	%3, %3, #32\n"					\
		"DCACHE	[%1+#-64], D0Ar6\n"				\
		"BR	$Lloop"id"\n"					\
									\
		"MOV	RAPF, %1\n"					\
		"27:\n"							\
		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"28:\n"							\
		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"29:\n"							\
		"SUB	%3, %3, #32\n"					\
		"30:\n"							\
		"MGETL	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"31:\n"							\
		"MSETL	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"32:\n"							\
		"SUB	%0, %0, #8\n"					\
		"33:\n"							\
		"SETL	[%0++], D0.7, D1.7\n"				\
		"SUB	%3, %3, #32\n"					\
		"1:"							\
		"DCACHE	[%1+#-64], D0Ar6\n"				\
		"GETL    D0Ar6, D1Ar5, [A0StP+#-40]\n"			\
		"GETL    D0FrT, D1RtP, [A0StP+#-32]\n"			\
		"GETL    D0.5, D1.5, [A0StP+#-24]\n"			\
		"GETL    D0.6, D1.6, [A0StP+#-16]\n"			\
		"GETL    D0.7, D1.7, [A0StP+#-8]\n"			\
		"SUB A0StP, A0StP, #40\n"				\
		"	.section .fixup,\"ax\"\n"			\
		"4:\n"							\
		"	ADD	%0, %0, #8\n"				\
		"3:\n"							\
		"	MOV	D0Ar2, TXSTATUS\n"			\
		"	MOV	D1Ar1, TXSTATUS\n"			\
		"	AND	D1Ar1, D1Ar1, #0xFFFFF8FF\n"		\
		"	MOV	TXSTATUS, D1Ar1\n"			\
			FIXUP						\
		"	MOVT    D0Ar2,#HI(1b)\n"			\
		"	JUMP    D0Ar2,#LO(1b)\n"			\
		"	.previous\n"					\
		"	.section __ex_table,\"a\"\n"			\
		"	.long 21b,3b\n"					\
		"	.long 22b,3b\n"					\
		"	.long 23b,3b\n"					\
		"	.long 24b,3b\n"					\
		"	.long 25b,3b\n"					\
		"	.long 26b,3b\n"					\
		"	.long 27b,3b\n"					\
		"	.long 28b,3b\n"					\
		"	.long 29b,3b\n"					\
		"	.long 30b,3b\n"					\
		"	.long 31b,3b\n"					\
		"	.long 32b,3b\n"					\
		"	.long 33b,4b\n"					\
		"	.previous\n"					\
		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
		: "D1Ar1", "D0Ar2", "cc", "memory")

/*	rewind 'to' and 'from'  pointers when a fault occurs
 *
 *	Rationale:
 *		A fault always occurs on writing to user buffer. A fault
 *		is at a single address, so we need to rewind by only 4
 *		bytes.
 *		Since we do a complete read from kernel buffer before
 *		writing, we need to rewind it also. The amount to be
 *		rewind equals the number of faulty writes in MSETD
 *		which is: [4 - (LSM_STEP-1)]*8
 *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
 *		and stored in D0Ar2
 *
 *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
 *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
 *			a fault happens at the 4th write, LSM_STEP will be 0
 *			instead of 4. The code copes with that.
 *
 *		n is updated by the number of successful writes, which is:
 *		n = n - (LSM_STEP-1)*8
 */
#define __asm_copy_to_user_64bit_rapf_loop(to,	from, ret, n, id)\
	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
		"LSR	D0Ar2, D0Ar2, #8\n"				\
		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
		"SUB	D0Ar2, D0Ar2, #1\n"				\
		"MOV	D1Ar1, #4\n"					\
		"SUB	D0Ar2, D1Ar1, D0Ar2\n"				\
		"LSL	D0Ar2, D0Ar2, #3\n"				\
		"LSL	D1Ar1, D1Ar1, #3\n"				\
		"SUB	D1Ar1, D1Ar1, D0Ar2\n"				\
		"SUB	%0, %0, #8\n"					\
		"SUB	%1,	%1,D0Ar2\n"				\
		"SUB	%3, %3, D1Ar1\n")

/*
 *	optimized copying loop using RAPF when 32 bit aligned
 *
 *	n		will be automatically decremented inside the loop
 *	ret		will be left intact. if error occurs we will rewind
 *			so that the original non optimized code will fill up
 *			this value correctly.
 *
 *	on fault:
 *		>	n will hold total number of uncopied bytes
 *
 *		>	{'to','from'} will be rewind back so that
 *			the non-optimized code will do the proper fix up
 *
 *	DCACHE drops the cacheline which helps in reducing cache
 *	pollution.
 *
 *	We introduce an extra SETD at the end of the loop to
 *	ensure we don't fall off the loop before we catch all
 *	erros.
 *
 *	NOTICE:
 *		LSM_STEP in TXSTATUS must be cleared in fix up code.
 *		since we're using M{S,G}ETL, a fault might happen at
 *		any address in the middle of M{S,G}ETL causing
 *		the value of LSM_STEP to be incorrect which can
 *		cause subsequent use of M{S,G}ET{L,D} to go wrong.
 *		ie: if LSM_STEP was 1 when a fault occurs, the
 *		next call to M{S,G}ET{L,D} will skip the first
 *		copy/getting as it think that the first 1 has already
 *		been done.
 *
 */
#define __asm_copy_user_32bit_rapf_loop(				\
			to,	from, ret, n, id, FIXUP)		\
	asm volatile (							\
		".balign 8\n"						\
		"MOV	RAPF, %1\n"					\
		"MSETL	[A0StP++], D0Ar6, D0FrT, D0.5, D0.6, D0.7\n"	\
		"MOV	D0Ar6, #0\n"					\
		"LSR	D1Ar5, %3, #6\n"				\
		"SUB	TXRPT, D1Ar5, #2\n"				\
		"MOV	RAPF, %1\n"					\
	"$Lloop"id":\n"							\
		"ADD	RAPF, %1, #64\n"				\
		"21:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"22:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"23:\n"							\
		"SUB	%3, %3, #16\n"					\
		"24:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"25:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"26:\n"							\
		"SUB	%3, %3, #16\n"					\
		"27:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"28:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"29:\n"							\
		"SUB	%3, %3, #16\n"					\
		"30:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"31:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"32:\n"							\
		"SUB	%3, %3, #16\n"					\
		"DCACHE	[%1+#-64], D0Ar6\n"				\
		"BR	$Lloop"id"\n"					\
									\
		"MOV	RAPF, %1\n"					\
		"33:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"34:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"35:\n"							\
		"SUB	%3, %3, #16\n"					\
		"36:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"37:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"38:\n"							\
		"SUB	%3, %3, #16\n"					\
		"39:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"40:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"41:\n"							\
		"SUB	%3, %3, #16\n"					\
		"42:\n"							\
		"MGETD	D0FrT, D0.5, D0.6, D0.7, [%1++]\n"		\
		"43:\n"							\
		"MSETD	[%0++], D0FrT, D0.5, D0.6, D0.7\n"		\
		"44:\n"							\
		"SUB	%0, %0, #4\n"					\
		"45:\n"							\
		"SETD	[%0++], D0.7\n"					\
		"SUB	%3, %3, #16\n"					\
		"1:"							\
		"DCACHE	[%1+#-64], D0Ar6\n"				\
		"GETL    D0Ar6, D1Ar5, [A0StP+#-40]\n"			\
		"GETL    D0FrT, D1RtP, [A0StP+#-32]\n"			\
		"GETL    D0.5, D1.5, [A0StP+#-24]\n"			\
		"GETL    D0.6, D1.6, [A0StP+#-16]\n"			\
		"GETL    D0.7, D1.7, [A0StP+#-8]\n"			\
		"SUB A0StP, A0StP, #40\n"				\
		"	.section .fixup,\"ax\"\n"			\
		"4:\n"							\
		"	ADD		%0, %0, #4\n"			\
		"3:\n"							\
		"	MOV	D0Ar2, TXSTATUS\n"			\
		"	MOV	D1Ar1, TXSTATUS\n"			\
		"	AND	D1Ar1, D1Ar1, #0xFFFFF8FF\n"		\
		"	MOV	TXSTATUS, D1Ar1\n"			\
			FIXUP						\
		"	MOVT    D0Ar2,#HI(1b)\n"			\
		"	JUMP    D0Ar2,#LO(1b)\n"			\
		"	.previous\n"					\
		"	.section __ex_table,\"a\"\n"			\
		"	.long 21b,3b\n"					\
		"	.long 22b,3b\n"					\
		"	.long 23b,3b\n"					\
		"	.long 24b,3b\n"					\
		"	.long 25b,3b\n"					\
		"	.long 26b,3b\n"					\
		"	.long 27b,3b\n"					\
		"	.long 28b,3b\n"					\
		"	.long 29b,3b\n"					\
		"	.long 30b,3b\n"					\
		"	.long 31b,3b\n"					\
		"	.long 32b,3b\n"					\
		"	.long 33b,3b\n"					\
		"	.long 34b,3b\n"					\
		"	.long 35b,3b\n"					\
		"	.long 36b,3b\n"					\
		"	.long 37b,3b\n"					\
		"	.long 38b,3b\n"					\
		"	.long 39b,3b\n"					\
		"	.long 40b,3b\n"					\
		"	.long 41b,3b\n"					\
		"	.long 42b,3b\n"					\
		"	.long 43b,3b\n"					\
		"	.long 44b,3b\n"					\
		"	.long 45b,4b\n"					\
		"	.previous\n"					\
		: "=r" (to), "=r" (from), "=r" (ret), "=d" (n)		\
		: "0" (to), "1" (from), "2" (ret), "3" (n)		\
		: "D1Ar1", "D0Ar2", "cc", "memory")

/*	rewind 'to' and 'from'  pointers when a fault occurs
 *
 *	Rationale:
 *		A fault always occurs on writing to user buffer. A fault
 *		is at a single address, so we need to rewind by only 4
 *		bytes.
 *		Since we do a complete read from kernel buffer before
 *		writing, we need to rewind it also. The amount to be
 *		rewind equals the number of faulty writes in MSETD
 *		which is: [4 - (LSM_STEP-1)]*4
 *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
 *		and stored in D0Ar2
 *
 *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
 *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
 *			a fault happens at the 4th write, LSM_STEP will be 0
 *			instead of 4. The code copes with that.
 *
 *		n is updated by the number of successful writes, which is:
 *		n = n - (LSM_STEP-1)*4
 */
#define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\
	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
		"LSR	D0Ar2, D0Ar2, #8\n"				\
		"ANDS	D0Ar2, D0Ar2, #0x7\n"				\
		"ADDZ	D0Ar2, D0Ar2, #4\n"				\
		"SUB	D0Ar2, D0Ar2, #1\n"				\
		"MOV	D1Ar1, #4\n"					\
		"SUB	D0Ar2, D1Ar1, D0Ar2\n"				\
		"LSL	D0Ar2, D0Ar2, #2\n"				\
		"LSL	D1Ar1, D1Ar1, #2\n"				\
		"SUB	D1Ar1, D1Ar1, D0Ar2\n"				\
		"SUB	%0, %0, #4\n"					\
		"SUB	%1,	%1,	D0Ar2\n"			\
		"SUB	%3, %3, D1Ar1\n")

unsigned long __copy_user(void __user *pdst, const void *psrc,
			  unsigned long n)
{
	register char __user *dst asm ("A0.2") = pdst;
	register const char *src asm ("A1.2") = psrc;
	unsigned long retn = 0;

	if (n == 0)
		return 0;

	if ((unsigned long) src & 1) {
		__asm_copy_to_user_1(dst, src, retn);
		n--;
		if (retn)
			return retn + n;
	}
	if ((unsigned long) dst & 1) {
		/* Worst case - byte copy */
		while (n > 0) {
			__asm_copy_to_user_1(dst, src, retn);
			n--;
			if (retn)
				return retn + n;
		}
	}
	if (((unsigned long) src & 2) && n >= 2) {
		__asm_copy_to_user_2(dst, src, retn);
		n -= 2;
		if (retn)
			return retn + n;
	}
	if ((unsigned long) dst & 2) {
		/* Second worst case - word copy */
		while (n >= 2) {
			__asm_copy_to_user_2(dst, src, retn);
			n -= 2;
			if (retn)
				return retn + n;
		}
	}

#ifdef USE_RAPF
	/* 64 bit copy loop */
	if (!(((unsigned long) src | (__force unsigned long) dst) & 7)) {
		if (n >= RAPF_MIN_BUF_SIZE) {
			/* copy user using 64 bit rapf copy */
			__asm_copy_to_user_64bit_rapf_loop(dst, src, retn,
							n, "64cu");
		}
		while (n >= 8) {
			__asm_copy_to_user_8x64(dst, src, retn);
			n -= 8;
			if (retn)
				return retn + n;
		}
	}
	if (n >= RAPF_MIN_BUF_SIZE) {
		/* copy user using 32 bit rapf copy */
		__asm_copy_to_user_32bit_rapf_loop(dst, src, retn, n, "32cu");
	}
#else
	/* 64 bit copy loop */
	if (!(((unsigned long) src | (__force unsigned long) dst) & 7)) {
		while (n >= 8) {
			__asm_copy_to_user_8x64(dst, src, retn);
			n -= 8;
			if (retn)
				return retn + n;
		}
	}
#endif

	while (n >= 16) {
		__asm_copy_to_user_16(dst, src, retn);
		n -= 16;
		if (retn)
			return retn + n;
	}

	while (n >= 4) {
		__asm_copy_to_user_4(dst, src, retn);
		n -= 4;
		if (retn)
			return retn + n;
	}

	switch (n) {
	case 0:
		break;
	case 1:
		__asm_copy_to_user_1(dst, src, retn);
		break;
	case 2:
		__asm_copy_to_user_2(dst, src, retn);
		break;
	case 3:
		__asm_copy_to_user_3(dst, src, retn);
		break;
	}

	/*
	 * If we get here, retn correctly reflects the number of failing
	 * bytes.
	 */
	return retn;
}
EXPORT_SYMBOL(__copy_user);

#define __asm_copy_from_user_1(to, from, ret) \
	__asm_copy_user_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"	\
		"2:	SETB [%0++],D1Ar1\n",	\
		"3:	ADD  %2,%2,#1\n",	\
		"	.long 2b,3b\n")

#define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_user_cont(to, from, ret,		\
		"	GETW D1Ar1,[%1++]\n"		\
		"2:	SETW [%0++],D1Ar1\n" COPY,	\
		"3:	ADD  %2,%2,#2\n" FIXUP,		\
		"	.long 2b,3b\n" TENTRY)

#define __asm_copy_from_user_2(to, from, ret) \
	__asm_copy_from_user_2x_cont(to, from, ret, "", "", "")

#define __asm_copy_from_user_3(to, from, ret)		\
	__asm_copy_from_user_2x_cont(to, from, ret,	\
		"	GETB D1Ar1,[%1++]\n"		\
		"4:	SETB [%0++],D1Ar1\n",		\
		"5:	ADD  %2,%2,#1\n",		\
		"	.long 4b,5b\n")

#define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
	__asm_copy_user_cont(to, from, ret,		\
		"	GETD D1Ar1,[%1++]\n"		\
		"2:	SETD [%0++],D1Ar1\n" COPY,	\
		"3:	ADD  %2,%2,#4\n" FIXUP,		\
		"	.long 2b,3b\n" TENTRY)

#define __asm_copy_from_user_4(to, from, ret) \
	__asm_copy_from_user_4x_cont(to, from, ret, "", "", "")

#define __asm_copy_from_user_8x64(to, from, ret) \
	asm volatile (				\
		"	GETL D0Ar2,D1Ar1,[%1++]\n"	\
		"2:	SETL [%0++],D0Ar2,D1Ar1\n"	\
		"1:\n"					\
		"	.section .fixup,\"ax\"\n"	\
		"3:	ADD  %2,%2,#8\n"		\
		"	MOVT    D0Ar2,#HI(1b)\n"	\
		"	JUMP    D0Ar2,#LO(1b)\n"	\
		"	.previous\n"			\
		"	.section __ex_table,\"a\"\n"	\
		"	.long 2b,3b\n"			\
		"	.previous\n"			\
		: "=a" (to), "=r" (from), "=r" (ret)	\
		: "0" (to), "1" (from), "2" (ret)	\
		: "D1Ar1", "D0Ar2", "memory")

/*	rewind 'from' pointer when a fault occurs
 *
 *	Rationale:
 *		A fault occurs while reading from user buffer, which is the
 *		source.
 *		Since we don't write to kernel buffer until we read first,
 *		the kernel buffer is at the right state and needn't be
 *		corrected, but the source must be rewound to the beginning of
 *		the block, which is LSM_STEP*8 bytes.
 *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
 *		and stored in D0Ar2
 *
 *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
 *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
 *			a fault happens at the 4th write, LSM_STEP will be 0
 *			instead of 4. The code copes with that.
 */
#define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id)	\
	__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id,		\
		"LSR	D0Ar2, D0Ar2, #5\n"				\
		"ANDS	D0Ar2, D0Ar2, #0x38\n"				\
		"ADDZ	D0Ar2, D0Ar2, #32\n"				\
		"SUB	%1, %1, D0Ar2\n")

/*	rewind 'from' pointer when a fault occurs
 *
 *	Rationale:
 *		A fault occurs while reading from user buffer, which is the
 *		source.
 *		Since we don't write to kernel buffer until we read first,
 *		the kernel buffer is at the right state and needn't be
 *		corrected, but the source must be rewound to the beginning of
 *		the block, which is LSM_STEP*4 bytes.
 *		LSM_STEP is bits 10:8 in TXSTATUS which is already read
 *		and stored in D0Ar2
 *
 *		NOTE: If a fault occurs at the last operation in M{G,S}ETL
 *			LSM_STEP will be 0. ie: we do 4 writes in our case, if
 *			a fault happens at the 4th write, LSM_STEP will be 0
 *			instead of 4. The code copes with that.
 */
#define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id)	\
	__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id,		\
		"LSR	D0Ar2, D0Ar2, #6\n"				\
		"ANDS	D0Ar2, D0Ar2, #0x1c\n"				\
		"ADDZ	D0Ar2, D0Ar2, #16\n"				\
		"SUB	%1, %1, D0Ar2\n")


/*
 * Copy from user to kernel. The return-value is the number of bytes that were
 * inaccessible.
 */
unsigned long raw_copy_from_user(void *pdst, const void __user *psrc,
				 unsigned long n)
{
	register char *dst asm ("A0.2") = pdst;
	register const char __user *src asm ("A1.2") = psrc;
	unsigned long retn = 0;

	if (n == 0)
		return 0;

	if ((unsigned long) src & 1) {
		__asm_copy_from_user_1(dst, src, retn);
		n--;
		if (retn)
			return retn + n;
	}
	if ((unsigned long) dst & 1) {
		/* Worst case - byte copy */
		while (n > 0) {
			__asm_copy_from_user_1(dst, src, retn);
			n--;
			if (retn)
				return retn + n;
		}
	}
	if (((unsigned long) src & 2) && n >= 2) {
		__asm_copy_from_user_2(dst, src, retn);
		n -= 2;
		if (retn)
			return retn + n;
	}
	if ((unsigned long) dst & 2) {
		/* Second worst case - word copy */
		while (n >= 2) {
			__asm_copy_from_user_2(dst, src, retn);
			n -= 2;
			if (retn)
				return retn + n;
		}
	}

#ifdef USE_RAPF
	/* 64 bit copy loop */
	if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
		if (n >= RAPF_MIN_BUF_SIZE) {
			/* Copy using fast 64bit rapf */
			__asm_copy_from_user_64bit_rapf_loop(dst, src, retn,
							n, "64cuz");
		}
		while (n >= 8) {
			__asm_copy_from_user_8x64(dst, src, retn);
			n -= 8;
			if (retn)
				return retn + n;
		}
	}

	if (n >= RAPF_MIN_BUF_SIZE) {
		/* Copy using fast 32bit rapf */
		__asm_copy_from_user_32bit_rapf_loop(dst, src, retn,
						n, "32cuz");
	}
#else
	/* 64 bit copy loop */
	if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
		while (n >= 8) {
			__asm_copy_from_user_8x64(dst, src, retn);
			n -= 8;
			if (retn)
				return retn + n;
		}
	}
#endif

	while (n >= 4) {
		__asm_copy_from_user_4(dst, src, retn);
		n -= 4;

		if (retn)
			return retn + n;
	}

	/* If we get here, there were no memory read faults.  */
	switch (n) {
		/* These copies are at least "naturally aligned" (so we don't
		   have to check each byte), due to the src alignment code.
		   The *_3 case *will* get the correct count for retn.  */
	case 0:
		/* This case deliberately left in (if you have doubts check the
		   generated assembly code).  */
		break;
	case 1:
		__asm_copy_from_user_1(dst, src, retn);
		break;
	case 2:
		__asm_copy_from_user_2(dst, src, retn);
		break;
	case 3:
		__asm_copy_from_user_3(dst, src, retn);
		break;
	}

	/* If we get here, retn correctly reflects the number of failing
	   bytes.  */
	return retn;
}
EXPORT_SYMBOL(raw_copy_from_user);

#define __asm_clear_8x64(to, ret) \
	asm volatile (					\
		"	MOV  D0Ar2,#0\n"		\
		"	MOV  D1Ar1,#0\n"		\
		"	SETL [%0],D0Ar2,D1Ar1\n"	\
		"2:	SETL [%0++],D0Ar2,D1Ar1\n"	\
		"1:\n"					\
		"	.section .fixup,\"ax\"\n"	\
		"3:	ADD  %1,%1,#8\n"		\
		"	MOVT    D0Ar2,#HI(1b)\n"	\
		"	JUMP    D0Ar2,#LO(1b)\n"	\
		"	.previous\n"			\
		"	.section __ex_table,\"a\"\n"	\
		"	.long 2b,3b\n"			\
		"	.previous\n"			\
		: "=r" (to), "=r" (ret)	\
		: "0" (to), "1" (ret)	\
		: "D1Ar1", "D0Ar2", "memory")

/* Zero userspace.  */

#define __asm_clear(to, ret, CLEAR, FIXUP, TENTRY) \
	asm volatile (					\
		"	MOV D1Ar1,#0\n"			\
			CLEAR				\
		"1:\n"					\
		"	.section .fixup,\"ax\"\n"	\
			FIXUP				\
		"	MOVT    D1Ar1,#HI(1b)\n"	\
		"	JUMP    D1Ar1,#LO(1b)\n"	\
		"	.previous\n"			\
		"	.section __ex_table,\"a\"\n"	\
			TENTRY				\
		"	.previous"			\
		: "=r" (to), "=r" (ret)			\
		: "0" (to), "1" (ret)			\
		: "D1Ar1", "memory")

#define __asm_clear_1(to, ret) \
	__asm_clear(to, ret,			\
		"	SETB [%0],D1Ar1\n"	\
		"2:	SETB [%0++],D1Ar1\n",	\
		"3:	ADD  %1,%1,#1\n",	\
		"	.long 2b,3b\n")

#define __asm_clear_2(to, ret) \
	__asm_clear(to, ret,			\
		"	SETW [%0],D1Ar1\n"	\
		"2:	SETW [%0++],D1Ar1\n",	\
		"3:	ADD  %1,%1,#2\n",	\
		"	.long 2b,3b\n")

#define __asm_clear_3(to, ret) \
	__asm_clear(to, ret,			\
		 "2:	SETW [%0++],D1Ar1\n"	\
		 "	SETB [%0],D1Ar1\n"	\
		 "3:	SETB [%0++],D1Ar1\n",	\
		 "4:	ADD  %1,%1,#2\n"	\
		 "5:	ADD  %1,%1,#1\n",	\
		 "	.long 2b,4b\n"		\
		 "	.long 3b,5b\n")

#define __asm_clear_4x_cont(to, ret, CLEAR, FIXUP, TENTRY) \
	__asm_clear(to, ret,				\
		"	SETD [%0],D1Ar1\n"		\
		"2:	SETD [%0++],D1Ar1\n" CLEAR,	\
		"3:	ADD  %1,%1,#4\n" FIXUP,		\
		"	.long 2b,3b\n" TENTRY)

#define __asm_clear_4(to, ret) \
	__asm_clear_4x_cont(to, ret, "", "", "")

#define __asm_clear_8x_cont(to, ret, CLEAR, FIXUP, TENTRY) \
	__asm_clear_4x_cont(to, ret,			\
		"	SETD [%0],D1Ar1\n"		\
		"4:	SETD [%0++],D1Ar1\n" CLEAR,	\
		"5:	ADD  %1,%1,#4\n" FIXUP,		\
		"	.long 4b,5b\n" TENTRY)

#define __asm_clear_8(to, ret) \
	__asm_clear_8x_cont(to, ret, "", "", "")

#define __asm_clear_12x_cont(to, ret, CLEAR, FIXUP, TENTRY) \
	__asm_clear_8x_cont(to, ret,			\
		"	SETD [%0],D1Ar1\n"		\
		"6:	SETD [%0++],D1Ar1\n" CLEAR,	\
		"7:	ADD  %1,%1,#4\n" FIXUP,		\
		"	.long 6b,7b\n" TENTRY)

#define __asm_clear_12(to, ret) \
	__asm_clear_12x_cont(to, ret, "", "", "")

#define __asm_clear_16x_cont(to, ret, CLEAR, FIXUP, TENTRY) \
	__asm_clear_12x_cont(to, ret,			\
		"	SETD [%0],D1Ar1\n"		\
		"8:	SETD [%0++],D1Ar1\n" CLEAR,	\
		"9:	ADD  %1,%1,#4\n" FIXUP,		\
		"	.long 8b,9b\n" TENTRY)

#define __asm_clear_16(to, ret) \
	__asm_clear_16x_cont(to, ret, "", "", "")

unsigned long __do_clear_user(void __user *pto, unsigned long pn)
{
	register char __user *dst asm ("D0Re0") = pto;
	register unsigned long n asm ("D1Re0") = pn;
	register unsigned long retn asm ("D0Ar6") = 0;

	if ((unsigned long) dst & 1) {
		__asm_clear_1(dst, retn);
		n--;
	}

	if ((unsigned long) dst & 2) {
		__asm_clear_2(dst, retn);
		n -= 2;
	}

	/* 64 bit copy loop */
	if (!((__force unsigned long) dst & 7)) {
		while (n >= 8) {
			__asm_clear_8x64(dst, retn);
			n -= 8;
		}
	}

	while (n >= 16) {
		__asm_clear_16(dst, retn);
		n -= 16;
	}

	while (n >= 4) {
		__asm_clear_4(dst, retn);
		n -= 4;
	}

	switch (n) {
	case 0:
		break;
	case 1:
		__asm_clear_1(dst, retn);
		break;
	case 2:
		__asm_clear_2(dst, retn);
		break;
	case 3:
		__asm_clear_3(dst, retn);
		break;
	}

	return retn;
}
EXPORT_SYMBOL(__do_clear_user);

unsigned char __get_user_asm_b(const void __user *addr, long *err)
{
	register unsigned char x asm ("D0Re0") = 0;
	asm volatile (
		"	GETB %0,[%2]\n"
		"1:\n"
		"	GETB %0,[%2]\n"
		"2:\n"
		"	.section .fixup,\"ax\"\n"
		"3:	MOV     D0FrT,%3\n"
		"	SETD    [%1],D0FrT\n"
		"	MOVT    D0FrT,#HI(2b)\n"
		"	JUMP    D0FrT,#LO(2b)\n"
		"	.previous\n"
		"	.section __ex_table,\"a\"\n"
		"	.long 1b,3b\n"
		"	.previous\n"
		: "=r" (x)
		: "r" (err), "r" (addr), "P" (-EFAULT)
		: "D0FrT");
	return x;
}
EXPORT_SYMBOL(__get_user_asm_b);

unsigned short __get_user_asm_w(const void __user *addr, long *err)
{
	register unsigned short x asm ("D0Re0") = 0;
	asm volatile (
		"	GETW %0,[%2]\n"
		"1:\n"
		"	GETW %0,[%2]\n"
		"2:\n"
		"	.section .fixup,\"ax\"\n"
		"3:	MOV     D0FrT,%3\n"
		"	SETD    [%1],D0FrT\n"
		"	MOVT    D0FrT,#HI(2b)\n"
		"	JUMP    D0FrT,#LO(2b)\n"
		"	.previous\n"
		"	.section __ex_table,\"a\"\n"
		"	.long 1b,3b\n"
		"	.previous\n"
		: "=r" (x)
		: "r" (err), "r" (addr), "P" (-EFAULT)
		: "D0FrT");
	return x;
}
EXPORT_SYMBOL(__get_user_asm_w);

unsigned int __get_user_asm_d(const void __user *addr, long *err)
{
	register unsigned int x asm ("D0Re0") = 0;
	asm volatile (
		"	GETD %0,[%2]\n"
		"1:\n"
		"	GETD %0,[%2]\n"
		"2:\n"
		"	.section .fixup,\"ax\"\n"
		"3:	MOV     D0FrT,%3\n"
		"	SETD    [%1],D0FrT\n"
		"	MOVT    D0FrT,#HI(2b)\n"
		"	JUMP    D0FrT,#LO(2b)\n"
		"	.previous\n"
		"	.section __ex_table,\"a\"\n"
		"	.long 1b,3b\n"
		"	.previous\n"
		: "=r" (x)
		: "r" (err), "r" (addr), "P" (-EFAULT)
		: "D0FrT");
	return x;
}
EXPORT_SYMBOL(__get_user_asm_d);

long __put_user_asm_b(unsigned int x, void __user *addr)
{
	register unsigned int err asm ("D0Re0") = 0;
	asm volatile (
		"	MOV  %0,#0\n"
		"	SETB [%2],%1\n"
		"1:\n"
		"	SETB [%2],%1\n"
		"2:\n"
		".section .fixup,\"ax\"\n"
		"3:	MOV     %0,%3\n"
		"	MOVT    D0FrT,#HI(2b)\n"
		"	JUMP    D0FrT,#LO(2b)\n"
		".previous\n"
		".section __ex_table,\"a\"\n"
		"	.long 1b,3b\n"
		".previous"
		: "=r"(err)
		: "d" (x), "a" (addr), "P"(-EFAULT)
		: "D0FrT");
	return err;
}
EXPORT_SYMBOL(__put_user_asm_b);

long __put_user_asm_w(unsigned int x, void __user *addr)
{
	register unsigned int err asm ("D0Re0") = 0;
	asm volatile (
		"	MOV  %0,#0\n"
		"	SETW [%2],%1\n"
		"1:\n"
		"	SETW [%2],%1\n"
		"2:\n"
		".section .fixup,\"ax\"\n"
		"3:	MOV     %0,%3\n"
		"	MOVT    D0FrT,#HI(2b)\n"
		"	JUMP    D0FrT,#LO(2b)\n"
		".previous\n"
		".section __ex_table,\"a\"\n"
		"	.long 1b,3b\n"
		".previous"
		: "=r"(err)
		: "d" (x), "a" (addr), "P"(-EFAULT)
		: "D0FrT");
	return err;
}
EXPORT_SYMBOL(__put_user_asm_w);

long __put_user_asm_d(unsigned int x, void __user *addr)
{
	register unsigned int err asm ("D0Re0") = 0;
	asm volatile (
		"	MOV  %0,#0\n"
		"	SETD [%2],%1\n"
		"1:\n"
		"	SETD [%2],%1\n"
		"2:\n"
		".section .fixup,\"ax\"\n"
		"3:	MOV     %0,%3\n"
		"	MOVT    D0FrT,#HI(2b)\n"
		"	JUMP    D0FrT,#LO(2b)\n"
		".previous\n"
		".section __ex_table,\"a\"\n"
		"	.long 1b,3b\n"
		".previous"
		: "=r"(err)
		: "d" (x), "a" (addr), "P"(-EFAULT)
		: "D0FrT");
	return err;
}
EXPORT_SYMBOL(__put_user_asm_d);

long __put_user_asm_l(unsigned long long x, void __user *addr)
{
	register unsigned int err asm ("D0Re0") = 0;
	asm volatile (
		"	MOV  %0,#0\n"
		"	SETL [%2],%1,%t1\n"
		"1:\n"
		"	SETL [%2],%1,%t1\n"
		"2:\n"
		".section .fixup,\"ax\"\n"
		"3:	MOV     %0,%3\n"
		"	MOVT    D0FrT,#HI(2b)\n"
		"	JUMP    D0FrT,#LO(2b)\n"
		".previous\n"
		".section __ex_table,\"a\"\n"
		"	.long 1b,3b\n"
		".previous"
		: "=r"(err)
		: "d" (x), "a" (addr), "P"(-EFAULT)
		: "D0FrT");
	return err;
}
EXPORT_SYMBOL(__put_user_asm_l);

long strnlen_user(const char __user *src, long count)
{
	long res;

	if (!access_ok(VERIFY_READ, src, 0))
		return 0;

	asm volatile ("	MOV     D0Ar4, %1\n"
		      "	MOV     D0Ar6, %2\n"
		      "0:\n"
		      "	SUBS    D0FrT, D0Ar6, #0\n"
		      "	SUB     D0Ar6, D0Ar6, #1\n"
		      "	BLE     2f\n"
		      "	GETB    D0FrT, [D0Ar4+#1++]\n"
		      "1:\n"
		      "	TST     D0FrT, #255\n"
		      "	BNE     0b\n"
		      "2:\n"
		      "	SUB     %0, %2, D0Ar6\n"
		      "3:\n"
		      "	.section .fixup,\"ax\"\n"
		      "4:\n"
		      "	MOV     %0, #0\n"
		      "	MOVT    D0FrT,#HI(3b)\n"
		      "	JUMP    D0FrT,#LO(3b)\n"
		      "	.previous\n"
		      "	.section __ex_table,\"a\"\n"
		      "	.long 1b,4b\n"
		      "	.previous\n"
		      : "=r" (res)
		      : "r" (src), "r" (count)
		      : "D0FrT", "D0Ar4", "D0Ar6", "cc");

	return res;
}
EXPORT_SYMBOL(strnlen_user);

long __strncpy_from_user(char *dst, const char __user *src, long count)
{
	long res;

	if (count == 0)
		return 0;

	/*
	 * Currently, in 2.4.0-test9, most ports use a simple byte-copy loop.
	 *  So do we.
	 *
	 *  This code is deduced from:
	 *
	 *      char tmp2;
	 *      long tmp1, tmp3;
	 *      tmp1 = count;
	 *      while ((*dst++ = (tmp2 = *src++)) != 0
	 *             && --tmp1)
	 *        ;
	 *
	 *      res = count - tmp1;
	 *
	 *  with tweaks.
	 */

	asm volatile ("	MOV  %0,%3\n"
		      "1:\n"
		      "	GETB D0FrT,[%2++]\n"
		      "2:\n"
		      "	CMP  D0FrT,#0\n"
		      "	SETB [%1++],D0FrT\n"
		      "	BEQ  3f\n"
		      "	SUBS %0,%0,#1\n"
		      "	BNZ  1b\n"
		      "3:\n"
		      "	SUB  %0,%3,%0\n"
		      "4:\n"
		      "	.section .fixup,\"ax\"\n"
		      "5:\n"
		      "	MOV  %0,%7\n"
		      "	MOVT    D0FrT,#HI(4b)\n"
		      "	JUMP    D0FrT,#LO(4b)\n"
		      "	.previous\n"
		      "	.section __ex_table,\"a\"\n"
		      "	.long 2b,5b\n"
		      "	.previous"
		      : "=r" (res), "=r" (dst), "=r" (src), "=r" (count)
		      : "3" (count), "1" (dst), "2" (src), "P" (-EFAULT)
		      : "D0FrT", "memory", "cc");

	return res;
}
EXPORT_SYMBOL(__strncpy_from_user);