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
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
|
// TITLE("Compare, Move, Zero, and Fill Memory Support")
//++
//
// Copyright (c) 1990 Microsoft Corporation
//
// Module Name:
//
// xxmvmem.s
//
// Abstract:
//
// This module implements functions to compare, move, zero, and fill
// blocks of memory. If the memory is aligned, then these functions
// are very efficient.
//
// N.B. These routines MUST preserve all floating state since they are
// frequently called from interrupt service routines that normally
// do not save or restore floating state.
//
// Author:
//
// David N. Cutler (davec) 11-Apr-1990
//
// Environment:
//
// User or Kernel mode.
//
// Revision History:
//
//--
#include "ksmips.h"
SBTTL("Compare Memory")
//++
//
// ULONG
// RtlCompareMemory (
// IN PVOID Source1,
// IN PVOID Source2,
// IN ULONG Length
// )
//
// Routine Description:
//
// This function compares two blocks of memory and returns the number
// of bytes that compared equal.
//
// Arguments:
//
// Source1 (a0) - Supplies a pointer to the first block of memory to
// compare.
//
// Source2 (a1) - Supplies a pointer to the second block of memory to
// compare.
//
// Length (a2) - Supplies the length, in bytes, of the memory to be
// compared.
//
// Return Value:
//
// The number of bytes that compared equal is returned as the function
// value. If all bytes compared equal, then the length of the orginal
// block of memory is returned.
//
//--
LEAF_ENTRY(RtlCompareMemory)
addu a3,a0,a2 // compute ending address of source1
move v0,a2 // save length of comparison
and t0,a2,32 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
addu t4,a0,t1 // compute ending block address
beq zero,t1,100f // if eq, no 32-byte block to compare
or t0,a0,a1 // merge and isolate alignment bits
and t0,t0,0x3 //
bne zero,t0,CompareUnaligned // if ne, unalignment comparison
//
// Compare memory aligned.
//
CompareAligned: //
.set noreorder
.set noat
10: lw t0,0(a0) // compare 32-byte block
lw t1,0(a1) //
lw t2,4(a0) //
bne t0,t1,90f // if ne, first word not equal
lw t3,4(a1) //
lw t0,8(a0) //
bne t2,t3,20f // if ne, second word not equal
lw t1,8(a1) //
lw t2,12(a0) //
bne t0,t1,30f // if ne, third word not equal
lw t3,12(a1) //
lw t0,16(a0) //
bne t2,t3,40f // if ne, fourth word not equal
lw t1,16(a1) //
lw t2,20(a0) //
bne t0,t1,50f // if ne, fifth word not equal
lw t3,20(a1) //
lw t0,24(a0) //
bne t2,t3,60f // if ne, sixth word not equal
lw t1,24(a1) //
lw t2,28(a0) //
bne t0,t1,70f // if ne, seventh word not equal
lw t3,28(a1) //
addu a0,a0,32 // advance source1 to next block
bne t2,t3,80f // if ne, eighth word not equal
nop //
bne a0,t4,10b // if ne, more 32-byte blocks to compare
addu a1,a1,32 // update source2 address
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
b 100f //
//
// Compare memory unaligned.
//
CompareUnaligned: //
and t0,a0,0x3 // isolate source1 alignment
bne zero,t0,CompareUnalignedS1 // if ne, source1 unaligned
//
// Source1 is aligned and Source2 is unaligned.
//
CompareUnalignedS2: //
.set noreorder
.set noat
10: lw t0,0(a0) // compare 32-byte block
lwr t1,0(a1) //
lwl t1,3(a1) //
lw t2,4(a0) //
bne t0,t1,90f // if ne, first word not equal
lwr t3,4(a1) //
lwl t3,7(a1) //
lw t0,8(a0) //
bne t2,t3,20f // if ne, second word not equal
lwr t1,8(a1) //
lwl t1,11(a1) //
lw t2,12(a0) //
bne t0,t1,30f // if ne, third word not equal
lwr t3,12(a1) //
lwl t3,15(a1) //
lw t0,16(a0) //
bne t2,t3,40f // if ne, fourth word not equal
lwr t1,16(a1) //
lwl t1,19(a1) //
lw t2,20(a0) //
bne t0,t1,50f // if ne, fifth word not equal
lwr t3,20(a1) //
lwl t3,23(a1) //
lw t0,24(a0) //
bne t2,t3,60f // if ne, sixth word not equal
lwr t1,24(a1) //
lwl t1,27(a1) //
lw t2,28(a0) //
bne t0,t1,70f // if ne, seventh word not equal
lwr t3,28(a1) //
lwl t3,31(a1) //
addu a0,a0,32 // advance source1 to next block
bne t2,t3,80f // if ne, eighth word not equal
nop //
bne a0,t4,10b // if ne, more 32-byte blocks to compare
addu a1,a1,32 // update source2 address
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
b 100f //
//
// Source1 is unaligned, check Source2 alignment.
//
CompareUnalignedS1: //
and t0,a1,0x3 // isolate Source2 alignment
bne zero,t0,CompareUnalignedS1AndS2 // if ne, Source2 unaligned
//
// Source1 is unaligned and Source2 is aligned.
//
.set noreorder
.set noat
10: lwr t0,0(a0) // compare 32-byte block
lwl t0,3(a0) //
lw t1,0(a1) //
lwr t2,4(a0) //
lwl t2,7(a0) //
bne t0,t1,90f // if ne, first word not equal
lw t3,4(a1) //
lwr t0,8(a0) //
lwl t0,11(a0) //
bne t2,t3,20f // if ne, second word not equal
lw t1,8(a1) //
lwr t2,12(a0) //
lwl t2,15(a0) //
bne t0,t1,30f // if ne, third word not equal
lw t3,12(a1) //
lwr t0,16(a0) //
lwl t0,19(a0) //
bne t2,t3,40f // if ne, fourth word not equal
lw t1,16(a1) //
lwr t2,20(a0) //
lwl t2,23(a0) //
bne t0,t1,50f // if ne, fifth word not equal
lw t3,20(a1) //
lwr t0,24(a0) //
lwl t0,27(a0) //
bne t2,t3,60f // if ne, sixth word not equal
lw t1,24(a1) //
lwr t2,28(a0) //
lwl t2,31(a0) //
bne t0,t1,70f // if ne, seventh word not equal
lw t3,28(a1) //
addu a0,a0,32 // advance source1 to next block
bne t2,t3,80f // if ne, eighth word not equal
nop //
bne a0,t4,10b // if ne, more 32-byte blocks to compare
addu a1,a1,32 // update source2 address
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
b 100f //
//
// Source1 and Source2 are unaligned.
//
CompareUnalignedS1AndS2: //
.set noreorder
.set noat
10: lwr t0,0(a0) // compare 32-byte block
lwl t0,3(a0) //
lwr t1,0(a1) //
lwl t1,3(a1) //
lwr t2,4(a0) //
lwl t2,7(a0) //
bne t0,t1,90f // if ne, first word not equal
lwr t3,4(a1) //
lwl t3,7(a1) //
lwr t0,8(a0) //
lwl t0,11(a0) //
bne t2,t3,20f // if ne, second word not equal
lwr t1,8(a1) //
lwl t1,11(a1) //
lwr t2,12(a0) //
lwl t2,15(a0) //
bne t0,t1,30f // if ne, third word not equal
lwr t3,12(a1) //
lwl t3,15(a1) //
lwr t0,16(a0) //
lwl t0,19(a0) //
bne t2,t3,40f // if ne, fourth word not equal
lwr t1,16(a1) //
lwl t1,19(a1) //
lwr t2,20(a0) //
lwl t2,23(a0) //
bne t0,t1,50f // if ne, fifth word not equal
lwr t3,20(a1) //
lwl t3,23(a1) //
lwr t0,24(a0) //
lwl t0,27(a0) //
bne t2,t3,60f // if ne, sixth word not equal
lwr t1,24(a1) //
lwl t1,27(a1) //
lwr t2,28(a0) //
lwl t2,31(a0) //
bne t0,t1,70f // if ne, seventh word not equal
lwr t3,28(a1) //
lwl t3,31(a1) //
addu a0,a0,32 // advance source1 to next block
bne t2,t3,80f // if ne, eighth word not equal
nop //
bne a0,t4,10b // if ne, more 32-byte blocks to compare
addu a1,a1,32 // update source2 address
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
b 100f //
//
// Adjust source1 and source2 pointers dependent on position of miscompare in
// block.
//
20: addu a0,a0,4 // mismatch on second word
addu a1,a1,4 //
b 90f //
30: addu a0,a0,8 // mismatch on third word
addu a1,a1,8 //
b 90f //
40: addu a0,a0,12 // mistmatch on fourth word
addu a1,a1,12 //
b 90f //
50: addu a0,a0,16 // mismatch on fifth word
addu a1,a1,16 //
b 90f //
60: addu a0,a0,20 // mismatch on sixth word
addu a1,a1,20 //
b 90f //
70: addu a0,a0,24 // mismatch on seventh word
addu a1,a1,24 //
b 90f //
80: subu a0,a0,4 // mismatch on eighth word
addu a1,a1,28 //
90: subu a2,a3,a0 // compute remaining bytes
//
// Compare 1-byte blocks.
//
100: addu t2,a0,a2 // compute ending block address
beq zero,a2,120f // if eq, no bytes to zero
110: lb t0,0(a0) // compare 1-byte block
lb t1,0(a1) //
addu a1,a1,1 // advance pointers to next block
bne t0,t1,120f // if ne, byte not equal
addu a0,a0,1 //
bne a0,t2,110b // if ne, more 1-byte block to zero
120: subu t0,a3,a0 // compute number of bytes not compared
subu v0,v0,t0 // compute number of byte that matched
j ra // return
.end RtlCompareMemory
SBTTL("Equal Memory")
//++
//
// ULONG
// RtlEqualMemory (
// IN PVOID Source1,
// IN PVOID Source2,
// IN ULONG Length
// )
//
// Routine Description:
//
// This function compares two blocks of memory for equality.
//
// Arguments:
//
// Source1 (a0) - Supplies a pointer to the first block of memory to
// compare.
//
// Source2 (a1) - Supplies a pointer to the second block of memory to
// compare.
//
// Length (a2) - Supplies the length, in bytes, of the memory to be
// compared.
//
// Return Value:
//
// If all bytes in the source strings match, then a value of TRUE is
// returned. Otherwise, FALSE is returned.
//
//--
LEAF_ENTRY(RtlEqualMemory)
li v0,FALSE // set return value FALSE
addu a3,a0,a2 // compute ending address of source1
and t0,a2,16 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
addu t4,a0,t1 // compute ending block address
beq zero,t1,20f // if eq, no 16-byte block to compare
or t0,a0,a1 // merge and isolate alignment bits
and t0,t0,0x3 //
bne zero,t0,EqualUnaligned // if ne, unalignment comparison
//
// Compare memory aligned.
//
EqualAligned: //
.set noreorder
.set noat
10: lw t0,0(a0) // compare 16-byte block
lw t1,0(a1) //
lw t2,4(a0) //
bne t0,t1,50f // if ne, first word not equal
lw t3,4(a1) //
lw t0,8(a0) //
bne t2,t3,50f // if ne, second word not equal
lw t1,8(a1) //
lw t2,12(a0) //
bne t0,t1,50f // if ne, third word not equal
lw t3,12(a1) //
bne t2,t3,50f // if ne, eighth word not equal
addu a0,a0,16 // advance source1 to next block
bne a0,t4,10b // if ne, more blocks to compare
addu a1,a1,16 // advance source2 to next block
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
b 20f //
//
// Compare memory unaligned.
//
EqualUnaligned: //
and t0,a0,0x3 // isolate source1 alignment
bne zero,t0,EqualUnalignedS1 // if ne, source1 unaligned
//
// Source1 is aligned and Source2 is unaligned.
//
EqualUnalignedS2: //
.set noreorder
.set noat
10: lw t0,0(a0) // compare 16-byte block
lwr t1,0(a1) //
lwl t1,3(a1) //
lw t2,4(a0) //
bne t0,t1,50f // if ne, first word not equal
lwr t3,4(a1) //
lwl t3,7(a1) //
lw t0,8(a0) //
bne t2,t3,50f // if ne, second word not equal
lwr t1,8(a1) //
lwl t1,11(a1) //
lw t2,12(a0) //
bne t0,t1,50f // if ne, third word not equal
lwr t3,12(a1) //
lwl t3,15(a1) //
bne t2,t3,50f // if ne, fourth word not equal
addu a0,a0,16 // advance source1 to next block
bne a0,t4,10b // if ne, more blocks to compare
addu a1,a1,16 // advance source2 to next block
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
b 20f //
//
// Source1 is unaligned, check Source2 alignment.
//
EqualUnalignedS1: //
and t0,a1,0x3 // isolate Source2 alignment
bne zero,t0,EqualUnalignedS1AndS2 // if ne, Source2 unaligned
//
// Source1 is unaligned and Source2 is aligned.
//
.set noreorder
.set noat
10: lwr t0,0(a0) // compare 16-byte block
lwl t0,3(a0) //
lw t1,0(a1) //
lwr t2,4(a0) //
lwl t2,7(a0) //
bne t0,t1,50f // if ne, first word not equal
lw t3,4(a1) //
lwr t0,8(a0) //
lwl t0,11(a0) //
bne t2,t3,50f // if ne, second word not equal
lw t1,8(a1) //
lwr t2,12(a0) //
lwl t2,15(a0) //
bne t0,t1,50f // if ne, third word not equal
lw t3,12(a1) //
bne t2,t3,50f // if ne, fourth word not equal
addu a0,a0,16 // advance source1 to next block
bne a0,t4,10b // if ne, more blocks to compare
addu a1,a1,16 // advance source2 to next block
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
b 20f //
//
// Source1 and Source2 are unaligned.
//
EqualUnalignedS1AndS2: //
.set noreorder
.set noat
10: lwr t0,0(a0) // compare 16-byte block
lwl t0,3(a0) //
lwr t1,0(a1) //
lwl t1,3(a1) //
lwr t2,4(a0) //
lwl t2,7(a0) //
bne t0,t1,50f // if ne, first word not equal
lwr t3,4(a1) //
lwl t3,7(a1) //
lwr t0,8(a0) //
lwl t0,11(a0) //
bne t2,t3,50f // if ne, second word not equal
lwr t1,8(a1) //
lwl t1,11(a1) //
lwr t2,12(a0) //
lwl t2,15(a0) //
bne t0,t1,50f // if ne, third word not equal
lwr t3,12(a1) //
lwl t3,15(a1) //
bne t2,t3,50f // if ne, fourth word not equal
addu a0,a0,16 // advance source1 to next block
bne a0,t4,10b // if ne, more blocks to compare
addu a1,a1,16 // advance source2 to next block
.set at
.set reorder
subu a2,a3,a0 // compute remaining bytes
//
// Compare 1-byte blocks.
//
20: addu t2,a0,a2 // compute ending block address
beq zero,a2,40f // if eq, no bytes to zero
30: lb t0,0(a0) // compare 1-byte block
lb t1,0(a1) //
addu a1,a1,1 // advance pointers to next block
bne t0,t1,50f // if ne, byte not equal
addu a0,a0,1 //
bne a0,t2,30b // if ne, more 1-byte block to zero
40: li v0,TRUE // set return value TRUE
50: j ra // return
.end RtlEqualMemory
SBTTL("Move Memory")
//++
//
// PVOID
// RtlMoveMemory (
// IN PVOID Destination,
// IN PVOID Source,
// IN ULONG Length
// )
//
// Routine Description:
//
// This function moves memory either forward or backward, aligned or
// unaligned, in 32-byte blocks, followed by 4-byte blocks, followed
// by any remaining bytes.
//
// Arguments:
//
// Destination (a0) - Supplies a pointer to the destination address of
// the move operation.
//
// Source (a1) - Supplies a pointer to the source address of the move
// operation.
//
// Length (a2) - Supplies the length, in bytes, of the memory to be moved.
//
// Return Value:
//
// The Destination address is returned as the function value.
//
// N.B. The C runtime entry points memmove and memcpy are equivalent to
// RtlMoveMemory htus alternate entry points are provided for these
// routines.
//--
LEAF_ENTRY(RtlMoveMemory)
ALTERNATE_ENTRY(memcpy)
ALTERNATE_ENTRY(memmove)
move v0,a0 // set return value
//
// If the source address is less than the destination address and source
// address plus the length of the move is greater than the destination
// address, then the source and destination overlap such that the move
// must be performed backwards.
//
10: bgeu a1,a0,MoveForward // if geu, no overlap possible
addu t0,a1,a2 // compute source ending address
bgtu t0,a0,MoveBackward // if gtu, source and destination overlap
//
// Move memory forward aligned and unaligned.
//
MoveForward: //
sltu t0,a2,8 // check if less than eight bytes
bne zero,t0,50f // if ne, less than eight bytes to move
xor t0,a0,a1 // compare alignment bits
and t0,t0,0x7 // isolate alignment comparison
bne zero,t0,MoveForwardUnaligned // if ne, incompatible alignment
//
// Move memory forward aligned.
//
MoveForwardAligned: //
subu t0,zero,a0 // compute bytes until aligned
and t0,t0,0x7 // isolate residual byte count
subu a2,a2,t0 // reduce number of bytes to move
beq zero,t0,10f // if eq, already aligned
ldr t1,0(a1) // move unaligned bytes
sdr t1,0(a0) //
addu a0,a0,t0 // align destination address
addu a1,a1,t0 // align source address
//
// Check for 32-byte blocks to move.
//
10: and t0,a2,32 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
addu t8,a0,t1 // compute ending block address
beq zero,t1,30f // if eq, no 32-byte block to zero
move a2,t0 // set residual number of bytes
//
// Check for odd number of 32-byte blocks to move.
//
and t0,t1,1 << 5 // test if even number of 32-byte blocks
beq zero,t0,20f // if eq, even number of 32-byte blocks
//
// Move one 32-byte block quadword aligned.
//
.set noreorder
ld t0,0(a1) // move 32-byte block
ld t1,8(a1) //
ld t2,16(a1) //
ld t3,24(a1) //
sd t0,0(a0) //
sd t1,8(a0) //
sd t2,16(a0) //
sd t3,24(a0) //
addu a0,a0,32 // advance pointers to next block
beq a0,t8,30f // if eq, end of block
addu a1,a1,32 //
.set reorder
//
// Move 64-byte blocks quadword aligned.
//
.set noreorder
20: ld t0,0(a1) // move 64-byte block
ld t1,8(a1) //
ld t2,16(a1) //
ld t3,24(a1) //
ld t4,32(a1) //
ld t5,40(a1) //
ld t6,48(a1) //
ld t7,56(a1) //
sd t0,0(a0) //
sd t1,8(a0) //
sd t2,16(a0) //
sd t3,24(a0) //
sd t4,32(a0) //
sd t5,40(a0) //
sd t6,48(a0) //
sd t7,56(a0) //
addu a0,a0,64 // advance pointers to next block
bne a0,t8,20b // if ne, more 64-byte blocks to zero
addu a1,a1,64 //
.set reorder
//
// Check for 4-byte blocks to move.
//
30: and t0,a2,4 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
addu t2,a0,t1 // compute ending block address
beq zero,t1,50f // if eq, no 4-byte block to zero
move a2,t0 // set residual number of bytes
//
// Move 4-byte block.
//
.set noreorder
40: lw t0,0(a1) // move 4-byte block
addu a0,a0,4 // advance pointers to next block
sw t0,-4(a0) //
bne a0,t2,40b // if ne, more 4-byte blocks to zero
addu a1,a1,4 //
.set reorder
//
// Move 1-byte blocks.
//
50: addu t2,a0,a2 // compute ending block address
beq zero,a2,70f // if eq, no bytes to zero
.set noreorder
60: lb t0,0(a1) // move 1-byte block
addu a0,a0,1 // advance pointers to next block
sb t0,-1(a0) //
bne a0,t2,60b // if ne, more 1-byte block to zero
addu a1,a1,1 //
.set reorder
70: j ra // return
//
// Move memory forward unaligned.
//
MoveForwardUnaligned: //
subu t0,zero,a0 // compute bytes until aligned
and t0,t0,0x7 // isolate residual byte count
subu a2,a2,t0 // reduce number of bytes to move
beq zero,t0,10f // if eq, already aligned
ldr t1,0(a1) // move unaligned bytes
ldl t1,7(a1) //
sdr t1,0(a0) //
addu a0,a0,t0 // align destination address
addu a1,a1,t0 // update source address
//
// Check for 32-byte blocks to move.
//
10: and t0,a2,32 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
addu t8,a0,t1 // compute ending block address
beq zero,t1,30f // if eq, no 32-byte block to zero
move a2,t0 // set residual number of bytes
//
// Check for odd number of 32-byte blocks to move.
//
and t0,t1,1 << 5 // test if even number of 32-byte blocks
beq zero,t0,20f // if eq, even number of 32-byte blocks
//
// Move one 32-byte block quadword aligned.
//
.set noreorder
ldr t0,0(a1) // move 32-byte block
ldl t0,7(a1) //
ldr t1,8(a1) //
ldl t1,15(a1) //
ldr t2,16(a1) //
ldl t2,23(a1) //
ldr t3,24(a1) //
ldl t3,31(a1) //
sd t0,0(a0) //
sd t1,8(a0) //
sd t2,16(a0) //
sd t3,24(a0) //
addu a0,a0,32 // advance pointers to next block
beq a0,t8,30f // if eq, end of block
addu a1,a1,32 //
.set reorder
//
// Move 64-byte block.
//
.set noreorder
20: ldr t0,0(a1) // move 64-byte block
ldl t0,7(a1) //
ldr t1,8(a1) //
ldl t1,15(a1) //
ldr t2,16(a1) //
ldl t2,23(a1) //
ldr t3,24(a1) //
ldl t3,31(a1) //
ldr t4,32(a1) //
ldl t4,39(a1) //
ldr t5,40(a1) //
ldl t5,47(a1) //
ldr t6,48(a1) //
ldl t6,55(a1) //
ldr t7,56(a1) //
ldl t7,63(a1) //
sd t0,0(a0) //
sd t1,8(a0) //
sd t2,16(a0) //
sd t3,24(a0) //
sd t4,32(a0) //
sd t5,40(a0) //
sd t6,48(a0) //
sd t7,56(a0) //
addu a0,a0,64 // advance pointers to next block
bne a0,t8,20b // if ne, more 32-byte blocks to zero
addu a1,a1,64 //
.set reorder
//
// Check for 4-byte blocks to move.
//
30: and t0,a2,4 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
addu t2,a0,t1 // compute ending block address
beq zero,t1,50f // if eq, no 4-byte block to zero
move a2,t0 // set residual number of bytes
//
// Move 4-byte block.
//
.set noreorder
40: lwr t0,0(a1) // move 4-byte block
lwl t0,3(a1) //
addu a0,a0,4 // advance pointers to next block
sw t0,-4(a0) //
bne a0,t2,40b // if ne, more 4-byte blocks to zero
addu a1,a1,4 //
.set reorder
//
// Move 1-byte blocks.
//
50: addu t2,a0,a2 // compute ending block address
beq zero,a2,70f // if eq, no bytes to zero
.set noreorder
60: lb t0,0(a1) // move 1-byte block
addu a0,a0,1 // advance pointers to next block
sb t0,-1(a0) //
bne a0,t2,60b // if ne, more 1-byte block to zero
addu a1,a1,1 //
.set reorder
70: j ra // return
//
// Move memory backward.
//
MoveBackward: //
addu a0,a0,a2 // compute ending destination address
addu a1,a1,a2 // compute ending source address
sltu t0,a2,8 // check if less than eight bytes
bne zero,t0,50f // if ne, less than eight bytes to move
xor t0,a0,a1 // compare alignment bits
and t0,t0,0x7 // isolate alignment comparison
bne zero,t0,MoveBackwardUnaligned // if ne, incompatible alignment
//
// Move memory backward aligned.
//
MoveBackwardAligned: //
and t0,a0,0x7 // isolate residual byte count
subu a2,a2,t0 // reduce number of bytes to move
beq zero,t0,10f // if eq, already aligned
ldl t1,-1(a1) // move unaligned bytes
sdl t1,-1(a0) //
subu a0,a0,t0 // align destination address
subu a1,a1,t0 // align source address
//
// Check for 32-byte blocks to move.
//
10: and t0,a2,32 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
subu t8,a0,t1 // compute ending block address
beq zero,t1,30f // if eq, no 32-byte block to zero
move a2,t0 // set residual number of bytes
//
// Check for odd number of 32-byte blocks to move.
//
and t0,t1,1 << 5 // test if even number of 32-byte blocks
beq zero,t0,20f // if eq, even number of 32-byte blocks
//
// Move one 32-byte block quadword aligned.
//
.set noreorder
ld t0,-8(a1) // move 32-byte block
ld t1,-16(a1) //
ld t2,-24(a1) //
ld t3,-32(a1) //
sd t0,-8(a0) //
sd t1,-16(a0) //
sd t2,-24(a0) //
sd t3,-32(a0) //
subu a0,a0,32 // advance pointers to next block
beq a0,t8,30f // if eq, end of block
subu a1,a1,32 //
.set reorder
//
// Move 64-byte blocks quadword aligned.
//
.set noreorder
20: ld t0,-8(a1) // move 64-byte block
ld t1,-16(a1) //
ld t2,-24(a1) //
ld t3,-32(a1) //
ld t4,-40(a1) //
ld t5,-48(a1) //
ld t6,-56(a1) //
ld t7,-64(a1) //
sd t0,-8(a0) //
sd t1,-16(a0) //
sd t2,-24(a0) //
sd t3,-32(a0) //
sd t4,-40(a0) //
sd t5,-48(a0) //
sd t6,-56(a0) //
sd t7,-64(a0) //
subu a0,a0,64 // advance pointers to next block
bne a0,t8,20b // if ne, more 64-byte blocks to zero
subu a1,a1,64 //
.set reorder
//
// Check for 4-byte blocks to move.
//
30: and t0,a2,4 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
subu t2,a0,t1 // compute ending block address
beq zero,t1,50f // if eq, no 4-byte block to zero
move a2,t0 // set residual number of bytes
//
// Move 4-byte block.
//
.set noreorder
40: lw t0,-4(a1) // move 4-byte block
subu a0,a0,4 // advance pointers to next block
sw t0,0(a0) //
bne a0,t2,40b // if ne, more 4-byte blocks to zero
subu a1,a1,4 //
.set reorder
//
// Move 1-byte blocks.
//
50: subu t2,a0,a2 // compute ending block address
beq zero,a2,70f // if eq, no bytes to zero
.set noreorder
60: lb t0,-1(a1) // move 1-byte block
subu a0,a0,1 // advance pointers to next block
sb t0,0(a0) //
bne a0,t2,60b // if ne, more 1-byte block to zero
subu a1,a1,1 //
.set reorder
70: j ra // return
//
// Move memory backward unaligned.
//
MoveBackwardUnaligned: //
and t0,a0,0x7 // isolate residual byte count
subu a2,a2,t0 // reduce number of bytes to move
beq zero,t0,10f // if eq, already aligned
ldl t1,-1(a1) // move unaligned bytes
ldr t1,-8(a1) //
sdl t1,-1(a0) //
subu a0,a0,t0 // align destination address
subu a1,a1,t0 // update source address
//
// Check for 32-byte blocks to move.
//
10: and t0,a2,32 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
subu t8,a0,t1 // compute ending block address
beq zero,t1,30f // if eq, no 32-byte block to zero
move a2,t0 // set residual number of bytes
//
// Check for odd number of 32-byte blocks to move.
//
and t0,t1,1 << 5 // test if even number of 32-byte blocks
beq zero,t0,20f // if eq, even number of 32-byte blocks
//
// Move one 32-byte block.
//
.set noreorder
ldr t0,-8(a1) // move 32-byte block
ldl t0,-1(a1) //
ldr t1,-16(a1) //
ldl t1,-9(a1) //
ldr t2,-24(a1) //
ldl t2,-17(a1) //
ldr t3,-32(a1) //
ldl t3,-25(a1) //
sd t0,-8(a0) //
sd t1,-16(a0) //
sd t2,-24(a0) //
sd t3,-32(a0) //
subu a0,a0,32 // advance pointers to next block
beq a0,t8,30f // if eq, end of block
subu a1,a1,32 //
.set reorder
//
// Move 32-byte block.
//
.set noreorder
20: ldr t0,-8(a1) // move 32-byte block
ldl t0,-1(a1) //
ldr t1,-16(a1) //
ldl t1,-9(a1) //
ldr t2,-24(a1) //
ldl t2,-17(a1) //
ldr t3,-32(a1) //
ldl t3,-25(a1) //
ldr t4,-40(a1) //
ldl t4,-33(a1) //
ldr t5,-48(a1) //
ldl t5,-41(a1) //
ldr t6,-56(a1) //
ldl t6,-49(a1) //
ldr t7,-64(a1) //
ldl t7,-57(a1) //
sd t0,-8(a0) //
sd t1,-16(a0) //
sd t2,-24(a0) //
sd t3,-32(a0) //
sd t4,-40(a0) //
sd t5,-48(a0) //
sd t6,-56(a0) //
sd t7,-64(a0) //
subu a0,a0,64 // advance pointers to next block
bne a0,t8,20b // if ne, more 64-byte blocks to zero
subu a1,a1,64 //
.set reorder
//
// Check for 4-byte blocks to move.
//
30: and t0,a2,4 - 1 // isolate residual bytes
subu t1,a2,t0 // subtract out residual bytes
subu t2,a0,t1 // compute ending block address
beq zero,t1,50f // if eq, no 4-byte block to zero
move a2,t0 // set residual number of bytes
//
// Move 4-byte block.
//
.set noreorder
40: lwr t0,-4(a1) // move 4-byte block
lwl t0,-1(a1) //
subu a0,a0,4 // advance pointers to next block
sw t0,0(a0) //
bne a0,t2,40b // if ne, more 4-byte blocks to zero
subu a1,a1,4 //
.set reorder
//
// Move 1-byte blocks.
//
50: subu t2,a0,a2 // compute ending block address
beq zero,a2,70f // if eq, no bytes to zero
.set noreorder
60: lb t0,-1(a1) // move 1-byte block
subu a0,a0,1 // advance pointers to next block
sb t0,0(a0) //
bne a0,t2,60b // if ne, more 1-byte block to zero
subu a1,a1,1 //
.set reorder
70: j ra // return
.end RtlMoveMemory
SBTTL("Zero Memory")
//++
//
// PVOID
// RtlZeroMemory (
// IN PVOID Destination,
// IN ULONG Length
// )
//
// Routine Description:
//
// This function zeros memory by first aligning the destination address to
// a longword boundary, and then zeroing 32-byte blocks, followed by 4-byte
// blocks, followed by any remaining bytes.
//
// Arguments:
//
// Destination (a0) - Supplies a pointer to the memory to zero.
//
// Length (a1) - Supplies the length, in bytes, of the memory to be zeroed.
//
// Return Value:
//
// The destination address is returned as the function value.
//
//--
LEAF_ENTRY(RtlZeroMemory)
move a2,zero // set fill pattern
b RtlpFillMemory //
SBTTL("Fill Memory")
//++
//
// PVOID
// RtlFillMemory (
// IN PVOID Destination,
// IN ULONG Length,
// IN UCHAR Fill
// )
//
// Routine Description:
//
// This function fills memory by first aligning the destination address to
// a longword boundary, and then filling 32-byte blocks, followed by 4-byte
// blocks, followed by any remaining bytes.
//
// Arguments:
//
// Destination (a0) - Supplies a pointer to the memory to fill.
//
// Length (a1) - Supplies the length, in bytes, of the memory to be filled.
//
// Fill (a2) - Supplies the fill byte.
//
// N.B. The alternate entry memset expects the length and fill arguments
// to be reversed.
//
// Return Value:
//
// The destination address is returned as the function value.
//
//--
ALTERNATE_ENTRY(memset)
move a3,a1 // swap length and fill arguments
move a1,a2 //
move a2,a3 //
ALTERNATE_ENTRY(RtlFillMemory)
and a2,a2,0xff // clear excess bits
sll t0,a2,8 // duplicate fill byte
or a2,a2,t0 // generate fill word
sll t0,a2,16 // duplicate fill word
or a2,a2,t0 // generate fill longword
//
// Fill memory with the pattern specified in register a2.
//
RtlpFillMemory: //
move v0,a0 // set return value
dsll a2,a2,32 // duplicate pattern to 64-bits
dsrl t0,a2,32 //
or a2,a2,t0 //
subu t0,zero,a0 // compute bytes until aligned
and t0,t0,0x7 // isolate residual byte count
subu t1,a1,t0 // reduce number of bytes to fill
blez t1,60f // if lez, less than 8 bytes to fill
move a1,t1 // set number of bytes to fill
beq zero,t0,10f // if eq, already aligned
sdr a2,0(a0) // fill unaligned bytes
addu a0,a0,t0 // align destination address
//
// Check for 32-byte blocks to fill.
//
10: and t0,a1,32 - 1 // isolate residual bytes
subu t1,a1,t0 // subtract out residual bytes
addu t2,a0,t1 // compute ending block address
beq zero,t1,40f // if eq, no 32-byte blocks to fill
move a1,t0 // set residual number of bytes
//
// Fill 32-byte blocks.
//
and t0,a0,1 << 2 // check if destintion quadword aligned
beq zero,t0,20f // if eq, yes
sw a2,0(a0) // store destination longword
addu a0,a0,4 // align destination address
addu a1,a1,t1 // recompute bytes to fill
subu a1,a1,4 // reduce count by 4
b 10b //
//
// The destination is quadword aligned.
//
20: and t0,t1,1 << 5 // test if even number of 32-byte blocks
beq zero,t0,30f // if eq, even number of 32-byte blocks
//
// Fill one 32-byte block.
//
.set noreorder
.set noat
sd a2,0(a0) // fill 32-byte block
sd a2,8(a0) //
sd a2,16(a0) //
addu a0,a0,32 // advance pointer to next block
beq a0,t2,40f // if ne, no 64-byte blocks to fill
sd a2,-8(a0) //
.set at
.set reorder
//
// Fill 64-byte block.
//
.set noreorder
.set noat
30: sd a2,0(a0) // fill 32-byte block
sd a2,8(a0) //
sd a2,16(a0) //
sd a2,24(a0) //
sd a2,32(a0) //
sd a2,40(a0) //
sd a2,48(a0) //
addu a0,a0,64 // advance pointer to next block
bne a0,t2,30b // if ne, more 32-byte blocks to fill
sd a2,-8(a0) //
.set at
.set reorder
//
// Check for 4-byte blocks to fill.
//
40: and t0,a1,4 - 1 // isolate residual bytes
subu t1,a1,t0 // subtract out residual bytes
addu t2,a0,t1 // compute ending block address
beq zero,t1,60f // if eq, no 4-byte block to fill
move a1,t0 // set residual number of bytes
//
// Fill 4-byte blocks.
//
.set noreorder
50: addu a0,a0,4 // advance pointer to next block
bne a0,t2,50b // if ne, more 4-byte blocks to fill
sw a2,-4(a0) // fill 4-byte block
.set reorder
//
// Check for 1-byte blocks to fill.
//
60: addu t2,a0,a1 // compute ending block address
beq zero,a1,80f // if eq, no bytes to fill
//
// Fill 1-byte blocks.
//
.set noreorder
70: addu a0,a0,1 // advance pointer to next block
bne a0,t2,70b // if ne, more 1-byte block to fill
sb a2,-1(a0) // fill 1-byte block
.set reorder
80: j ra // return
.end RtlZeroMemory
SBTTL("Fill Memory Ulong")
//++
//
// PVOID
// RtlFillMemoryUlong (
// IN PVOID Destination,
// IN ULONG Length,
// IN ULONG Pattern
// )
//
// Routine Description:
//
// This function fills memory with the specified longowrd pattern by
// filling 32-byte blocks followed by 4-byte blocks.
//
// N.B. This routine assumes that the destination address is aligned
// on a longword boundary and that the length is an even multiple
// of longwords.
//
// Arguments:
//
// Destination (a0) - Supplies a pointer to the memory to fill.
//
// Length (a1) - Supplies the length, in bytes, of the memory to be filled.
//
// Pattern (a2) - Supplies the fill pattern.
//
// Return Value:
//
// The destination address is returned as the function value.
//
//--
LEAF_ENTRY(RtlFillMemoryUlong)
move v0,a0 // set function value
srl a1,a1,2 // make sure length is an even number
sll a1,a1,2 // of longwords
dsll a2,a2,32 // duplicate pattern to 64-bits
dsrl t0,a2,32 //
or a2,a2,t0 //
//
// Check for 32-byte blocks to fill.
//
10: and t0,a1,32 - 1 // isolate residual bytes
subu t1,a1,t0 // subtract out residual bytes
addu t2,a0,t1 // compute ending block address
beq zero,t1,40f // if eq, no 32-byte blocks to fill
move a1,t0 // set residual number of bytes
//
// Fill 32-byte blocks.
//
and t0,a0,1 << 2 // check if destintion quadword aligned
beq zero,t0,20f // if eq, yes
sw a2,0(a0) // store destination longword
addu a0,a0,4 // align destination address
addu a1,a1,t1 // recompute bytes to fill
subu a1,a1,4 // reduce count by 4
b 10b //
//
// The destination is quadword aligned.
//
20: and t0,t1,1 << 5 // test if even number of 32-byte blocks
beq zero,t0,30f // if eq, even number of 32-byte blocks
//
// Fill one 32-byte block.
//
.set noreorder
.set noat
sd a2,0(a0) // fill 32-byte block
sd a2,8(a0) //
sd a2,16(a0) //
addu a0,a0,32 // advance pointer to next block
beq a0,t2,40f // if ne, no 64-byte blocks to fill
sd a2,-8(a0) //
.set at
.set reorder
//
// Fill 64-byte block.
//
.set noreorder
.set noat
30: sd a2,0(a0) // fill 32-byte block
sd a2,8(a0) //
sd a2,16(a0) //
sd a2,24(a0) //
sd a2,32(a0) //
sd a2,40(a0) //
sd a2,48(a0) //
addu a0,a0,64 // advance pointer to next block
bne a0,t2,30b // if ne, more 32-byte blocks to fill
sd a2,-8(a0) //
.set at
.set reorder
//
// Check for 4-byte blocks to fill.
//
40: addu t2,a1,a0 // compute ending block address
beq zero,a1,60f // if eq, no 4-byte block to fill
//
// Fill 4-byte blocks.
//
.set noreorder
50: addu a0,a0,4 // advance pointer to next block
bne a0,t2,50b // if ne, more 4-byte blocks to fill
sw a2,-4(a0) // fill 4-byte block
.set reorder
60: j ra // return
.end RtlFillMemoryUlong
|
