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
1441
1442
1443
1444
|
#!/usr/bin/env perl
# ====================================================================
# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
# project. The module is, however, dual licensed under OpenSSL and
# CRYPTOGAMS licenses depending on where you obtain it. For further
# details see http://www.openssl.org/~appro/cryptogams/.
# ====================================================================
# October 2005.
#
# Montgomery multiplication routine for x86_64. While it gives modest
# 9% improvement of rsa4096 sign on Opteron, rsa512 sign runs more
# than twice, >2x, as fast. Most common rsa1024 sign is improved by
# respectful 50%. It remains to be seen if loop unrolling and
# dedicated squaring routine can provide further improvement...
# July 2011.
#
# Add dedicated squaring procedure. Performance improvement varies
# from platform to platform, but in average it's ~5%/15%/25%/33%
# for 512-/1024-/2048-/4096-bit RSA *sign* benchmarks respectively.
# August 2011.
#
# Unroll and modulo-schedule inner loops in such manner that they
# are "fallen through" for input lengths of 8, which is critical for
# 1024-bit RSA *sign*. Average performance improvement in comparison
# to *initial* version of this module from 2005 is ~0%/30%/40%/45%
# for 512-/1024-/2048-/4096-bit RSA *sign* benchmarks respectively.
# June 2013.
#
# Optimize reduction in squaring procedure and improve 1024+-bit RSA
# sign performance by 10-16% on Intel Sandy Bridge and later
# (virtually same on non-Intel processors).
# August 2013.
#
# Add MULX/ADOX/ADCX code path.
$flavour = shift;
$output = shift;
if ($flavour =~ /\./) { $output = $flavour; undef $flavour; }
$win64=0; $win64=1 if ($flavour =~ /[nm]asm|mingw64/ || $output =~ /\.asm$/);
$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or
( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or
die "can't locate x86_64-xlate.pl";
open OUT,"| \"$^X\" $xlate $flavour $output";
*STDOUT=*OUT;
if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1`
=~ /GNU assembler version ([2-9]\.[0-9]+)/) {
$addx = ($1>=2.23);
}
if (!$addx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) &&
`nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)/) {
$addx = ($1>=2.10);
}
if (!$addx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
`ml64 2>&1` =~ /Version ([0-9]+)\./) {
$addx = ($1>=12);
}
if (!$addx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9])\.([0-9]+)/) {
my $ver = $2 + $3/100.0; # 3.1->3.01, 3.10->3.10
$addx = ($ver>=3.03);
}
# int bn_mul_mont(
$rp="%rdi"; # BN_ULONG *rp,
$ap="%rsi"; # const BN_ULONG *ap,
$bp="%rdx"; # const BN_ULONG *bp,
$np="%rcx"; # const BN_ULONG *np,
$n0="%r8"; # const BN_ULONG *n0,
$num="%r9"; # int num);
$lo0="%r10";
$hi0="%r11";
$hi1="%r13";
$i="%r14";
$j="%r15";
$m0="%rbx";
$m1="%rbp";
$code=<<___;
.text
.extern OPENSSL_ia32cap_P
.globl bn_mul_mont
.type bn_mul_mont,\@function,6
.align 16
bn_mul_mont:
test \$3,${num}d
jnz .Lmul_enter
cmp \$8,${num}d
jb .Lmul_enter
___
$code.=<<___ if ($addx);
mov OPENSSL_ia32cap_P+8(%rip),%r11d
___
$code.=<<___;
cmp $ap,$bp
jne .Lmul4x_enter
test \$7,${num}d
jz .Lsqr8x_enter
jmp .Lmul4x_enter
.align 16
.Lmul_enter:
push %rbx
push %rbp
push %r12
push %r13
push %r14
push %r15
mov ${num}d,${num}d
lea 2($num),%r10
mov %rsp,%r11
neg %r10
lea (%rsp,%r10,8),%rsp # tp=alloca(8*(num+2))
and \$-1024,%rsp # minimize TLB usage
mov %r11,8(%rsp,$num,8) # tp[num+1]=%rsp
.Lmul_body:
mov $bp,%r12 # reassign $bp
___
$bp="%r12";
$code.=<<___;
mov ($n0),$n0 # pull n0[0] value
mov ($bp),$m0 # m0=bp[0]
mov ($ap),%rax
xor $i,$i # i=0
xor $j,$j # j=0
mov $n0,$m1
mulq $m0 # ap[0]*bp[0]
mov %rax,$lo0
mov ($np),%rax
imulq $lo0,$m1 # "tp[0]"*n0
mov %rdx,$hi0
mulq $m1 # np[0]*m1
add %rax,$lo0 # discarded
mov 8($ap),%rax
adc \$0,%rdx
mov %rdx,$hi1
lea 1($j),$j # j++
jmp .L1st_enter
.align 16
.L1st:
add %rax,$hi1
mov ($ap,$j,8),%rax
adc \$0,%rdx
add $hi0,$hi1 # np[j]*m1+ap[j]*bp[0]
mov $lo0,$hi0
adc \$0,%rdx
mov $hi1,-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$hi1
.L1st_enter:
mulq $m0 # ap[j]*bp[0]
add %rax,$hi0
mov ($np,$j,8),%rax
adc \$0,%rdx
lea 1($j),$j # j++
mov %rdx,$lo0
mulq $m1 # np[j]*m1
cmp $num,$j
jne .L1st
add %rax,$hi1
mov ($ap),%rax # ap[0]
adc \$0,%rdx
add $hi0,$hi1 # np[j]*m1+ap[j]*bp[0]
adc \$0,%rdx
mov $hi1,-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$hi1
mov $lo0,$hi0
xor %rdx,%rdx
add $hi0,$hi1
adc \$0,%rdx
mov $hi1,-8(%rsp,$num,8)
mov %rdx,(%rsp,$num,8) # store upmost overflow bit
lea 1($i),$i # i++
jmp .Louter
.align 16
.Louter:
mov ($bp,$i,8),$m0 # m0=bp[i]
xor $j,$j # j=0
mov $n0,$m1
mov (%rsp),$lo0
mulq $m0 # ap[0]*bp[i]
add %rax,$lo0 # ap[0]*bp[i]+tp[0]
mov ($np),%rax
adc \$0,%rdx
imulq $lo0,$m1 # tp[0]*n0
mov %rdx,$hi0
mulq $m1 # np[0]*m1
add %rax,$lo0 # discarded
mov 8($ap),%rax
adc \$0,%rdx
mov 8(%rsp),$lo0 # tp[1]
mov %rdx,$hi1
lea 1($j),$j # j++
jmp .Linner_enter
.align 16
.Linner:
add %rax,$hi1
mov ($ap,$j,8),%rax
adc \$0,%rdx
add $lo0,$hi1 # np[j]*m1+ap[j]*bp[i]+tp[j]
mov (%rsp,$j,8),$lo0
adc \$0,%rdx
mov $hi1,-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$hi1
.Linner_enter:
mulq $m0 # ap[j]*bp[i]
add %rax,$hi0
mov ($np,$j,8),%rax
adc \$0,%rdx
add $hi0,$lo0 # ap[j]*bp[i]+tp[j]
mov %rdx,$hi0
adc \$0,$hi0
lea 1($j),$j # j++
mulq $m1 # np[j]*m1
cmp $num,$j
jne .Linner
add %rax,$hi1
mov ($ap),%rax # ap[0]
adc \$0,%rdx
add $lo0,$hi1 # np[j]*m1+ap[j]*bp[i]+tp[j]
mov (%rsp,$j,8),$lo0
adc \$0,%rdx
mov $hi1,-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$hi1
xor %rdx,%rdx
add $hi0,$hi1
adc \$0,%rdx
add $lo0,$hi1 # pull upmost overflow bit
adc \$0,%rdx
mov $hi1,-8(%rsp,$num,8)
mov %rdx,(%rsp,$num,8) # store upmost overflow bit
lea 1($i),$i # i++
cmp $num,$i
jb .Louter
xor $i,$i # i=0 and clear CF!
mov (%rsp),%rax # tp[0]
lea (%rsp),$ap # borrow ap for tp
mov $num,$j # j=num
jmp .Lsub
.align 16
.Lsub: sbb ($np,$i,8),%rax
mov %rax,($rp,$i,8) # rp[i]=tp[i]-np[i]
mov 8($ap,$i,8),%rax # tp[i+1]
lea 1($i),$i # i++
dec $j # doesnn't affect CF!
jnz .Lsub
sbb \$0,%rax # handle upmost overflow bit
xor $i,$i
and %rax,$ap
not %rax
mov $rp,$np
and %rax,$np
mov $num,$j # j=num
or $np,$ap # ap=borrow?tp:rp
.align 16
.Lcopy: # copy or in-place refresh
mov ($ap,$i,8),%rax
mov $i,(%rsp,$i,8) # zap temporary vector
mov %rax,($rp,$i,8) # rp[i]=tp[i]
lea 1($i),$i
sub \$1,$j
jnz .Lcopy
mov 8(%rsp,$num,8),%rsi # restore %rsp
mov \$1,%rax
mov (%rsi),%r15
mov 8(%rsi),%r14
mov 16(%rsi),%r13
mov 24(%rsi),%r12
mov 32(%rsi),%rbp
mov 40(%rsi),%rbx
lea 48(%rsi),%rsp
.Lmul_epilogue:
ret
.size bn_mul_mont,.-bn_mul_mont
___
{{{
my @A=("%r10","%r11");
my @N=("%r13","%rdi");
$code.=<<___;
.type bn_mul4x_mont,\@function,6
.align 16
bn_mul4x_mont:
.Lmul4x_enter:
___
$code.=<<___ if ($addx);
and \$0x80100,%r11d
cmp \$0x80100,%r11d
je .Lmulx4x_enter
___
$code.=<<___;
push %rbx
push %rbp
push %r12
push %r13
push %r14
push %r15
mov ${num}d,${num}d
lea 4($num),%r10
mov %rsp,%r11
neg %r10
lea (%rsp,%r10,8),%rsp # tp=alloca(8*(num+4))
and \$-1024,%rsp # minimize TLB usage
mov %r11,8(%rsp,$num,8) # tp[num+1]=%rsp
.Lmul4x_body:
mov $rp,16(%rsp,$num,8) # tp[num+2]=$rp
mov %rdx,%r12 # reassign $bp
___
$bp="%r12";
$code.=<<___;
mov ($n0),$n0 # pull n0[0] value
mov ($bp),$m0 # m0=bp[0]
mov ($ap),%rax
xor $i,$i # i=0
xor $j,$j # j=0
mov $n0,$m1
mulq $m0 # ap[0]*bp[0]
mov %rax,$A[0]
mov ($np),%rax
imulq $A[0],$m1 # "tp[0]"*n0
mov %rdx,$A[1]
mulq $m1 # np[0]*m1
add %rax,$A[0] # discarded
mov 8($ap),%rax
adc \$0,%rdx
mov %rdx,$N[1]
mulq $m0
add %rax,$A[1]
mov 8($np),%rax
adc \$0,%rdx
mov %rdx,$A[0]
mulq $m1
add %rax,$N[1]
mov 16($ap),%rax
adc \$0,%rdx
add $A[1],$N[1]
lea 4($j),$j # j++
adc \$0,%rdx
mov $N[1],(%rsp)
mov %rdx,$N[0]
jmp .L1st4x
.align 16
.L1st4x:
mulq $m0 # ap[j]*bp[0]
add %rax,$A[0]
mov -16($np,$j,8),%rax
adc \$0,%rdx
mov %rdx,$A[1]
mulq $m1 # np[j]*m1
add %rax,$N[0]
mov -8($ap,$j,8),%rax
adc \$0,%rdx
add $A[0],$N[0] # np[j]*m1+ap[j]*bp[0]
adc \$0,%rdx
mov $N[0],-24(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[1]
mulq $m0 # ap[j]*bp[0]
add %rax,$A[1]
mov -8($np,$j,8),%rax
adc \$0,%rdx
mov %rdx,$A[0]
mulq $m1 # np[j]*m1
add %rax,$N[1]
mov ($ap,$j,8),%rax
adc \$0,%rdx
add $A[1],$N[1] # np[j]*m1+ap[j]*bp[0]
adc \$0,%rdx
mov $N[1],-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[0]
mulq $m0 # ap[j]*bp[0]
add %rax,$A[0]
mov ($np,$j,8),%rax
adc \$0,%rdx
mov %rdx,$A[1]
mulq $m1 # np[j]*m1
add %rax,$N[0]
mov 8($ap,$j,8),%rax
adc \$0,%rdx
add $A[0],$N[0] # np[j]*m1+ap[j]*bp[0]
adc \$0,%rdx
mov $N[0],-8(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[1]
mulq $m0 # ap[j]*bp[0]
add %rax,$A[1]
mov 8($np,$j,8),%rax
adc \$0,%rdx
lea 4($j),$j # j++
mov %rdx,$A[0]
mulq $m1 # np[j]*m1
add %rax,$N[1]
mov -16($ap,$j,8),%rax
adc \$0,%rdx
add $A[1],$N[1] # np[j]*m1+ap[j]*bp[0]
adc \$0,%rdx
mov $N[1],-32(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[0]
cmp $num,$j
jb .L1st4x
mulq $m0 # ap[j]*bp[0]
add %rax,$A[0]
mov -16($np,$j,8),%rax
adc \$0,%rdx
mov %rdx,$A[1]
mulq $m1 # np[j]*m1
add %rax,$N[0]
mov -8($ap,$j,8),%rax
adc \$0,%rdx
add $A[0],$N[0] # np[j]*m1+ap[j]*bp[0]
adc \$0,%rdx
mov $N[0],-24(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[1]
mulq $m0 # ap[j]*bp[0]
add %rax,$A[1]
mov -8($np,$j,8),%rax
adc \$0,%rdx
mov %rdx,$A[0]
mulq $m1 # np[j]*m1
add %rax,$N[1]
mov ($ap),%rax # ap[0]
adc \$0,%rdx
add $A[1],$N[1] # np[j]*m1+ap[j]*bp[0]
adc \$0,%rdx
mov $N[1],-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[0]
xor $N[1],$N[1]
add $A[0],$N[0]
adc \$0,$N[1]
mov $N[0],-8(%rsp,$j,8)
mov $N[1],(%rsp,$j,8) # store upmost overflow bit
lea 1($i),$i # i++
.align 4
.Louter4x:
mov ($bp,$i,8),$m0 # m0=bp[i]
xor $j,$j # j=0
mov (%rsp),$A[0]
mov $n0,$m1
mulq $m0 # ap[0]*bp[i]
add %rax,$A[0] # ap[0]*bp[i]+tp[0]
mov ($np),%rax
adc \$0,%rdx
imulq $A[0],$m1 # tp[0]*n0
mov %rdx,$A[1]
mulq $m1 # np[0]*m1
add %rax,$A[0] # "$N[0]", discarded
mov 8($ap),%rax
adc \$0,%rdx
mov %rdx,$N[1]
mulq $m0 # ap[j]*bp[i]
add %rax,$A[1]
mov 8($np),%rax
adc \$0,%rdx
add 8(%rsp),$A[1] # +tp[1]
adc \$0,%rdx
mov %rdx,$A[0]
mulq $m1 # np[j]*m1
add %rax,$N[1]
mov 16($ap),%rax
adc \$0,%rdx
add $A[1],$N[1] # np[j]*m1+ap[j]*bp[i]+tp[j]
lea 4($j),$j # j+=2
adc \$0,%rdx
mov $N[1],(%rsp) # tp[j-1]
mov %rdx,$N[0]
jmp .Linner4x
.align 16
.Linner4x:
mulq $m0 # ap[j]*bp[i]
add %rax,$A[0]
mov -16($np,$j,8),%rax
adc \$0,%rdx
add -16(%rsp,$j,8),$A[0] # ap[j]*bp[i]+tp[j]
adc \$0,%rdx
mov %rdx,$A[1]
mulq $m1 # np[j]*m1
add %rax,$N[0]
mov -8($ap,$j,8),%rax
adc \$0,%rdx
add $A[0],$N[0]
adc \$0,%rdx
mov $N[0],-24(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[1]
mulq $m0 # ap[j]*bp[i]
add %rax,$A[1]
mov -8($np,$j,8),%rax
adc \$0,%rdx
add -8(%rsp,$j,8),$A[1]
adc \$0,%rdx
mov %rdx,$A[0]
mulq $m1 # np[j]*m1
add %rax,$N[1]
mov ($ap,$j,8),%rax
adc \$0,%rdx
add $A[1],$N[1]
adc \$0,%rdx
mov $N[1],-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[0]
mulq $m0 # ap[j]*bp[i]
add %rax,$A[0]
mov ($np,$j,8),%rax
adc \$0,%rdx
add (%rsp,$j,8),$A[0] # ap[j]*bp[i]+tp[j]
adc \$0,%rdx
mov %rdx,$A[1]
mulq $m1 # np[j]*m1
add %rax,$N[0]
mov 8($ap,$j,8),%rax
adc \$0,%rdx
add $A[0],$N[0]
adc \$0,%rdx
mov $N[0],-8(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[1]
mulq $m0 # ap[j]*bp[i]
add %rax,$A[1]
mov 8($np,$j,8),%rax
adc \$0,%rdx
add 8(%rsp,$j,8),$A[1]
adc \$0,%rdx
lea 4($j),$j # j++
mov %rdx,$A[0]
mulq $m1 # np[j]*m1
add %rax,$N[1]
mov -16($ap,$j,8),%rax
adc \$0,%rdx
add $A[1],$N[1]
adc \$0,%rdx
mov $N[1],-32(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[0]
cmp $num,$j
jb .Linner4x
mulq $m0 # ap[j]*bp[i]
add %rax,$A[0]
mov -16($np,$j,8),%rax
adc \$0,%rdx
add -16(%rsp,$j,8),$A[0] # ap[j]*bp[i]+tp[j]
adc \$0,%rdx
mov %rdx,$A[1]
mulq $m1 # np[j]*m1
add %rax,$N[0]
mov -8($ap,$j,8),%rax
adc \$0,%rdx
add $A[0],$N[0]
adc \$0,%rdx
mov $N[0],-24(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[1]
mulq $m0 # ap[j]*bp[i]
add %rax,$A[1]
mov -8($np,$j,8),%rax
adc \$0,%rdx
add -8(%rsp,$j,8),$A[1]
adc \$0,%rdx
lea 1($i),$i # i++
mov %rdx,$A[0]
mulq $m1 # np[j]*m1
add %rax,$N[1]
mov ($ap),%rax # ap[0]
adc \$0,%rdx
add $A[1],$N[1]
adc \$0,%rdx
mov $N[1],-16(%rsp,$j,8) # tp[j-1]
mov %rdx,$N[0]
xor $N[1],$N[1]
add $A[0],$N[0]
adc \$0,$N[1]
add (%rsp,$num,8),$N[0] # pull upmost overflow bit
adc \$0,$N[1]
mov $N[0],-8(%rsp,$j,8)
mov $N[1],(%rsp,$j,8) # store upmost overflow bit
cmp $num,$i
jb .Louter4x
___
{
my @ri=("%rax","%rdx",$m0,$m1);
$code.=<<___;
mov 16(%rsp,$num,8),$rp # restore $rp
mov 0(%rsp),@ri[0] # tp[0]
pxor %xmm0,%xmm0
mov 8(%rsp),@ri[1] # tp[1]
shr \$2,$num # num/=4
lea (%rsp),$ap # borrow ap for tp
xor $i,$i # i=0 and clear CF!
sub 0($np),@ri[0]
mov 16($ap),@ri[2] # tp[2]
mov 24($ap),@ri[3] # tp[3]
sbb 8($np),@ri[1]
lea -1($num),$j # j=num/4-1
jmp .Lsub4x
.align 16
.Lsub4x:
mov @ri[0],0($rp,$i,8) # rp[i]=tp[i]-np[i]
mov @ri[1],8($rp,$i,8) # rp[i]=tp[i]-np[i]
sbb 16($np,$i,8),@ri[2]
mov 32($ap,$i,8),@ri[0] # tp[i+1]
mov 40($ap,$i,8),@ri[1]
sbb 24($np,$i,8),@ri[3]
mov @ri[2],16($rp,$i,8) # rp[i]=tp[i]-np[i]
mov @ri[3],24($rp,$i,8) # rp[i]=tp[i]-np[i]
sbb 32($np,$i,8),@ri[0]
mov 48($ap,$i,8),@ri[2]
mov 56($ap,$i,8),@ri[3]
sbb 40($np,$i,8),@ri[1]
lea 4($i),$i # i++
dec $j # doesnn't affect CF!
jnz .Lsub4x
mov @ri[0],0($rp,$i,8) # rp[i]=tp[i]-np[i]
mov 32($ap,$i,8),@ri[0] # load overflow bit
sbb 16($np,$i,8),@ri[2]
mov @ri[1],8($rp,$i,8) # rp[i]=tp[i]-np[i]
sbb 24($np,$i,8),@ri[3]
mov @ri[2],16($rp,$i,8) # rp[i]=tp[i]-np[i]
sbb \$0,@ri[0] # handle upmost overflow bit
mov @ri[3],24($rp,$i,8) # rp[i]=tp[i]-np[i]
xor $i,$i # i=0
and @ri[0],$ap
not @ri[0]
mov $rp,$np
and @ri[0],$np
lea -1($num),$j
or $np,$ap # ap=borrow?tp:rp
movdqu ($ap),%xmm1
movdqa %xmm0,(%rsp)
movdqu %xmm1,($rp)
jmp .Lcopy4x
.align 16
.Lcopy4x: # copy or in-place refresh
movdqu 16($ap,$i),%xmm2
movdqu 32($ap,$i),%xmm1
movdqa %xmm0,16(%rsp,$i)
movdqu %xmm2,16($rp,$i)
movdqa %xmm0,32(%rsp,$i)
movdqu %xmm1,32($rp,$i)
lea 32($i),$i
dec $j
jnz .Lcopy4x
shl \$2,$num
movdqu 16($ap,$i),%xmm2
movdqa %xmm0,16(%rsp,$i)
movdqu %xmm2,16($rp,$i)
___
}
$code.=<<___;
mov 8(%rsp,$num,8),%rsi # restore %rsp
mov \$1,%rax
mov (%rsi),%r15
mov 8(%rsi),%r14
mov 16(%rsi),%r13
mov 24(%rsi),%r12
mov 32(%rsi),%rbp
mov 40(%rsi),%rbx
lea 48(%rsi),%rsp
.Lmul4x_epilogue:
ret
.size bn_mul4x_mont,.-bn_mul4x_mont
___
}}}
{{{
######################################################################
# void bn_sqr8x_mont(
my $rptr="%rdi"; # const BN_ULONG *rptr,
my $aptr="%rsi"; # const BN_ULONG *aptr,
my $bptr="%rdx"; # not used
my $nptr="%rcx"; # const BN_ULONG *nptr,
my $n0 ="%r8"; # const BN_ULONG *n0);
my $num ="%r9"; # int num, has to be divisible by 8
my ($i,$j,$tptr)=("%rbp","%rcx",$rptr);
my @A0=("%r10","%r11");
my @A1=("%r12","%r13");
my ($a0,$a1,$ai)=("%r14","%r15","%rbx");
$code.=<<___ if ($addx);
.extern bn_sqrx8x_internal # see x86_64-mont5 module
___
$code.=<<___;
.extern bn_sqr8x_internal # see x86_64-mont5 module
.type bn_sqr8x_mont,\@function,6
.align 32
bn_sqr8x_mont:
.Lsqr8x_enter:
mov %rsp,%rax
push %rbx
push %rbp
push %r12
push %r13
push %r14
push %r15
mov ${num}d,%r10d
shl \$3,${num}d # convert $num to bytes
shl \$3+2,%r10 # 4*$num
neg $num
##############################################################
# ensure that stack frame doesn't alias with $aptr modulo
# 4096. this is done to allow memory disambiguation logic
# do its job.
#
lea -64(%rsp,$num,2),%r11
mov ($n0),$n0 # *n0
sub $aptr,%r11
and \$4095,%r11
cmp %r11,%r10
jb .Lsqr8x_sp_alt
sub %r11,%rsp # align with $aptr
lea -64(%rsp,$num,2),%rsp # alloca(frame+2*$num)
jmp .Lsqr8x_sp_done
.align 32
.Lsqr8x_sp_alt:
lea 4096-64(,$num,2),%r10 # 4096-frame-2*$num
lea -64(%rsp,$num,2),%rsp # alloca(frame+2*$num)
sub %r10,%r11
mov \$0,%r10
cmovc %r10,%r11
sub %r11,%rsp
.Lsqr8x_sp_done:
and \$-64,%rsp
mov $num,%r10
neg $num
mov $n0, 32(%rsp)
mov %rax, 40(%rsp) # save original %rsp
.Lsqr8x_body:
movq $nptr, %xmm2 # save pointer to modulus
pxor %xmm0,%xmm0
movq $rptr,%xmm1 # save $rptr
movq %r10, %xmm3 # -$num
___
$code.=<<___ if ($addx);
mov OPENSSL_ia32cap_P+8(%rip),%eax
and \$0x80100,%eax
cmp \$0x80100,%eax
jne .Lsqr8x_nox
call bn_sqrx8x_internal # see x86_64-mont5 module
# %rax top-most carry
# %rbp nptr
# %rcx -8*num
# %r8 end of tp[2*num]
lea (%r8,%rcx),%rbx
mov %rcx,$num
mov %rcx,%rdx
movq %xmm1,$rptr
sar \$3+2,%rcx # %cf=0
jmp .Lsqr8x_sub
.align 32
.Lsqr8x_nox:
___
$code.=<<___;
call bn_sqr8x_internal # see x86_64-mont5 module
# %rax top-most carry
# %rbp nptr
# %r8 -8*num
# %rdi end of tp[2*num]
lea (%rdi,$num),%rbx
mov $num,%rcx
mov $num,%rdx
movq %xmm1,$rptr
sar \$3+2,%rcx # %cf=0
jmp .Lsqr8x_sub
.align 32
.Lsqr8x_sub:
mov 8*0(%rbx),%r12
mov 8*1(%rbx),%r13
mov 8*2(%rbx),%r14
mov 8*3(%rbx),%r15
lea 8*4(%rbx),%rbx
sbb 8*0(%rbp),%r12
sbb 8*1(%rbp),%r13
sbb 8*2(%rbp),%r14
sbb 8*3(%rbp),%r15
lea 8*4(%rbp),%rbp
mov %r12,8*0($rptr)
mov %r13,8*1($rptr)
mov %r14,8*2($rptr)
mov %r15,8*3($rptr)
lea 8*4($rptr),$rptr
inc %rcx # preserves %cf
jnz .Lsqr8x_sub
sbb \$0,%rax # top-most carry
lea (%rbx,$num),%rbx # rewind
lea ($rptr,$num),$rptr # rewind
movq %rax,%xmm1
pxor %xmm0,%xmm0
pshufd \$0,%xmm1,%xmm1
mov 40(%rsp),%rsi # restore %rsp
jmp .Lsqr8x_cond_copy
.align 32
.Lsqr8x_cond_copy:
movdqa 16*0(%rbx),%xmm2
movdqa 16*1(%rbx),%xmm3
lea 16*2(%rbx),%rbx
movdqu 16*0($rptr),%xmm4
movdqu 16*1($rptr),%xmm5
lea 16*2($rptr),$rptr
movdqa %xmm0,-16*2(%rbx) # zero tp
movdqa %xmm0,-16*1(%rbx)
movdqa %xmm0,-16*2(%rbx,%rdx)
movdqa %xmm0,-16*1(%rbx,%rdx)
pcmpeqd %xmm1,%xmm0
pand %xmm1,%xmm2
pand %xmm1,%xmm3
pand %xmm0,%xmm4
pand %xmm0,%xmm5
pxor %xmm0,%xmm0
por %xmm2,%xmm4
por %xmm3,%xmm5
movdqu %xmm4,-16*2($rptr)
movdqu %xmm5,-16*1($rptr)
add \$32,$num
jnz .Lsqr8x_cond_copy
mov \$1,%rax
mov -48(%rsi),%r15
mov -40(%rsi),%r14
mov -32(%rsi),%r13
mov -24(%rsi),%r12
mov -16(%rsi),%rbp
mov -8(%rsi),%rbx
lea (%rsi),%rsp
.Lsqr8x_epilogue:
ret
.size bn_sqr8x_mont,.-bn_sqr8x_mont
___
}}}
if ($addx) {{{
my $bp="%rdx"; # original value
$code.=<<___;
.type bn_mulx4x_mont,\@function,6
.align 32
bn_mulx4x_mont:
.Lmulx4x_enter:
mov %rsp,%rax
push %rbx
push %rbp
push %r12
push %r13
push %r14
push %r15
shl \$3,${num}d # convert $num to bytes
.byte 0x67
xor %r10,%r10
sub $num,%r10 # -$num
mov ($n0),$n0 # *n0
lea -72(%rsp,%r10),%rsp # alloca(frame+$num+8)
lea ($bp,$num),%r10
and \$-128,%rsp
##############################################################
# Stack layout
# +0 num
# +8 off-loaded &b[i]
# +16 end of b[num]
# +24 saved n0
# +32 saved rp
# +40 saved %rsp
# +48 inner counter
# +56
# +64 tmp[num+1]
#
mov $num,0(%rsp) # save $num
shr \$5,$num
mov %r10,16(%rsp) # end of b[num]
sub \$1,$num
mov $n0, 24(%rsp) # save *n0
mov $rp, 32(%rsp) # save $rp
mov %rax,40(%rsp) # save original %rsp
mov $num,48(%rsp) # inner counter
jmp .Lmulx4x_body
.align 32
.Lmulx4x_body:
___
my ($aptr, $bptr, $nptr, $tptr, $mi, $bi, $zero, $num)=
("%rsi","%rdi","%rcx","%rbx","%r8","%r9","%rbp","%rax");
my $rptr=$bptr;
$code.=<<___;
lea 8($bp),$bptr
mov ($bp),%rdx # b[0], $bp==%rdx actually
lea 64+32(%rsp),$tptr
mov %rdx,$bi
mulx 0*8($aptr),$mi,%rax # a[0]*b[0]
mulx 1*8($aptr),%r11,%r14 # a[1]*b[0]
add %rax,%r11
mov $bptr,8(%rsp) # off-load &b[i]
mulx 2*8($aptr),%r12,%r13 # ...
adc %r14,%r12
adc \$0,%r13
mov $mi,$bptr # borrow $bptr
imulq 24(%rsp),$mi # "t[0]"*n0
xor $zero,$zero # cf=0, of=0
mulx 3*8($aptr),%rax,%r14
mov $mi,%rdx
lea 4*8($aptr),$aptr
adcx %rax,%r13
adcx $zero,%r14 # cf=0
mulx 0*8($nptr),%rax,%r10
adcx %rax,$bptr # discarded
adox %r11,%r10
mulx 1*8($nptr),%rax,%r11
adcx %rax,%r10
adox %r12,%r11
.byte 0xc4,0x62,0xfb,0xf6,0xa1,0x10,0x00,0x00,0x00 # mulx 2*8($nptr),%rax,%r12
mov 48(%rsp),$bptr # counter value
mov %r10,-4*8($tptr)
adcx %rax,%r11
adox %r13,%r12
mulx 3*8($nptr),%rax,%r15
mov $bi,%rdx
mov %r11,-3*8($tptr)
adcx %rax,%r12
adox $zero,%r15 # of=0
lea 4*8($nptr),$nptr
mov %r12,-2*8($tptr)
jmp .Lmulx4x_1st
.align 32
.Lmulx4x_1st:
adcx $zero,%r15 # cf=0, modulo-scheduled
mulx 0*8($aptr),%r10,%rax # a[4]*b[0]
adcx %r14,%r10
mulx 1*8($aptr),%r11,%r14 # a[5]*b[0]
adcx %rax,%r11
mulx 2*8($aptr),%r12,%rax # ...
adcx %r14,%r12
mulx 3*8($aptr),%r13,%r14
.byte 0x67,0x67
mov $mi,%rdx
adcx %rax,%r13
adcx $zero,%r14 # cf=0
lea 4*8($aptr),$aptr
lea 4*8($tptr),$tptr
adox %r15,%r10
mulx 0*8($nptr),%rax,%r15
adcx %rax,%r10
adox %r15,%r11
mulx 1*8($nptr),%rax,%r15
adcx %rax,%r11
adox %r15,%r12
mulx 2*8($nptr),%rax,%r15
mov %r10,-5*8($tptr)
adcx %rax,%r12
mov %r11,-4*8($tptr)
adox %r15,%r13
mulx 3*8($nptr),%rax,%r15
mov $bi,%rdx
mov %r12,-3*8($tptr)
adcx %rax,%r13
adox $zero,%r15
lea 4*8($nptr),$nptr
mov %r13,-2*8($tptr)
dec $bptr # of=0, pass cf
jnz .Lmulx4x_1st
mov 0(%rsp),$num # load num
mov 8(%rsp),$bptr # re-load &b[i]
adc $zero,%r15 # modulo-scheduled
add %r15,%r14
sbb %r15,%r15 # top-most carry
mov %r14,-1*8($tptr)
jmp .Lmulx4x_outer
.align 32
.Lmulx4x_outer:
mov ($bptr),%rdx # b[i]
lea 8($bptr),$bptr # b++
sub $num,$aptr # rewind $aptr
mov %r15,($tptr) # save top-most carry
lea 64+4*8(%rsp),$tptr
sub $num,$nptr # rewind $nptr
mulx 0*8($aptr),$mi,%r11 # a[0]*b[i]
xor %ebp,%ebp # xor $zero,$zero # cf=0, of=0
mov %rdx,$bi
mulx 1*8($aptr),%r14,%r12 # a[1]*b[i]
adox -4*8($tptr),$mi
adcx %r14,%r11
mulx 2*8($aptr),%r15,%r13 # ...
adox -3*8($tptr),%r11
adcx %r15,%r12
adox $zero,%r12
adcx $zero,%r13
mov $bptr,8(%rsp) # off-load &b[i]
.byte 0x67
mov $mi,%r15
imulq 24(%rsp),$mi # "t[0]"*n0
xor %ebp,%ebp # xor $zero,$zero # cf=0, of=0
mulx 3*8($aptr),%rax,%r14
mov $mi,%rdx
adox -2*8($tptr),%r12
adcx %rax,%r13
adox -1*8($tptr),%r13
adcx $zero,%r14
lea 4*8($aptr),$aptr
adox $zero,%r14
mulx 0*8($nptr),%rax,%r10
adcx %rax,%r15 # discarded
adox %r11,%r10
mulx 1*8($nptr),%rax,%r11
adcx %rax,%r10
adox %r12,%r11
mulx 2*8($nptr),%rax,%r12
mov %r10,-4*8($tptr)
adcx %rax,%r11
adox %r13,%r12
mulx 3*8($nptr),%rax,%r15
mov $bi,%rdx
mov %r11,-3*8($tptr)
lea 4*8($nptr),$nptr
adcx %rax,%r12
adox $zero,%r15 # of=0
mov 48(%rsp),$bptr # counter value
mov %r12,-2*8($tptr)
jmp .Lmulx4x_inner
.align 32
.Lmulx4x_inner:
mulx 0*8($aptr),%r10,%rax # a[4]*b[i]
adcx $zero,%r15 # cf=0, modulo-scheduled
adox %r14,%r10
mulx 1*8($aptr),%r11,%r14 # a[5]*b[i]
adcx 0*8($tptr),%r10
adox %rax,%r11
mulx 2*8($aptr),%r12,%rax # ...
adcx 1*8($tptr),%r11
adox %r14,%r12
mulx 3*8($aptr),%r13,%r14
mov $mi,%rdx
adcx 2*8($tptr),%r12
adox %rax,%r13
adcx 3*8($tptr),%r13
adox $zero,%r14 # of=0
lea 4*8($aptr),$aptr
lea 4*8($tptr),$tptr
adcx $zero,%r14 # cf=0
adox %r15,%r10
mulx 0*8($nptr),%rax,%r15
adcx %rax,%r10
adox %r15,%r11
mulx 1*8($nptr),%rax,%r15
adcx %rax,%r11
adox %r15,%r12
mulx 2*8($nptr),%rax,%r15
mov %r10,-5*8($tptr)
adcx %rax,%r12
adox %r15,%r13
mulx 3*8($nptr),%rax,%r15
mov $bi,%rdx
mov %r11,-4*8($tptr)
mov %r12,-3*8($tptr)
adcx %rax,%r13
adox $zero,%r15
lea 4*8($nptr),$nptr
mov %r13,-2*8($tptr)
dec $bptr # of=0, pass cf
jnz .Lmulx4x_inner
mov 0(%rsp),$num # load num
mov 8(%rsp),$bptr # re-load &b[i]
adc $zero,%r15 # modulo-scheduled
sub 0*8($tptr),$zero # pull top-most carry
adc %r15,%r14
sbb %r15,%r15 # top-most carry
mov %r14,-1*8($tptr)
cmp 16(%rsp),$bptr
jne .Lmulx4x_outer
lea 64(%rsp),$tptr
sub $num,$nptr # rewind $nptr
neg %r15
mov $num,%rdx
shr \$3+2,$num # %cf=0
mov 32(%rsp),$rptr # restore rp
jmp .Lmulx4x_sub
.align 32
.Lmulx4x_sub:
mov 8*0($tptr),%r11
mov 8*1($tptr),%r12
mov 8*2($tptr),%r13
mov 8*3($tptr),%r14
lea 8*4($tptr),$tptr
sbb 8*0($nptr),%r11
sbb 8*1($nptr),%r12
sbb 8*2($nptr),%r13
sbb 8*3($nptr),%r14
lea 8*4($nptr),$nptr
mov %r11,8*0($rptr)
mov %r12,8*1($rptr)
mov %r13,8*2($rptr)
mov %r14,8*3($rptr)
lea 8*4($rptr),$rptr
dec $num # preserves %cf
jnz .Lmulx4x_sub
sbb \$0,%r15 # top-most carry
lea 64(%rsp),$tptr
sub %rdx,$rptr # rewind
movq %r15,%xmm1
pxor %xmm0,%xmm0
pshufd \$0,%xmm1,%xmm1
mov 40(%rsp),%rsi # restore %rsp
jmp .Lmulx4x_cond_copy
.align 32
.Lmulx4x_cond_copy:
movdqa 16*0($tptr),%xmm2
movdqa 16*1($tptr),%xmm3
lea 16*2($tptr),$tptr
movdqu 16*0($rptr),%xmm4
movdqu 16*1($rptr),%xmm5
lea 16*2($rptr),$rptr
movdqa %xmm0,-16*2($tptr) # zero tp
movdqa %xmm0,-16*1($tptr)
pcmpeqd %xmm1,%xmm0
pand %xmm1,%xmm2
pand %xmm1,%xmm3
pand %xmm0,%xmm4
pand %xmm0,%xmm5
pxor %xmm0,%xmm0
por %xmm2,%xmm4
por %xmm3,%xmm5
movdqu %xmm4,-16*2($rptr)
movdqu %xmm5,-16*1($rptr)
sub \$32,%rdx
jnz .Lmulx4x_cond_copy
mov %rdx,($tptr)
mov \$1,%rax
mov -48(%rsi),%r15
mov -40(%rsi),%r14
mov -32(%rsi),%r13
mov -24(%rsi),%r12
mov -16(%rsi),%rbp
mov -8(%rsi),%rbx
lea (%rsi),%rsp
.Lmulx4x_epilogue:
ret
.size bn_mulx4x_mont,.-bn_mulx4x_mont
___
}}}
$code.=<<___;
.asciz "Montgomery Multiplication for x86_64, CRYPTOGAMS by <appro\@openssl.org>"
.align 16
___
# EXCEPTION_DISPOSITION handler (EXCEPTION_RECORD *rec,ULONG64 frame,
# CONTEXT *context,DISPATCHER_CONTEXT *disp)
if ($win64) {
$rec="%rcx";
$frame="%rdx";
$context="%r8";
$disp="%r9";
$code.=<<___;
.extern __imp_RtlVirtualUnwind
.type mul_handler,\@abi-omnipotent
.align 16
mul_handler:
push %rsi
push %rdi
push %rbx
push %rbp
push %r12
push %r13
push %r14
push %r15
pushfq
sub \$64,%rsp
mov 120($context),%rax # pull context->Rax
mov 248($context),%rbx # pull context->Rip
mov 8($disp),%rsi # disp->ImageBase
mov 56($disp),%r11 # disp->HandlerData
mov 0(%r11),%r10d # HandlerData[0]
lea (%rsi,%r10),%r10 # end of prologue label
cmp %r10,%rbx # context->Rip<end of prologue label
jb .Lcommon_seh_tail
mov 152($context),%rax # pull context->Rsp
mov 4(%r11),%r10d # HandlerData[1]
lea (%rsi,%r10),%r10 # epilogue label
cmp %r10,%rbx # context->Rip>=epilogue label
jae .Lcommon_seh_tail
mov 192($context),%r10 # pull $num
mov 8(%rax,%r10,8),%rax # pull saved stack pointer
lea 48(%rax),%rax
mov -8(%rax),%rbx
mov -16(%rax),%rbp
mov -24(%rax),%r12
mov -32(%rax),%r13
mov -40(%rax),%r14
mov -48(%rax),%r15
mov %rbx,144($context) # restore context->Rbx
mov %rbp,160($context) # restore context->Rbp
mov %r12,216($context) # restore context->R12
mov %r13,224($context) # restore context->R13
mov %r14,232($context) # restore context->R14
mov %r15,240($context) # restore context->R15
jmp .Lcommon_seh_tail
.size mul_handler,.-mul_handler
.type sqr_handler,\@abi-omnipotent
.align 16
sqr_handler:
push %rsi
push %rdi
push %rbx
push %rbp
push %r12
push %r13
push %r14
push %r15
pushfq
sub \$64,%rsp
mov 120($context),%rax # pull context->Rax
mov 248($context),%rbx # pull context->Rip
mov 8($disp),%rsi # disp->ImageBase
mov 56($disp),%r11 # disp->HandlerData
mov 0(%r11),%r10d # HandlerData[0]
lea (%rsi,%r10),%r10 # end of prologue label
cmp %r10,%rbx # context->Rip<.Lsqr_body
jb .Lcommon_seh_tail
mov 152($context),%rax # pull context->Rsp
mov 4(%r11),%r10d # HandlerData[1]
lea (%rsi,%r10),%r10 # epilogue label
cmp %r10,%rbx # context->Rip>=.Lsqr_epilogue
jae .Lcommon_seh_tail
mov 40(%rax),%rax # pull saved stack pointer
mov -8(%rax),%rbx
mov -16(%rax),%rbp
mov -24(%rax),%r12
mov -32(%rax),%r13
mov -40(%rax),%r14
mov -48(%rax),%r15
mov %rbx,144($context) # restore context->Rbx
mov %rbp,160($context) # restore context->Rbp
mov %r12,216($context) # restore context->R12
mov %r13,224($context) # restore context->R13
mov %r14,232($context) # restore context->R14
mov %r15,240($context) # restore context->R15
.Lcommon_seh_tail:
mov 8(%rax),%rdi
mov 16(%rax),%rsi
mov %rax,152($context) # restore context->Rsp
mov %rsi,168($context) # restore context->Rsi
mov %rdi,176($context) # restore context->Rdi
mov 40($disp),%rdi # disp->ContextRecord
mov $context,%rsi # context
mov \$154,%ecx # sizeof(CONTEXT)
.long 0xa548f3fc # cld; rep movsq
mov $disp,%rsi
xor %rcx,%rcx # arg1, UNW_FLAG_NHANDLER
mov 8(%rsi),%rdx # arg2, disp->ImageBase
mov 0(%rsi),%r8 # arg3, disp->ControlPc
mov 16(%rsi),%r9 # arg4, disp->FunctionEntry
mov 40(%rsi),%r10 # disp->ContextRecord
lea 56(%rsi),%r11 # &disp->HandlerData
lea 24(%rsi),%r12 # &disp->EstablisherFrame
mov %r10,32(%rsp) # arg5
mov %r11,40(%rsp) # arg6
mov %r12,48(%rsp) # arg7
mov %rcx,56(%rsp) # arg8, (NULL)
call *__imp_RtlVirtualUnwind(%rip)
mov \$1,%eax # ExceptionContinueSearch
add \$64,%rsp
popfq
pop %r15
pop %r14
pop %r13
pop %r12
pop %rbp
pop %rbx
pop %rdi
pop %rsi
ret
.size sqr_handler,.-sqr_handler
.section .pdata
.align 4
.rva .LSEH_begin_bn_mul_mont
.rva .LSEH_end_bn_mul_mont
.rva .LSEH_info_bn_mul_mont
.rva .LSEH_begin_bn_mul4x_mont
.rva .LSEH_end_bn_mul4x_mont
.rva .LSEH_info_bn_mul4x_mont
.rva .LSEH_begin_bn_sqr8x_mont
.rva .LSEH_end_bn_sqr8x_mont
.rva .LSEH_info_bn_sqr8x_mont
___
$code.=<<___ if ($addx);
.rva .LSEH_begin_bn_mulx4x_mont
.rva .LSEH_end_bn_mulx4x_mont
.rva .LSEH_info_bn_mulx4x_mont
___
$code.=<<___;
.section .xdata
.align 8
.LSEH_info_bn_mul_mont:
.byte 9,0,0,0
.rva mul_handler
.rva .Lmul_body,.Lmul_epilogue # HandlerData[]
.LSEH_info_bn_mul4x_mont:
.byte 9,0,0,0
.rva mul_handler
.rva .Lmul4x_body,.Lmul4x_epilogue # HandlerData[]
.LSEH_info_bn_sqr8x_mont:
.byte 9,0,0,0
.rva sqr_handler
.rva .Lsqr8x_body,.Lsqr8x_epilogue # HandlerData[]
___
$code.=<<___ if ($addx);
.LSEH_info_bn_mulx4x_mont:
.byte 9,0,0,0
.rva sqr_handler
.rva .Lmulx4x_body,.Lmulx4x_epilogue # HandlerData[]
___
}
print $code;
close STDOUT;
|