forked from beagleboard/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathaesni-intel_asm.S
2783 lines (2583 loc) · 76.2 KB
/
aesni-intel_asm.S
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
/*
* Implement AES algorithm in Intel AES-NI instructions.
*
* The white paper of AES-NI instructions can be downloaded from:
* http://softwarecommunity.intel.com/isn/downloads/intelavx/AES-Instructions-Set_WP.pdf
*
* Copyright (C) 2008, Intel Corp.
* Author: Huang Ying <[email protected]>
* Vinodh Gopal <[email protected]>
* Kahraman Akdemir
*
* Added RFC4106 AES-GCM support for 128-bit keys under the AEAD
* interface for 64-bit kernels.
* Authors: Erdinc Ozturk ([email protected])
* Aidan O'Mahony ([email protected])
* Adrian Hoban <[email protected]>
* James Guilford ([email protected])
* Gabriele Paoloni <[email protected]>
* Tadeusz Struk ([email protected])
* Wajdi Feghali ([email protected])
* Copyright (c) 2010, Intel Corporation.
*
* Ported x86_64 version to x86:
* Author: Mathias Krause <[email protected]>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#include <linux/linkage.h>
#include <asm/inst.h>
/*
* The following macros are used to move an (un)aligned 16 byte value to/from
* an XMM register. This can done for either FP or integer values, for FP use
* movaps (move aligned packed single) or integer use movdqa (move double quad
* aligned). It doesn't make a performance difference which instruction is used
* since Nehalem (original Core i7) was released. However, the movaps is a byte
* shorter, so that is the one we'll use for now. (same for unaligned).
*/
#define MOVADQ movaps
#define MOVUDQ movups
#ifdef __x86_64__
.data
.align 16
.Lgf128mul_x_ble_mask:
.octa 0x00000000000000010000000000000087
POLY: .octa 0xC2000000000000000000000000000001
TWOONE: .octa 0x00000001000000000000000000000001
# order of these constants should not change.
# more specifically, ALL_F should follow SHIFT_MASK,
# and ZERO should follow ALL_F
SHUF_MASK: .octa 0x000102030405060708090A0B0C0D0E0F
MASK1: .octa 0x0000000000000000ffffffffffffffff
MASK2: .octa 0xffffffffffffffff0000000000000000
SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100
ALL_F: .octa 0xffffffffffffffffffffffffffffffff
ZERO: .octa 0x00000000000000000000000000000000
ONE: .octa 0x00000000000000000000000000000001
F_MIN_MASK: .octa 0xf1f2f3f4f5f6f7f8f9fafbfcfdfeff0
dec: .octa 0x1
enc: .octa 0x2
.text
#define STACK_OFFSET 8*3
#define HashKey 16*0 // store HashKey <<1 mod poly here
#define HashKey_2 16*1 // store HashKey^2 <<1 mod poly here
#define HashKey_3 16*2 // store HashKey^3 <<1 mod poly here
#define HashKey_4 16*3 // store HashKey^4 <<1 mod poly here
#define HashKey_k 16*4 // store XOR of High 64 bits and Low 64
// bits of HashKey <<1 mod poly here
//(for Karatsuba purposes)
#define HashKey_2_k 16*5 // store XOR of High 64 bits and Low 64
// bits of HashKey^2 <<1 mod poly here
// (for Karatsuba purposes)
#define HashKey_3_k 16*6 // store XOR of High 64 bits and Low 64
// bits of HashKey^3 <<1 mod poly here
// (for Karatsuba purposes)
#define HashKey_4_k 16*7 // store XOR of High 64 bits and Low 64
// bits of HashKey^4 <<1 mod poly here
// (for Karatsuba purposes)
#define VARIABLE_OFFSET 16*8
#define arg1 rdi
#define arg2 rsi
#define arg3 rdx
#define arg4 rcx
#define arg5 r8
#define arg6 r9
#define arg7 STACK_OFFSET+8(%r14)
#define arg8 STACK_OFFSET+16(%r14)
#define arg9 STACK_OFFSET+24(%r14)
#define arg10 STACK_OFFSET+32(%r14)
#define keysize 2*15*16(%arg1)
#endif
#define STATE1 %xmm0
#define STATE2 %xmm4
#define STATE3 %xmm5
#define STATE4 %xmm6
#define STATE STATE1
#define IN1 %xmm1
#define IN2 %xmm7
#define IN3 %xmm8
#define IN4 %xmm9
#define IN IN1
#define KEY %xmm2
#define IV %xmm3
#define BSWAP_MASK %xmm10
#define CTR %xmm11
#define INC %xmm12
#define GF128MUL_MASK %xmm10
#ifdef __x86_64__
#define AREG %rax
#define KEYP %rdi
#define OUTP %rsi
#define UKEYP OUTP
#define INP %rdx
#define LEN %rcx
#define IVP %r8
#define KLEN %r9d
#define T1 %r10
#define TKEYP T1
#define T2 %r11
#define TCTR_LOW T2
#else
#define AREG %eax
#define KEYP %edi
#define OUTP AREG
#define UKEYP OUTP
#define INP %edx
#define LEN %esi
#define IVP %ebp
#define KLEN %ebx
#define T1 %ecx
#define TKEYP T1
#endif
#ifdef __x86_64__
/* GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
*
*
* Input: A and B (128-bits each, bit-reflected)
* Output: C = A*B*x mod poly, (i.e. >>1 )
* To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
* GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
*
*/
.macro GHASH_MUL GH HK TMP1 TMP2 TMP3 TMP4 TMP5
movdqa \GH, \TMP1
pshufd $78, \GH, \TMP2
pshufd $78, \HK, \TMP3
pxor \GH, \TMP2 # TMP2 = a1+a0
pxor \HK, \TMP3 # TMP3 = b1+b0
PCLMULQDQ 0x11, \HK, \TMP1 # TMP1 = a1*b1
PCLMULQDQ 0x00, \HK, \GH # GH = a0*b0
PCLMULQDQ 0x00, \TMP3, \TMP2 # TMP2 = (a0+a1)*(b1+b0)
pxor \GH, \TMP2
pxor \TMP1, \TMP2 # TMP2 = (a0*b0)+(a1*b0)
movdqa \TMP2, \TMP3
pslldq $8, \TMP3 # left shift TMP3 2 DWs
psrldq $8, \TMP2 # right shift TMP2 2 DWs
pxor \TMP3, \GH
pxor \TMP2, \TMP1 # TMP2:GH holds the result of GH*HK
# first phase of the reduction
movdqa \GH, \TMP2
movdqa \GH, \TMP3
movdqa \GH, \TMP4 # copy GH into TMP2,TMP3 and TMP4
# in in order to perform
# independent shifts
pslld $31, \TMP2 # packed right shift <<31
pslld $30, \TMP3 # packed right shift <<30
pslld $25, \TMP4 # packed right shift <<25
pxor \TMP3, \TMP2 # xor the shifted versions
pxor \TMP4, \TMP2
movdqa \TMP2, \TMP5
psrldq $4, \TMP5 # right shift TMP5 1 DW
pslldq $12, \TMP2 # left shift TMP2 3 DWs
pxor \TMP2, \GH
# second phase of the reduction
movdqa \GH,\TMP2 # copy GH into TMP2,TMP3 and TMP4
# in in order to perform
# independent shifts
movdqa \GH,\TMP3
movdqa \GH,\TMP4
psrld $1,\TMP2 # packed left shift >>1
psrld $2,\TMP3 # packed left shift >>2
psrld $7,\TMP4 # packed left shift >>7
pxor \TMP3,\TMP2 # xor the shifted versions
pxor \TMP4,\TMP2
pxor \TMP5, \TMP2
pxor \TMP2, \GH
pxor \TMP1, \GH # result is in TMP1
.endm
/*
* if a = number of total plaintext bytes
* b = floor(a/16)
* num_initial_blocks = b mod 4
* encrypt the initial num_initial_blocks blocks and apply ghash on
* the ciphertext
* %r10, %r11, %r12, %rax, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers
* are clobbered
* arg1, %arg2, %arg3, %r14 are used as a pointer only, not modified
*/
.macro INITIAL_BLOCKS_DEC num_initial_blocks TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \
XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
MOVADQ SHUF_MASK(%rip), %xmm14
mov arg7, %r10 # %r10 = AAD
mov arg8, %r12 # %r12 = aadLen
mov %r12, %r11
pxor %xmm\i, %xmm\i
_get_AAD_loop\num_initial_blocks\operation:
movd (%r10), \TMP1
pslldq $12, \TMP1
psrldq $4, %xmm\i
pxor \TMP1, %xmm\i
add $4, %r10
sub $4, %r12
jne _get_AAD_loop\num_initial_blocks\operation
cmp $16, %r11
je _get_AAD_loop2_done\num_initial_blocks\operation
mov $16, %r12
_get_AAD_loop2\num_initial_blocks\operation:
psrldq $4, %xmm\i
sub $4, %r12
cmp %r11, %r12
jne _get_AAD_loop2\num_initial_blocks\operation
_get_AAD_loop2_done\num_initial_blocks\operation:
PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data
xor %r11, %r11 # initialise the data pointer offset as zero
# start AES for num_initial_blocks blocks
mov %arg5, %rax # %rax = *Y0
movdqu (%rax), \XMM0 # XMM0 = Y0
PSHUFB_XMM %xmm14, \XMM0
.if (\i == 5) || (\i == 6) || (\i == 7)
MOVADQ ONE(%RIP),\TMP1
MOVADQ (%arg1),\TMP2
.irpc index, \i_seq
paddd \TMP1, \XMM0 # INCR Y0
movdqa \XMM0, %xmm\index
PSHUFB_XMM %xmm14, %xmm\index # perform a 16 byte swap
pxor \TMP2, %xmm\index
.endr
lea 0x10(%arg1),%r10
mov keysize,%eax
shr $2,%eax # 128->4, 192->6, 256->8
add $5,%eax # 128->9, 192->11, 256->13
aes_loop_initial_dec\num_initial_blocks:
MOVADQ (%r10),\TMP1
.irpc index, \i_seq
AESENC \TMP1, %xmm\index
.endr
add $16,%r10
sub $1,%eax
jnz aes_loop_initial_dec\num_initial_blocks
MOVADQ (%r10), \TMP1
.irpc index, \i_seq
AESENCLAST \TMP1, %xmm\index # Last Round
.endr
.irpc index, \i_seq
movdqu (%arg3 , %r11, 1), \TMP1
pxor \TMP1, %xmm\index
movdqu %xmm\index, (%arg2 , %r11, 1)
# write back plaintext/ciphertext for num_initial_blocks
add $16, %r11
movdqa \TMP1, %xmm\index
PSHUFB_XMM %xmm14, %xmm\index
# prepare plaintext/ciphertext for GHASH computation
.endr
.endif
GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
# apply GHASH on num_initial_blocks blocks
.if \i == 5
pxor %xmm5, %xmm6
GHASH_MUL %xmm6, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
pxor %xmm6, %xmm7
GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
pxor %xmm7, %xmm8
GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.elseif \i == 6
pxor %xmm6, %xmm7
GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
pxor %xmm7, %xmm8
GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.elseif \i == 7
pxor %xmm7, %xmm8
GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.endif
cmp $64, %r13
jl _initial_blocks_done\num_initial_blocks\operation
# no need for precomputed values
/*
*
* Precomputations for HashKey parallel with encryption of first 4 blocks.
* Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
*/
MOVADQ ONE(%rip), \TMP1
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM1
PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM2
PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM3
PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM4
PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
MOVADQ 0(%arg1),\TMP1
pxor \TMP1, \XMM1
pxor \TMP1, \XMM2
pxor \TMP1, \XMM3
pxor \TMP1, \XMM4
movdqa \TMP3, \TMP5
pshufd $78, \TMP3, \TMP1
pxor \TMP3, \TMP1
movdqa \TMP1, HashKey_k(%rsp)
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^2<<1 (mod poly)
movdqa \TMP5, HashKey_2(%rsp)
# HashKey_2 = HashKey^2<<1 (mod poly)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
movdqa \TMP1, HashKey_2_k(%rsp)
.irpc index, 1234 # do 4 rounds
movaps 0x10*\index(%arg1), \TMP1
AESENC \TMP1, \XMM1
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
.endr
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
movdqa \TMP5, HashKey_3(%rsp)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
movdqa \TMP1, HashKey_3_k(%rsp)
.irpc index, 56789 # do next 5 rounds
movaps 0x10*\index(%arg1), \TMP1
AESENC \TMP1, \XMM1
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
.endr
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
movdqa \TMP5, HashKey_4(%rsp)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
movdqa \TMP1, HashKey_4_k(%rsp)
lea 0xa0(%arg1),%r10
mov keysize,%eax
shr $2,%eax # 128->4, 192->6, 256->8
sub $4,%eax # 128->0, 192->2, 256->4
jz aes_loop_pre_dec_done\num_initial_blocks
aes_loop_pre_dec\num_initial_blocks:
MOVADQ (%r10),\TMP2
.irpc index, 1234
AESENC \TMP2, %xmm\index
.endr
add $16,%r10
sub $1,%eax
jnz aes_loop_pre_dec\num_initial_blocks
aes_loop_pre_dec_done\num_initial_blocks:
MOVADQ (%r10), \TMP2
AESENCLAST \TMP2, \XMM1
AESENCLAST \TMP2, \XMM2
AESENCLAST \TMP2, \XMM3
AESENCLAST \TMP2, \XMM4
movdqu 16*0(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM1
movdqu \XMM1, 16*0(%arg2 , %r11 , 1)
movdqa \TMP1, \XMM1
movdqu 16*1(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM2
movdqu \XMM2, 16*1(%arg2 , %r11 , 1)
movdqa \TMP1, \XMM2
movdqu 16*2(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM3
movdqu \XMM3, 16*2(%arg2 , %r11 , 1)
movdqa \TMP1, \XMM3
movdqu 16*3(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM4
movdqu \XMM4, 16*3(%arg2 , %r11 , 1)
movdqa \TMP1, \XMM4
add $64, %r11
PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
pxor \XMMDst, \XMM1
# combine GHASHed value with the corresponding ciphertext
PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
_initial_blocks_done\num_initial_blocks\operation:
.endm
/*
* if a = number of total plaintext bytes
* b = floor(a/16)
* num_initial_blocks = b mod 4
* encrypt the initial num_initial_blocks blocks and apply ghash on
* the ciphertext
* %r10, %r11, %r12, %rax, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers
* are clobbered
* arg1, %arg2, %arg3, %r14 are used as a pointer only, not modified
*/
.macro INITIAL_BLOCKS_ENC num_initial_blocks TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \
XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation
MOVADQ SHUF_MASK(%rip), %xmm14
mov arg7, %r10 # %r10 = AAD
mov arg8, %r12 # %r12 = aadLen
mov %r12, %r11
pxor %xmm\i, %xmm\i
_get_AAD_loop\num_initial_blocks\operation:
movd (%r10), \TMP1
pslldq $12, \TMP1
psrldq $4, %xmm\i
pxor \TMP1, %xmm\i
add $4, %r10
sub $4, %r12
jne _get_AAD_loop\num_initial_blocks\operation
cmp $16, %r11
je _get_AAD_loop2_done\num_initial_blocks\operation
mov $16, %r12
_get_AAD_loop2\num_initial_blocks\operation:
psrldq $4, %xmm\i
sub $4, %r12
cmp %r11, %r12
jne _get_AAD_loop2\num_initial_blocks\operation
_get_AAD_loop2_done\num_initial_blocks\operation:
PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data
xor %r11, %r11 # initialise the data pointer offset as zero
# start AES for num_initial_blocks blocks
mov %arg5, %rax # %rax = *Y0
movdqu (%rax), \XMM0 # XMM0 = Y0
PSHUFB_XMM %xmm14, \XMM0
.if (\i == 5) || (\i == 6) || (\i == 7)
MOVADQ ONE(%RIP),\TMP1
MOVADQ 0(%arg1),\TMP2
.irpc index, \i_seq
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, %xmm\index
PSHUFB_XMM %xmm14, %xmm\index # perform a 16 byte swap
pxor \TMP2, %xmm\index
.endr
lea 0x10(%arg1),%r10
mov keysize,%eax
shr $2,%eax # 128->4, 192->6, 256->8
add $5,%eax # 128->9, 192->11, 256->13
aes_loop_initial_enc\num_initial_blocks:
MOVADQ (%r10),\TMP1
.irpc index, \i_seq
AESENC \TMP1, %xmm\index
.endr
add $16,%r10
sub $1,%eax
jnz aes_loop_initial_enc\num_initial_blocks
MOVADQ (%r10), \TMP1
.irpc index, \i_seq
AESENCLAST \TMP1, %xmm\index # Last Round
.endr
.irpc index, \i_seq
movdqu (%arg3 , %r11, 1), \TMP1
pxor \TMP1, %xmm\index
movdqu %xmm\index, (%arg2 , %r11, 1)
# write back plaintext/ciphertext for num_initial_blocks
add $16, %r11
PSHUFB_XMM %xmm14, %xmm\index
# prepare plaintext/ciphertext for GHASH computation
.endr
.endif
GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
# apply GHASH on num_initial_blocks blocks
.if \i == 5
pxor %xmm5, %xmm6
GHASH_MUL %xmm6, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
pxor %xmm6, %xmm7
GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
pxor %xmm7, %xmm8
GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.elseif \i == 6
pxor %xmm6, %xmm7
GHASH_MUL %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
pxor %xmm7, %xmm8
GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.elseif \i == 7
pxor %xmm7, %xmm8
GHASH_MUL %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.endif
cmp $64, %r13
jl _initial_blocks_done\num_initial_blocks\operation
# no need for precomputed values
/*
*
* Precomputations for HashKey parallel with encryption of first 4 blocks.
* Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
*/
MOVADQ ONE(%RIP),\TMP1
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM1
PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM2
PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM3
PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
paddd \TMP1, \XMM0 # INCR Y0
MOVADQ \XMM0, \XMM4
PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
MOVADQ 0(%arg1),\TMP1
pxor \TMP1, \XMM1
pxor \TMP1, \XMM2
pxor \TMP1, \XMM3
pxor \TMP1, \XMM4
movdqa \TMP3, \TMP5
pshufd $78, \TMP3, \TMP1
pxor \TMP3, \TMP1
movdqa \TMP1, HashKey_k(%rsp)
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^2<<1 (mod poly)
movdqa \TMP5, HashKey_2(%rsp)
# HashKey_2 = HashKey^2<<1 (mod poly)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
movdqa \TMP1, HashKey_2_k(%rsp)
.irpc index, 1234 # do 4 rounds
movaps 0x10*\index(%arg1), \TMP1
AESENC \TMP1, \XMM1
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
.endr
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
movdqa \TMP5, HashKey_3(%rsp)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
movdqa \TMP1, HashKey_3_k(%rsp)
.irpc index, 56789 # do next 5 rounds
movaps 0x10*\index(%arg1), \TMP1
AESENC \TMP1, \XMM1
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
.endr
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
movdqa \TMP5, HashKey_4(%rsp)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
movdqa \TMP1, HashKey_4_k(%rsp)
lea 0xa0(%arg1),%r10
mov keysize,%eax
shr $2,%eax # 128->4, 192->6, 256->8
sub $4,%eax # 128->0, 192->2, 256->4
jz aes_loop_pre_enc_done\num_initial_blocks
aes_loop_pre_enc\num_initial_blocks:
MOVADQ (%r10),\TMP2
.irpc index, 1234
AESENC \TMP2, %xmm\index
.endr
add $16,%r10
sub $1,%eax
jnz aes_loop_pre_enc\num_initial_blocks
aes_loop_pre_enc_done\num_initial_blocks:
MOVADQ (%r10), \TMP2
AESENCLAST \TMP2, \XMM1
AESENCLAST \TMP2, \XMM2
AESENCLAST \TMP2, \XMM3
AESENCLAST \TMP2, \XMM4
movdqu 16*0(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM1
movdqu 16*1(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM2
movdqu 16*2(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM3
movdqu 16*3(%arg3 , %r11 , 1), \TMP1
pxor \TMP1, \XMM4
movdqu \XMM1, 16*0(%arg2 , %r11 , 1)
movdqu \XMM2, 16*1(%arg2 , %r11 , 1)
movdqu \XMM3, 16*2(%arg2 , %r11 , 1)
movdqu \XMM4, 16*3(%arg2 , %r11 , 1)
add $64, %r11
PSHUFB_XMM %xmm14, \XMM1 # perform a 16 byte swap
pxor \XMMDst, \XMM1
# combine GHASHed value with the corresponding ciphertext
PSHUFB_XMM %xmm14, \XMM2 # perform a 16 byte swap
PSHUFB_XMM %xmm14, \XMM3 # perform a 16 byte swap
PSHUFB_XMM %xmm14, \XMM4 # perform a 16 byte swap
_initial_blocks_done\num_initial_blocks\operation:
.endm
/*
* encrypt 4 blocks at a time
* ghash the 4 previously encrypted ciphertext blocks
* arg1, %arg2, %arg3 are used as pointers only, not modified
* %r11 is the data offset value
*/
.macro GHASH_4_ENCRYPT_4_PARALLEL_ENC TMP1 TMP2 TMP3 TMP4 TMP5 \
TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM1, \XMM5
movdqa \XMM2, \XMM6
movdqa \XMM3, \XMM7
movdqa \XMM4, \XMM8
movdqa SHUF_MASK(%rip), %xmm15
# multiply TMP5 * HashKey using karatsuba
movdqa \XMM5, \TMP4
pshufd $78, \XMM5, \TMP6
pxor \XMM5, \TMP6
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa HashKey_4(%rsp), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1
movdqa \XMM0, \XMM1
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa \XMM0, \XMM2
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa \XMM0, \XMM3
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa \XMM0, \XMM4
PSHUFB_XMM %xmm15, \XMM1 # perform a 16 byte swap
PCLMULQDQ 0x00, \TMP5, \XMM5 # XMM5 = a0*b0
PSHUFB_XMM %xmm15, \XMM2 # perform a 16 byte swap
PSHUFB_XMM %xmm15, \XMM3 # perform a 16 byte swap
PSHUFB_XMM %xmm15, \XMM4 # perform a 16 byte swap
pxor (%arg1), \XMM1
pxor (%arg1), \XMM2
pxor (%arg1), \XMM3
pxor (%arg1), \XMM4
movdqa HashKey_4_k(%rsp), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0)
movaps 0x10(%arg1), \TMP1
AESENC \TMP1, \XMM1 # Round 1
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
movaps 0x20(%arg1), \TMP1
AESENC \TMP1, \XMM1 # Round 2
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
movdqa \XMM6, \TMP1
pshufd $78, \XMM6, \TMP2
pxor \XMM6, \TMP2
movdqa HashKey_3(%rsp), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1
movaps 0x30(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 3
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
PCLMULQDQ 0x00, \TMP5, \XMM6 # XMM6 = a0*b0
movaps 0x40(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 4
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
movdqa HashKey_3_k(%rsp), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x50(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 5
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
pxor \TMP1, \TMP4
# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
pxor \XMM6, \XMM5
pxor \TMP2, \TMP6
movdqa \XMM7, \TMP1
pshufd $78, \XMM7, \TMP2
pxor \XMM7, \TMP2
movdqa HashKey_2(%rsp ), \TMP5
# Multiply TMP5 * HashKey using karatsuba
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
movaps 0x60(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 6
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
PCLMULQDQ 0x00, \TMP5, \XMM7 # XMM7 = a0*b0
movaps 0x70(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 7
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
movdqa HashKey_2_k(%rsp), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x80(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 8
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
pxor \TMP1, \TMP4
# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
pxor \XMM7, \XMM5
pxor \TMP2, \TMP6
# Multiply XMM8 * HashKey
# XMM8 and TMP5 hold the values for the two operands
movdqa \XMM8, \TMP1
pshufd $78, \XMM8, \TMP2
pxor \XMM8, \TMP2
movdqa HashKey(%rsp), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
movaps 0x90(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 9
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
PCLMULQDQ 0x00, \TMP5, \XMM8 # XMM8 = a0*b0
lea 0xa0(%arg1),%r10
mov keysize,%eax
shr $2,%eax # 128->4, 192->6, 256->8
sub $4,%eax # 128->0, 192->2, 256->4
jz aes_loop_par_enc_done
aes_loop_par_enc:
MOVADQ (%r10),\TMP3
.irpc index, 1234
AESENC \TMP3, %xmm\index
.endr
add $16,%r10
sub $1,%eax
jnz aes_loop_par_enc
aes_loop_par_enc_done:
MOVADQ (%r10), \TMP3
AESENCLAST \TMP3, \XMM1 # Round 10
AESENCLAST \TMP3, \XMM2
AESENCLAST \TMP3, \XMM3
AESENCLAST \TMP3, \XMM4
movdqa HashKey_k(%rsp), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movdqu (%arg3,%r11,1), \TMP3
pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK
movdqu 16(%arg3,%r11,1), \TMP3
pxor \TMP3, \XMM2 # Ciphertext/Plaintext XOR EK
movdqu 32(%arg3,%r11,1), \TMP3
pxor \TMP3, \XMM3 # Ciphertext/Plaintext XOR EK
movdqu 48(%arg3,%r11,1), \TMP3
pxor \TMP3, \XMM4 # Ciphertext/Plaintext XOR EK
movdqu \XMM1, (%arg2,%r11,1) # Write to the ciphertext buffer
movdqu \XMM2, 16(%arg2,%r11,1) # Write to the ciphertext buffer
movdqu \XMM3, 32(%arg2,%r11,1) # Write to the ciphertext buffer
movdqu \XMM4, 48(%arg2,%r11,1) # Write to the ciphertext buffer
PSHUFB_XMM %xmm15, \XMM1 # perform a 16 byte swap
PSHUFB_XMM %xmm15, \XMM2 # perform a 16 byte swap
PSHUFB_XMM %xmm15, \XMM3 # perform a 16 byte swap
PSHUFB_XMM %xmm15, \XMM4 # perform a 16 byte swap
pxor \TMP4, \TMP1
pxor \XMM8, \XMM5
pxor \TMP6, \TMP2
pxor \TMP1, \TMP2
pxor \XMM5, \TMP2
movdqa \TMP2, \TMP3
pslldq $8, \TMP3 # left shift TMP3 2 DWs
psrldq $8, \TMP2 # right shift TMP2 2 DWs
pxor \TMP3, \XMM5
pxor \TMP2, \TMP1 # accumulate the results in TMP1:XMM5
# first phase of reduction
movdqa \XMM5, \TMP2
movdqa \XMM5, \TMP3
movdqa \XMM5, \TMP4
# move XMM5 into TMP2, TMP3, TMP4 in order to perform shifts independently
pslld $31, \TMP2 # packed right shift << 31
pslld $30, \TMP3 # packed right shift << 30
pslld $25, \TMP4 # packed right shift << 25
pxor \TMP3, \TMP2 # xor the shifted versions
pxor \TMP4, \TMP2
movdqa \TMP2, \TMP5
psrldq $4, \TMP5 # right shift T5 1 DW
pslldq $12, \TMP2 # left shift T2 3 DWs
pxor \TMP2, \XMM5
# second phase of reduction
movdqa \XMM5,\TMP2 # make 3 copies of XMM5 into TMP2, TMP3, TMP4
movdqa \XMM5,\TMP3
movdqa \XMM5,\TMP4
psrld $1, \TMP2 # packed left shift >>1
psrld $2, \TMP3 # packed left shift >>2
psrld $7, \TMP4 # packed left shift >>7
pxor \TMP3,\TMP2 # xor the shifted versions
pxor \TMP4,\TMP2
pxor \TMP5, \TMP2
pxor \TMP2, \XMM5
pxor \TMP1, \XMM5 # result is in TMP1
pxor \XMM5, \XMM1
.endm
/*
* decrypt 4 blocks at a time
* ghash the 4 previously decrypted ciphertext blocks
* arg1, %arg2, %arg3 are used as pointers only, not modified
* %r11 is the data offset value
*/
.macro GHASH_4_ENCRYPT_4_PARALLEL_DEC TMP1 TMP2 TMP3 TMP4 TMP5 \
TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM1, \XMM5
movdqa \XMM2, \XMM6
movdqa \XMM3, \XMM7
movdqa \XMM4, \XMM8
movdqa SHUF_MASK(%rip), %xmm15
# multiply TMP5 * HashKey using karatsuba
movdqa \XMM5, \TMP4
pshufd $78, \XMM5, \TMP6
pxor \XMM5, \TMP6
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa HashKey_4(%rsp), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1
movdqa \XMM0, \XMM1
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa \XMM0, \XMM2
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa \XMM0, \XMM3
paddd ONE(%rip), \XMM0 # INCR CNT
movdqa \XMM0, \XMM4
PSHUFB_XMM %xmm15, \XMM1 # perform a 16 byte swap
PCLMULQDQ 0x00, \TMP5, \XMM5 # XMM5 = a0*b0
PSHUFB_XMM %xmm15, \XMM2 # perform a 16 byte swap
PSHUFB_XMM %xmm15, \XMM3 # perform a 16 byte swap
PSHUFB_XMM %xmm15, \XMM4 # perform a 16 byte swap
pxor (%arg1), \XMM1
pxor (%arg1), \XMM2
pxor (%arg1), \XMM3
pxor (%arg1), \XMM4
movdqa HashKey_4_k(%rsp), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0)
movaps 0x10(%arg1), \TMP1
AESENC \TMP1, \XMM1 # Round 1
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
movaps 0x20(%arg1), \TMP1
AESENC \TMP1, \XMM1 # Round 2
AESENC \TMP1, \XMM2
AESENC \TMP1, \XMM3
AESENC \TMP1, \XMM4
movdqa \XMM6, \TMP1
pshufd $78, \XMM6, \TMP2
pxor \XMM6, \TMP2
movdqa HashKey_3(%rsp), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1
movaps 0x30(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 3
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
PCLMULQDQ 0x00, \TMP5, \XMM6 # XMM6 = a0*b0
movaps 0x40(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 4
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
movdqa HashKey_3_k(%rsp), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x50(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 5
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
pxor \TMP1, \TMP4
# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
pxor \XMM6, \XMM5
pxor \TMP2, \TMP6
movdqa \XMM7, \TMP1
pshufd $78, \XMM7, \TMP2
pxor \XMM7, \TMP2
movdqa HashKey_2(%rsp ), \TMP5
# Multiply TMP5 * HashKey using karatsuba
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
movaps 0x60(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 6
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
PCLMULQDQ 0x00, \TMP5, \XMM7 # XMM7 = a0*b0
movaps 0x70(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 7
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
movdqa HashKey_2_k(%rsp), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x80(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 8
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
pxor \TMP1, \TMP4
# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
pxor \XMM7, \XMM5
pxor \TMP2, \TMP6
# Multiply XMM8 * HashKey
# XMM8 and TMP5 hold the values for the two operands
movdqa \XMM8, \TMP1
pshufd $78, \XMM8, \TMP2
pxor \XMM8, \TMP2
movdqa HashKey(%rsp), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
movaps 0x90(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 9
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
PCLMULQDQ 0x00, \TMP5, \XMM8 # XMM8 = a0*b0
lea 0xa0(%arg1),%r10
mov keysize,%eax
shr $2,%eax # 128->4, 192->6, 256->8
sub $4,%eax # 128->0, 192->2, 256->4
jz aes_loop_par_dec_done
aes_loop_par_dec:
MOVADQ (%r10),\TMP3
.irpc index, 1234
AESENC \TMP3, %xmm\index
.endr
add $16,%r10
sub $1,%eax