summaryrefslogtreecommitdiff
path: root/main/openssl/crypto/sha/asm/sha1-armv8.pl
blob: c1f552b6b3d6de78f6b9eea68087754234f07e4f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
#!/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/.
# ====================================================================
#
# SHA1 for ARMv8.
#
# Performance in cycles per processed byte and improvement coefficient
# over code generated with "default" compiler:
#
#		hardware-assisted	software(*)
# Apple A7	2.31			4.13 (+14%)
# Cortex-A5x	n/a			n/a
#
# (*)	Software results are presented mostly for reference purposes.

$flavour = shift;
open STDOUT,">".shift;

($ctx,$inp,$num)=("x0","x1","x2");
@Xw=map("w$_",(3..17,19));
@Xx=map("x$_",(3..17,19));
@V=($A,$B,$C,$D,$E)=map("w$_",(20..24));
($t0,$t1,$t2,$K)=map("w$_",(25..28));


sub BODY_00_19 {
my ($i,$a,$b,$c,$d,$e)=@_;
my $j=($i+2)&15;

$code.=<<___ if ($i<15 && !($i&1));
	lsr	@Xx[$i+1],@Xx[$i],#32
___
$code.=<<___ if ($i<14 && !($i&1));
	ldr	@Xx[$i+2],[$inp,#`($i+2)*4-64`]
___
$code.=<<___ if ($i<14 && ($i&1));
#ifdef	__ARMEB__
	ror	@Xx[$i+1],@Xx[$i+1],#32
#else
	rev32	@Xx[$i+1],@Xx[$i+1]
#endif
___
$code.=<<___ if ($i<14);
	bic	$t0,$d,$b
	and	$t1,$c,$b
	ror	$t2,$a,#27
	add	$d,$d,$K		// future e+=K
	orr	$t0,$t0,$t1
	add	$e,$e,$t2		// e+=rot(a,5)
	ror	$b,$b,#2
	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
	add	$e,$e,$t0		// e+=F(b,c,d)
___
$code.=<<___ if ($i==19);
	movz	$K,#0xeba1
	movk	$K,#0x6ed9,lsl#16
___
$code.=<<___ if ($i>=14);
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+2)&15]
	bic	$t0,$d,$b
	and	$t1,$c,$b
	ror	$t2,$a,#27
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+8)&15]
	add	$d,$d,$K		// future e+=K
	orr	$t0,$t0,$t1
	add	$e,$e,$t2		// e+=rot(a,5)
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+13)&15]
	ror	$b,$b,#2
	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
	add	$e,$e,$t0		// e+=F(b,c,d)
	 ror	@Xw[$j],@Xw[$j],#31
___
}

sub BODY_40_59 {
my ($i,$a,$b,$c,$d,$e)=@_;
my $j=($i+2)&15;

$code.=<<___ if ($i==59);
	movz	$K,#0xc1d6
	movk	$K,#0xca62,lsl#16
___
$code.=<<___;
	orr	$t0,$b,$c
	and	$t1,$b,$c
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+2)&15]
	ror	$t2,$a,#27
	and	$t0,$t0,$d
	add	$d,$d,$K		// future e+=K
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+8)&15]
	add	$e,$e,$t2		// e+=rot(a,5)
	orr	$t0,$t0,$t1
	ror	$b,$b,#2
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+13)&15]
	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
	add	$e,$e,$t0		// e+=F(b,c,d)
	 ror	@Xw[$j],@Xw[$j],#31
___
}

sub BODY_20_39 {
my ($i,$a,$b,$c,$d,$e)=@_;
my $j=($i+2)&15;

$code.=<<___ if ($i==39);
	movz	$K,#0xbcdc
	movk	$K,#0x8f1b,lsl#16
___
$code.=<<___ if ($i<78);
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+2)&15]
	eor	$t0,$d,$b
	ror	$t2,$a,#27
	add	$d,$d,$K		// future e+=K
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+8)&15]
	eor	$t0,$t0,$c
	add	$e,$e,$t2		// e+=rot(a,5)
	ror	$b,$b,#2
	 eor	@Xw[$j],@Xw[$j],@Xw[($j+13)&15]
	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
	add	$e,$e,$t0		// e+=F(b,c,d)
	 ror	@Xw[$j],@Xw[$j],#31
___
$code.=<<___ if ($i==78);
	ldp	@Xw[1],@Xw[2],[$ctx]
	eor	$t0,$d,$b
	ror	$t2,$a,#27
	add	$d,$d,$K		// future e+=K
	eor	$t0,$t0,$c
	add	$e,$e,$t2		// e+=rot(a,5)
	ror	$b,$b,#2
	add	$d,$d,@Xw[($i+1)&15]	// future e+=X[i]
	add	$e,$e,$t0		// e+=F(b,c,d)
___
$code.=<<___ if ($i==79);
	ldp	@Xw[3],@Xw[4],[$ctx,#8]
	eor	$t0,$d,$b
	ror	$t2,$a,#27
	eor	$t0,$t0,$c
	add	$e,$e,$t2		// e+=rot(a,5)
	ror	$b,$b,#2
	ldr	@Xw[5],[$ctx,#16]
	add	$e,$e,$t0		// e+=F(b,c,d)
___
}

$code.=<<___;
#include "arm_arch.h"

.text

.globl	sha1_block_data_order
.type	sha1_block_data_order,%function
.align	6
sha1_block_data_order:
	ldr	x16,.LOPENSSL_armcap_P
	adr	x17,.LOPENSSL_armcap_P
	add	x16,x16,x17
	ldr	w16,[x16]
	tst	w16,#ARMV8_SHA1
	b.ne	.Lv8_entry

	stp	x29,x30,[sp,#-96]!
	add	x29,sp,#0
	stp	x19,x20,[sp,#16]
	stp	x21,x22,[sp,#32]
	stp	x23,x24,[sp,#48]
	stp	x25,x26,[sp,#64]
	stp	x27,x28,[sp,#80]

	ldp	$A,$B,[$ctx]
	ldp	$C,$D,[$ctx,#8]
	ldr	$E,[$ctx,#16]

.Loop:
	ldr	@Xx[0],[$inp],#64
	movz	$K,#0x7999
	sub	$num,$num,#1
	movk	$K,#0x5a82,lsl#16
#ifdef	__ARMEB__
	ror	$Xx[0],@Xx[0],#32
#else
	rev32	@Xx[0],@Xx[0]
#endif
	add	$E,$E,$K		// warm it up
	add	$E,$E,@Xw[0]
___
for($i=0;$i<20;$i++)	{ &BODY_00_19($i,@V); unshift(@V,pop(@V)); }
for(;$i<40;$i++)	{ &BODY_20_39($i,@V); unshift(@V,pop(@V)); }
for(;$i<60;$i++)	{ &BODY_40_59($i,@V); unshift(@V,pop(@V)); }
for(;$i<80;$i++)	{ &BODY_20_39($i,@V); unshift(@V,pop(@V)); }
$code.=<<___;
	add	$B,$B,@Xw[2]
	add	$C,$C,@Xw[3]
	add	$A,$A,@Xw[1]
	add	$D,$D,@Xw[4]
	add	$E,$E,@Xw[5]
	stp	$A,$B,[$ctx]
	stp	$C,$D,[$ctx,#8]
	str	$E,[$ctx,#16]
	cbnz	$num,.Loop

	ldp	x19,x20,[sp,#16]
	ldp	x21,x22,[sp,#32]
	ldp	x23,x24,[sp,#48]
	ldp	x25,x26,[sp,#64]
	ldp	x27,x28,[sp,#80]
	ldr	x29,[sp],#96
	ret
.size	sha1_block_data_order,.-sha1_block_data_order
___
{{{
my ($ABCD,$E,$E0,$E1)=map("v$_.16b",(0..3));
my @MSG=map("v$_.16b",(4..7));
my @Kxx=map("v$_.4s",(16..19));
my ($W0,$W1)=("v20.4s","v21.4s");
my $ABCD_SAVE="v22.16b";

$code.=<<___;
.type	sha1_block_armv8,%function
.align	6
sha1_block_armv8:
.Lv8_entry:
	stp	x29,x30,[sp,#-16]!
	add	x29,sp,#0

	adr	x4,.Lconst
	eor	$E,$E,$E
	ld1.32	{$ABCD},[$ctx],#16
	ld1.32	{$E}[0],[$ctx]
	sub	$ctx,$ctx,#16
	ld1.32	{@Kxx[0]-@Kxx[3]},[x4]

.Loop_hw:
	ld1	{@MSG[0]-@MSG[3]},[$inp],#64
	sub	$num,$num,#1
	rev32	@MSG[0],@MSG[0]
	rev32	@MSG[1],@MSG[1]

	add.i32	$W0,@Kxx[0],@MSG[0]
	rev32	@MSG[2],@MSG[2]
	orr	$ABCD_SAVE,$ABCD,$ABCD	// offload

	add.i32	$W1,@Kxx[0],@MSG[1]
	rev32	@MSG[3],@MSG[3]
	sha1h	$E1,$ABCD
	sha1c	$ABCD,$E,$W0		// 0
	add.i32	$W0,@Kxx[$j],@MSG[2]
	sha1su0	@MSG[0],@MSG[1],@MSG[2]
___
for ($j=0,$i=1;$i<20-3;$i++) {
my $f=("c","p","m","p")[$i/5];
$code.=<<___;
	sha1h	$E0,$ABCD		// $i
	sha1$f	$ABCD,$E1,$W1
	add.i32	$W1,@Kxx[$j],@MSG[3]
	sha1su1	@MSG[0],@MSG[3]
___
$code.=<<___ if ($i<20-4);
	sha1su0	@MSG[1],@MSG[2],@MSG[3]
___
	($E0,$E1)=($E1,$E0);		($W0,$W1)=($W1,$W0);
	push(@MSG,shift(@MSG));		$j++ if ((($i+3)%5)==0);
}
$code.=<<___;
	sha1h	$E0,$ABCD		// $i
	sha1p	$ABCD,$E1,$W1
	add.i32	$W1,@Kxx[$j],@MSG[3]

	sha1h	$E1,$ABCD		// 18
	sha1p	$ABCD,$E0,$W0

	sha1h	$E0,$ABCD		// 19
	sha1p	$ABCD,$E1,$W1

	add.i32	$E,$E,$E0
	add.i32	$ABCD,$ABCD,$ABCD_SAVE

	cbnz	$num,.Loop_hw

	st1.32	{$ABCD},[$ctx],#16
	st1.32	{$E}[0],[$ctx]

	ldr	x29,[sp],#16
	ret
.size	sha1_block_armv8,.-sha1_block_armv8
.align	6
.Lconst:
.long	0x5a827999,0x5a827999,0x5a827999,0x5a827999	//K_00_19
.long	0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1	//K_20_39
.long	0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc	//K_40_59
.long	0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6	//K_60_79
.LOPENSSL_armcap_P:
.quad	OPENSSL_armcap_P-.
.asciz	"SHA1 block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
.align	2
.comm	OPENSSL_armcap_P,4,4
___
}}}

{   my	%opcode = (
	"sha1c"		=> 0x5e000000,	"sha1p"		=> 0x5e001000,
	"sha1m"		=> 0x5e002000,	"sha1su0"	=> 0x5e003000,
	"sha1h"		=> 0x5e280800,	"sha1su1"	=> 0x5e281800	);

    sub unsha1 {
	my ($mnemonic,$arg)=@_;

	$arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)[^,]*(?:,\s*[qv]([0-9]+))?/o
	&&
	sprintf ".inst\t0x%08x\t//%s %s",
			$opcode{$mnemonic}|$1|($2<<5)|($3<<16),
			$mnemonic,$arg;
    }
}

foreach(split("\n",$code)) {

	s/\`([^\`]*)\`/eval($1)/geo;

	s/\b(sha1\w+)\s+([qv].*)/unsha1($1,$2)/geo;

	s/\.\w?32\b//o		and s/\.16b/\.4s/go;
	m/(ld|st)1[^\[]+\[0\]/o	and s/\.4s/\.s/go;

	print $_,"\n";
}

close STDOUT;