Index: stable/11/crypto/openssl/crypto/aes/asm/aesv8-armx.pl =================================================================== --- stable/11/crypto/openssl/crypto/aes/asm/aesv8-armx.pl (revision 325332) +++ stable/11/crypto/openssl/crypto/aes/asm/aesv8-armx.pl (revision 325333) @@ -1,989 +1,989 @@ #!/usr/bin/env perl # # ==================================================================== # Written by Andy Polyakov 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/. # ==================================================================== # # This module implements support for ARMv8 AES instructions. The # module is endian-agnostic in sense that it supports both big- and # little-endian cases. As does it support both 32- and 64-bit modes # of operation. Latter is achieved by limiting amount of utilized # registers to 16, which implies additional NEON load and integer # instructions. This has no effect on mighty Apple A7, where results # are literally equal to the theoretical estimates based on AES # instruction latencies and issue rates. On Cortex-A53, an in-order # execution core, this costs up to 10-15%, which is partially # compensated by implementing dedicated code path for 128-bit # CBC encrypt case. On Cortex-A57 parallelizable mode performance # seems to be limited by sheer amount of NEON instructions... # # Performance in cycles per byte processed with 128-bit key: # # CBC enc CBC dec CTR # Apple A7 2.39 1.20 1.20 # Cortex-A53 1.32 1.29 1.46 # Cortex-A57(*) 1.95 0.85 0.93 # Denver 1.96 0.86 0.80 # # (*) original 3.64/1.34/1.32 results were for r0p0 revision # and are still same even for updated module; $flavour = shift; open STDOUT,">".shift; $prefix="aes_v8"; $code=<<___; #include "arm_arch.h" #if __ARM_MAX_ARCH__>=7 .text ___ -$code.=".arch armv8-a+crypto\n" if ($flavour =~ /64/); +# $code.=".arch armv8-a+crypto\n" if ($flavour =~ /64/); $code.=".arch armv7-a\n.fpu neon\n.code 32\n" if ($flavour !~ /64/); #^^^^^^ this is done to simplify adoption by not depending # on latest binutils. # Assembler mnemonics are an eclectic mix of 32- and 64-bit syntax, # NEON is mostly 32-bit mnemonics, integer - mostly 64. Goal is to # maintain both 32- and 64-bit codes within single module and # transliterate common code to either flavour with regex vodoo. # {{{ my ($inp,$bits,$out,$ptr,$rounds)=("x0","w1","x2","x3","w12"); my ($zero,$rcon,$mask,$in0,$in1,$tmp,$key)= $flavour=~/64/? map("q$_",(0..6)) : map("q$_",(0..3,8..10)); $code.=<<___; .align 5 rcon: .long 0x01,0x01,0x01,0x01 .long 0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d // rotate-n-splat .long 0x1b,0x1b,0x1b,0x1b .globl ${prefix}_set_encrypt_key .type ${prefix}_set_encrypt_key,%function .align 5 ${prefix}_set_encrypt_key: .Lenc_key: ___ $code.=<<___ if ($flavour =~ /64/); stp x29,x30,[sp,#-16]! add x29,sp,#0 ___ $code.=<<___; mov $ptr,#-1 cmp $inp,#0 b.eq .Lenc_key_abort cmp $out,#0 b.eq .Lenc_key_abort mov $ptr,#-2 cmp $bits,#128 b.lt .Lenc_key_abort cmp $bits,#256 b.gt .Lenc_key_abort tst $bits,#0x3f b.ne .Lenc_key_abort adr $ptr,rcon cmp $bits,#192 veor $zero,$zero,$zero vld1.8 {$in0},[$inp],#16 mov $bits,#8 // reuse $bits vld1.32 {$rcon,$mask},[$ptr],#32 b.lt .Loop128 b.eq .L192 b .L256 .align 4 .Loop128: vtbl.8 $key,{$in0},$mask vext.8 $tmp,$zero,$in0,#12 vst1.32 {$in0},[$out],#16 aese $key,$zero subs $bits,$bits,#1 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $key,$key,$rcon veor $in0,$in0,$tmp vshl.u8 $rcon,$rcon,#1 veor $in0,$in0,$key b.ne .Loop128 vld1.32 {$rcon},[$ptr] vtbl.8 $key,{$in0},$mask vext.8 $tmp,$zero,$in0,#12 vst1.32 {$in0},[$out],#16 aese $key,$zero veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $key,$key,$rcon veor $in0,$in0,$tmp vshl.u8 $rcon,$rcon,#1 veor $in0,$in0,$key vtbl.8 $key,{$in0},$mask vext.8 $tmp,$zero,$in0,#12 vst1.32 {$in0},[$out],#16 aese $key,$zero veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $key,$key,$rcon veor $in0,$in0,$tmp veor $in0,$in0,$key vst1.32 {$in0},[$out] add $out,$out,#0x50 mov $rounds,#10 b .Ldone .align 4 .L192: vld1.8 {$in1},[$inp],#8 vmov.i8 $key,#8 // borrow $key vst1.32 {$in0},[$out],#16 vsub.i8 $mask,$mask,$key // adjust the mask .Loop192: vtbl.8 $key,{$in1},$mask vext.8 $tmp,$zero,$in0,#12 vst1.32 {$in1},[$out],#8 aese $key,$zero subs $bits,$bits,#1 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in0,$in0,$tmp vdup.32 $tmp,${in0}[3] veor $tmp,$tmp,$in1 veor $key,$key,$rcon vext.8 $in1,$zero,$in1,#12 vshl.u8 $rcon,$rcon,#1 veor $in1,$in1,$tmp veor $in0,$in0,$key veor $in1,$in1,$key vst1.32 {$in0},[$out],#16 b.ne .Loop192 mov $rounds,#12 add $out,$out,#0x20 b .Ldone .align 4 .L256: vld1.8 {$in1},[$inp] mov $bits,#7 mov $rounds,#14 vst1.32 {$in0},[$out],#16 .Loop256: vtbl.8 $key,{$in1},$mask vext.8 $tmp,$zero,$in0,#12 vst1.32 {$in1},[$out],#16 aese $key,$zero subs $bits,$bits,#1 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in0,$in0,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $key,$key,$rcon veor $in0,$in0,$tmp vshl.u8 $rcon,$rcon,#1 veor $in0,$in0,$key vst1.32 {$in0},[$out],#16 b.eq .Ldone vdup.32 $key,${in0}[3] // just splat vext.8 $tmp,$zero,$in1,#12 aese $key,$zero veor $in1,$in1,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in1,$in1,$tmp vext.8 $tmp,$zero,$tmp,#12 veor $in1,$in1,$tmp veor $in1,$in1,$key b .Loop256 .Ldone: str $rounds,[$out] mov $ptr,#0 .Lenc_key_abort: mov x0,$ptr // return value `"ldr x29,[sp],#16" if ($flavour =~ /64/)` ret .size ${prefix}_set_encrypt_key,.-${prefix}_set_encrypt_key .globl ${prefix}_set_decrypt_key .type ${prefix}_set_decrypt_key,%function .align 5 ${prefix}_set_decrypt_key: ___ $code.=<<___ if ($flavour =~ /64/); stp x29,x30,[sp,#-16]! add x29,sp,#0 ___ $code.=<<___ if ($flavour !~ /64/); stmdb sp!,{r4,lr} ___ $code.=<<___; bl .Lenc_key cmp x0,#0 b.ne .Ldec_key_abort sub $out,$out,#240 // restore original $out mov x4,#-16 add $inp,$out,x12,lsl#4 // end of key schedule vld1.32 {v0.16b},[$out] vld1.32 {v1.16b},[$inp] vst1.32 {v0.16b},[$inp],x4 vst1.32 {v1.16b},[$out],#16 .Loop_imc: vld1.32 {v0.16b},[$out] vld1.32 {v1.16b},[$inp] aesimc v0.16b,v0.16b aesimc v1.16b,v1.16b vst1.32 {v0.16b},[$inp],x4 vst1.32 {v1.16b},[$out],#16 cmp $inp,$out b.hi .Loop_imc vld1.32 {v0.16b},[$out] aesimc v0.16b,v0.16b vst1.32 {v0.16b},[$inp] eor x0,x0,x0 // return value .Ldec_key_abort: ___ $code.=<<___ if ($flavour !~ /64/); ldmia sp!,{r4,pc} ___ $code.=<<___ if ($flavour =~ /64/); ldp x29,x30,[sp],#16 ret ___ $code.=<<___; .size ${prefix}_set_decrypt_key,.-${prefix}_set_decrypt_key ___ }}} {{{ sub gen_block () { my $dir = shift; my ($e,$mc) = $dir eq "en" ? ("e","mc") : ("d","imc"); my ($inp,$out,$key)=map("x$_",(0..2)); my $rounds="w3"; my ($rndkey0,$rndkey1,$inout)=map("q$_",(0..3)); $code.=<<___; .globl ${prefix}_${dir}crypt .type ${prefix}_${dir}crypt,%function .align 5 ${prefix}_${dir}crypt: ldr $rounds,[$key,#240] vld1.32 {$rndkey0},[$key],#16 vld1.8 {$inout},[$inp] sub $rounds,$rounds,#2 vld1.32 {$rndkey1},[$key],#16 .Loop_${dir}c: aes$e $inout,$rndkey0 aes$mc $inout,$inout vld1.32 {$rndkey0},[$key],#16 subs $rounds,$rounds,#2 aes$e $inout,$rndkey1 aes$mc $inout,$inout vld1.32 {$rndkey1},[$key],#16 b.gt .Loop_${dir}c aes$e $inout,$rndkey0 aes$mc $inout,$inout vld1.32 {$rndkey0},[$key] aes$e $inout,$rndkey1 veor $inout,$inout,$rndkey0 vst1.8 {$inout},[$out] ret .size ${prefix}_${dir}crypt,.-${prefix}_${dir}crypt ___ } &gen_block("en"); &gen_block("de"); }}} {{{ my ($inp,$out,$len,$key,$ivp)=map("x$_",(0..4)); my $enc="w5"; my ($rounds,$cnt,$key_,$step,$step1)=($enc,"w6","x7","x8","x12"); my ($dat0,$dat1,$in0,$in1,$tmp0,$tmp1,$ivec,$rndlast)=map("q$_",(0..7)); my ($dat,$tmp,$rndzero_n_last)=($dat0,$tmp0,$tmp1); my ($key4,$key5,$key6,$key7)=("x6","x12","x14",$key); ### q8-q15 preloaded key schedule $code.=<<___; .globl ${prefix}_cbc_encrypt .type ${prefix}_cbc_encrypt,%function .align 5 ${prefix}_cbc_encrypt: ___ $code.=<<___ if ($flavour =~ /64/); stp x29,x30,[sp,#-16]! add x29,sp,#0 ___ $code.=<<___ if ($flavour !~ /64/); mov ip,sp stmdb sp!,{r4-r8,lr} vstmdb sp!,{d8-d15} @ ABI specification says so ldmia ip,{r4-r5} @ load remaining args ___ $code.=<<___; subs $len,$len,#16 mov $step,#16 b.lo .Lcbc_abort cclr $step,eq cmp $enc,#0 // en- or decrypting? ldr $rounds,[$key,#240] and $len,$len,#-16 vld1.8 {$ivec},[$ivp] vld1.8 {$dat},[$inp],$step vld1.32 {q8-q9},[$key] // load key schedule... sub $rounds,$rounds,#6 add $key_,$key,x5,lsl#4 // pointer to last 7 round keys sub $rounds,$rounds,#2 vld1.32 {q10-q11},[$key_],#32 vld1.32 {q12-q13},[$key_],#32 vld1.32 {q14-q15},[$key_],#32 vld1.32 {$rndlast},[$key_] add $key_,$key,#32 mov $cnt,$rounds b.eq .Lcbc_dec cmp $rounds,#2 veor $dat,$dat,$ivec veor $rndzero_n_last,q8,$rndlast b.eq .Lcbc_enc128 vld1.32 {$in0-$in1},[$key_] add $key_,$key,#16 add $key4,$key,#16*4 add $key5,$key,#16*5 aese $dat,q8 aesmc $dat,$dat add $key6,$key,#16*6 add $key7,$key,#16*7 b .Lenter_cbc_enc .align 4 .Loop_cbc_enc: aese $dat,q8 aesmc $dat,$dat vst1.8 {$ivec},[$out],#16 .Lenter_cbc_enc: aese $dat,q9 aesmc $dat,$dat aese $dat,$in0 aesmc $dat,$dat vld1.32 {q8},[$key4] cmp $rounds,#4 aese $dat,$in1 aesmc $dat,$dat vld1.32 {q9},[$key5] b.eq .Lcbc_enc192 aese $dat,q8 aesmc $dat,$dat vld1.32 {q8},[$key6] aese $dat,q9 aesmc $dat,$dat vld1.32 {q9},[$key7] nop .Lcbc_enc192: aese $dat,q8 aesmc $dat,$dat subs $len,$len,#16 aese $dat,q9 aesmc $dat,$dat cclr $step,eq aese $dat,q10 aesmc $dat,$dat aese $dat,q11 aesmc $dat,$dat vld1.8 {q8},[$inp],$step aese $dat,q12 aesmc $dat,$dat veor q8,q8,$rndzero_n_last aese $dat,q13 aesmc $dat,$dat vld1.32 {q9},[$key_] // re-pre-load rndkey[1] aese $dat,q14 aesmc $dat,$dat aese $dat,q15 veor $ivec,$dat,$rndlast b.hs .Loop_cbc_enc vst1.8 {$ivec},[$out],#16 b .Lcbc_done .align 5 .Lcbc_enc128: vld1.32 {$in0-$in1},[$key_] aese $dat,q8 aesmc $dat,$dat b .Lenter_cbc_enc128 .Loop_cbc_enc128: aese $dat,q8 aesmc $dat,$dat vst1.8 {$ivec},[$out],#16 .Lenter_cbc_enc128: aese $dat,q9 aesmc $dat,$dat subs $len,$len,#16 aese $dat,$in0 aesmc $dat,$dat cclr $step,eq aese $dat,$in1 aesmc $dat,$dat aese $dat,q10 aesmc $dat,$dat aese $dat,q11 aesmc $dat,$dat vld1.8 {q8},[$inp],$step aese $dat,q12 aesmc $dat,$dat aese $dat,q13 aesmc $dat,$dat aese $dat,q14 aesmc $dat,$dat veor q8,q8,$rndzero_n_last aese $dat,q15 veor $ivec,$dat,$rndlast b.hs .Loop_cbc_enc128 vst1.8 {$ivec},[$out],#16 b .Lcbc_done ___ { my ($dat2,$in2,$tmp2)=map("q$_",(10,11,9)); $code.=<<___; .align 5 .Lcbc_dec: vld1.8 {$dat2},[$inp],#16 subs $len,$len,#32 // bias add $cnt,$rounds,#2 vorr $in1,$dat,$dat vorr $dat1,$dat,$dat vorr $in2,$dat2,$dat2 b.lo .Lcbc_dec_tail vorr $dat1,$dat2,$dat2 vld1.8 {$dat2},[$inp],#16 vorr $in0,$dat,$dat vorr $in1,$dat1,$dat1 vorr $in2,$dat2,$dat2 .Loop3x_cbc_dec: aesd $dat0,q8 aesimc $dat0,$dat0 aesd $dat1,q8 aesimc $dat1,$dat1 aesd $dat2,q8 aesimc $dat2,$dat2 vld1.32 {q8},[$key_],#16 subs $cnt,$cnt,#2 aesd $dat0,q9 aesimc $dat0,$dat0 aesd $dat1,q9 aesimc $dat1,$dat1 aesd $dat2,q9 aesimc $dat2,$dat2 vld1.32 {q9},[$key_],#16 b.gt .Loop3x_cbc_dec aesd $dat0,q8 aesimc $dat0,$dat0 aesd $dat1,q8 aesimc $dat1,$dat1 aesd $dat2,q8 aesimc $dat2,$dat2 veor $tmp0,$ivec,$rndlast subs $len,$len,#0x30 veor $tmp1,$in0,$rndlast mov.lo x6,$len // x6, $cnt, is zero at this point aesd $dat0,q9 aesimc $dat0,$dat0 aesd $dat1,q9 aesimc $dat1,$dat1 aesd $dat2,q9 aesimc $dat2,$dat2 veor $tmp2,$in1,$rndlast add $inp,$inp,x6 // $inp is adjusted in such way that // at exit from the loop $dat1-$dat2 // are loaded with last "words" vorr $ivec,$in2,$in2 mov $key_,$key aesd $dat0,q12 aesimc $dat0,$dat0 aesd $dat1,q12 aesimc $dat1,$dat1 aesd $dat2,q12 aesimc $dat2,$dat2 vld1.8 {$in0},[$inp],#16 aesd $dat0,q13 aesimc $dat0,$dat0 aesd $dat1,q13 aesimc $dat1,$dat1 aesd $dat2,q13 aesimc $dat2,$dat2 vld1.8 {$in1},[$inp],#16 aesd $dat0,q14 aesimc $dat0,$dat0 aesd $dat1,q14 aesimc $dat1,$dat1 aesd $dat2,q14 aesimc $dat2,$dat2 vld1.8 {$in2},[$inp],#16 aesd $dat0,q15 aesd $dat1,q15 aesd $dat2,q15 vld1.32 {q8},[$key_],#16 // re-pre-load rndkey[0] add $cnt,$rounds,#2 veor $tmp0,$tmp0,$dat0 veor $tmp1,$tmp1,$dat1 veor $dat2,$dat2,$tmp2 vld1.32 {q9},[$key_],#16 // re-pre-load rndkey[1] vst1.8 {$tmp0},[$out],#16 vorr $dat0,$in0,$in0 vst1.8 {$tmp1},[$out],#16 vorr $dat1,$in1,$in1 vst1.8 {$dat2},[$out],#16 vorr $dat2,$in2,$in2 b.hs .Loop3x_cbc_dec cmn $len,#0x30 b.eq .Lcbc_done nop .Lcbc_dec_tail: aesd $dat1,q8 aesimc $dat1,$dat1 aesd $dat2,q8 aesimc $dat2,$dat2 vld1.32 {q8},[$key_],#16 subs $cnt,$cnt,#2 aesd $dat1,q9 aesimc $dat1,$dat1 aesd $dat2,q9 aesimc $dat2,$dat2 vld1.32 {q9},[$key_],#16 b.gt .Lcbc_dec_tail aesd $dat1,q8 aesimc $dat1,$dat1 aesd $dat2,q8 aesimc $dat2,$dat2 aesd $dat1,q9 aesimc $dat1,$dat1 aesd $dat2,q9 aesimc $dat2,$dat2 aesd $dat1,q12 aesimc $dat1,$dat1 aesd $dat2,q12 aesimc $dat2,$dat2 cmn $len,#0x20 aesd $dat1,q13 aesimc $dat1,$dat1 aesd $dat2,q13 aesimc $dat2,$dat2 veor $tmp1,$ivec,$rndlast aesd $dat1,q14 aesimc $dat1,$dat1 aesd $dat2,q14 aesimc $dat2,$dat2 veor $tmp2,$in1,$rndlast aesd $dat1,q15 aesd $dat2,q15 b.eq .Lcbc_dec_one veor $tmp1,$tmp1,$dat1 veor $tmp2,$tmp2,$dat2 vorr $ivec,$in2,$in2 vst1.8 {$tmp1},[$out],#16 vst1.8 {$tmp2},[$out],#16 b .Lcbc_done .Lcbc_dec_one: veor $tmp1,$tmp1,$dat2 vorr $ivec,$in2,$in2 vst1.8 {$tmp1},[$out],#16 .Lcbc_done: vst1.8 {$ivec},[$ivp] .Lcbc_abort: ___ } $code.=<<___ if ($flavour !~ /64/); vldmia sp!,{d8-d15} ldmia sp!,{r4-r8,pc} ___ $code.=<<___ if ($flavour =~ /64/); ldr x29,[sp],#16 ret ___ $code.=<<___; .size ${prefix}_cbc_encrypt,.-${prefix}_cbc_encrypt ___ }}} {{{ my ($inp,$out,$len,$key,$ivp)=map("x$_",(0..4)); my ($rounds,$cnt,$key_)=("w5","w6","x7"); my ($ctr,$tctr0,$tctr1,$tctr2)=map("w$_",(8..10,12)); my $step="x12"; # aliases with $tctr2 my ($dat0,$dat1,$in0,$in1,$tmp0,$tmp1,$ivec,$rndlast)=map("q$_",(0..7)); my ($dat2,$in2,$tmp2)=map("q$_",(10,11,9)); my ($dat,$tmp)=($dat0,$tmp0); ### q8-q15 preloaded key schedule $code.=<<___; .globl ${prefix}_ctr32_encrypt_blocks .type ${prefix}_ctr32_encrypt_blocks,%function .align 5 ${prefix}_ctr32_encrypt_blocks: ___ $code.=<<___ if ($flavour =~ /64/); stp x29,x30,[sp,#-16]! add x29,sp,#0 ___ $code.=<<___ if ($flavour !~ /64/); mov ip,sp stmdb sp!,{r4-r10,lr} vstmdb sp!,{d8-d15} @ ABI specification says so ldr r4, [ip] @ load remaining arg ___ $code.=<<___; ldr $rounds,[$key,#240] ldr $ctr, [$ivp, #12] vld1.32 {$dat0},[$ivp] vld1.32 {q8-q9},[$key] // load key schedule... sub $rounds,$rounds,#4 mov $step,#16 cmp $len,#2 add $key_,$key,x5,lsl#4 // pointer to last 5 round keys sub $rounds,$rounds,#2 vld1.32 {q12-q13},[$key_],#32 vld1.32 {q14-q15},[$key_],#32 vld1.32 {$rndlast},[$key_] add $key_,$key,#32 mov $cnt,$rounds cclr $step,lo #ifndef __ARMEB__ rev $ctr, $ctr #endif vorr $dat1,$dat0,$dat0 add $tctr1, $ctr, #1 vorr $dat2,$dat0,$dat0 add $ctr, $ctr, #2 vorr $ivec,$dat0,$dat0 rev $tctr1, $tctr1 vmov.32 ${dat1}[3],$tctr1 b.ls .Lctr32_tail rev $tctr2, $ctr sub $len,$len,#3 // bias vmov.32 ${dat2}[3],$tctr2 b .Loop3x_ctr32 .align 4 .Loop3x_ctr32: aese $dat0,q8 aesmc $dat0,$dat0 aese $dat1,q8 aesmc $dat1,$dat1 aese $dat2,q8 aesmc $dat2,$dat2 vld1.32 {q8},[$key_],#16 subs $cnt,$cnt,#2 aese $dat0,q9 aesmc $dat0,$dat0 aese $dat1,q9 aesmc $dat1,$dat1 aese $dat2,q9 aesmc $dat2,$dat2 vld1.32 {q9},[$key_],#16 b.gt .Loop3x_ctr32 aese $dat0,q8 aesmc $tmp0,$dat0 aese $dat1,q8 aesmc $tmp1,$dat1 vld1.8 {$in0},[$inp],#16 vorr $dat0,$ivec,$ivec aese $dat2,q8 aesmc $dat2,$dat2 vld1.8 {$in1},[$inp],#16 vorr $dat1,$ivec,$ivec aese $tmp0,q9 aesmc $tmp0,$tmp0 aese $tmp1,q9 aesmc $tmp1,$tmp1 vld1.8 {$in2},[$inp],#16 mov $key_,$key aese $dat2,q9 aesmc $tmp2,$dat2 vorr $dat2,$ivec,$ivec add $tctr0,$ctr,#1 aese $tmp0,q12 aesmc $tmp0,$tmp0 aese $tmp1,q12 aesmc $tmp1,$tmp1 veor $in0,$in0,$rndlast add $tctr1,$ctr,#2 aese $tmp2,q12 aesmc $tmp2,$tmp2 veor $in1,$in1,$rndlast add $ctr,$ctr,#3 aese $tmp0,q13 aesmc $tmp0,$tmp0 aese $tmp1,q13 aesmc $tmp1,$tmp1 veor $in2,$in2,$rndlast rev $tctr0,$tctr0 aese $tmp2,q13 aesmc $tmp2,$tmp2 vmov.32 ${dat0}[3], $tctr0 rev $tctr1,$tctr1 aese $tmp0,q14 aesmc $tmp0,$tmp0 aese $tmp1,q14 aesmc $tmp1,$tmp1 vmov.32 ${dat1}[3], $tctr1 rev $tctr2,$ctr aese $tmp2,q14 aesmc $tmp2,$tmp2 vmov.32 ${dat2}[3], $tctr2 subs $len,$len,#3 aese $tmp0,q15 aese $tmp1,q15 aese $tmp2,q15 veor $in0,$in0,$tmp0 vld1.32 {q8},[$key_],#16 // re-pre-load rndkey[0] vst1.8 {$in0},[$out],#16 veor $in1,$in1,$tmp1 mov $cnt,$rounds vst1.8 {$in1},[$out],#16 veor $in2,$in2,$tmp2 vld1.32 {q9},[$key_],#16 // re-pre-load rndkey[1] vst1.8 {$in2},[$out],#16 b.hs .Loop3x_ctr32 adds $len,$len,#3 b.eq .Lctr32_done cmp $len,#1 mov $step,#16 cclr $step,eq .Lctr32_tail: aese $dat0,q8 aesmc $dat0,$dat0 aese $dat1,q8 aesmc $dat1,$dat1 vld1.32 {q8},[$key_],#16 subs $cnt,$cnt,#2 aese $dat0,q9 aesmc $dat0,$dat0 aese $dat1,q9 aesmc $dat1,$dat1 vld1.32 {q9},[$key_],#16 b.gt .Lctr32_tail aese $dat0,q8 aesmc $dat0,$dat0 aese $dat1,q8 aesmc $dat1,$dat1 aese $dat0,q9 aesmc $dat0,$dat0 aese $dat1,q9 aesmc $dat1,$dat1 vld1.8 {$in0},[$inp],$step aese $dat0,q12 aesmc $dat0,$dat0 aese $dat1,q12 aesmc $dat1,$dat1 vld1.8 {$in1},[$inp] aese $dat0,q13 aesmc $dat0,$dat0 aese $dat1,q13 aesmc $dat1,$dat1 veor $in0,$in0,$rndlast aese $dat0,q14 aesmc $dat0,$dat0 aese $dat1,q14 aesmc $dat1,$dat1 veor $in1,$in1,$rndlast aese $dat0,q15 aese $dat1,q15 cmp $len,#1 veor $in0,$in0,$dat0 veor $in1,$in1,$dat1 vst1.8 {$in0},[$out],#16 b.eq .Lctr32_done vst1.8 {$in1},[$out] .Lctr32_done: ___ $code.=<<___ if ($flavour !~ /64/); vldmia sp!,{d8-d15} ldmia sp!,{r4-r10,pc} ___ $code.=<<___ if ($flavour =~ /64/); ldr x29,[sp],#16 ret ___ $code.=<<___; .size ${prefix}_ctr32_encrypt_blocks,.-${prefix}_ctr32_encrypt_blocks ___ }}} $code.=<<___; #endif ___ ######################################## if ($flavour =~ /64/) { ######## 64-bit code my %opcode = ( "aesd" => 0x4e285800, "aese" => 0x4e284800, "aesimc"=> 0x4e287800, "aesmc" => 0x4e286800 ); local *unaes = sub { my ($mnemonic,$arg)=@_; $arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)/o && sprintf ".inst\t0x%08x\t//%s %s", $opcode{$mnemonic}|$1|($2<<5), $mnemonic,$arg; }; foreach(split("\n",$code)) { s/\`([^\`]*)\`/eval($1)/geo; s/\bq([0-9]+)\b/"v".($1<8?$1:$1+8).".16b"/geo; # old->new registers s/@\s/\/\//o; # old->new style commentary #s/[v]?(aes\w+)\s+([qv].*)/unaes($1,$2)/geo or s/cclr\s+([wx])([^,]+),\s*([a-z]+)/csel $1$2,$1zr,$1$2,$3/o or s/mov\.([a-z]+)\s+([wx][0-9]+),\s*([wx][0-9]+)/csel $2,$3,$2,$1/o or s/vmov\.i8/movi/o or # fix up legacy mnemonics s/vext\.8/ext/o or s/vrev32\.8/rev32/o or s/vtst\.8/cmtst/o or s/vshr/ushr/o or s/^(\s+)v/$1/o or # strip off v prefix s/\bbx\s+lr\b/ret/o; # fix up remainig legacy suffixes s/\.[ui]?8//o; m/\],#8/o and s/\.16b/\.8b/go; s/\.[ui]?32//o and s/\.16b/\.4s/go; s/\.[ui]?64//o and s/\.16b/\.2d/go; s/\.[42]([sd])\[([0-3])\]/\.$1\[$2\]/o; print $_,"\n"; } } else { ######## 32-bit code my %opcode = ( "aesd" => 0xf3b00340, "aese" => 0xf3b00300, "aesimc"=> 0xf3b003c0, "aesmc" => 0xf3b00380 ); local *unaes = sub { my ($mnemonic,$arg)=@_; if ($arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)/o) { my $word = $opcode{$mnemonic}|(($1&7)<<13)|(($1&8)<<19) |(($2&7)<<1) |(($2&8)<<2); # since ARMv7 instructions are always encoded little-endian. # correct solution is to use .inst directive, but older # assemblers don't implement it:-( sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s", $word&0xff,($word>>8)&0xff, ($word>>16)&0xff,($word>>24)&0xff, $mnemonic,$arg; } }; sub unvtbl { my $arg=shift; $arg =~ m/q([0-9]+),\s*\{q([0-9]+)\},\s*q([0-9]+)/o && sprintf "vtbl.8 d%d,{q%d},d%d\n\t". "vtbl.8 d%d,{q%d},d%d", 2*$1,$2,2*$3, 2*$1+1,$2,2*$3+1; } sub unvdup32 { my $arg=shift; $arg =~ m/q([0-9]+),\s*q([0-9]+)\[([0-3])\]/o && sprintf "vdup.32 q%d,d%d[%d]",$1,2*$2+($3>>1),$3&1; } sub unvmov32 { my $arg=shift; $arg =~ m/q([0-9]+)\[([0-3])\],(.*)/o && sprintf "vmov.32 d%d[%d],%s",2*$1+($2>>1),$2&1,$3; } foreach(split("\n",$code)) { s/\`([^\`]*)\`/eval($1)/geo; s/\b[wx]([0-9]+)\b/r$1/go; # new->old registers s/\bv([0-9])\.[12468]+[bsd]\b/q$1/go; # new->old registers s/\/\/\s?/@ /o; # new->old style commentary # fix up remainig new-style suffixes s/\{q([0-9]+)\},\s*\[(.+)\],#8/sprintf "{d%d},[$2]!",2*$1/eo or s/\],#[0-9]+/]!/o; s/[v]?(aes\w+)\s+([qv].*)/unaes($1,$2)/geo or s/cclr\s+([^,]+),\s*([a-z]+)/mov$2 $1,#0/o or s/vtbl\.8\s+(.*)/unvtbl($1)/geo or s/vdup\.32\s+(.*)/unvdup32($1)/geo or s/vmov\.32\s+(.*)/unvmov32($1)/geo or s/^(\s+)b\./$1b/o or s/^(\s+)mov\./$1mov/o or s/^(\s+)ret/$1bx\tlr/o; print $_,"\n"; } } close STDOUT; Index: stable/11/crypto/openssl/crypto/arm64cpuid.S =================================================================== --- stable/11/crypto/openssl/crypto/arm64cpuid.S (revision 325332) +++ stable/11/crypto/openssl/crypto/arm64cpuid.S (revision 325333) @@ -1,46 +1,45 @@ #include "arm_arch.h" .text -.arch armv8-a+crypto .align 5 .global _armv7_neon_probe .type _armv7_neon_probe,%function _armv7_neon_probe: orr v15.16b, v15.16b, v15.16b ret .size _armv7_neon_probe,.-_armv7_neon_probe .global _armv7_tick .type _armv7_tick,%function _armv7_tick: mrs x0, CNTVCT_EL0 ret .size _armv7_tick,.-_armv7_tick .global _armv8_aes_probe .type _armv8_aes_probe,%function _armv8_aes_probe: aese v0.16b, v0.16b ret .size _armv8_aes_probe,.-_armv8_aes_probe .global _armv8_sha1_probe .type _armv8_sha1_probe,%function _armv8_sha1_probe: sha1h s0, s0 ret .size _armv8_sha1_probe,.-_armv8_sha1_probe .global _armv8_sha256_probe .type _armv8_sha256_probe,%function _armv8_sha256_probe: sha256su0 v0.4s, v0.4s ret .size _armv8_sha256_probe,.-_armv8_sha256_probe .global _armv8_pmull_probe .type _armv8_pmull_probe,%function _armv8_pmull_probe: pmull v0.1q, v0.1d, v0.1d ret .size _armv8_pmull_probe,.-_armv8_pmull_probe Index: stable/11/crypto/openssl/crypto/modes/asm/ghashv8-armx.pl =================================================================== --- stable/11/crypto/openssl/crypto/modes/asm/ghashv8-armx.pl (revision 325332) +++ stable/11/crypto/openssl/crypto/modes/asm/ghashv8-armx.pl (revision 325333) @@ -1,409 +1,409 @@ #!/usr/bin/env perl # # ==================================================================== # Written by Andy Polyakov 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/. # ==================================================================== # # GHASH for ARMv8 Crypto Extension, 64-bit polynomial multiplication. # # June 2014 # # Initial version was developed in tight cooperation with Ard # Biesheuvel from bits-n-pieces from # other assembly modules. Just like aesv8-armx.pl this module # supports both AArch32 and AArch64 execution modes. # # July 2014 # # Implement 2x aggregated reduction [see ghash-x86.pl for background # information]. # # Current performance in cycles per processed byte: # # PMULL[2] 32-bit NEON(*) # Apple A7 0.92 5.62 # Cortex-A53 1.01 8.39 # Cortex-A57 1.17 7.61 # # (*) presented for reference/comparison purposes; $flavour = shift; open STDOUT,">".shift; $Xi="x0"; # argument block $Htbl="x1"; $inp="x2"; $len="x3"; $inc="x12"; { my ($Xl,$Xm,$Xh,$IN)=map("q$_",(0..3)); my ($t0,$t1,$t2,$xC2,$H,$Hhl,$H2)=map("q$_",(8..14)); $code=<<___; #include "arm_arch.h" .text ___ -$code.=".arch armv8-a+crypto\n" if ($flavour =~ /64/); +# $code.=".arch armv8-a+crypto\n" if ($flavour =~ /64/); $code.=".fpu neon\n.code 32\n" if ($flavour !~ /64/); ################################################################################ # void gcm_init_v8(u128 Htable[16],const u64 H[2]); # # input: 128-bit H - secret parameter E(K,0^128) # output: precomputed table filled with degrees of twisted H; # H is twisted to handle reverse bitness of GHASH; # only few of 16 slots of Htable[16] are used; # data is opaque to outside world (which allows to # optimize the code independently); # $code.=<<___; .global gcm_init_v8 .type gcm_init_v8,%function .align 4 gcm_init_v8: vld1.64 {$t1},[x1] @ load input H vmov.i8 $xC2,#0xe1 vshl.i64 $xC2,$xC2,#57 @ 0xc2.0 vext.8 $IN,$t1,$t1,#8 vshr.u64 $t2,$xC2,#63 vdup.32 $t1,${t1}[1] vext.8 $t0,$t2,$xC2,#8 @ t0=0xc2....01 vshr.u64 $t2,$IN,#63 vshr.s32 $t1,$t1,#31 @ broadcast carry bit vand $t2,$t2,$t0 vshl.i64 $IN,$IN,#1 vext.8 $t2,$t2,$t2,#8 vand $t0,$t0,$t1 vorr $IN,$IN,$t2 @ H<<<=1 veor $H,$IN,$t0 @ twisted H vst1.64 {$H},[x0],#16 @ store Htable[0] @ calculate H^2 vext.8 $t0,$H,$H,#8 @ Karatsuba pre-processing vpmull.p64 $Xl,$H,$H veor $t0,$t0,$H vpmull2.p64 $Xh,$H,$H vpmull.p64 $Xm,$t0,$t0 vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing veor $t2,$Xl,$Xh veor $Xm,$Xm,$t1 veor $Xm,$Xm,$t2 vpmull.p64 $t2,$Xl,$xC2 @ 1st phase vmov $Xh#lo,$Xm#hi @ Xh|Xm - 256-bit result vmov $Xm#hi,$Xl#lo @ Xm is rotated Xl veor $Xl,$Xm,$t2 vext.8 $t2,$Xl,$Xl,#8 @ 2nd phase vpmull.p64 $Xl,$Xl,$xC2 veor $t2,$t2,$Xh veor $H2,$Xl,$t2 vext.8 $t1,$H2,$H2,#8 @ Karatsuba pre-processing veor $t1,$t1,$H2 vext.8 $Hhl,$t0,$t1,#8 @ pack Karatsuba pre-processed vst1.64 {$Hhl-$H2},[x0] @ store Htable[1..2] ret .size gcm_init_v8,.-gcm_init_v8 ___ ################################################################################ # void gcm_gmult_v8(u64 Xi[2],const u128 Htable[16]); # # input: Xi - current hash value; # Htable - table precomputed in gcm_init_v8; # output: Xi - next hash value Xi; # $code.=<<___; .global gcm_gmult_v8 .type gcm_gmult_v8,%function .align 4 gcm_gmult_v8: vld1.64 {$t1},[$Xi] @ load Xi vmov.i8 $xC2,#0xe1 vld1.64 {$H-$Hhl},[$Htbl] @ load twisted H, ... vshl.u64 $xC2,$xC2,#57 #ifndef __ARMEB__ vrev64.8 $t1,$t1 #endif vext.8 $IN,$t1,$t1,#8 vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo veor $t1,$t1,$IN @ Karatsuba pre-processing vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing veor $t2,$Xl,$Xh veor $Xm,$Xm,$t1 veor $Xm,$Xm,$t2 vpmull.p64 $t2,$Xl,$xC2 @ 1st phase of reduction vmov $Xh#lo,$Xm#hi @ Xh|Xm - 256-bit result vmov $Xm#hi,$Xl#lo @ Xm is rotated Xl veor $Xl,$Xm,$t2 vext.8 $t2,$Xl,$Xl,#8 @ 2nd phase of reduction vpmull.p64 $Xl,$Xl,$xC2 veor $t2,$t2,$Xh veor $Xl,$Xl,$t2 #ifndef __ARMEB__ vrev64.8 $Xl,$Xl #endif vext.8 $Xl,$Xl,$Xl,#8 vst1.64 {$Xl},[$Xi] @ write out Xi ret .size gcm_gmult_v8,.-gcm_gmult_v8 ___ ################################################################################ # void gcm_ghash_v8(u64 Xi[2],const u128 Htable[16],const u8 *inp,size_t len); # # input: table precomputed in gcm_init_v8; # current hash value Xi; # pointer to input data; # length of input data in bytes, but divisible by block size; # output: next hash value Xi; # $code.=<<___; .global gcm_ghash_v8 .type gcm_ghash_v8,%function .align 4 gcm_ghash_v8: ___ $code.=<<___ if ($flavour !~ /64/); vstmdb sp!,{d8-d15} @ 32-bit ABI says so ___ $code.=<<___; vld1.64 {$Xl},[$Xi] @ load [rotated] Xi @ "[rotated]" means that @ loaded value would have @ to be rotated in order to @ make it appear as in @ alorithm specification subs $len,$len,#32 @ see if $len is 32 or larger mov $inc,#16 @ $inc is used as post- @ increment for input pointer; @ as loop is modulo-scheduled @ $inc is zeroed just in time @ to preclude oversteping @ inp[len], which means that @ last block[s] are actually @ loaded twice, but last @ copy is not processed vld1.64 {$H-$Hhl},[$Htbl],#32 @ load twisted H, ..., H^2 vmov.i8 $xC2,#0xe1 vld1.64 {$H2},[$Htbl] cclr $inc,eq @ is it time to zero $inc? vext.8 $Xl,$Xl,$Xl,#8 @ rotate Xi vld1.64 {$t0},[$inp],#16 @ load [rotated] I[0] vshl.u64 $xC2,$xC2,#57 @ compose 0xc2.0 constant #ifndef __ARMEB__ vrev64.8 $t0,$t0 vrev64.8 $Xl,$Xl #endif vext.8 $IN,$t0,$t0,#8 @ rotate I[0] b.lo .Lodd_tail_v8 @ $len was less than 32 ___ { my ($Xln,$Xmn,$Xhn,$In) = map("q$_",(4..7)); ####### # Xi+2 =[H*(Ii+1 + Xi+1)] mod P = # [(H*Ii+1) + (H*Xi+1)] mod P = # [(H*Ii+1) + H^2*(Ii+Xi)] mod P # $code.=<<___; vld1.64 {$t1},[$inp],$inc @ load [rotated] I[1] #ifndef __ARMEB__ vrev64.8 $t1,$t1 #endif vext.8 $In,$t1,$t1,#8 veor $IN,$IN,$Xl @ I[i]^=Xi vpmull.p64 $Xln,$H,$In @ H·Ii+1 veor $t1,$t1,$In @ Karatsuba pre-processing vpmull2.p64 $Xhn,$H,$In b .Loop_mod2x_v8 .align 4 .Loop_mod2x_v8: vext.8 $t2,$IN,$IN,#8 subs $len,$len,#32 @ is there more data? vpmull.p64 $Xl,$H2,$IN @ H^2.lo·Xi.lo cclr $inc,lo @ is it time to zero $inc? vpmull.p64 $Xmn,$Hhl,$t1 veor $t2,$t2,$IN @ Karatsuba pre-processing vpmull2.p64 $Xh,$H2,$IN @ H^2.hi·Xi.hi veor $Xl,$Xl,$Xln @ accumulate vpmull2.p64 $Xm,$Hhl,$t2 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi) vld1.64 {$t0},[$inp],$inc @ load [rotated] I[i+2] veor $Xh,$Xh,$Xhn cclr $inc,eq @ is it time to zero $inc? veor $Xm,$Xm,$Xmn vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing veor $t2,$Xl,$Xh veor $Xm,$Xm,$t1 vld1.64 {$t1},[$inp],$inc @ load [rotated] I[i+3] #ifndef __ARMEB__ vrev64.8 $t0,$t0 #endif veor $Xm,$Xm,$t2 vpmull.p64 $t2,$Xl,$xC2 @ 1st phase of reduction #ifndef __ARMEB__ vrev64.8 $t1,$t1 #endif vmov $Xh#lo,$Xm#hi @ Xh|Xm - 256-bit result vmov $Xm#hi,$Xl#lo @ Xm is rotated Xl vext.8 $In,$t1,$t1,#8 vext.8 $IN,$t0,$t0,#8 veor $Xl,$Xm,$t2 vpmull.p64 $Xln,$H,$In @ H·Ii+1 veor $IN,$IN,$Xh @ accumulate $IN early vext.8 $t2,$Xl,$Xl,#8 @ 2nd phase of reduction vpmull.p64 $Xl,$Xl,$xC2 veor $IN,$IN,$t2 veor $t1,$t1,$In @ Karatsuba pre-processing veor $IN,$IN,$Xl vpmull2.p64 $Xhn,$H,$In b.hs .Loop_mod2x_v8 @ there was at least 32 more bytes veor $Xh,$Xh,$t2 vext.8 $IN,$t0,$t0,#8 @ re-construct $IN adds $len,$len,#32 @ re-construct $len veor $Xl,$Xl,$Xh @ re-construct $Xl b.eq .Ldone_v8 @ is $len zero? ___ } $code.=<<___; .Lodd_tail_v8: vext.8 $t2,$Xl,$Xl,#8 veor $IN,$IN,$Xl @ inp^=Xi veor $t1,$t0,$t2 @ $t1 is rotated inp^Xi vpmull.p64 $Xl,$H,$IN @ H.lo·Xi.lo veor $t1,$t1,$IN @ Karatsuba pre-processing vpmull2.p64 $Xh,$H,$IN @ H.hi·Xi.hi vpmull.p64 $Xm,$Hhl,$t1 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) vext.8 $t1,$Xl,$Xh,#8 @ Karatsuba post-processing veor $t2,$Xl,$Xh veor $Xm,$Xm,$t1 veor $Xm,$Xm,$t2 vpmull.p64 $t2,$Xl,$xC2 @ 1st phase of reduction vmov $Xh#lo,$Xm#hi @ Xh|Xm - 256-bit result vmov $Xm#hi,$Xl#lo @ Xm is rotated Xl veor $Xl,$Xm,$t2 vext.8 $t2,$Xl,$Xl,#8 @ 2nd phase of reduction vpmull.p64 $Xl,$Xl,$xC2 veor $t2,$t2,$Xh veor $Xl,$Xl,$t2 .Ldone_v8: #ifndef __ARMEB__ vrev64.8 $Xl,$Xl #endif vext.8 $Xl,$Xl,$Xl,#8 vst1.64 {$Xl},[$Xi] @ write out Xi ___ $code.=<<___ if ($flavour !~ /64/); vldmia sp!,{d8-d15} @ 32-bit ABI says so ___ $code.=<<___; ret .size gcm_ghash_v8,.-gcm_ghash_v8 ___ } $code.=<<___; .asciz "GHASH for ARMv8, CRYPTOGAMS by " .align 2 ___ if ($flavour =~ /64/) { ######## 64-bit code sub unvmov { my $arg=shift; $arg =~ m/q([0-9]+)#(lo|hi),\s*q([0-9]+)#(lo|hi)/o && sprintf "ins v%d.d[%d],v%d.d[%d]",$1,($2 eq "lo")?0:1,$3,($4 eq "lo")?0:1; } foreach(split("\n",$code)) { s/cclr\s+([wx])([^,]+),\s*([a-z]+)/csel $1$2,$1zr,$1$2,$3/o or s/vmov\.i8/movi/o or # fix up legacy mnemonics s/vmov\s+(.*)/unvmov($1)/geo or s/vext\.8/ext/o or s/vshr\.s/sshr\.s/o or s/vshr/ushr/o or s/^(\s+)v/$1/o or # strip off v prefix s/\bbx\s+lr\b/ret/o; s/\bq([0-9]+)\b/"v".($1<8?$1:$1+8).".16b"/geo; # old->new registers s/@\s/\/\//o; # old->new style commentary # fix up remainig legacy suffixes s/\.[ui]?8(\s)/$1/o; s/\.[uis]?32//o and s/\.16b/\.4s/go; m/\.p64/o and s/\.16b/\.1q/o; # 1st pmull argument m/l\.p64/o and s/\.16b/\.1d/go; # 2nd and 3rd pmull arguments s/\.[uisp]?64//o and s/\.16b/\.2d/go; s/\.[42]([sd])\[([0-3])\]/\.$1\[$2\]/o; print $_,"\n"; } } else { ######## 32-bit code sub unvdup32 { my $arg=shift; $arg =~ m/q([0-9]+),\s*q([0-9]+)\[([0-3])\]/o && sprintf "vdup.32 q%d,d%d[%d]",$1,2*$2+($3>>1),$3&1; } sub unvpmullp64 { my ($mnemonic,$arg)=@_; if ($arg =~ m/q([0-9]+),\s*q([0-9]+),\s*q([0-9]+)/o) { my $word = 0xf2a00e00|(($1&7)<<13)|(($1&8)<<19) |(($2&7)<<17)|(($2&8)<<4) |(($3&7)<<1) |(($3&8)<<2); $word |= 0x00010001 if ($mnemonic =~ "2"); # since ARMv7 instructions are always encoded little-endian. # correct solution is to use .inst directive, but older # assemblers don't implement it:-( sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s", $word&0xff,($word>>8)&0xff, ($word>>16)&0xff,($word>>24)&0xff, $mnemonic,$arg; } } foreach(split("\n",$code)) { s/\b[wx]([0-9]+)\b/r$1/go; # new->old registers s/\bv([0-9])\.[12468]+[bsd]\b/q$1/go; # new->old registers s/\/\/\s?/@ /o; # new->old style commentary # fix up remainig new-style suffixes s/\],#[0-9]+/]!/o; s/cclr\s+([^,]+),\s*([a-z]+)/mov$2 $1,#0/o or s/vdup\.32\s+(.*)/unvdup32($1)/geo or s/v?(pmull2?)\.p64\s+(.*)/unvpmullp64($1,$2)/geo or s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo or s/^(\s+)b\./$1b/o or s/^(\s+)ret/$1bx\tlr/o; print $_,"\n"; } } close STDOUT; # enforce flush Index: stable/11/secure/lib/libcrypto/Makefile =================================================================== --- stable/11/secure/lib/libcrypto/Makefile (revision 325332) +++ stable/11/secure/lib/libcrypto/Makefile (revision 325333) @@ -1,481 +1,492 @@ # $FreeBSD$ SHLIBDIR?= /lib SUBDIR= engines .include LIB= crypto SHLIB_MAJOR= 8 NO_LINT= .if exists(Makefile.man) .include "Makefile.man" .endif .include "Makefile.inc" .if defined(NOTYET) MAN+= config.5 des_modes.7 .endif # base sources SRCS= cpt_err.c cryptlib.c cversion.c ex_data.c mem.c mem_dbg.c o_dir.c \ o_fips.c o_init.c o_str.c o_time.c uid.c -.if defined(ASM_amd64) +.if defined(ASM_aarch64) +SRCS+= arm64cpuid.S armcap.c mem_clr.c +CFLAGS.arm64cpuid.S= -march=armv8-a+crypto +.elif defined(ASM_amd64) SRCS+= x86_64cpuid.S .elif defined(ASM_arm) SRCS+= armcap.c armv4cpuid.S .elif defined(ASM_i386) SRCS+= x86cpuid.S .else SRCS+= mem_clr.c .endif INCS+= crypto.h ebcdic.h opensslv.h ossl_typ.h symhacks.h ../e_os2.h # aes SRCS+= aes_cfb.c aes_ctr.c aes_ecb.c aes_ige.c aes_misc.c aes_ofb.c aes_wrap.c -.if defined(ASM_amd64) +.if defined(ASM_aarch64) +SRCS+= aes_cbc.c aes_core.c aesv8-armx.S +CFLAGS.aesv8-armx.S= -march=armv8-a+crypto +.elif defined(ASM_amd64) SRCS+= aes-x86_64.S aesni-mb-x86_64.S aesni-sha1-x86_64.S \ aesni-sha256-x86_64.S aesni-x86_64.S bsaes-x86_64.S vpaes-x86_64.S .elif defined(ASM_arm) SRCS+= aes-armv4.S aes_cbc.c aesv8-armx.S bsaes-armv7.S .elif defined(ASM_i386) SRCS+= aes-586.S aesni-x86.S vpaes-x86.S .else SRCS+= aes_cbc.c aes_core.c .endif INCS+= aes.h # asn1 SRCS+= a_bitstr.c a_bool.c a_bytes.c a_d2i_fp.c a_digest.c a_dup.c a_enum.c \ a_gentm.c a_i2d_fp.c a_int.c a_mbstr.c a_object.c a_octet.c a_print.c \ a_set.c a_sign.c a_strex.c a_strnid.c a_time.c a_type.c a_utctm.c \ a_utf8.c a_verify.c ameth_lib.c asn1_err.c asn1_gen.c asn1_lib.c \ asn1_par.c asn_mime.c asn_moid.c asn_pack.c bio_asn1.c bio_ndef.c \ d2i_pr.c d2i_pu.c evp_asn1.c f_enum.c f_int.c f_string.c i2d_pr.c \ i2d_pu.c n_pkey.c nsseq.c p5_pbe.c p5_pbev2.c p8_pkey.c t_bitst.c \ t_crl.c t_pkey.c t_req.c t_spki.c t_x509.c t_x509a.c tasn_dec.c \ tasn_enc.c tasn_fre.c tasn_new.c tasn_prn.c tasn_typ.c tasn_utl.c \ x_algor.c x_attrib.c x_bignum.c x_crl.c x_exten.c x_info.c x_long.c \ x_name.c x_nx509.c x_pkey.c x_pubkey.c x_req.c x_sig.c x_spki.c \ x_val.c x_x509.c x_x509a.c INCS+= asn1.h asn1_mac.h asn1t.h # bf SRCS+= bf_cfb64.c bf_ecb.c bf_ofb64.c bf_skey.c .if defined(ASM_i386) .if ${MACHINE_CPU:Mi686} SRCS+= bf-686.S .else SRCS+= bf-586.S .endif .else SRCS+= bf_enc.c .endif INCS+= blowfish.h # bio SRCS+= b_dump.c b_print.c b_sock.c bf_buff.c bf_nbio.c bf_null.c bio_cb.c \ bio_err.c bio_lib.c bss_acpt.c bss_bio.c bss_conn.c bss_dgram.c \ bss_fd.c bss_file.c bss_log.c bss_mem.c bss_null.c bss_sock.c INCS+= bio.h # bn SRCS+= bn_add.c bn_blind.c bn_const.c bn_ctx.c bn_depr.c bn_div.c bn_err.c \ bn_exp.c bn_exp2.c bn_gcd.c bn_gf2m.c bn_kron.c bn_lib.c bn_mod.c \ bn_mont.c bn_mpi.c bn_mul.c bn_nist.c bn_prime.c bn_print.c bn_rand.c \ bn_recp.c bn_shift.c bn_sqr.c bn_sqrt.c bn_word.c bn_x931p.c .if defined(ASM_amd64) SRCS+= rsaz-avx2.S rsaz-x86_64.S rsaz_exp.c x86_64-gcc.c x86_64-gf2m.S \ x86_64-mont.S x86_64-mont5.S .elif defined(ASM_arm) SRCS+= armv4-mont.S armv4-gf2m.S bn_asm.c .elif defined(ASM_i386) SRCS+= bn-586.S co-586.S x86-gf2m.S x86-mont.S .else SRCS+= bn_asm.c .endif INCS+= bn.h # buffer SRCS+= buf_err.c buf_str.c buffer.c INCS+= buffer.h # camellia SRCS+= cmll_cfb.c cmll_ctr.c cmll_ecb.c cmll_ofb.c cmll_utl.c .if defined(ASM_amd64) SRCS+= cmll_misc.c cmll-x86_64.S .elif defined(ASM_i386) SRCS+= cmll-x86.S .else SRCS+= camellia.c cmll_cbc.c cmll_misc.c .endif INCS+= camellia.h # cast SRCS+= c_cfb64.c c_ecb.c c_enc.c c_ofb64.c c_skey.c INCS+= cast.h # cmac SRCS+= cm_ameth.c cm_pmeth.c cmac.c INCS+= cmac.h # cms SRCS+= cms_asn1.c cms_att.c cms_dd.c cms_enc.c cms_env.c cms_err.c \ cms_ess.c cms_io.c cms_kari.c cms_lib.c cms_pwri.c cms_sd.c \ cms_smime.c INCS+= cms.h # comp SRCS+= c_rle.c c_zlib.c comp_err.c comp_lib.c INCS+= comp.h # conf SRCS+= conf_api.c conf_def.c conf_err.c conf_lib.c conf_mall.c conf_mod.c \ conf_sap.c INCS+= conf.h conf_api.h # des SRCS+= cbc_cksm.c cbc_enc.c cfb64ede.c cfb64enc.c cfb_enc.c des_old.c \ des_old2.c ecb3_enc.c ecb_enc.c ede_cbcm_enc.c enc_read.c enc_writ.c \ fcrypt.c ofb64ede.c ofb64enc.c ofb_enc.c pcbc_enc.c qud_cksm.c \ rand_key.c read2pwd.c rpc_enc.c set_key.c str2key.c xcbc_enc.c .if defined(ASM_i386) SRCS+= crypt586.S des-586.S .else SRCS+= des_enc.c fcrypt_b.c .endif INCS+= des.h des_old.h # dh SRCS+= dh_ameth.c dh_asn1.c dh_check.c dh_depr.c dh_err.c dh_gen.c dh_kdf.c \ dh_key.c dh_lib.c dh_pmeth.c dh_prn.c dh_rfc5114.c INCS+= dh.h # dsa SRCS+= dsa_ameth.c dsa_asn1.c dsa_depr.c dsa_err.c dsa_gen.c dsa_key.c \ dsa_lib.c dsa_ossl.c dsa_pmeth.c dsa_prn.c dsa_sign.c dsa_vrf.c INCS+= dsa.h # dso SRCS+= dso_dlfcn.c dso_err.c dso_lib.c dso_openssl.c INCS+= dso.h # ec SRCS+= ec2_mult.c ec2_oct.c ec2_smpl.c ec_ameth.c ec_asn1.c ec_check.c \ ec_curve.c ec_cvt.c ec_err.c ec_key.c ec_lib.c ec_mult.c ec_oct.c \ ec_pmeth.c ec_print.c eck_prn.c ecp_mont.c ecp_nist.c ecp_oct.c \ ecp_smpl.c .if defined(ASM_amd64) SRCS+= ecp_nistz256.c ecp_nistz256-x86_64.S .endif INCS+= ec.h # ecdh SRCS+= ech_err.c ech_kdf.c ech_key.c ech_lib.c ech_ossl.c INCS+= ecdh.h # ecdsa SRCS+= ecs_asn1.c ecs_err.c ecs_lib.c ecs_ossl.c ecs_sign.c ecs_vrf.c INCS+= ecdsa.h # engine SRCS+= eng_all.c eng_cnf.c eng_cryptodev.c eng_ctrl.c eng_dyn.c eng_err.c \ eng_fat.c eng_init.c eng_lib.c eng_list.c eng_openssl.c eng_pkey.c \ eng_rdrand.c eng_table.c tb_asnmth.c tb_cipher.c tb_dh.c tb_digest.c \ tb_dsa.c tb_ecdh.c tb_ecdsa.c tb_pkmeth.c tb_rand.c tb_rsa.c tb_store.c INCS+= engine.h # err SRCS+= err.c err_all.c err_prn.c INCS+= err.h # evp SRCS+= bio_b64.c bio_enc.c bio_md.c bio_ok.c c_all.c c_allc.c c_alld.c \ digest.c e_aes.c e_aes_cbc_hmac_sha1.c e_aes_cbc_hmac_sha256.c e_bf.c \ e_camellia.c e_cast.c e_des.c e_des3.c e_idea.c e_null.c e_old.c \ e_rc2.c e_rc4.c e_rc4_hmac_md5.c e_rc5.c e_seed.c e_xcbc_d.c encode.c \ evp_acnf.c evp_cnf.c evp_enc.c evp_err.c evp_key.c evp_lib.c \ evp_pbe.c evp_pkey.c m_dss.c m_dss1.c m_ecdsa.c m_md4.c m_md5.c \ m_mdc2.c m_null.c m_ripemd.c m_sha.c m_sha1.c m_sigver.c m_wp.c \ names.c p5_crpt.c p5_crpt2.c p_dec.c p_enc.c p_lib.c p_open.c \ p_seal.c p_sign.c p_verify.c pmeth_fn.c pmeth_gn.c pmeth_lib.c INCS+= evp.h # hmac SRCS+= hm_ameth.c hm_pmeth.c hmac.c INCS+= hmac.h # idea SRCS+= i_cbc.c i_cfb64.c i_ecb.c i_ofb64.c i_skey.c INCS+= idea.h # krb5 INCS+= krb5_asn.h # lhash SRCS+= lh_stats.c lhash.c INCS+= lhash.h # md4 SRCS+= md4_dgst.c md4_one.c INCS+= md4.h # md5 SRCS+= md5_dgst.c md5_one.c .if defined(ASM_amd64) SRCS+= md5-x86_64.S .elif defined(ASM_i386) SRCS+= md5-586.S .endif INCS+= md5.h # mdc2 SRCS+= mdc2_one.c mdc2dgst.c INCS+= mdc2.h # modes SRCS+= cbc128.c ccm128.c cfb128.c ctr128.c cts128.c gcm128.c ofb128.c \ wrap128.c xts128.c -.if defined(ASM_amd64) +.if defined(ASM_aarch64) +SRCS+= ghashv8-armx.S +CFLAGS.ghashv8-armx.S= -march=armv8-a+crypto +.elif defined(ASM_amd64) SRCS+= aesni-gcm-x86_64.S ghash-x86_64.S .elif defined(ASM_arm) SRCS+= ghash-armv4.S ghashv8-armx.S .elif defined(ASM_i386) SRCS+= ghash-x86.S .endif INCS+= modes.h # objects SRCS+= o_names.c obj_dat.c obj_err.c obj_lib.c obj_xref.c INCS+= obj_mac.h objects.h # ocsp SRCS+= ocsp_asn.c ocsp_cl.c ocsp_err.c ocsp_ext.c ocsp_ht.c ocsp_lib.c \ ocsp_prn.c ocsp_srv.c ocsp_vfy.c INCS+= ocsp.h # pem SRCS+= pem_all.c pem_err.c pem_info.c pem_lib.c pem_oth.c pem_pk8.c \ pem_pkey.c pem_seal.c pem_sign.c pem_x509.c pem_xaux.c pvkfmt.c INCS+= pem.h pem2.h # pkcs12 SRCS+= p12_add.c p12_asn.c p12_attr.c p12_crpt.c p12_crt.c p12_decr.c \ p12_init.c p12_key.c p12_kiss.c p12_mutl.c p12_npas.c p12_p8d.c \ p12_p8e.c p12_utl.c pk12err.c INCS+= pkcs12.h # pkcs7 SRCS+= bio_pk7.c pk7_asn1.c pk7_attr.c pk7_doit.c pk7_lib.c pk7_mime.c \ pk7_smime.c pkcs7err.c INCS+= pkcs7.h # pqueue SRCS+= pqueue.c INCS+= pqueue.h # rand SRCS+= md_rand.c rand_egd.c rand_err.c rand_lib.c rand_unix.c randfile.c INCS+= rand.h # rc2 SRCS+= rc2_cbc.c rc2_ecb.c rc2_skey.c rc2cfb64.c rc2ofb64.c INCS+= rc2.h # rc4 SRCS+= rc4_utl.c .if defined(ASM_amd64) SRCS+= rc4-md5-x86_64.S rc4-x86_64.S .elif defined(ASM_i386) SRCS+= rc4-586.S .else SRCS+= rc4_enc.c rc4_skey.c .endif INCS+= rc4.h # rc5 SRCS+= rc5_ecb.c rc5_skey.c rc5cfb64.c rc5ofb64.c .if defined(ASM_i386) SRCS+= rc5-586.S .else SRCS+= rc5_enc.c .endif INCS+= rc5.h # ripemd SRCS+= rmd_dgst.c rmd_one.c .if defined(ASM_i386) SRCS+= rmd-586.S .endif INCS+= ripemd.h # rsa SRCS+= rsa_ameth.c rsa_asn1.c rsa_chk.c rsa_crpt.c rsa_depr.c rsa_eay.c \ rsa_err.c rsa_gen.c rsa_lib.c rsa_none.c rsa_null.c rsa_oaep.c \ rsa_pk1.c rsa_pmeth.c rsa_prn.c rsa_pss.c rsa_saos.c rsa_sign.c \ rsa_ssl.c rsa_x931.c INCS+= rsa.h # seed SRCS+= seed.c seed_cbc.c seed_cfb.c seed_ecb.c seed_ofb.c INCS+= seed.h # sha SRCS+= sha1_one.c sha1dgst.c sha256.c sha512.c sha_dgst.c sha_one.c -.if defined(ASM_amd64) +.if defined(ASM_aarch64) +SRCS+= sha1-armv8.S sha256-armv8.S sha512-armv8.S +.elif defined(ASM_amd64) SRCS+= sha1-mb-x86_64.S sha1-x86_64.S sha256-mb-x86_64.S sha256-x86_64.S \ sha512-x86_64.S .elif defined(ASM_arm) SRCS+= sha1-armv4-large.S sha256-armv4.S sha512-armv4.S .elif defined(ASM_i386) SRCS+= sha1-586.S sha256-586.S sha512-586.S .endif INCS+= sha.h # srp SRCS+= srp_lib.c srp_vfy.c INCS+= srp.h # stack SRCS+= stack.c INCS+= safestack.h stack.h # ts SRCS+= ts_asn1.c ts_conf.c ts_err.c ts_lib.c ts_req_print.c ts_req_utils.c \ ts_rsp_print.c ts_rsp_sign.c ts_rsp_utils.c ts_rsp_verify.c \ ts_verify_ctx.c INCS+= ts.h # txt_db SRCS+= txt_db.c INCS+= txt_db.h # ui SRCS+= ui_compat.c ui_err.c ui_lib.c ui_openssl.c ui_util.c INCS+= ui.h ui_compat.h # whrlpool SRCS+= wp_dgst.c .if defined(ASM_amd64) SRCS+= wp-x86_64.S .elif defined(ASM_i386) SRCS+= wp-mmx.S wp_block.c .else SRCS+= wp_block.c .endif INCS+= whrlpool.h # x509 SRCS+= by_dir.c by_file.c x509_att.c x509_cmp.c x509_d2.c x509_def.c \ x509_err.c x509_ext.c x509_lu.c x509_obj.c x509_r2x.c x509_req.c \ x509_set.c x509_trs.c x509_txt.c x509_v3.c x509_vfy.c x509_vpm.c \ x509cset.c x509name.c x509rset.c x509spki.c x509type.c x_all.c INCS+= x509.h x509_vfy.h # x509v3 SRCS+= pcy_cache.c pcy_data.c pcy_lib.c pcy_map.c pcy_node.c pcy_tree.c \ v3_addr.c v3_akey.c v3_akeya.c v3_alt.c v3_asid.c v3_bcons.c \ v3_bitst.c v3_conf.c v3_cpols.c v3_crld.c v3_enum.c v3_extku.c \ v3_genn.c v3_ia5.c v3_info.c v3_int.c v3_lib.c v3_ncons.c v3_ocsp.c \ v3_pci.c v3_pcia.c v3_pcons.c v3_pku.c v3_pmaps.c v3_prn.c v3_purp.c \ v3_scts.c v3_skey.c v3_sxnet.c v3_utl.c v3err.c INCS+= x509v3.h SRCS+= buildinf.h INCS+= opensslconf.h INCSDIR= ${INCLUDEDIR}/openssl CSTD= gnu89 CFLAGS+= -I${.OBJDIR} CFLAGS+= -I${LCRYPTO_SRC}/crypto CFLAGS+= -I${LCRYPTO_SRC}/crypto/asn1 CFLAGS+= -I${LCRYPTO_SRC}/crypto/evp CFLAGS+= -I${LCRYPTO_SRC}/crypto/modes .if !empty(SRCS:M*.S) ACFLAGS+= -Wa,--noexecstack .endif CLEANFILES= buildinf.h opensslconf.h opensslconf.h.tmp buildinf.h: Makefile ( echo "#ifndef MK1MF_BUILD"; \ echo " /* auto-generated by util/mkbuildinf.pl for crypto/cversion.c */"; \ echo " #define CFLAGS \"compiler: ${COMPILER_TYPE}\""; \ echo " #define PLATFORM \"platform: FreeBSD-${MACHINE_ARCH}\""; \ echo "#endif" ) > ${.TARGET} opensslconf.h: opensslconf-${MACHINE_CPUARCH:C/^(amd64|i386)$/x86/}.h.in .if defined(ASM_${MACHINE_CPUARCH}) sed 's/%%ASM%%//; /%%NO_ASM%%/d' ${.ALLSRC} > ${.TARGET}.tmp .else sed '/%%ASM%%/d; s/%%NO_ASM%%//' ${.ALLSRC} > ${.TARGET}.tmp .endif ${CP} ${.TARGET}.tmp ${.TARGET} .include .if defined(ASM_${MACHINE_CPUARCH}) .PATH: ${.CURDIR}/${MACHINE_CPUARCH} .if defined(ASM_amd64) .PATH: ${LCRYPTO_SRC}/crypto/bn/asm .endif .endif .PATH: ${LCRYPTO_SRC}/crypto \ ${LCRYPTO_SRC}/crypto/aes \ ${LCRYPTO_SRC}/crypto/asn1 \ ${LCRYPTO_SRC}/crypto/bf \ ${LCRYPTO_SRC}/crypto/bio \ ${LCRYPTO_SRC}/crypto/bn \ ${LCRYPTO_SRC}/crypto/buffer \ ${LCRYPTO_SRC}/crypto/camellia \ ${LCRYPTO_SRC}/crypto/cast \ ${LCRYPTO_SRC}/crypto/cmac \ ${LCRYPTO_SRC}/crypto/cms \ ${LCRYPTO_SRC}/crypto/comp \ ${LCRYPTO_SRC}/crypto/conf \ ${LCRYPTO_SRC}/crypto/des \ ${LCRYPTO_SRC}/crypto/dh \ ${LCRYPTO_SRC}/crypto/dsa \ ${LCRYPTO_SRC}/crypto/dso \ ${LCRYPTO_SRC}/crypto/ec \ ${LCRYPTO_SRC}/crypto/ecdh \ ${LCRYPTO_SRC}/crypto/ecdsa \ ${LCRYPTO_SRC}/crypto/engine \ ${LCRYPTO_SRC}/crypto/err \ ${LCRYPTO_SRC}/crypto/evp \ ${LCRYPTO_SRC}/crypto/hmac \ ${LCRYPTO_SRC}/crypto/idea \ ${LCRYPTO_SRC}/crypto/krb5 \ ${LCRYPTO_SRC}/crypto/lhash \ ${LCRYPTO_SRC}/crypto/md4 \ ${LCRYPTO_SRC}/crypto/md5 \ ${LCRYPTO_SRC}/crypto/mdc2 \ ${LCRYPTO_SRC}/crypto/modes \ ${LCRYPTO_SRC}/crypto/objects \ ${LCRYPTO_SRC}/crypto/ocsp \ ${LCRYPTO_SRC}/crypto/pem \ ${LCRYPTO_SRC}/crypto/pkcs12 \ ${LCRYPTO_SRC}/crypto/pkcs7 \ ${LCRYPTO_SRC}/crypto/pqueue \ ${LCRYPTO_SRC}/crypto/rand \ ${LCRYPTO_SRC}/crypto/rc2 \ ${LCRYPTO_SRC}/crypto/rc4 \ ${LCRYPTO_SRC}/crypto/rc5 \ ${LCRYPTO_SRC}/crypto/ripemd \ ${LCRYPTO_SRC}/crypto/rsa \ ${LCRYPTO_SRC}/crypto/seed \ ${LCRYPTO_SRC}/crypto/sha \ ${LCRYPTO_SRC}/crypto/srp \ ${LCRYPTO_SRC}/crypto/stack \ ${LCRYPTO_SRC}/crypto/ts \ ${LCRYPTO_SRC}/crypto/txt_db \ ${LCRYPTO_SRC}/crypto/ui \ ${LCRYPTO_SRC}/crypto/whrlpool \ ${LCRYPTO_SRC}/crypto/x509 \ ${LCRYPTO_SRC}/crypto/x509v3 \ ${.CURDIR}/man Index: stable/11/secure/lib/libcrypto/Makefile.asm =================================================================== --- stable/11/secure/lib/libcrypto/Makefile.asm (revision 325332) +++ stable/11/secure/lib/libcrypto/Makefile.asm (revision 325333) @@ -1,196 +1,233 @@ # $FreeBSD$ # Use this to help generate the asm *.S files after an import. It is not # perfect by any means, but does what is needed. # Do a 'make -f Makefile.asm all' and it will generate *.S. Move them # to the arch subdir, and correct any exposed paths and $ FreeBSD $ tags. .include "Makefile.inc" -.if defined(ASM_amd64) +.if defined(ASM_aarch64) + +.PATH: ${LCRYPTO_SRC}/crypto \ + ${LCRYPTO_SRC}/crypto/aes/asm \ + ${LCRYPTO_SRC}/crypto/modes/asm \ + ${LCRYPTO_SRC}/crypto/sha/asm + +PERLPATH= -I${LCRYPTO_SRC}/crypto/perlasm + +# aes +SRCS= aesv8-armx.pl + +# modes +SRCS+= ghashv8-armx.pl + +# sha +SRCS+= sha1-armv8.pl sha512-armv8.pl + +ASM= ${SRCS:R:S/$/.S/} sha256-armv8.S + +all: ${ASM} + +CLEANFILES= ${ASM} ${SRCS:R:S/$/.s/} sha256-armv8.s +.SUFFIXES: .pl + +sha256-armv8.S: sha512-armv8.pl + env CC=cc perl ${.ALLSRC} 64 ${.TARGET:R:S/$/.s/} + ( echo '/* $$'FreeBSD'$$ */' ;\ + echo '/* Do not modify. This file is auto-generated from ${.ALLSRC:T:R:S/$/.pl/}. */' ;\ + cat ${.TARGET:R:S/$/.s/}) > ${.TARGET} + +.pl.S: + env CC=cc perl ${.IMPSRC} 64 ${.TARGET:R:S/$/.s/} + ( echo '/* $$'FreeBSD'$$ */' ;\ + echo '/* Do not modify. This file is auto-generated from ${.IMPSRC:T:R:S/$/.pl/}. */' ;\ + cat ${.TARGET:R:S/$/.s/}) > ${.TARGET} + +.elif defined(ASM_amd64) .PATH: ${LCRYPTO_SRC}/crypto \ ${LCRYPTO_SRC}/crypto/aes/asm \ ${LCRYPTO_SRC}/crypto/bn/asm \ ${LCRYPTO_SRC}/crypto/camellia/asm \ ${LCRYPTO_SRC}/crypto/ec/asm \ ${LCRYPTO_SRC}/crypto/md5/asm \ ${LCRYPTO_SRC}/crypto/modes/asm \ ${LCRYPTO_SRC}/crypto/rc4/asm \ ${LCRYPTO_SRC}/crypto/sha/asm \ ${LCRYPTO_SRC}/crypto/whrlpool/asm # aes SRCS= aes-x86_64.pl aesni-mb-x86_64.pl aesni-sha1-x86_64.pl \ aesni-sha256-x86_64.pl aesni-x86_64.pl bsaes-x86_64.pl \ vpaes-x86_64.pl # bn SRCS+= rsaz-avx2.pl rsaz-x86_64.pl x86_64-gf2m.pl x86_64-mont.pl \ x86_64-mont5.pl # camellia SRCS+= cmll-x86_64.pl # ec SRCS+= ecp_nistz256-x86_64.pl # md5 SRCS+= md5-x86_64.pl # modes SRCS+= aesni-gcm-x86_64.pl ghash-x86_64.pl # rc4 SRCS+= rc4-md5-x86_64.pl rc4-x86_64.pl # sha SRCS+= sha1-mb-x86_64.pl sha1-x86_64.pl sha256-mb-x86_64.pl # whrlpool SRCS+= wp-x86_64.pl # cpuid SRCS+= x86_64cpuid.pl SHA_ASM= sha256-x86_64 sha512-x86_64 SHA_SRC= sha512-x86_64.pl SHA_TMP= ${SHA_ASM:S/$/.s/} ASM= ${SRCS:R:S/$/.S/} ${SHA_ASM:S/$/.S/} all: ${ASM} CLEANFILES= ${ASM} ${SHA_ASM:S/$/.s/} .SUFFIXES: .pl .pl.S: ( echo '/* $$'FreeBSD'$$ */' ;\ echo '/* Do not modify. This file is auto-generated from ${.IMPSRC:T}. */' ;\ env CC=cc perl ${.IMPSRC} elf ) > ${.TARGET} ${SHA_TMP}: ${SHA_SRC} env CC=cc perl ${.ALLSRC} elf ${.TARGET} .for s in ${SHA_ASM} ${s}.S: ${s}.s ( echo '/* $$'FreeBSD'$$ */' ;\ echo '/* Do not modify. This file is auto-generated from ${SHA_SRC}. */' ;\ cat ${s}.s ) > ${.TARGET} .endfor .elif defined(ASM_arm) .PATH: ${LCRYPTO_SRC}/crypto \ ${LCRYPTO_SRC}/crypto/aes/asm \ ${LCRYPTO_SRC}/crypto/bn/asm \ ${LCRYPTO_SRC}/crypto/modes/asm \ ${LCRYPTO_SRC}/crypto/sha/asm PERLPATH= -I${LCRYPTO_SRC}/crypto/perlasm # aes SRCS= aesv8-armx.pl bsaes-armv7.pl # bn SRCS+= armv4-mont.pl armv4-gf2m.pl # modes SRCS+= ghash-armv4.pl ghashv8-armx.pl # sha SRCS+= sha1-armv4-large.pl sha256-armv4.pl sha512-armv4.pl ASM= aes-armv4.S ${SRCS:R:S/$/.S/} all: ${ASM} CLEANFILES= ${ASM} ${SRCS:R:S/$/.s/} .SUFFIXES: .pl aes-armv4.S: aes-armv4.pl ( echo '/* $$'FreeBSD'$$ */' ;\ echo '/* Do not modify. This file is auto-generated from ${.ALLSRC:T}. */' ;\ env CC=cc perl ${.ALLSRC} elf ) > ${.TARGET} .pl.S: env CC=cc perl ${.IMPSRC} elf ${.TARGET:R:S/$/.s/} ( echo '/* $$'FreeBSD'$$ */' ;\ echo '/* Do not modify. This file is auto-generated from ${.IMPSRC:T:R:S/$/.pl/}. */' ;\ cat ${.TARGET:R:S/$/.s/}) > ${.TARGET} .elif defined(ASM_i386) .PATH: ${LCRYPTO_SRC}/crypto \ ${LCRYPTO_SRC}/crypto/aes/asm \ ${LCRYPTO_SRC}/crypto/bf/asm \ ${LCRYPTO_SRC}/crypto/bn/asm \ ${LCRYPTO_SRC}/crypto/camellia/asm \ ${LCRYPTO_SRC}/crypto/des/asm \ ${LCRYPTO_SRC}/crypto/md5/asm \ ${LCRYPTO_SRC}/crypto/modes/asm \ ${LCRYPTO_SRC}/crypto/rc4/asm \ ${LCRYPTO_SRC}/crypto/rc5/asm \ ${LCRYPTO_SRC}/crypto/ripemd/asm \ ${LCRYPTO_SRC}/crypto/sha/asm \ ${LCRYPTO_SRC}/crypto/whrlpool/asm PERLPATH= -I${LCRYPTO_SRC}/crypto/des/asm -I${LCRYPTO_SRC}/crypto/perlasm # aes SRCS= aes-586.pl aesni-x86.pl vpaes-x86.pl # blowfish SRCS+= bf-586.pl bf-686.pl # bn SRCS+= bn-586.pl co-586.pl x86-gf2m.pl x86-mont.pl # camellia SRCS+= cmll-x86.pl # des SRCS+= crypt586.pl des-586.pl # md5 SRCS+= md5-586.pl # modes SRCS+= ghash-x86.pl # rc4 SRCS+= rc4-586.pl # rc5 SRCS+= rc5-586.pl # ripemd SRCS+= rmd-586.pl # sha SRCS+= sha1-586.pl sha256-586.pl sha512-586.pl # whrlpool SRCS+= wp-mmx.pl # cpuid SRCS+= x86cpuid.pl ASM= ${SRCS:R:S/$/.S/} all: ${ASM} CLEANFILES= ${ASM} .SUFFIXES: .pl .pl.S: ( echo '/* $$'FreeBSD'$$ */' ;\ echo '/* Do not modify. This file is auto-generated from ${.IMPSRC:T}. */' ;\ echo '#ifdef PIC' ;\ env CC=cc perl ${PERLPATH} ${.IMPSRC} elf ${CFLAGS} -fpic -DPIC ;\ echo '#else' ;\ env CC=cc perl ${PERLPATH} ${.IMPSRC} elf ${CFLAGS} ;\ echo '#endif') |\ sed -E 's|(\.file[[:blank:]]+)".*"|\1"${.TARGET}"|' > ${.TARGET} .endif .include Index: stable/11/secure/lib/libcrypto/Makefile.inc =================================================================== --- stable/11/secure/lib/libcrypto/Makefile.inc (revision 325332) +++ stable/11/secure/lib/libcrypto/Makefile.inc (revision 325333) @@ -1,104 +1,106 @@ # $FreeBSD$ .include # OpenSSL version used for manual page generation OPENSSL_VER= 1.0.2k OPENSSL_DATE= 2017-01-26 LCRYPTO_SRC= ${SRCTOP}/crypto/openssl LCRYPTO_DOC= ${LCRYPTO_SRC}/doc CFLAGS+= -I${LCRYPTO_SRC} CFLAGS+= -DTERMIOS -DANSI_SOURCE CFLAGS+= -DOPENSSL_THREADS -DDSO_DLFCN -DHAVE_DLFCN_H .include .if ${TARGET_ENDIANNESS} == 1234 CFLAGS+=-DL_ENDIAN .elif ${TARGET_ENDIANNESS} == 4321 CFLAGS+=-DB_ENDIAN .endif -.if ${MACHINE_CPUARCH} == "amd64" || ${MACHINE_CPUARCH} == "i386" +.if ${MACHINE_CPUARCH} == "aarch64" || ${MACHINE_CPUARCH} == "arm" +ASM_${MACHINE_CPUARCH}= +.elif ${MACHINE_CPUARCH} == "amd64" || ${MACHINE_CPUARCH} == "i386" _ASM_AVX!= { \ echo vzeroall | \ ${CC} -x assembler -o /dev/null -c - 2> /dev/null; \ } && echo yes || echo no .if ${_ASM_AVX} == yes ASM_${MACHINE_CPUARCH}= .endif -.elif ${MACHINE_CPUARCH} == "arm" -ASM_arm= .endif -.if defined(ASM_amd64) +.if defined(ASM_aarch64) +CFLAGS+=-DSHA1_ASM -DSHA256_ASM -DSHA512_ASM +.elif defined(ASM_amd64) CFLAGS+=-DOPENSSL_IA32_SSE2 CFLAGS+=-DAES_ASM -DBSAES_ASM -DVPAES_ASM CFLAGS+=-DECP_NISTZ256_ASM CFLAGS+=-DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_MONT5 -DOPENSSL_BN_ASM_GF2m CFLAGS+=-DMD5_ASM CFLAGS+=-DGHASH_ASM CFLAGS+=-DSHA1_ASM -DSHA256_ASM -DSHA512_ASM CFLAGS+=-DWHIRLPOOL_ASM .elif defined(ASM_arm) CFLAGS+=-DAES_ASM -DBSAES_ASM CFLAGS+=-DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_GF2m CFLAGS+=-DGHASH_ASM CFLAGS+=-DSHA1_ASM -DSHA256_ASM -DSHA512_ASM .elif defined(ASM_i386) CFLAGS+=-DOPENSSL_IA32_SSE2 CFLAGS+=-DAES_ASM -DVPAES_ASM CFLAGS+=-DOPENSSL_BN_ASM_PART_WORDS -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_GF2m CFLAGS+=-DMD5_ASM CFLAGS+=-DGHASH_ASM CFLAGS+=-DRMD160_ASM CFLAGS+=-DSHA1_ASM -DSHA256_ASM -DSHA512_ASM CFLAGS+=-DWHIRLPOOL_ASM .endif MANDIR= ${SHAREDIR}/openssl/man/man .if defined(LIB) _docs= ${LIB} _skip= SSLeay_version des_modes _sec= 3 .else _docs= apps _skip= config _sec= 1 .endif man-update: .for manpage in ${MAN} @(sec=${manpage:E}; \ pod=${manpage:R}.pod; \ cp ${LCRYPTO_DOC}/${_docs}/$$pod .; \ pod2man --section=$$sec --release="${OPENSSL_VER}" \ --date="${OPENSSL_DATE}" --center="OpenSSL" \ $$pod > ${.CURDIR}/man/${manpage}; \ rm -f $$pod; \ ${ECHO} ${manpage}) .endfor man-makefile-update: rm -f ${.CURDIR}/Makefile.man echo '# $$'FreeBSD'$$' >> ${.CURDIR}/Makefile.man echo '# DO NOT EDIT: generated from man-makefile-update target' >> \ ${.CURDIR}/Makefile.man for i in ${LCRYPTO_DOC}/${_docs}/*.pod; do \ fn=`basename $$i .pod`; \ if ! echo '${_skip}' | grep -qw "$$fn"; then \ ${ECHO} "MAN+= $$fn.${_sec}" >> ${.CURDIR}/Makefile.man; \ fi; \ done for i in ${LCRYPTO_DOC}/${_docs}/*.pod; do \ fn=`basename $$i .pod`; \ if ! echo '${_skip}' | grep -qw "$$fn"; then \ perl ${LCRYPTO_SRC}/util/extract-names.pl < $$i | \ awk "/^$$fn\$$/ { next; } \ { print \"MLINKS+= $$fn.${_sec} \" \$$1 \".${_sec}\" }" >> \ ${.CURDIR}/Makefile.man; \ fi; \ done Index: stable/11/secure/lib/libcrypto/aarch64/aesv8-armx.S =================================================================== --- stable/11/secure/lib/libcrypto/aarch64/aesv8-armx.S (nonexistent) +++ stable/11/secure/lib/libcrypto/aarch64/aesv8-armx.S (revision 325333) @@ -0,0 +1,748 @@ +/* $FreeBSD$ */ +/* Do not modify. This file is auto-generated from aesv8-armx.pl. */ +#include "arm_arch.h" + +#if __ARM_MAX_ARCH__>=7 +.text +.align 5 +rcon: +.long 0x01,0x01,0x01,0x01 +.long 0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d // rotate-n-splat +.long 0x1b,0x1b,0x1b,0x1b + +.globl aes_v8_set_encrypt_key +.type aes_v8_set_encrypt_key,%function +.align 5 +aes_v8_set_encrypt_key: +.Lenc_key: + stp x29,x30,[sp,#-16]! + add x29,sp,#0 + mov x3,#-1 + cmp x0,#0 + b.eq .Lenc_key_abort + cmp x2,#0 + b.eq .Lenc_key_abort + mov x3,#-2 + cmp w1,#128 + b.lt .Lenc_key_abort + cmp w1,#256 + b.gt .Lenc_key_abort + tst w1,#0x3f + b.ne .Lenc_key_abort + + adr x3,rcon + cmp w1,#192 + + eor v0.16b,v0.16b,v0.16b + ld1 {v3.16b},[x0],#16 + mov w1,#8 // reuse w1 + ld1 {v1.4s,v2.4s},[x3],#32 + + b.lt .Loop128 + b.eq .L192 + b .L256 + +.align 4 +.Loop128: + tbl v6.16b,{v3.16b},v2.16b + ext v5.16b,v0.16b,v3.16b,#12 + st1 {v3.4s},[x2],#16 + aese v6.16b,v0.16b + subs w1,w1,#1 + + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v6.16b,v6.16b,v1.16b + eor v3.16b,v3.16b,v5.16b + shl v1.16b,v1.16b,#1 + eor v3.16b,v3.16b,v6.16b + b.ne .Loop128 + + ld1 {v1.4s},[x3] + + tbl v6.16b,{v3.16b},v2.16b + ext v5.16b,v0.16b,v3.16b,#12 + st1 {v3.4s},[x2],#16 + aese v6.16b,v0.16b + + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v6.16b,v6.16b,v1.16b + eor v3.16b,v3.16b,v5.16b + shl v1.16b,v1.16b,#1 + eor v3.16b,v3.16b,v6.16b + + tbl v6.16b,{v3.16b},v2.16b + ext v5.16b,v0.16b,v3.16b,#12 + st1 {v3.4s},[x2],#16 + aese v6.16b,v0.16b + + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v6.16b,v6.16b,v1.16b + eor v3.16b,v3.16b,v5.16b + eor v3.16b,v3.16b,v6.16b + st1 {v3.4s},[x2] + add x2,x2,#0x50 + + mov w12,#10 + b .Ldone + +.align 4 +.L192: + ld1 {v4.8b},[x0],#8 + movi v6.16b,#8 // borrow v6.16b + st1 {v3.4s},[x2],#16 + sub v2.16b,v2.16b,v6.16b // adjust the mask + +.Loop192: + tbl v6.16b,{v4.16b},v2.16b + ext v5.16b,v0.16b,v3.16b,#12 + st1 {v4.8b},[x2],#8 + aese v6.16b,v0.16b + subs w1,w1,#1 + + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v3.16b,v3.16b,v5.16b + + dup v5.4s,v3.s[3] + eor v5.16b,v5.16b,v4.16b + eor v6.16b,v6.16b,v1.16b + ext v4.16b,v0.16b,v4.16b,#12 + shl v1.16b,v1.16b,#1 + eor v4.16b,v4.16b,v5.16b + eor v3.16b,v3.16b,v6.16b + eor v4.16b,v4.16b,v6.16b + st1 {v3.4s},[x2],#16 + b.ne .Loop192 + + mov w12,#12 + add x2,x2,#0x20 + b .Ldone + +.align 4 +.L256: + ld1 {v4.16b},[x0] + mov w1,#7 + mov w12,#14 + st1 {v3.4s},[x2],#16 + +.Loop256: + tbl v6.16b,{v4.16b},v2.16b + ext v5.16b,v0.16b,v3.16b,#12 + st1 {v4.4s},[x2],#16 + aese v6.16b,v0.16b + subs w1,w1,#1 + + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v3.16b,v3.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v6.16b,v6.16b,v1.16b + eor v3.16b,v3.16b,v5.16b + shl v1.16b,v1.16b,#1 + eor v3.16b,v3.16b,v6.16b + st1 {v3.4s},[x2],#16 + b.eq .Ldone + + dup v6.4s,v3.s[3] // just splat + ext v5.16b,v0.16b,v4.16b,#12 + aese v6.16b,v0.16b + + eor v4.16b,v4.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v4.16b,v4.16b,v5.16b + ext v5.16b,v0.16b,v5.16b,#12 + eor v4.16b,v4.16b,v5.16b + + eor v4.16b,v4.16b,v6.16b + b .Loop256 + +.Ldone: + str w12,[x2] + mov x3,#0 + +.Lenc_key_abort: + mov x0,x3 // return value + ldr x29,[sp],#16 + ret +.size aes_v8_set_encrypt_key,.-aes_v8_set_encrypt_key + +.globl aes_v8_set_decrypt_key +.type aes_v8_set_decrypt_key,%function +.align 5 +aes_v8_set_decrypt_key: + stp x29,x30,[sp,#-16]! + add x29,sp,#0 + bl .Lenc_key + + cmp x0,#0 + b.ne .Ldec_key_abort + + sub x2,x2,#240 // restore original x2 + mov x4,#-16 + add x0,x2,x12,lsl#4 // end of key schedule + + ld1 {v0.4s},[x2] + ld1 {v1.4s},[x0] + st1 {v0.4s},[x0],x4 + st1 {v1.4s},[x2],#16 + +.Loop_imc: + ld1 {v0.4s},[x2] + ld1 {v1.4s},[x0] + aesimc v0.16b,v0.16b + aesimc v1.16b,v1.16b + st1 {v0.4s},[x0],x4 + st1 {v1.4s},[x2],#16 + cmp x0,x2 + b.hi .Loop_imc + + ld1 {v0.4s},[x2] + aesimc v0.16b,v0.16b + st1 {v0.4s},[x0] + + eor x0,x0,x0 // return value +.Ldec_key_abort: + ldp x29,x30,[sp],#16 + ret +.size aes_v8_set_decrypt_key,.-aes_v8_set_decrypt_key +.globl aes_v8_encrypt +.type aes_v8_encrypt,%function +.align 5 +aes_v8_encrypt: + ldr w3,[x2,#240] + ld1 {v0.4s},[x2],#16 + ld1 {v2.16b},[x0] + sub w3,w3,#2 + ld1 {v1.4s},[x2],#16 + +.Loop_enc: + aese v2.16b,v0.16b + aesmc v2.16b,v2.16b + ld1 {v0.4s},[x2],#16 + subs w3,w3,#2 + aese v2.16b,v1.16b + aesmc v2.16b,v2.16b + ld1 {v1.4s},[x2],#16 + b.gt .Loop_enc + + aese v2.16b,v0.16b + aesmc v2.16b,v2.16b + ld1 {v0.4s},[x2] + aese v2.16b,v1.16b + eor v2.16b,v2.16b,v0.16b + + st1 {v2.16b},[x1] + ret +.size aes_v8_encrypt,.-aes_v8_encrypt +.globl aes_v8_decrypt +.type aes_v8_decrypt,%function +.align 5 +aes_v8_decrypt: + ldr w3,[x2,#240] + ld1 {v0.4s},[x2],#16 + ld1 {v2.16b},[x0] + sub w3,w3,#2 + ld1 {v1.4s},[x2],#16 + +.Loop_dec: + aesd v2.16b,v0.16b + aesimc v2.16b,v2.16b + ld1 {v0.4s},[x2],#16 + subs w3,w3,#2 + aesd v2.16b,v1.16b + aesimc v2.16b,v2.16b + ld1 {v1.4s},[x2],#16 + b.gt .Loop_dec + + aesd v2.16b,v0.16b + aesimc v2.16b,v2.16b + ld1 {v0.4s},[x2] + aesd v2.16b,v1.16b + eor v2.16b,v2.16b,v0.16b + + st1 {v2.16b},[x1] + ret +.size aes_v8_decrypt,.-aes_v8_decrypt +.globl aes_v8_cbc_encrypt +.type aes_v8_cbc_encrypt,%function +.align 5 +aes_v8_cbc_encrypt: + stp x29,x30,[sp,#-16]! + add x29,sp,#0 + subs x2,x2,#16 + mov x8,#16 + b.lo .Lcbc_abort + csel x8,xzr,x8,eq + + cmp w5,#0 // en- or decrypting? + ldr w5,[x3,#240] + and x2,x2,#-16 + ld1 {v6.16b},[x4] + ld1 {v0.16b},[x0],x8 + + ld1 {v16.4s-v17.4s},[x3] // load key schedule... + sub w5,w5,#6 + add x7,x3,x5,lsl#4 // pointer to last 7 round keys + sub w5,w5,#2 + ld1 {v18.4s-v19.4s},[x7],#32 + ld1 {v20.4s-v21.4s},[x7],#32 + ld1 {v22.4s-v23.4s},[x7],#32 + ld1 {v7.4s},[x7] + + add x7,x3,#32 + mov w6,w5 + b.eq .Lcbc_dec + + cmp w5,#2 + eor v0.16b,v0.16b,v6.16b + eor v5.16b,v16.16b,v7.16b + b.eq .Lcbc_enc128 + + ld1 {v2.4s-v3.4s},[x7] + add x7,x3,#16 + add x6,x3,#16*4 + add x12,x3,#16*5 + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + add x14,x3,#16*6 + add x3,x3,#16*7 + b .Lenter_cbc_enc + +.align 4 +.Loop_cbc_enc: + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + st1 {v6.16b},[x1],#16 +.Lenter_cbc_enc: + aese v0.16b,v17.16b + aesmc v0.16b,v0.16b + aese v0.16b,v2.16b + aesmc v0.16b,v0.16b + ld1 {v16.4s},[x6] + cmp w5,#4 + aese v0.16b,v3.16b + aesmc v0.16b,v0.16b + ld1 {v17.4s},[x12] + b.eq .Lcbc_enc192 + + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + ld1 {v16.4s},[x14] + aese v0.16b,v17.16b + aesmc v0.16b,v0.16b + ld1 {v17.4s},[x3] + nop + +.Lcbc_enc192: + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + subs x2,x2,#16 + aese v0.16b,v17.16b + aesmc v0.16b,v0.16b + csel x8,xzr,x8,eq + aese v0.16b,v18.16b + aesmc v0.16b,v0.16b + aese v0.16b,v19.16b + aesmc v0.16b,v0.16b + ld1 {v16.16b},[x0],x8 + aese v0.16b,v20.16b + aesmc v0.16b,v0.16b + eor v16.16b,v16.16b,v5.16b + aese v0.16b,v21.16b + aesmc v0.16b,v0.16b + ld1 {v17.4s},[x7] // re-pre-load rndkey[1] + aese v0.16b,v22.16b + aesmc v0.16b,v0.16b + aese v0.16b,v23.16b + eor v6.16b,v0.16b,v7.16b + b.hs .Loop_cbc_enc + + st1 {v6.16b},[x1],#16 + b .Lcbc_done + +.align 5 +.Lcbc_enc128: + ld1 {v2.4s-v3.4s},[x7] + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + b .Lenter_cbc_enc128 +.Loop_cbc_enc128: + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + st1 {v6.16b},[x1],#16 +.Lenter_cbc_enc128: + aese v0.16b,v17.16b + aesmc v0.16b,v0.16b + subs x2,x2,#16 + aese v0.16b,v2.16b + aesmc v0.16b,v0.16b + csel x8,xzr,x8,eq + aese v0.16b,v3.16b + aesmc v0.16b,v0.16b + aese v0.16b,v18.16b + aesmc v0.16b,v0.16b + aese v0.16b,v19.16b + aesmc v0.16b,v0.16b + ld1 {v16.16b},[x0],x8 + aese v0.16b,v20.16b + aesmc v0.16b,v0.16b + aese v0.16b,v21.16b + aesmc v0.16b,v0.16b + aese v0.16b,v22.16b + aesmc v0.16b,v0.16b + eor v16.16b,v16.16b,v5.16b + aese v0.16b,v23.16b + eor v6.16b,v0.16b,v7.16b + b.hs .Loop_cbc_enc128 + + st1 {v6.16b},[x1],#16 + b .Lcbc_done +.align 5 +.Lcbc_dec: + ld1 {v18.16b},[x0],#16 + subs x2,x2,#32 // bias + add w6,w5,#2 + orr v3.16b,v0.16b,v0.16b + orr v1.16b,v0.16b,v0.16b + orr v19.16b,v18.16b,v18.16b + b.lo .Lcbc_dec_tail + + orr v1.16b,v18.16b,v18.16b + ld1 {v18.16b},[x0],#16 + orr v2.16b,v0.16b,v0.16b + orr v3.16b,v1.16b,v1.16b + orr v19.16b,v18.16b,v18.16b + +.Loop3x_cbc_dec: + aesd v0.16b,v16.16b + aesimc v0.16b,v0.16b + aesd v1.16b,v16.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v16.16b + aesimc v18.16b,v18.16b + ld1 {v16.4s},[x7],#16 + subs w6,w6,#2 + aesd v0.16b,v17.16b + aesimc v0.16b,v0.16b + aesd v1.16b,v17.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v17.16b + aesimc v18.16b,v18.16b + ld1 {v17.4s},[x7],#16 + b.gt .Loop3x_cbc_dec + + aesd v0.16b,v16.16b + aesimc v0.16b,v0.16b + aesd v1.16b,v16.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v16.16b + aesimc v18.16b,v18.16b + eor v4.16b,v6.16b,v7.16b + subs x2,x2,#0x30 + eor v5.16b,v2.16b,v7.16b + csel x6,x2,x6,lo // x6, w6, is zero at this point + aesd v0.16b,v17.16b + aesimc v0.16b,v0.16b + aesd v1.16b,v17.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v17.16b + aesimc v18.16b,v18.16b + eor v17.16b,v3.16b,v7.16b + add x0,x0,x6 // x0 is adjusted in such way that + // at exit from the loop v1.16b-v18.16b + // are loaded with last "words" + orr v6.16b,v19.16b,v19.16b + mov x7,x3 + aesd v0.16b,v20.16b + aesimc v0.16b,v0.16b + aesd v1.16b,v20.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v20.16b + aesimc v18.16b,v18.16b + ld1 {v2.16b},[x0],#16 + aesd v0.16b,v21.16b + aesimc v0.16b,v0.16b + aesd v1.16b,v21.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v21.16b + aesimc v18.16b,v18.16b + ld1 {v3.16b},[x0],#16 + aesd v0.16b,v22.16b + aesimc v0.16b,v0.16b + aesd v1.16b,v22.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v22.16b + aesimc v18.16b,v18.16b + ld1 {v19.16b},[x0],#16 + aesd v0.16b,v23.16b + aesd v1.16b,v23.16b + aesd v18.16b,v23.16b + ld1 {v16.4s},[x7],#16 // re-pre-load rndkey[0] + add w6,w5,#2 + eor v4.16b,v4.16b,v0.16b + eor v5.16b,v5.16b,v1.16b + eor v18.16b,v18.16b,v17.16b + ld1 {v17.4s},[x7],#16 // re-pre-load rndkey[1] + st1 {v4.16b},[x1],#16 + orr v0.16b,v2.16b,v2.16b + st1 {v5.16b},[x1],#16 + orr v1.16b,v3.16b,v3.16b + st1 {v18.16b},[x1],#16 + orr v18.16b,v19.16b,v19.16b + b.hs .Loop3x_cbc_dec + + cmn x2,#0x30 + b.eq .Lcbc_done + nop + +.Lcbc_dec_tail: + aesd v1.16b,v16.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v16.16b + aesimc v18.16b,v18.16b + ld1 {v16.4s},[x7],#16 + subs w6,w6,#2 + aesd v1.16b,v17.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v17.16b + aesimc v18.16b,v18.16b + ld1 {v17.4s},[x7],#16 + b.gt .Lcbc_dec_tail + + aesd v1.16b,v16.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v16.16b + aesimc v18.16b,v18.16b + aesd v1.16b,v17.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v17.16b + aesimc v18.16b,v18.16b + aesd v1.16b,v20.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v20.16b + aesimc v18.16b,v18.16b + cmn x2,#0x20 + aesd v1.16b,v21.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v21.16b + aesimc v18.16b,v18.16b + eor v5.16b,v6.16b,v7.16b + aesd v1.16b,v22.16b + aesimc v1.16b,v1.16b + aesd v18.16b,v22.16b + aesimc v18.16b,v18.16b + eor v17.16b,v3.16b,v7.16b + aesd v1.16b,v23.16b + aesd v18.16b,v23.16b + b.eq .Lcbc_dec_one + eor v5.16b,v5.16b,v1.16b + eor v17.16b,v17.16b,v18.16b + orr v6.16b,v19.16b,v19.16b + st1 {v5.16b},[x1],#16 + st1 {v17.16b},[x1],#16 + b .Lcbc_done + +.Lcbc_dec_one: + eor v5.16b,v5.16b,v18.16b + orr v6.16b,v19.16b,v19.16b + st1 {v5.16b},[x1],#16 + +.Lcbc_done: + st1 {v6.16b},[x4] +.Lcbc_abort: + ldr x29,[sp],#16 + ret +.size aes_v8_cbc_encrypt,.-aes_v8_cbc_encrypt +.globl aes_v8_ctr32_encrypt_blocks +.type aes_v8_ctr32_encrypt_blocks,%function +.align 5 +aes_v8_ctr32_encrypt_blocks: + stp x29,x30,[sp,#-16]! + add x29,sp,#0 + ldr w5,[x3,#240] + + ldr w8, [x4, #12] + ld1 {v0.4s},[x4] + + ld1 {v16.4s-v17.4s},[x3] // load key schedule... + sub w5,w5,#4 + mov x12,#16 + cmp x2,#2 + add x7,x3,x5,lsl#4 // pointer to last 5 round keys + sub w5,w5,#2 + ld1 {v20.4s-v21.4s},[x7],#32 + ld1 {v22.4s-v23.4s},[x7],#32 + ld1 {v7.4s},[x7] + add x7,x3,#32 + mov w6,w5 + csel x12,xzr,x12,lo +#ifndef __ARMEB__ + rev w8, w8 +#endif + orr v1.16b,v0.16b,v0.16b + add w10, w8, #1 + orr v18.16b,v0.16b,v0.16b + add w8, w8, #2 + orr v6.16b,v0.16b,v0.16b + rev w10, w10 + mov v1.s[3],w10 + b.ls .Lctr32_tail + rev w12, w8 + sub x2,x2,#3 // bias + mov v18.s[3],w12 + b .Loop3x_ctr32 + +.align 4 +.Loop3x_ctr32: + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + aese v1.16b,v16.16b + aesmc v1.16b,v1.16b + aese v18.16b,v16.16b + aesmc v18.16b,v18.16b + ld1 {v16.4s},[x7],#16 + subs w6,w6,#2 + aese v0.16b,v17.16b + aesmc v0.16b,v0.16b + aese v1.16b,v17.16b + aesmc v1.16b,v1.16b + aese v18.16b,v17.16b + aesmc v18.16b,v18.16b + ld1 {v17.4s},[x7],#16 + b.gt .Loop3x_ctr32 + + aese v0.16b,v16.16b + aesmc v4.16b,v0.16b + aese v1.16b,v16.16b + aesmc v5.16b,v1.16b + ld1 {v2.16b},[x0],#16 + orr v0.16b,v6.16b,v6.16b + aese v18.16b,v16.16b + aesmc v18.16b,v18.16b + ld1 {v3.16b},[x0],#16 + orr v1.16b,v6.16b,v6.16b + aese v4.16b,v17.16b + aesmc v4.16b,v4.16b + aese v5.16b,v17.16b + aesmc v5.16b,v5.16b + ld1 {v19.16b},[x0],#16 + mov x7,x3 + aese v18.16b,v17.16b + aesmc v17.16b,v18.16b + orr v18.16b,v6.16b,v6.16b + add w9,w8,#1 + aese v4.16b,v20.16b + aesmc v4.16b,v4.16b + aese v5.16b,v20.16b + aesmc v5.16b,v5.16b + eor v2.16b,v2.16b,v7.16b + add w10,w8,#2 + aese v17.16b,v20.16b + aesmc v17.16b,v17.16b + eor v3.16b,v3.16b,v7.16b + add w8,w8,#3 + aese v4.16b,v21.16b + aesmc v4.16b,v4.16b + aese v5.16b,v21.16b + aesmc v5.16b,v5.16b + eor v19.16b,v19.16b,v7.16b + rev w9,w9 + aese v17.16b,v21.16b + aesmc v17.16b,v17.16b + mov v0.s[3], w9 + rev w10,w10 + aese v4.16b,v22.16b + aesmc v4.16b,v4.16b + aese v5.16b,v22.16b + aesmc v5.16b,v5.16b + mov v1.s[3], w10 + rev w12,w8 + aese v17.16b,v22.16b + aesmc v17.16b,v17.16b + mov v18.s[3], w12 + subs x2,x2,#3 + aese v4.16b,v23.16b + aese v5.16b,v23.16b + aese v17.16b,v23.16b + + eor v2.16b,v2.16b,v4.16b + ld1 {v16.4s},[x7],#16 // re-pre-load rndkey[0] + st1 {v2.16b},[x1],#16 + eor v3.16b,v3.16b,v5.16b + mov w6,w5 + st1 {v3.16b},[x1],#16 + eor v19.16b,v19.16b,v17.16b + ld1 {v17.4s},[x7],#16 // re-pre-load rndkey[1] + st1 {v19.16b},[x1],#16 + b.hs .Loop3x_ctr32 + + adds x2,x2,#3 + b.eq .Lctr32_done + cmp x2,#1 + mov x12,#16 + csel x12,xzr,x12,eq + +.Lctr32_tail: + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + aese v1.16b,v16.16b + aesmc v1.16b,v1.16b + ld1 {v16.4s},[x7],#16 + subs w6,w6,#2 + aese v0.16b,v17.16b + aesmc v0.16b,v0.16b + aese v1.16b,v17.16b + aesmc v1.16b,v1.16b + ld1 {v17.4s},[x7],#16 + b.gt .Lctr32_tail + + aese v0.16b,v16.16b + aesmc v0.16b,v0.16b + aese v1.16b,v16.16b + aesmc v1.16b,v1.16b + aese v0.16b,v17.16b + aesmc v0.16b,v0.16b + aese v1.16b,v17.16b + aesmc v1.16b,v1.16b + ld1 {v2.16b},[x0],x12 + aese v0.16b,v20.16b + aesmc v0.16b,v0.16b + aese v1.16b,v20.16b + aesmc v1.16b,v1.16b + ld1 {v3.16b},[x0] + aese v0.16b,v21.16b + aesmc v0.16b,v0.16b + aese v1.16b,v21.16b + aesmc v1.16b,v1.16b + eor v2.16b,v2.16b,v7.16b + aese v0.16b,v22.16b + aesmc v0.16b,v0.16b + aese v1.16b,v22.16b + aesmc v1.16b,v1.16b + eor v3.16b,v3.16b,v7.16b + aese v0.16b,v23.16b + aese v1.16b,v23.16b + + cmp x2,#1 + eor v2.16b,v2.16b,v0.16b + eor v3.16b,v3.16b,v1.16b + st1 {v2.16b},[x1],#16 + b.eq .Lctr32_done + st1 {v3.16b},[x1] + +.Lctr32_done: + ldr x29,[sp],#16 + ret +.size aes_v8_ctr32_encrypt_blocks,.-aes_v8_ctr32_encrypt_blocks +#endif Property changes on: stable/11/secure/lib/libcrypto/aarch64/aesv8-armx.S ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: stable/11/secure/lib/libcrypto/aarch64/ghashv8-armx.S =================================================================== --- stable/11/secure/lib/libcrypto/aarch64/ghashv8-armx.S (nonexistent) +++ stable/11/secure/lib/libcrypto/aarch64/ghashv8-armx.S (revision 325333) @@ -0,0 +1,228 @@ +/* $FreeBSD$ */ +/* Do not modify. This file is auto-generated from ghashv8-armx.pl. */ +#include "arm_arch.h" + +.text +.global gcm_init_v8 +.type gcm_init_v8,%function +.align 4 +gcm_init_v8: + ld1 {v17.2d},[x1] //load input H + movi v19.16b,#0xe1 + shl v19.2d,v19.2d,#57 //0xc2.0 + ext v3.16b,v17.16b,v17.16b,#8 + ushr v18.2d,v19.2d,#63 + dup v17.4s,v17.s[1] + ext v16.16b,v18.16b,v19.16b,#8 //t0=0xc2....01 + ushr v18.2d,v3.2d,#63 + sshr v17.4s,v17.4s,#31 //broadcast carry bit + and v18.16b,v18.16b,v16.16b + shl v3.2d,v3.2d,#1 + ext v18.16b,v18.16b,v18.16b,#8 + and v16.16b,v16.16b,v17.16b + orr v3.16b,v3.16b,v18.16b //H<<<=1 + eor v20.16b,v3.16b,v16.16b //twisted H + st1 {v20.2d},[x0],#16 //store Htable[0] + + //calculate H^2 + ext v16.16b,v20.16b,v20.16b,#8 //Karatsuba pre-processing + pmull v0.1q,v20.1d,v20.1d + eor v16.16b,v16.16b,v20.16b + pmull2 v2.1q,v20.2d,v20.2d + pmull v1.1q,v16.1d,v16.1d + + ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing + eor v18.16b,v0.16b,v2.16b + eor v1.16b,v1.16b,v17.16b + eor v1.16b,v1.16b,v18.16b + pmull v18.1q,v0.1d,v19.1d //1st phase + + ins v2.d[0],v1.d[1] + ins v1.d[1],v0.d[0] + eor v0.16b,v1.16b,v18.16b + + ext v18.16b,v0.16b,v0.16b,#8 //2nd phase + pmull v0.1q,v0.1d,v19.1d + eor v18.16b,v18.16b,v2.16b + eor v22.16b,v0.16b,v18.16b + + ext v17.16b,v22.16b,v22.16b,#8 //Karatsuba pre-processing + eor v17.16b,v17.16b,v22.16b + ext v21.16b,v16.16b,v17.16b,#8 //pack Karatsuba pre-processed + st1 {v21.2d-v22.2d},[x0] //store Htable[1..2] + + ret +.size gcm_init_v8,.-gcm_init_v8 +.global gcm_gmult_v8 +.type gcm_gmult_v8,%function +.align 4 +gcm_gmult_v8: + ld1 {v17.2d},[x0] //load Xi + movi v19.16b,#0xe1 + ld1 {v20.2d-v21.2d},[x1] //load twisted H, ... + shl v19.2d,v19.2d,#57 +#ifndef __ARMEB__ + rev64 v17.16b,v17.16b +#endif + ext v3.16b,v17.16b,v17.16b,#8 + + pmull v0.1q,v20.1d,v3.1d //H.lo·Xi.lo + eor v17.16b,v17.16b,v3.16b //Karatsuba pre-processing + pmull2 v2.1q,v20.2d,v3.2d //H.hi·Xi.hi + pmull v1.1q,v21.1d,v17.1d //(H.lo+H.hi)·(Xi.lo+Xi.hi) + + ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing + eor v18.16b,v0.16b,v2.16b + eor v1.16b,v1.16b,v17.16b + eor v1.16b,v1.16b,v18.16b + pmull v18.1q,v0.1d,v19.1d //1st phase of reduction + + ins v2.d[0],v1.d[1] + ins v1.d[1],v0.d[0] + eor v0.16b,v1.16b,v18.16b + + ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction + pmull v0.1q,v0.1d,v19.1d + eor v18.16b,v18.16b,v2.16b + eor v0.16b,v0.16b,v18.16b + +#ifndef __ARMEB__ + rev64 v0.16b,v0.16b +#endif + ext v0.16b,v0.16b,v0.16b,#8 + st1 {v0.2d},[x0] //write out Xi + + ret +.size gcm_gmult_v8,.-gcm_gmult_v8 +.global gcm_ghash_v8 +.type gcm_ghash_v8,%function +.align 4 +gcm_ghash_v8: + ld1 {v0.2d},[x0] //load [rotated] Xi + //"[rotated]" means that + //loaded value would have + //to be rotated in order to + //make it appear as in + //alorithm specification + subs x3,x3,#32 //see if x3 is 32 or larger + mov x12,#16 //x12 is used as post- + //increment for input pointer; + //as loop is modulo-scheduled + //x12 is zeroed just in time + //to preclude oversteping + //inp[len], which means that + //last block[s] are actually + //loaded twice, but last + //copy is not processed + ld1 {v20.2d-v21.2d},[x1],#32 //load twisted H, ..., H^2 + movi v19.16b,#0xe1 + ld1 {v22.2d},[x1] + csel x12,xzr,x12,eq //is it time to zero x12? + ext v0.16b,v0.16b,v0.16b,#8 //rotate Xi + ld1 {v16.2d},[x2],#16 //load [rotated] I[0] + shl v19.2d,v19.2d,#57 //compose 0xc2.0 constant +#ifndef __ARMEB__ + rev64 v16.16b,v16.16b + rev64 v0.16b,v0.16b +#endif + ext v3.16b,v16.16b,v16.16b,#8 //rotate I[0] + b.lo .Lodd_tail_v8 //x3 was less than 32 + ld1 {v17.2d},[x2],x12 //load [rotated] I[1] +#ifndef __ARMEB__ + rev64 v17.16b,v17.16b +#endif + ext v7.16b,v17.16b,v17.16b,#8 + eor v3.16b,v3.16b,v0.16b //I[i]^=Xi + pmull v4.1q,v20.1d,v7.1d //H·Ii+1 + eor v17.16b,v17.16b,v7.16b //Karatsuba pre-processing + pmull2 v6.1q,v20.2d,v7.2d + b .Loop_mod2x_v8 + +.align 4 +.Loop_mod2x_v8: + ext v18.16b,v3.16b,v3.16b,#8 + subs x3,x3,#32 //is there more data? + pmull v0.1q,v22.1d,v3.1d //H^2.lo·Xi.lo + csel x12,xzr,x12,lo //is it time to zero x12? + + pmull v5.1q,v21.1d,v17.1d + eor v18.16b,v18.16b,v3.16b //Karatsuba pre-processing + pmull2 v2.1q,v22.2d,v3.2d //H^2.hi·Xi.hi + eor v0.16b,v0.16b,v4.16b //accumulate + pmull2 v1.1q,v21.2d,v18.2d //(H^2.lo+H^2.hi)·(Xi.lo+Xi.hi) + ld1 {v16.2d},[x2],x12 //load [rotated] I[i+2] + + eor v2.16b,v2.16b,v6.16b + csel x12,xzr,x12,eq //is it time to zero x12? + eor v1.16b,v1.16b,v5.16b + + ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing + eor v18.16b,v0.16b,v2.16b + eor v1.16b,v1.16b,v17.16b + ld1 {v17.2d},[x2],x12 //load [rotated] I[i+3] +#ifndef __ARMEB__ + rev64 v16.16b,v16.16b +#endif + eor v1.16b,v1.16b,v18.16b + pmull v18.1q,v0.1d,v19.1d //1st phase of reduction + +#ifndef __ARMEB__ + rev64 v17.16b,v17.16b +#endif + ins v2.d[0],v1.d[1] + ins v1.d[1],v0.d[0] + ext v7.16b,v17.16b,v17.16b,#8 + ext v3.16b,v16.16b,v16.16b,#8 + eor v0.16b,v1.16b,v18.16b + pmull v4.1q,v20.1d,v7.1d //H·Ii+1 + eor v3.16b,v3.16b,v2.16b //accumulate v3.16b early + + ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction + pmull v0.1q,v0.1d,v19.1d + eor v3.16b,v3.16b,v18.16b + eor v17.16b,v17.16b,v7.16b //Karatsuba pre-processing + eor v3.16b,v3.16b,v0.16b + pmull2 v6.1q,v20.2d,v7.2d + b.hs .Loop_mod2x_v8 //there was at least 32 more bytes + + eor v2.16b,v2.16b,v18.16b + ext v3.16b,v16.16b,v16.16b,#8 //re-construct v3.16b + adds x3,x3,#32 //re-construct x3 + eor v0.16b,v0.16b,v2.16b //re-construct v0.16b + b.eq .Ldone_v8 //is x3 zero? +.Lodd_tail_v8: + ext v18.16b,v0.16b,v0.16b,#8 + eor v3.16b,v3.16b,v0.16b //inp^=Xi + eor v17.16b,v16.16b,v18.16b //v17.16b is rotated inp^Xi + + pmull v0.1q,v20.1d,v3.1d //H.lo·Xi.lo + eor v17.16b,v17.16b,v3.16b //Karatsuba pre-processing + pmull2 v2.1q,v20.2d,v3.2d //H.hi·Xi.hi + pmull v1.1q,v21.1d,v17.1d //(H.lo+H.hi)·(Xi.lo+Xi.hi) + + ext v17.16b,v0.16b,v2.16b,#8 //Karatsuba post-processing + eor v18.16b,v0.16b,v2.16b + eor v1.16b,v1.16b,v17.16b + eor v1.16b,v1.16b,v18.16b + pmull v18.1q,v0.1d,v19.1d //1st phase of reduction + + ins v2.d[0],v1.d[1] + ins v1.d[1],v0.d[0] + eor v0.16b,v1.16b,v18.16b + + ext v18.16b,v0.16b,v0.16b,#8 //2nd phase of reduction + pmull v0.1q,v0.1d,v19.1d + eor v18.16b,v18.16b,v2.16b + eor v0.16b,v0.16b,v18.16b + +.Ldone_v8: +#ifndef __ARMEB__ + rev64 v0.16b,v0.16b +#endif + ext v0.16b,v0.16b,v0.16b,#8 + st1 {v0.2d},[x0] //write out Xi + + ret +.size gcm_ghash_v8,.-gcm_ghash_v8 +.asciz "GHASH for ARMv8, CRYPTOGAMS by " +.align 2 Property changes on: stable/11/secure/lib/libcrypto/aarch64/ghashv8-armx.S ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: stable/11/secure/lib/libcrypto/aarch64/sha1-armv8.S =================================================================== --- stable/11/secure/lib/libcrypto/aarch64/sha1-armv8.S (nonexistent) +++ stable/11/secure/lib/libcrypto/aarch64/sha1-armv8.S (revision 325333) @@ -0,0 +1,1213 @@ +/* $FreeBSD$ */ +/* Do not modify. This file is auto-generated from sha1-armv8.pl. */ +#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 w20,w21,[x0] + ldp w22,w23,[x0,#8] + ldr w24,[x0,#16] + +.Loop: + ldr x3,[x1],#64 + movz w28,#0x7999 + sub x2,x2,#1 + movk w28,#0x5a82,lsl#16 +#ifdef __ARMEB__ + ror x3,x3,#32 +#else + rev32 x3,x3 +#endif + add w24,w24,w28 // warm it up + add w24,w24,w3 + lsr x4,x3,#32 + ldr x5,[x1,#-56] + bic w25,w23,w21 + and w26,w22,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + orr w25,w25,w26 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + add w23,w23,w4 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) +#ifdef __ARMEB__ + ror x5,x5,#32 +#else + rev32 x5,x5 +#endif + bic w25,w22,w20 + and w26,w21,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + orr w25,w25,w26 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + add w22,w22,w5 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + lsr x6,x5,#32 + ldr x7,[x1,#-48] + bic w25,w21,w24 + and w26,w20,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + orr w25,w25,w26 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + add w21,w21,w6 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) +#ifdef __ARMEB__ + ror x7,x7,#32 +#else + rev32 x7,x7 +#endif + bic w25,w20,w23 + and w26,w24,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + orr w25,w25,w26 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + add w20,w20,w7 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + lsr x8,x7,#32 + ldr x9,[x1,#-40] + bic w25,w24,w22 + and w26,w23,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + orr w25,w25,w26 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + add w24,w24,w8 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) +#ifdef __ARMEB__ + ror x9,x9,#32 +#else + rev32 x9,x9 +#endif + bic w25,w23,w21 + and w26,w22,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + orr w25,w25,w26 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + add w23,w23,w9 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + lsr x10,x9,#32 + ldr x11,[x1,#-32] + bic w25,w22,w20 + and w26,w21,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + orr w25,w25,w26 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + add w22,w22,w10 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) +#ifdef __ARMEB__ + ror x11,x11,#32 +#else + rev32 x11,x11 +#endif + bic w25,w21,w24 + and w26,w20,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + orr w25,w25,w26 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + add w21,w21,w11 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + lsr x12,x11,#32 + ldr x13,[x1,#-24] + bic w25,w20,w23 + and w26,w24,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + orr w25,w25,w26 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + add w20,w20,w12 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) +#ifdef __ARMEB__ + ror x13,x13,#32 +#else + rev32 x13,x13 +#endif + bic w25,w24,w22 + and w26,w23,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + orr w25,w25,w26 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + add w24,w24,w13 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + lsr x14,x13,#32 + ldr x15,[x1,#-16] + bic w25,w23,w21 + and w26,w22,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + orr w25,w25,w26 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + add w23,w23,w14 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) +#ifdef __ARMEB__ + ror x15,x15,#32 +#else + rev32 x15,x15 +#endif + bic w25,w22,w20 + and w26,w21,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + orr w25,w25,w26 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + add w22,w22,w15 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + lsr x16,x15,#32 + ldr x17,[x1,#-8] + bic w25,w21,w24 + and w26,w20,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + orr w25,w25,w26 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + add w21,w21,w16 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) +#ifdef __ARMEB__ + ror x17,x17,#32 +#else + rev32 x17,x17 +#endif + bic w25,w20,w23 + and w26,w24,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + orr w25,w25,w26 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + add w20,w20,w17 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + lsr x19,x17,#32 + eor w3,w3,w5 + bic w25,w24,w22 + and w26,w23,w22 + ror w27,w21,#27 + eor w3,w3,w11 + add w24,w24,w28 // future e+=K + orr w25,w25,w26 + add w20,w20,w27 // e+=rot(a,5) + eor w3,w3,w16 + ror w22,w22,#2 + add w24,w24,w19 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w3,w3,#31 + eor w4,w4,w6 + bic w25,w23,w21 + and w26,w22,w21 + ror w27,w20,#27 + eor w4,w4,w12 + add w23,w23,w28 // future e+=K + orr w25,w25,w26 + add w24,w24,w27 // e+=rot(a,5) + eor w4,w4,w17 + ror w21,w21,#2 + add w23,w23,w3 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w4,w4,#31 + eor w5,w5,w7 + bic w25,w22,w20 + and w26,w21,w20 + ror w27,w24,#27 + eor w5,w5,w13 + add w22,w22,w28 // future e+=K + orr w25,w25,w26 + add w23,w23,w27 // e+=rot(a,5) + eor w5,w5,w19 + ror w20,w20,#2 + add w22,w22,w4 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w5,w5,#31 + eor w6,w6,w8 + bic w25,w21,w24 + and w26,w20,w24 + ror w27,w23,#27 + eor w6,w6,w14 + add w21,w21,w28 // future e+=K + orr w25,w25,w26 + add w22,w22,w27 // e+=rot(a,5) + eor w6,w6,w3 + ror w24,w24,#2 + add w21,w21,w5 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w6,w6,#31 + eor w7,w7,w9 + bic w25,w20,w23 + and w26,w24,w23 + ror w27,w22,#27 + eor w7,w7,w15 + add w20,w20,w28 // future e+=K + orr w25,w25,w26 + add w21,w21,w27 // e+=rot(a,5) + eor w7,w7,w4 + ror w23,w23,#2 + add w20,w20,w6 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w7,w7,#31 + movz w28,#0xeba1 + movk w28,#0x6ed9,lsl#16 + eor w8,w8,w10 + bic w25,w24,w22 + and w26,w23,w22 + ror w27,w21,#27 + eor w8,w8,w16 + add w24,w24,w28 // future e+=K + orr w25,w25,w26 + add w20,w20,w27 // e+=rot(a,5) + eor w8,w8,w5 + ror w22,w22,#2 + add w24,w24,w7 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w8,w8,#31 + eor w9,w9,w11 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w9,w9,w17 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w9,w9,w6 + add w23,w23,w8 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w9,w9,#31 + eor w10,w10,w12 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w10,w10,w19 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w10,w10,w7 + add w22,w22,w9 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w10,w10,#31 + eor w11,w11,w13 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w11,w11,w3 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w11,w11,w8 + add w21,w21,w10 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w11,w11,#31 + eor w12,w12,w14 + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w12,w12,w4 + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + eor w12,w12,w9 + add w20,w20,w11 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w12,w12,#31 + eor w13,w13,w15 + eor w25,w24,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + eor w13,w13,w5 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + eor w13,w13,w10 + add w24,w24,w12 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w13,w13,#31 + eor w14,w14,w16 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w14,w14,w6 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w14,w14,w11 + add w23,w23,w13 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w14,w14,#31 + eor w15,w15,w17 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w15,w15,w7 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w15,w15,w12 + add w22,w22,w14 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w15,w15,#31 + eor w16,w16,w19 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w16,w16,w8 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w16,w16,w13 + add w21,w21,w15 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w16,w16,#31 + eor w17,w17,w3 + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w17,w17,w9 + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + eor w17,w17,w14 + add w20,w20,w16 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w17,w17,#31 + eor w19,w19,w4 + eor w25,w24,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + eor w19,w19,w10 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + eor w19,w19,w15 + add w24,w24,w17 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w19,w19,#31 + eor w3,w3,w5 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w3,w3,w11 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w3,w3,w16 + add w23,w23,w19 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w3,w3,#31 + eor w4,w4,w6 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w4,w4,w12 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w4,w4,w17 + add w22,w22,w3 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w4,w4,#31 + eor w5,w5,w7 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w5,w5,w13 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w5,w5,w19 + add w21,w21,w4 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w5,w5,#31 + eor w6,w6,w8 + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w6,w6,w14 + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + eor w6,w6,w3 + add w20,w20,w5 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w6,w6,#31 + eor w7,w7,w9 + eor w25,w24,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + eor w7,w7,w15 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + eor w7,w7,w4 + add w24,w24,w6 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w7,w7,#31 + eor w8,w8,w10 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w8,w8,w16 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w8,w8,w5 + add w23,w23,w7 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w8,w8,#31 + eor w9,w9,w11 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w9,w9,w17 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w9,w9,w6 + add w22,w22,w8 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w9,w9,#31 + eor w10,w10,w12 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w10,w10,w19 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w10,w10,w7 + add w21,w21,w9 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w10,w10,#31 + eor w11,w11,w13 + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w11,w11,w3 + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + eor w11,w11,w8 + add w20,w20,w10 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w11,w11,#31 + movz w28,#0xbcdc + movk w28,#0x8f1b,lsl#16 + eor w12,w12,w14 + eor w25,w24,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + eor w12,w12,w4 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + eor w12,w12,w9 + add w24,w24,w11 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w12,w12,#31 + orr w25,w21,w22 + and w26,w21,w22 + eor w13,w13,w15 + ror w27,w20,#27 + and w25,w25,w23 + add w23,w23,w28 // future e+=K + eor w13,w13,w5 + add w24,w24,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w21,w21,#2 + eor w13,w13,w10 + add w23,w23,w12 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w13,w13,#31 + orr w25,w20,w21 + and w26,w20,w21 + eor w14,w14,w16 + ror w27,w24,#27 + and w25,w25,w22 + add w22,w22,w28 // future e+=K + eor w14,w14,w6 + add w23,w23,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w20,w20,#2 + eor w14,w14,w11 + add w22,w22,w13 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w14,w14,#31 + orr w25,w24,w20 + and w26,w24,w20 + eor w15,w15,w17 + ror w27,w23,#27 + and w25,w25,w21 + add w21,w21,w28 // future e+=K + eor w15,w15,w7 + add w22,w22,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w24,w24,#2 + eor w15,w15,w12 + add w21,w21,w14 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w15,w15,#31 + orr w25,w23,w24 + and w26,w23,w24 + eor w16,w16,w19 + ror w27,w22,#27 + and w25,w25,w20 + add w20,w20,w28 // future e+=K + eor w16,w16,w8 + add w21,w21,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w23,w23,#2 + eor w16,w16,w13 + add w20,w20,w15 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w16,w16,#31 + orr w25,w22,w23 + and w26,w22,w23 + eor w17,w17,w3 + ror w27,w21,#27 + and w25,w25,w24 + add w24,w24,w28 // future e+=K + eor w17,w17,w9 + add w20,w20,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w22,w22,#2 + eor w17,w17,w14 + add w24,w24,w16 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w17,w17,#31 + orr w25,w21,w22 + and w26,w21,w22 + eor w19,w19,w4 + ror w27,w20,#27 + and w25,w25,w23 + add w23,w23,w28 // future e+=K + eor w19,w19,w10 + add w24,w24,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w21,w21,#2 + eor w19,w19,w15 + add w23,w23,w17 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w19,w19,#31 + orr w25,w20,w21 + and w26,w20,w21 + eor w3,w3,w5 + ror w27,w24,#27 + and w25,w25,w22 + add w22,w22,w28 // future e+=K + eor w3,w3,w11 + add w23,w23,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w20,w20,#2 + eor w3,w3,w16 + add w22,w22,w19 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w3,w3,#31 + orr w25,w24,w20 + and w26,w24,w20 + eor w4,w4,w6 + ror w27,w23,#27 + and w25,w25,w21 + add w21,w21,w28 // future e+=K + eor w4,w4,w12 + add w22,w22,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w24,w24,#2 + eor w4,w4,w17 + add w21,w21,w3 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w4,w4,#31 + orr w25,w23,w24 + and w26,w23,w24 + eor w5,w5,w7 + ror w27,w22,#27 + and w25,w25,w20 + add w20,w20,w28 // future e+=K + eor w5,w5,w13 + add w21,w21,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w23,w23,#2 + eor w5,w5,w19 + add w20,w20,w4 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w5,w5,#31 + orr w25,w22,w23 + and w26,w22,w23 + eor w6,w6,w8 + ror w27,w21,#27 + and w25,w25,w24 + add w24,w24,w28 // future e+=K + eor w6,w6,w14 + add w20,w20,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w22,w22,#2 + eor w6,w6,w3 + add w24,w24,w5 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w6,w6,#31 + orr w25,w21,w22 + and w26,w21,w22 + eor w7,w7,w9 + ror w27,w20,#27 + and w25,w25,w23 + add w23,w23,w28 // future e+=K + eor w7,w7,w15 + add w24,w24,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w21,w21,#2 + eor w7,w7,w4 + add w23,w23,w6 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w7,w7,#31 + orr w25,w20,w21 + and w26,w20,w21 + eor w8,w8,w10 + ror w27,w24,#27 + and w25,w25,w22 + add w22,w22,w28 // future e+=K + eor w8,w8,w16 + add w23,w23,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w20,w20,#2 + eor w8,w8,w5 + add w22,w22,w7 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w8,w8,#31 + orr w25,w24,w20 + and w26,w24,w20 + eor w9,w9,w11 + ror w27,w23,#27 + and w25,w25,w21 + add w21,w21,w28 // future e+=K + eor w9,w9,w17 + add w22,w22,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w24,w24,#2 + eor w9,w9,w6 + add w21,w21,w8 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w9,w9,#31 + orr w25,w23,w24 + and w26,w23,w24 + eor w10,w10,w12 + ror w27,w22,#27 + and w25,w25,w20 + add w20,w20,w28 // future e+=K + eor w10,w10,w19 + add w21,w21,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w23,w23,#2 + eor w10,w10,w7 + add w20,w20,w9 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w10,w10,#31 + orr w25,w22,w23 + and w26,w22,w23 + eor w11,w11,w13 + ror w27,w21,#27 + and w25,w25,w24 + add w24,w24,w28 // future e+=K + eor w11,w11,w3 + add w20,w20,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w22,w22,#2 + eor w11,w11,w8 + add w24,w24,w10 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w11,w11,#31 + orr w25,w21,w22 + and w26,w21,w22 + eor w12,w12,w14 + ror w27,w20,#27 + and w25,w25,w23 + add w23,w23,w28 // future e+=K + eor w12,w12,w4 + add w24,w24,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w21,w21,#2 + eor w12,w12,w9 + add w23,w23,w11 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w12,w12,#31 + orr w25,w20,w21 + and w26,w20,w21 + eor w13,w13,w15 + ror w27,w24,#27 + and w25,w25,w22 + add w22,w22,w28 // future e+=K + eor w13,w13,w5 + add w23,w23,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w20,w20,#2 + eor w13,w13,w10 + add w22,w22,w12 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w13,w13,#31 + orr w25,w24,w20 + and w26,w24,w20 + eor w14,w14,w16 + ror w27,w23,#27 + and w25,w25,w21 + add w21,w21,w28 // future e+=K + eor w14,w14,w6 + add w22,w22,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w24,w24,#2 + eor w14,w14,w11 + add w21,w21,w13 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w14,w14,#31 + orr w25,w23,w24 + and w26,w23,w24 + eor w15,w15,w17 + ror w27,w22,#27 + and w25,w25,w20 + add w20,w20,w28 // future e+=K + eor w15,w15,w7 + add w21,w21,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w23,w23,#2 + eor w15,w15,w12 + add w20,w20,w14 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w15,w15,#31 + movz w28,#0xc1d6 + movk w28,#0xca62,lsl#16 + orr w25,w22,w23 + and w26,w22,w23 + eor w16,w16,w19 + ror w27,w21,#27 + and w25,w25,w24 + add w24,w24,w28 // future e+=K + eor w16,w16,w8 + add w20,w20,w27 // e+=rot(a,5) + orr w25,w25,w26 + ror w22,w22,#2 + eor w16,w16,w13 + add w24,w24,w15 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w16,w16,#31 + eor w17,w17,w3 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w17,w17,w9 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w17,w17,w14 + add w23,w23,w16 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w17,w17,#31 + eor w19,w19,w4 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w19,w19,w10 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w19,w19,w15 + add w22,w22,w17 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w19,w19,#31 + eor w3,w3,w5 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w3,w3,w11 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w3,w3,w16 + add w21,w21,w19 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w3,w3,#31 + eor w4,w4,w6 + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w4,w4,w12 + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + eor w4,w4,w17 + add w20,w20,w3 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w4,w4,#31 + eor w5,w5,w7 + eor w25,w24,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + eor w5,w5,w13 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + eor w5,w5,w19 + add w24,w24,w4 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w5,w5,#31 + eor w6,w6,w8 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w6,w6,w14 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w6,w6,w3 + add w23,w23,w5 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w6,w6,#31 + eor w7,w7,w9 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w7,w7,w15 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w7,w7,w4 + add w22,w22,w6 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w7,w7,#31 + eor w8,w8,w10 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w8,w8,w16 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w8,w8,w5 + add w21,w21,w7 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w8,w8,#31 + eor w9,w9,w11 + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w9,w9,w17 + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + eor w9,w9,w6 + add w20,w20,w8 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w9,w9,#31 + eor w10,w10,w12 + eor w25,w24,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + eor w10,w10,w19 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + eor w10,w10,w7 + add w24,w24,w9 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w10,w10,#31 + eor w11,w11,w13 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w11,w11,w3 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w11,w11,w8 + add w23,w23,w10 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w11,w11,#31 + eor w12,w12,w14 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w12,w12,w4 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w12,w12,w9 + add w22,w22,w11 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w12,w12,#31 + eor w13,w13,w15 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w13,w13,w5 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w13,w13,w10 + add w21,w21,w12 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w13,w13,#31 + eor w14,w14,w16 + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w14,w14,w6 + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + eor w14,w14,w11 + add w20,w20,w13 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ror w14,w14,#31 + eor w15,w15,w17 + eor w25,w24,w22 + ror w27,w21,#27 + add w24,w24,w28 // future e+=K + eor w15,w15,w7 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + eor w15,w15,w12 + add w24,w24,w14 // future e+=X[i] + add w20,w20,w25 // e+=F(b,c,d) + ror w15,w15,#31 + eor w16,w16,w19 + eor w25,w23,w21 + ror w27,w20,#27 + add w23,w23,w28 // future e+=K + eor w16,w16,w8 + eor w25,w25,w22 + add w24,w24,w27 // e+=rot(a,5) + ror w21,w21,#2 + eor w16,w16,w13 + add w23,w23,w15 // future e+=X[i] + add w24,w24,w25 // e+=F(b,c,d) + ror w16,w16,#31 + eor w17,w17,w3 + eor w25,w22,w20 + ror w27,w24,#27 + add w22,w22,w28 // future e+=K + eor w17,w17,w9 + eor w25,w25,w21 + add w23,w23,w27 // e+=rot(a,5) + ror w20,w20,#2 + eor w17,w17,w14 + add w22,w22,w16 // future e+=X[i] + add w23,w23,w25 // e+=F(b,c,d) + ror w17,w17,#31 + eor w19,w19,w4 + eor w25,w21,w24 + ror w27,w23,#27 + add w21,w21,w28 // future e+=K + eor w19,w19,w10 + eor w25,w25,w20 + add w22,w22,w27 // e+=rot(a,5) + ror w24,w24,#2 + eor w19,w19,w15 + add w21,w21,w17 // future e+=X[i] + add w22,w22,w25 // e+=F(b,c,d) + ror w19,w19,#31 + ldp w4,w5,[x0] + eor w25,w20,w23 + ror w27,w22,#27 + add w20,w20,w28 // future e+=K + eor w25,w25,w24 + add w21,w21,w27 // e+=rot(a,5) + ror w23,w23,#2 + add w20,w20,w19 // future e+=X[i] + add w21,w21,w25 // e+=F(b,c,d) + ldp w6,w7,[x0,#8] + eor w25,w24,w22 + ror w27,w21,#27 + eor w25,w25,w23 + add w20,w20,w27 // e+=rot(a,5) + ror w22,w22,#2 + ldr w8,[x0,#16] + add w20,w20,w25 // e+=F(b,c,d) + add w21,w21,w5 + add w22,w22,w6 + add w20,w20,w4 + add w23,w23,w7 + add w24,w24,w8 + stp w20,w21,[x0] + stp w22,w23,[x0,#8] + str w24,[x0,#16] + cbnz x2,.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 +.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 v1.16b,v1.16b,v1.16b + ld1 {v0.4s},[x0],#16 + ld1 {v1.s}[0],[x0] + sub x0,x0,#16 + ld1 {v16.4s-v19.4s},[x4] + +.Loop_hw: + ld1 {v4.16b-v7.16b},[x1],#64 + sub x2,x2,#1 + rev32 v4.16b,v4.16b + rev32 v5.16b,v5.16b + + add v20.4s,v16.4s,v4.4s + rev32 v6.16b,v6.16b + orr v22.16b,v0.16b,v0.16b // offload + + add v21.4s,v16.4s,v5.4s + rev32 v7.16b,v7.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b + .inst 0x5e140020 //sha1c v0.16b,v1.16b,v20.4s // 0 + add v20.4s,v16.4s,v6.4s + .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 1 + .inst 0x5e150060 //sha1c v0.16b,v3.16b,v21.4s + add v21.4s,v16.4s,v7.4s + .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b + .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 2 + .inst 0x5e140040 //sha1c v0.16b,v2.16b,v20.4s + add v20.4s,v16.4s,v4.4s + .inst 0x5e281885 //sha1su1 v5.16b,v4.16b + .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 3 + .inst 0x5e150060 //sha1c v0.16b,v3.16b,v21.4s + add v21.4s,v17.4s,v5.4s + .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b + .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 4 + .inst 0x5e140040 //sha1c v0.16b,v2.16b,v20.4s + add v20.4s,v17.4s,v6.4s + .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b + .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 5 + .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s + add v21.4s,v17.4s,v7.4s + .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b + .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 6 + .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s + add v20.4s,v17.4s,v4.4s + .inst 0x5e281885 //sha1su1 v5.16b,v4.16b + .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 7 + .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s + add v21.4s,v17.4s,v5.4s + .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b + .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 8 + .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s + add v20.4s,v18.4s,v6.4s + .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b + .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 9 + .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s + add v21.4s,v18.4s,v7.4s + .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b + .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 10 + .inst 0x5e142040 //sha1m v0.16b,v2.16b,v20.4s + add v20.4s,v18.4s,v4.4s + .inst 0x5e281885 //sha1su1 v5.16b,v4.16b + .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 11 + .inst 0x5e152060 //sha1m v0.16b,v3.16b,v21.4s + add v21.4s,v18.4s,v5.4s + .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b + .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 12 + .inst 0x5e142040 //sha1m v0.16b,v2.16b,v20.4s + add v20.4s,v18.4s,v6.4s + .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b + .inst 0x5e0630a4 //sha1su0 v4.16b,v5.16b,v6.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 13 + .inst 0x5e152060 //sha1m v0.16b,v3.16b,v21.4s + add v21.4s,v19.4s,v7.4s + .inst 0x5e2818e4 //sha1su1 v4.16b,v7.16b + .inst 0x5e0730c5 //sha1su0 v5.16b,v6.16b,v7.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 14 + .inst 0x5e142040 //sha1m v0.16b,v2.16b,v20.4s + add v20.4s,v19.4s,v4.4s + .inst 0x5e281885 //sha1su1 v5.16b,v4.16b + .inst 0x5e0430e6 //sha1su0 v6.16b,v7.16b,v4.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 15 + .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s + add v21.4s,v19.4s,v5.4s + .inst 0x5e2818a6 //sha1su1 v6.16b,v5.16b + .inst 0x5e053087 //sha1su0 v7.16b,v4.16b,v5.16b + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 16 + .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s + add v20.4s,v19.4s,v6.4s + .inst 0x5e2818c7 //sha1su1 v7.16b,v6.16b + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 17 + .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s + add v21.4s,v19.4s,v7.4s + + .inst 0x5e280803 //sha1h v3.16b,v0.16b // 18 + .inst 0x5e141040 //sha1p v0.16b,v2.16b,v20.4s + + .inst 0x5e280802 //sha1h v2.16b,v0.16b // 19 + .inst 0x5e151060 //sha1p v0.16b,v3.16b,v21.4s + + add v1.4s,v1.4s,v2.4s + add v0.4s,v0.4s,v22.4s + + cbnz x2,.Loop_hw + + st1 {v0.4s},[x0],#16 + st1 {v1.s}[0],[x0] + + 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 " +.align 2 +.comm OPENSSL_armcap_P,4,4 Property changes on: stable/11/secure/lib/libcrypto/aarch64/sha1-armv8.S ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: stable/11/secure/lib/libcrypto/aarch64/sha256-armv8.S =================================================================== --- stable/11/secure/lib/libcrypto/aarch64/sha256-armv8.S (nonexistent) +++ stable/11/secure/lib/libcrypto/aarch64/sha256-armv8.S (revision 325333) @@ -0,0 +1,1143 @@ +/* $FreeBSD$ */ +/* Do not modify. This file is auto-generated from sha512-armv8.pl. */ +#include "arm_arch.h" + +.text + +.globl sha256_block_data_order +.type sha256_block_data_order,%function +.align 6 +sha256_block_data_order: + ldr x16,.LOPENSSL_armcap_P + adr x17,.LOPENSSL_armcap_P + add x16,x16,x17 + ldr w16,[x16] + tst w16,#ARMV8_SHA256 + b.ne .Lv8_entry + stp x29,x30,[sp,#-128]! + 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] + sub sp,sp,#4*4 + + ldp w20,w21,[x0] // load context + ldp w22,w23,[x0,#2*4] + ldp w24,w25,[x0,#4*4] + add x2,x1,x2,lsl#6 // end of input + ldp w26,w27,[x0,#6*4] + adr x30,K256 + stp x0,x2,[x29,#96] + +.Loop: + ldp w3,w4,[x1],#2*4 + ldr w19,[x30],#4 // *K++ + eor w28,w21,w22 // magic seed + str x1,[x29,#112] +#ifndef __ARMEB__ + rev w3,w3 // 0 +#endif + ror w16,w24,#6 + add w27,w27,w19 // h+=K[i] + eor w6,w24,w24,ror#14 + and w17,w25,w24 + bic w19,w26,w24 + add w27,w27,w3 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w20,w21 // a^b, b^c in next round + eor w16,w16,w6,ror#11 // Sigma1(e) + ror w6,w20,#2 + add w27,w27,w17 // h+=Ch(e,f,g) + eor w17,w20,w20,ror#9 + add w27,w27,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w23,w23,w27 // d+=h + eor w28,w28,w21 // Maj(a,b,c) + eor w17,w6,w17,ror#13 // Sigma0(a) + add w27,w27,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w27,w27,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w4,w4 // 1 +#endif + ldp w5,w6,[x1],#2*4 + add w27,w27,w17 // h+=Sigma0(a) + ror w16,w23,#6 + add w26,w26,w28 // h+=K[i] + eor w7,w23,w23,ror#14 + and w17,w24,w23 + bic w28,w25,w23 + add w26,w26,w4 // h+=X[i] + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w27,w20 // a^b, b^c in next round + eor w16,w16,w7,ror#11 // Sigma1(e) + ror w7,w27,#2 + add w26,w26,w17 // h+=Ch(e,f,g) + eor w17,w27,w27,ror#9 + add w26,w26,w16 // h+=Sigma1(e) + and w19,w19,w28 // (b^c)&=(a^b) + add w22,w22,w26 // d+=h + eor w19,w19,w20 // Maj(a,b,c) + eor w17,w7,w17,ror#13 // Sigma0(a) + add w26,w26,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + //add w26,w26,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w5,w5 // 2 +#endif + add w26,w26,w17 // h+=Sigma0(a) + ror w16,w22,#6 + add w25,w25,w19 // h+=K[i] + eor w8,w22,w22,ror#14 + and w17,w23,w22 + bic w19,w24,w22 + add w25,w25,w5 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w26,w27 // a^b, b^c in next round + eor w16,w16,w8,ror#11 // Sigma1(e) + ror w8,w26,#2 + add w25,w25,w17 // h+=Ch(e,f,g) + eor w17,w26,w26,ror#9 + add w25,w25,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w21,w21,w25 // d+=h + eor w28,w28,w27 // Maj(a,b,c) + eor w17,w8,w17,ror#13 // Sigma0(a) + add w25,w25,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w25,w25,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w6,w6 // 3 +#endif + ldp w7,w8,[x1],#2*4 + add w25,w25,w17 // h+=Sigma0(a) + ror w16,w21,#6 + add w24,w24,w28 // h+=K[i] + eor w9,w21,w21,ror#14 + and w17,w22,w21 + bic w28,w23,w21 + add w24,w24,w6 // h+=X[i] + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w25,w26 // a^b, b^c in next round + eor w16,w16,w9,ror#11 // Sigma1(e) + ror w9,w25,#2 + add w24,w24,w17 // h+=Ch(e,f,g) + eor w17,w25,w25,ror#9 + add w24,w24,w16 // h+=Sigma1(e) + and w19,w19,w28 // (b^c)&=(a^b) + add w20,w20,w24 // d+=h + eor w19,w19,w26 // Maj(a,b,c) + eor w17,w9,w17,ror#13 // Sigma0(a) + add w24,w24,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + //add w24,w24,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w7,w7 // 4 +#endif + add w24,w24,w17 // h+=Sigma0(a) + ror w16,w20,#6 + add w23,w23,w19 // h+=K[i] + eor w10,w20,w20,ror#14 + and w17,w21,w20 + bic w19,w22,w20 + add w23,w23,w7 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w24,w25 // a^b, b^c in next round + eor w16,w16,w10,ror#11 // Sigma1(e) + ror w10,w24,#2 + add w23,w23,w17 // h+=Ch(e,f,g) + eor w17,w24,w24,ror#9 + add w23,w23,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w27,w27,w23 // d+=h + eor w28,w28,w25 // Maj(a,b,c) + eor w17,w10,w17,ror#13 // Sigma0(a) + add w23,w23,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w23,w23,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w8,w8 // 5 +#endif + ldp w9,w10,[x1],#2*4 + add w23,w23,w17 // h+=Sigma0(a) + ror w16,w27,#6 + add w22,w22,w28 // h+=K[i] + eor w11,w27,w27,ror#14 + and w17,w20,w27 + bic w28,w21,w27 + add w22,w22,w8 // h+=X[i] + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w23,w24 // a^b, b^c in next round + eor w16,w16,w11,ror#11 // Sigma1(e) + ror w11,w23,#2 + add w22,w22,w17 // h+=Ch(e,f,g) + eor w17,w23,w23,ror#9 + add w22,w22,w16 // h+=Sigma1(e) + and w19,w19,w28 // (b^c)&=(a^b) + add w26,w26,w22 // d+=h + eor w19,w19,w24 // Maj(a,b,c) + eor w17,w11,w17,ror#13 // Sigma0(a) + add w22,w22,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + //add w22,w22,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w9,w9 // 6 +#endif + add w22,w22,w17 // h+=Sigma0(a) + ror w16,w26,#6 + add w21,w21,w19 // h+=K[i] + eor w12,w26,w26,ror#14 + and w17,w27,w26 + bic w19,w20,w26 + add w21,w21,w9 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w22,w23 // a^b, b^c in next round + eor w16,w16,w12,ror#11 // Sigma1(e) + ror w12,w22,#2 + add w21,w21,w17 // h+=Ch(e,f,g) + eor w17,w22,w22,ror#9 + add w21,w21,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w25,w25,w21 // d+=h + eor w28,w28,w23 // Maj(a,b,c) + eor w17,w12,w17,ror#13 // Sigma0(a) + add w21,w21,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w21,w21,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w10,w10 // 7 +#endif + ldp w11,w12,[x1],#2*4 + add w21,w21,w17 // h+=Sigma0(a) + ror w16,w25,#6 + add w20,w20,w28 // h+=K[i] + eor w13,w25,w25,ror#14 + and w17,w26,w25 + bic w28,w27,w25 + add w20,w20,w10 // h+=X[i] + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w21,w22 // a^b, b^c in next round + eor w16,w16,w13,ror#11 // Sigma1(e) + ror w13,w21,#2 + add w20,w20,w17 // h+=Ch(e,f,g) + eor w17,w21,w21,ror#9 + add w20,w20,w16 // h+=Sigma1(e) + and w19,w19,w28 // (b^c)&=(a^b) + add w24,w24,w20 // d+=h + eor w19,w19,w22 // Maj(a,b,c) + eor w17,w13,w17,ror#13 // Sigma0(a) + add w20,w20,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + //add w20,w20,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w11,w11 // 8 +#endif + add w20,w20,w17 // h+=Sigma0(a) + ror w16,w24,#6 + add w27,w27,w19 // h+=K[i] + eor w14,w24,w24,ror#14 + and w17,w25,w24 + bic w19,w26,w24 + add w27,w27,w11 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w20,w21 // a^b, b^c in next round + eor w16,w16,w14,ror#11 // Sigma1(e) + ror w14,w20,#2 + add w27,w27,w17 // h+=Ch(e,f,g) + eor w17,w20,w20,ror#9 + add w27,w27,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w23,w23,w27 // d+=h + eor w28,w28,w21 // Maj(a,b,c) + eor w17,w14,w17,ror#13 // Sigma0(a) + add w27,w27,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w27,w27,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w12,w12 // 9 +#endif + ldp w13,w14,[x1],#2*4 + add w27,w27,w17 // h+=Sigma0(a) + ror w16,w23,#6 + add w26,w26,w28 // h+=K[i] + eor w15,w23,w23,ror#14 + and w17,w24,w23 + bic w28,w25,w23 + add w26,w26,w12 // h+=X[i] + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w27,w20 // a^b, b^c in next round + eor w16,w16,w15,ror#11 // Sigma1(e) + ror w15,w27,#2 + add w26,w26,w17 // h+=Ch(e,f,g) + eor w17,w27,w27,ror#9 + add w26,w26,w16 // h+=Sigma1(e) + and w19,w19,w28 // (b^c)&=(a^b) + add w22,w22,w26 // d+=h + eor w19,w19,w20 // Maj(a,b,c) + eor w17,w15,w17,ror#13 // Sigma0(a) + add w26,w26,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + //add w26,w26,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w13,w13 // 10 +#endif + add w26,w26,w17 // h+=Sigma0(a) + ror w16,w22,#6 + add w25,w25,w19 // h+=K[i] + eor w0,w22,w22,ror#14 + and w17,w23,w22 + bic w19,w24,w22 + add w25,w25,w13 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w26,w27 // a^b, b^c in next round + eor w16,w16,w0,ror#11 // Sigma1(e) + ror w0,w26,#2 + add w25,w25,w17 // h+=Ch(e,f,g) + eor w17,w26,w26,ror#9 + add w25,w25,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w21,w21,w25 // d+=h + eor w28,w28,w27 // Maj(a,b,c) + eor w17,w0,w17,ror#13 // Sigma0(a) + add w25,w25,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w25,w25,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w14,w14 // 11 +#endif + ldp w15,w0,[x1],#2*4 + add w25,w25,w17 // h+=Sigma0(a) + str w6,[sp,#12] + ror w16,w21,#6 + add w24,w24,w28 // h+=K[i] + eor w6,w21,w21,ror#14 + and w17,w22,w21 + bic w28,w23,w21 + add w24,w24,w14 // h+=X[i] + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w25,w26 // a^b, b^c in next round + eor w16,w16,w6,ror#11 // Sigma1(e) + ror w6,w25,#2 + add w24,w24,w17 // h+=Ch(e,f,g) + eor w17,w25,w25,ror#9 + add w24,w24,w16 // h+=Sigma1(e) + and w19,w19,w28 // (b^c)&=(a^b) + add w20,w20,w24 // d+=h + eor w19,w19,w26 // Maj(a,b,c) + eor w17,w6,w17,ror#13 // Sigma0(a) + add w24,w24,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + //add w24,w24,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w15,w15 // 12 +#endif + add w24,w24,w17 // h+=Sigma0(a) + str w7,[sp,#0] + ror w16,w20,#6 + add w23,w23,w19 // h+=K[i] + eor w7,w20,w20,ror#14 + and w17,w21,w20 + bic w19,w22,w20 + add w23,w23,w15 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w24,w25 // a^b, b^c in next round + eor w16,w16,w7,ror#11 // Sigma1(e) + ror w7,w24,#2 + add w23,w23,w17 // h+=Ch(e,f,g) + eor w17,w24,w24,ror#9 + add w23,w23,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w27,w27,w23 // d+=h + eor w28,w28,w25 // Maj(a,b,c) + eor w17,w7,w17,ror#13 // Sigma0(a) + add w23,w23,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w23,w23,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w0,w0 // 13 +#endif + ldp w1,w2,[x1] + add w23,w23,w17 // h+=Sigma0(a) + str w8,[sp,#4] + ror w16,w27,#6 + add w22,w22,w28 // h+=K[i] + eor w8,w27,w27,ror#14 + and w17,w20,w27 + bic w28,w21,w27 + add w22,w22,w0 // h+=X[i] + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w23,w24 // a^b, b^c in next round + eor w16,w16,w8,ror#11 // Sigma1(e) + ror w8,w23,#2 + add w22,w22,w17 // h+=Ch(e,f,g) + eor w17,w23,w23,ror#9 + add w22,w22,w16 // h+=Sigma1(e) + and w19,w19,w28 // (b^c)&=(a^b) + add w26,w26,w22 // d+=h + eor w19,w19,w24 // Maj(a,b,c) + eor w17,w8,w17,ror#13 // Sigma0(a) + add w22,w22,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + //add w22,w22,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w1,w1 // 14 +#endif + ldr w6,[sp,#12] + add w22,w22,w17 // h+=Sigma0(a) + str w9,[sp,#8] + ror w16,w26,#6 + add w21,w21,w19 // h+=K[i] + eor w9,w26,w26,ror#14 + and w17,w27,w26 + bic w19,w20,w26 + add w21,w21,w1 // h+=X[i] + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w22,w23 // a^b, b^c in next round + eor w16,w16,w9,ror#11 // Sigma1(e) + ror w9,w22,#2 + add w21,w21,w17 // h+=Ch(e,f,g) + eor w17,w22,w22,ror#9 + add w21,w21,w16 // h+=Sigma1(e) + and w28,w28,w19 // (b^c)&=(a^b) + add w25,w25,w21 // d+=h + eor w28,w28,w23 // Maj(a,b,c) + eor w17,w9,w17,ror#13 // Sigma0(a) + add w21,w21,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + //add w21,w21,w17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev w2,w2 // 15 +#endif + ldr w7,[sp,#0] + add w21,w21,w17 // h+=Sigma0(a) + str w10,[sp,#12] + ror w16,w25,#6 + add w20,w20,w28 // h+=K[i] + ror w9,w4,#7 + and w17,w26,w25 + ror w8,w1,#17 + bic w28,w27,w25 + ror w10,w21,#2 + add w20,w20,w2 // h+=X[i] + eor w16,w16,w25,ror#11 + eor w9,w9,w4,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w21,w22 // a^b, b^c in next round + eor w16,w16,w25,ror#25 // Sigma1(e) + eor w10,w10,w21,ror#13 + add w20,w20,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w8,w8,w1,ror#19 + eor w9,w9,w4,lsr#3 // sigma0(X[i+1]) + add w20,w20,w16 // h+=Sigma1(e) + eor w19,w19,w22 // Maj(a,b,c) + eor w17,w10,w21,ror#22 // Sigma0(a) + eor w8,w8,w1,lsr#10 // sigma1(X[i+14]) + add w3,w3,w12 + add w24,w24,w20 // d+=h + add w20,w20,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w3,w3,w9 + add w20,w20,w17 // h+=Sigma0(a) + add w3,w3,w8 +.Loop_16_xx: + ldr w8,[sp,#4] + str w11,[sp,#0] + ror w16,w24,#6 + add w27,w27,w19 // h+=K[i] + ror w10,w5,#7 + and w17,w25,w24 + ror w9,w2,#17 + bic w19,w26,w24 + ror w11,w20,#2 + add w27,w27,w3 // h+=X[i] + eor w16,w16,w24,ror#11 + eor w10,w10,w5,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w20,w21 // a^b, b^c in next round + eor w16,w16,w24,ror#25 // Sigma1(e) + eor w11,w11,w20,ror#13 + add w27,w27,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w9,w9,w2,ror#19 + eor w10,w10,w5,lsr#3 // sigma0(X[i+1]) + add w27,w27,w16 // h+=Sigma1(e) + eor w28,w28,w21 // Maj(a,b,c) + eor w17,w11,w20,ror#22 // Sigma0(a) + eor w9,w9,w2,lsr#10 // sigma1(X[i+14]) + add w4,w4,w13 + add w23,w23,w27 // d+=h + add w27,w27,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w4,w4,w10 + add w27,w27,w17 // h+=Sigma0(a) + add w4,w4,w9 + ldr w9,[sp,#8] + str w12,[sp,#4] + ror w16,w23,#6 + add w26,w26,w28 // h+=K[i] + ror w11,w6,#7 + and w17,w24,w23 + ror w10,w3,#17 + bic w28,w25,w23 + ror w12,w27,#2 + add w26,w26,w4 // h+=X[i] + eor w16,w16,w23,ror#11 + eor w11,w11,w6,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w27,w20 // a^b, b^c in next round + eor w16,w16,w23,ror#25 // Sigma1(e) + eor w12,w12,w27,ror#13 + add w26,w26,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w10,w10,w3,ror#19 + eor w11,w11,w6,lsr#3 // sigma0(X[i+1]) + add w26,w26,w16 // h+=Sigma1(e) + eor w19,w19,w20 // Maj(a,b,c) + eor w17,w12,w27,ror#22 // Sigma0(a) + eor w10,w10,w3,lsr#10 // sigma1(X[i+14]) + add w5,w5,w14 + add w22,w22,w26 // d+=h + add w26,w26,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w5,w5,w11 + add w26,w26,w17 // h+=Sigma0(a) + add w5,w5,w10 + ldr w10,[sp,#12] + str w13,[sp,#8] + ror w16,w22,#6 + add w25,w25,w19 // h+=K[i] + ror w12,w7,#7 + and w17,w23,w22 + ror w11,w4,#17 + bic w19,w24,w22 + ror w13,w26,#2 + add w25,w25,w5 // h+=X[i] + eor w16,w16,w22,ror#11 + eor w12,w12,w7,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w26,w27 // a^b, b^c in next round + eor w16,w16,w22,ror#25 // Sigma1(e) + eor w13,w13,w26,ror#13 + add w25,w25,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w11,w11,w4,ror#19 + eor w12,w12,w7,lsr#3 // sigma0(X[i+1]) + add w25,w25,w16 // h+=Sigma1(e) + eor w28,w28,w27 // Maj(a,b,c) + eor w17,w13,w26,ror#22 // Sigma0(a) + eor w11,w11,w4,lsr#10 // sigma1(X[i+14]) + add w6,w6,w15 + add w21,w21,w25 // d+=h + add w25,w25,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w6,w6,w12 + add w25,w25,w17 // h+=Sigma0(a) + add w6,w6,w11 + ldr w11,[sp,#0] + str w14,[sp,#12] + ror w16,w21,#6 + add w24,w24,w28 // h+=K[i] + ror w13,w8,#7 + and w17,w22,w21 + ror w12,w5,#17 + bic w28,w23,w21 + ror w14,w25,#2 + add w24,w24,w6 // h+=X[i] + eor w16,w16,w21,ror#11 + eor w13,w13,w8,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w25,w26 // a^b, b^c in next round + eor w16,w16,w21,ror#25 // Sigma1(e) + eor w14,w14,w25,ror#13 + add w24,w24,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w12,w12,w5,ror#19 + eor w13,w13,w8,lsr#3 // sigma0(X[i+1]) + add w24,w24,w16 // h+=Sigma1(e) + eor w19,w19,w26 // Maj(a,b,c) + eor w17,w14,w25,ror#22 // Sigma0(a) + eor w12,w12,w5,lsr#10 // sigma1(X[i+14]) + add w7,w7,w0 + add w20,w20,w24 // d+=h + add w24,w24,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w7,w7,w13 + add w24,w24,w17 // h+=Sigma0(a) + add w7,w7,w12 + ldr w12,[sp,#4] + str w15,[sp,#0] + ror w16,w20,#6 + add w23,w23,w19 // h+=K[i] + ror w14,w9,#7 + and w17,w21,w20 + ror w13,w6,#17 + bic w19,w22,w20 + ror w15,w24,#2 + add w23,w23,w7 // h+=X[i] + eor w16,w16,w20,ror#11 + eor w14,w14,w9,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w24,w25 // a^b, b^c in next round + eor w16,w16,w20,ror#25 // Sigma1(e) + eor w15,w15,w24,ror#13 + add w23,w23,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w13,w13,w6,ror#19 + eor w14,w14,w9,lsr#3 // sigma0(X[i+1]) + add w23,w23,w16 // h+=Sigma1(e) + eor w28,w28,w25 // Maj(a,b,c) + eor w17,w15,w24,ror#22 // Sigma0(a) + eor w13,w13,w6,lsr#10 // sigma1(X[i+14]) + add w8,w8,w1 + add w27,w27,w23 // d+=h + add w23,w23,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w8,w8,w14 + add w23,w23,w17 // h+=Sigma0(a) + add w8,w8,w13 + ldr w13,[sp,#8] + str w0,[sp,#4] + ror w16,w27,#6 + add w22,w22,w28 // h+=K[i] + ror w15,w10,#7 + and w17,w20,w27 + ror w14,w7,#17 + bic w28,w21,w27 + ror w0,w23,#2 + add w22,w22,w8 // h+=X[i] + eor w16,w16,w27,ror#11 + eor w15,w15,w10,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w23,w24 // a^b, b^c in next round + eor w16,w16,w27,ror#25 // Sigma1(e) + eor w0,w0,w23,ror#13 + add w22,w22,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w14,w14,w7,ror#19 + eor w15,w15,w10,lsr#3 // sigma0(X[i+1]) + add w22,w22,w16 // h+=Sigma1(e) + eor w19,w19,w24 // Maj(a,b,c) + eor w17,w0,w23,ror#22 // Sigma0(a) + eor w14,w14,w7,lsr#10 // sigma1(X[i+14]) + add w9,w9,w2 + add w26,w26,w22 // d+=h + add w22,w22,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w9,w9,w15 + add w22,w22,w17 // h+=Sigma0(a) + add w9,w9,w14 + ldr w14,[sp,#12] + str w1,[sp,#8] + ror w16,w26,#6 + add w21,w21,w19 // h+=K[i] + ror w0,w11,#7 + and w17,w27,w26 + ror w15,w8,#17 + bic w19,w20,w26 + ror w1,w22,#2 + add w21,w21,w9 // h+=X[i] + eor w16,w16,w26,ror#11 + eor w0,w0,w11,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w22,w23 // a^b, b^c in next round + eor w16,w16,w26,ror#25 // Sigma1(e) + eor w1,w1,w22,ror#13 + add w21,w21,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w15,w15,w8,ror#19 + eor w0,w0,w11,lsr#3 // sigma0(X[i+1]) + add w21,w21,w16 // h+=Sigma1(e) + eor w28,w28,w23 // Maj(a,b,c) + eor w17,w1,w22,ror#22 // Sigma0(a) + eor w15,w15,w8,lsr#10 // sigma1(X[i+14]) + add w10,w10,w3 + add w25,w25,w21 // d+=h + add w21,w21,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w10,w10,w0 + add w21,w21,w17 // h+=Sigma0(a) + add w10,w10,w15 + ldr w15,[sp,#0] + str w2,[sp,#12] + ror w16,w25,#6 + add w20,w20,w28 // h+=K[i] + ror w1,w12,#7 + and w17,w26,w25 + ror w0,w9,#17 + bic w28,w27,w25 + ror w2,w21,#2 + add w20,w20,w10 // h+=X[i] + eor w16,w16,w25,ror#11 + eor w1,w1,w12,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w21,w22 // a^b, b^c in next round + eor w16,w16,w25,ror#25 // Sigma1(e) + eor w2,w2,w21,ror#13 + add w20,w20,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w0,w0,w9,ror#19 + eor w1,w1,w12,lsr#3 // sigma0(X[i+1]) + add w20,w20,w16 // h+=Sigma1(e) + eor w19,w19,w22 // Maj(a,b,c) + eor w17,w2,w21,ror#22 // Sigma0(a) + eor w0,w0,w9,lsr#10 // sigma1(X[i+14]) + add w11,w11,w4 + add w24,w24,w20 // d+=h + add w20,w20,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w11,w11,w1 + add w20,w20,w17 // h+=Sigma0(a) + add w11,w11,w0 + ldr w0,[sp,#4] + str w3,[sp,#0] + ror w16,w24,#6 + add w27,w27,w19 // h+=K[i] + ror w2,w13,#7 + and w17,w25,w24 + ror w1,w10,#17 + bic w19,w26,w24 + ror w3,w20,#2 + add w27,w27,w11 // h+=X[i] + eor w16,w16,w24,ror#11 + eor w2,w2,w13,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w20,w21 // a^b, b^c in next round + eor w16,w16,w24,ror#25 // Sigma1(e) + eor w3,w3,w20,ror#13 + add w27,w27,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w1,w1,w10,ror#19 + eor w2,w2,w13,lsr#3 // sigma0(X[i+1]) + add w27,w27,w16 // h+=Sigma1(e) + eor w28,w28,w21 // Maj(a,b,c) + eor w17,w3,w20,ror#22 // Sigma0(a) + eor w1,w1,w10,lsr#10 // sigma1(X[i+14]) + add w12,w12,w5 + add w23,w23,w27 // d+=h + add w27,w27,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w12,w12,w2 + add w27,w27,w17 // h+=Sigma0(a) + add w12,w12,w1 + ldr w1,[sp,#8] + str w4,[sp,#4] + ror w16,w23,#6 + add w26,w26,w28 // h+=K[i] + ror w3,w14,#7 + and w17,w24,w23 + ror w2,w11,#17 + bic w28,w25,w23 + ror w4,w27,#2 + add w26,w26,w12 // h+=X[i] + eor w16,w16,w23,ror#11 + eor w3,w3,w14,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w27,w20 // a^b, b^c in next round + eor w16,w16,w23,ror#25 // Sigma1(e) + eor w4,w4,w27,ror#13 + add w26,w26,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w2,w2,w11,ror#19 + eor w3,w3,w14,lsr#3 // sigma0(X[i+1]) + add w26,w26,w16 // h+=Sigma1(e) + eor w19,w19,w20 // Maj(a,b,c) + eor w17,w4,w27,ror#22 // Sigma0(a) + eor w2,w2,w11,lsr#10 // sigma1(X[i+14]) + add w13,w13,w6 + add w22,w22,w26 // d+=h + add w26,w26,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w13,w13,w3 + add w26,w26,w17 // h+=Sigma0(a) + add w13,w13,w2 + ldr w2,[sp,#12] + str w5,[sp,#8] + ror w16,w22,#6 + add w25,w25,w19 // h+=K[i] + ror w4,w15,#7 + and w17,w23,w22 + ror w3,w12,#17 + bic w19,w24,w22 + ror w5,w26,#2 + add w25,w25,w13 // h+=X[i] + eor w16,w16,w22,ror#11 + eor w4,w4,w15,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w26,w27 // a^b, b^c in next round + eor w16,w16,w22,ror#25 // Sigma1(e) + eor w5,w5,w26,ror#13 + add w25,w25,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w3,w3,w12,ror#19 + eor w4,w4,w15,lsr#3 // sigma0(X[i+1]) + add w25,w25,w16 // h+=Sigma1(e) + eor w28,w28,w27 // Maj(a,b,c) + eor w17,w5,w26,ror#22 // Sigma0(a) + eor w3,w3,w12,lsr#10 // sigma1(X[i+14]) + add w14,w14,w7 + add w21,w21,w25 // d+=h + add w25,w25,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w14,w14,w4 + add w25,w25,w17 // h+=Sigma0(a) + add w14,w14,w3 + ldr w3,[sp,#0] + str w6,[sp,#12] + ror w16,w21,#6 + add w24,w24,w28 // h+=K[i] + ror w5,w0,#7 + and w17,w22,w21 + ror w4,w13,#17 + bic w28,w23,w21 + ror w6,w25,#2 + add w24,w24,w14 // h+=X[i] + eor w16,w16,w21,ror#11 + eor w5,w5,w0,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w25,w26 // a^b, b^c in next round + eor w16,w16,w21,ror#25 // Sigma1(e) + eor w6,w6,w25,ror#13 + add w24,w24,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w4,w4,w13,ror#19 + eor w5,w5,w0,lsr#3 // sigma0(X[i+1]) + add w24,w24,w16 // h+=Sigma1(e) + eor w19,w19,w26 // Maj(a,b,c) + eor w17,w6,w25,ror#22 // Sigma0(a) + eor w4,w4,w13,lsr#10 // sigma1(X[i+14]) + add w15,w15,w8 + add w20,w20,w24 // d+=h + add w24,w24,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w15,w15,w5 + add w24,w24,w17 // h+=Sigma0(a) + add w15,w15,w4 + ldr w4,[sp,#4] + str w7,[sp,#0] + ror w16,w20,#6 + add w23,w23,w19 // h+=K[i] + ror w6,w1,#7 + and w17,w21,w20 + ror w5,w14,#17 + bic w19,w22,w20 + ror w7,w24,#2 + add w23,w23,w15 // h+=X[i] + eor w16,w16,w20,ror#11 + eor w6,w6,w1,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w24,w25 // a^b, b^c in next round + eor w16,w16,w20,ror#25 // Sigma1(e) + eor w7,w7,w24,ror#13 + add w23,w23,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w5,w5,w14,ror#19 + eor w6,w6,w1,lsr#3 // sigma0(X[i+1]) + add w23,w23,w16 // h+=Sigma1(e) + eor w28,w28,w25 // Maj(a,b,c) + eor w17,w7,w24,ror#22 // Sigma0(a) + eor w5,w5,w14,lsr#10 // sigma1(X[i+14]) + add w0,w0,w9 + add w27,w27,w23 // d+=h + add w23,w23,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w0,w0,w6 + add w23,w23,w17 // h+=Sigma0(a) + add w0,w0,w5 + ldr w5,[sp,#8] + str w8,[sp,#4] + ror w16,w27,#6 + add w22,w22,w28 // h+=K[i] + ror w7,w2,#7 + and w17,w20,w27 + ror w6,w15,#17 + bic w28,w21,w27 + ror w8,w23,#2 + add w22,w22,w0 // h+=X[i] + eor w16,w16,w27,ror#11 + eor w7,w7,w2,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w23,w24 // a^b, b^c in next round + eor w16,w16,w27,ror#25 // Sigma1(e) + eor w8,w8,w23,ror#13 + add w22,w22,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w6,w6,w15,ror#19 + eor w7,w7,w2,lsr#3 // sigma0(X[i+1]) + add w22,w22,w16 // h+=Sigma1(e) + eor w19,w19,w24 // Maj(a,b,c) + eor w17,w8,w23,ror#22 // Sigma0(a) + eor w6,w6,w15,lsr#10 // sigma1(X[i+14]) + add w1,w1,w10 + add w26,w26,w22 // d+=h + add w22,w22,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w1,w1,w7 + add w22,w22,w17 // h+=Sigma0(a) + add w1,w1,w6 + ldr w6,[sp,#12] + str w9,[sp,#8] + ror w16,w26,#6 + add w21,w21,w19 // h+=K[i] + ror w8,w3,#7 + and w17,w27,w26 + ror w7,w0,#17 + bic w19,w20,w26 + ror w9,w22,#2 + add w21,w21,w1 // h+=X[i] + eor w16,w16,w26,ror#11 + eor w8,w8,w3,ror#18 + orr w17,w17,w19 // Ch(e,f,g) + eor w19,w22,w23 // a^b, b^c in next round + eor w16,w16,w26,ror#25 // Sigma1(e) + eor w9,w9,w22,ror#13 + add w21,w21,w17 // h+=Ch(e,f,g) + and w28,w28,w19 // (b^c)&=(a^b) + eor w7,w7,w0,ror#19 + eor w8,w8,w3,lsr#3 // sigma0(X[i+1]) + add w21,w21,w16 // h+=Sigma1(e) + eor w28,w28,w23 // Maj(a,b,c) + eor w17,w9,w22,ror#22 // Sigma0(a) + eor w7,w7,w0,lsr#10 // sigma1(X[i+14]) + add w2,w2,w11 + add w25,w25,w21 // d+=h + add w21,w21,w28 // h+=Maj(a,b,c) + ldr w28,[x30],#4 // *K++, w19 in next round + add w2,w2,w8 + add w21,w21,w17 // h+=Sigma0(a) + add w2,w2,w7 + ldr w7,[sp,#0] + str w10,[sp,#12] + ror w16,w25,#6 + add w20,w20,w28 // h+=K[i] + ror w9,w4,#7 + and w17,w26,w25 + ror w8,w1,#17 + bic w28,w27,w25 + ror w10,w21,#2 + add w20,w20,w2 // h+=X[i] + eor w16,w16,w25,ror#11 + eor w9,w9,w4,ror#18 + orr w17,w17,w28 // Ch(e,f,g) + eor w28,w21,w22 // a^b, b^c in next round + eor w16,w16,w25,ror#25 // Sigma1(e) + eor w10,w10,w21,ror#13 + add w20,w20,w17 // h+=Ch(e,f,g) + and w19,w19,w28 // (b^c)&=(a^b) + eor w8,w8,w1,ror#19 + eor w9,w9,w4,lsr#3 // sigma0(X[i+1]) + add w20,w20,w16 // h+=Sigma1(e) + eor w19,w19,w22 // Maj(a,b,c) + eor w17,w10,w21,ror#22 // Sigma0(a) + eor w8,w8,w1,lsr#10 // sigma1(X[i+14]) + add w3,w3,w12 + add w24,w24,w20 // d+=h + add w20,w20,w19 // h+=Maj(a,b,c) + ldr w19,[x30],#4 // *K++, w28 in next round + add w3,w3,w9 + add w20,w20,w17 // h+=Sigma0(a) + add w3,w3,w8 + cbnz w19,.Loop_16_xx + + ldp x0,x2,[x29,#96] + ldr x1,[x29,#112] + sub x30,x30,#260 // rewind + + ldp w3,w4,[x0] + ldp w5,w6,[x0,#2*4] + add x1,x1,#14*4 // advance input pointer + ldp w7,w8,[x0,#4*4] + add w20,w20,w3 + ldp w9,w10,[x0,#6*4] + add w21,w21,w4 + add w22,w22,w5 + add w23,w23,w6 + stp w20,w21,[x0] + add w24,w24,w7 + add w25,w25,w8 + stp w22,w23,[x0,#2*4] + add w26,w26,w9 + add w27,w27,w10 + cmp x1,x2 + stp w24,w25,[x0,#4*4] + stp w26,w27,[x0,#6*4] + b.ne .Loop + + ldp x19,x20,[x29,#16] + add sp,sp,#4*4 + ldp x21,x22,[x29,#32] + ldp x23,x24,[x29,#48] + ldp x25,x26,[x29,#64] + ldp x27,x28,[x29,#80] + ldp x29,x30,[sp],#128 + ret +.size sha256_block_data_order,.-sha256_block_data_order + +.align 6 +.type K256,%object +K256: + .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 + .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 + .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 + .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 + .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc + .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da + .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 + .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 + .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 + .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 + .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 + .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 + .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 + .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 + .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 + .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 + .long 0 //terminator +.size K256,.-K256 +.align 3 +.LOPENSSL_armcap_P: + .quad OPENSSL_armcap_P-. +.asciz "SHA256 block transform for ARMv8, CRYPTOGAMS by " +.align 2 +.type sha256_block_armv8,%function +.align 6 +sha256_block_armv8: +.Lv8_entry: + stp x29,x30,[sp,#-16]! + add x29,sp,#0 + + ld1 {v0.4s,v1.4s},[x0] + adr x3,K256 + +.Loop_hw: + ld1 {v4.16b-v7.16b},[x1],#64 + sub x2,x2,#1 + ld1 {v16.4s},[x3],#16 + rev32 v4.16b,v4.16b + rev32 v5.16b,v5.16b + rev32 v6.16b,v6.16b + rev32 v7.16b,v7.16b + orr v18.16b,v0.16b,v0.16b // offload + orr v19.16b,v1.16b,v1.16b + ld1 {v17.4s},[x3],#16 + add v16.4s,v16.4s,v4.4s + .inst 0x5e2828a4 //sha256su0 v4.16b,v5.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + .inst 0x5e0760c4 //sha256su1 v4.16b,v6.16b,v7.16b + ld1 {v16.4s},[x3],#16 + add v17.4s,v17.4s,v5.4s + .inst 0x5e2828c5 //sha256su0 v5.16b,v6.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + .inst 0x5e0460e5 //sha256su1 v5.16b,v7.16b,v4.16b + ld1 {v17.4s},[x3],#16 + add v16.4s,v16.4s,v6.4s + .inst 0x5e2828e6 //sha256su0 v6.16b,v7.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + .inst 0x5e056086 //sha256su1 v6.16b,v4.16b,v5.16b + ld1 {v16.4s},[x3],#16 + add v17.4s,v17.4s,v7.4s + .inst 0x5e282887 //sha256su0 v7.16b,v4.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + .inst 0x5e0660a7 //sha256su1 v7.16b,v5.16b,v6.16b + ld1 {v17.4s},[x3],#16 + add v16.4s,v16.4s,v4.4s + .inst 0x5e2828a4 //sha256su0 v4.16b,v5.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + .inst 0x5e0760c4 //sha256su1 v4.16b,v6.16b,v7.16b + ld1 {v16.4s},[x3],#16 + add v17.4s,v17.4s,v5.4s + .inst 0x5e2828c5 //sha256su0 v5.16b,v6.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + .inst 0x5e0460e5 //sha256su1 v5.16b,v7.16b,v4.16b + ld1 {v17.4s},[x3],#16 + add v16.4s,v16.4s,v6.4s + .inst 0x5e2828e6 //sha256su0 v6.16b,v7.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + .inst 0x5e056086 //sha256su1 v6.16b,v4.16b,v5.16b + ld1 {v16.4s},[x3],#16 + add v17.4s,v17.4s,v7.4s + .inst 0x5e282887 //sha256su0 v7.16b,v4.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + .inst 0x5e0660a7 //sha256su1 v7.16b,v5.16b,v6.16b + ld1 {v17.4s},[x3],#16 + add v16.4s,v16.4s,v4.4s + .inst 0x5e2828a4 //sha256su0 v4.16b,v5.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + .inst 0x5e0760c4 //sha256su1 v4.16b,v6.16b,v7.16b + ld1 {v16.4s},[x3],#16 + add v17.4s,v17.4s,v5.4s + .inst 0x5e2828c5 //sha256su0 v5.16b,v6.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + .inst 0x5e0460e5 //sha256su1 v5.16b,v7.16b,v4.16b + ld1 {v17.4s},[x3],#16 + add v16.4s,v16.4s,v6.4s + .inst 0x5e2828e6 //sha256su0 v6.16b,v7.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + .inst 0x5e056086 //sha256su1 v6.16b,v4.16b,v5.16b + ld1 {v16.4s},[x3],#16 + add v17.4s,v17.4s,v7.4s + .inst 0x5e282887 //sha256su0 v7.16b,v4.16b + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + .inst 0x5e0660a7 //sha256su1 v7.16b,v5.16b,v6.16b + ld1 {v17.4s},[x3],#16 + add v16.4s,v16.4s,v4.4s + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + + ld1 {v16.4s},[x3],#16 + add v17.4s,v17.4s,v5.4s + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + + ld1 {v17.4s},[x3] + add v16.4s,v16.4s,v6.4s + sub x3,x3,#64*4-16 // rewind + orr v2.16b,v0.16b,v0.16b + .inst 0x5e104020 //sha256h v0.16b,v1.16b,v16.4s + .inst 0x5e105041 //sha256h2 v1.16b,v2.16b,v16.4s + + add v17.4s,v17.4s,v7.4s + orr v2.16b,v0.16b,v0.16b + .inst 0x5e114020 //sha256h v0.16b,v1.16b,v17.4s + .inst 0x5e115041 //sha256h2 v1.16b,v2.16b,v17.4s + + add v0.4s,v0.4s,v18.4s + add v1.4s,v1.4s,v19.4s + + cbnz x2,.Loop_hw + + st1 {v0.4s,v1.4s},[x0] + + ldr x29,[sp],#16 + ret +.size sha256_block_armv8,.-sha256_block_armv8 +.comm OPENSSL_armcap_P,4,4 Property changes on: stable/11/secure/lib/libcrypto/aarch64/sha256-armv8.S ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: stable/11/secure/lib/libcrypto/aarch64/sha512-armv8.S =================================================================== --- stable/11/secure/lib/libcrypto/aarch64/sha512-armv8.S (nonexistent) +++ stable/11/secure/lib/libcrypto/aarch64/sha512-armv8.S (revision 325333) @@ -0,0 +1,1023 @@ +/* $FreeBSD$ */ +/* Do not modify. This file is auto-generated from sha512-armv8.pl. */ +#include "arm_arch.h" + +.text + +.globl sha512_block_data_order +.type sha512_block_data_order,%function +.align 6 +sha512_block_data_order: + stp x29,x30,[sp,#-128]! + 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] + sub sp,sp,#4*8 + + ldp x20,x21,[x0] // load context + ldp x22,x23,[x0,#2*8] + ldp x24,x25,[x0,#4*8] + add x2,x1,x2,lsl#7 // end of input + ldp x26,x27,[x0,#6*8] + adr x30,K512 + stp x0,x2,[x29,#96] + +.Loop: + ldp x3,x4,[x1],#2*8 + ldr x19,[x30],#8 // *K++ + eor x28,x21,x22 // magic seed + str x1,[x29,#112] +#ifndef __ARMEB__ + rev x3,x3 // 0 +#endif + ror x16,x24,#14 + add x27,x27,x19 // h+=K[i] + eor x6,x24,x24,ror#23 + and x17,x25,x24 + bic x19,x26,x24 + add x27,x27,x3 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x20,x21 // a^b, b^c in next round + eor x16,x16,x6,ror#18 // Sigma1(e) + ror x6,x20,#28 + add x27,x27,x17 // h+=Ch(e,f,g) + eor x17,x20,x20,ror#5 + add x27,x27,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x23,x23,x27 // d+=h + eor x28,x28,x21 // Maj(a,b,c) + eor x17,x6,x17,ror#34 // Sigma0(a) + add x27,x27,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x27,x27,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x4,x4 // 1 +#endif + ldp x5,x6,[x1],#2*8 + add x27,x27,x17 // h+=Sigma0(a) + ror x16,x23,#14 + add x26,x26,x28 // h+=K[i] + eor x7,x23,x23,ror#23 + and x17,x24,x23 + bic x28,x25,x23 + add x26,x26,x4 // h+=X[i] + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x27,x20 // a^b, b^c in next round + eor x16,x16,x7,ror#18 // Sigma1(e) + ror x7,x27,#28 + add x26,x26,x17 // h+=Ch(e,f,g) + eor x17,x27,x27,ror#5 + add x26,x26,x16 // h+=Sigma1(e) + and x19,x19,x28 // (b^c)&=(a^b) + add x22,x22,x26 // d+=h + eor x19,x19,x20 // Maj(a,b,c) + eor x17,x7,x17,ror#34 // Sigma0(a) + add x26,x26,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + //add x26,x26,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x5,x5 // 2 +#endif + add x26,x26,x17 // h+=Sigma0(a) + ror x16,x22,#14 + add x25,x25,x19 // h+=K[i] + eor x8,x22,x22,ror#23 + and x17,x23,x22 + bic x19,x24,x22 + add x25,x25,x5 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x26,x27 // a^b, b^c in next round + eor x16,x16,x8,ror#18 // Sigma1(e) + ror x8,x26,#28 + add x25,x25,x17 // h+=Ch(e,f,g) + eor x17,x26,x26,ror#5 + add x25,x25,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x21,x21,x25 // d+=h + eor x28,x28,x27 // Maj(a,b,c) + eor x17,x8,x17,ror#34 // Sigma0(a) + add x25,x25,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x25,x25,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x6,x6 // 3 +#endif + ldp x7,x8,[x1],#2*8 + add x25,x25,x17 // h+=Sigma0(a) + ror x16,x21,#14 + add x24,x24,x28 // h+=K[i] + eor x9,x21,x21,ror#23 + and x17,x22,x21 + bic x28,x23,x21 + add x24,x24,x6 // h+=X[i] + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x25,x26 // a^b, b^c in next round + eor x16,x16,x9,ror#18 // Sigma1(e) + ror x9,x25,#28 + add x24,x24,x17 // h+=Ch(e,f,g) + eor x17,x25,x25,ror#5 + add x24,x24,x16 // h+=Sigma1(e) + and x19,x19,x28 // (b^c)&=(a^b) + add x20,x20,x24 // d+=h + eor x19,x19,x26 // Maj(a,b,c) + eor x17,x9,x17,ror#34 // Sigma0(a) + add x24,x24,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + //add x24,x24,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x7,x7 // 4 +#endif + add x24,x24,x17 // h+=Sigma0(a) + ror x16,x20,#14 + add x23,x23,x19 // h+=K[i] + eor x10,x20,x20,ror#23 + and x17,x21,x20 + bic x19,x22,x20 + add x23,x23,x7 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x24,x25 // a^b, b^c in next round + eor x16,x16,x10,ror#18 // Sigma1(e) + ror x10,x24,#28 + add x23,x23,x17 // h+=Ch(e,f,g) + eor x17,x24,x24,ror#5 + add x23,x23,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x27,x27,x23 // d+=h + eor x28,x28,x25 // Maj(a,b,c) + eor x17,x10,x17,ror#34 // Sigma0(a) + add x23,x23,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x23,x23,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x8,x8 // 5 +#endif + ldp x9,x10,[x1],#2*8 + add x23,x23,x17 // h+=Sigma0(a) + ror x16,x27,#14 + add x22,x22,x28 // h+=K[i] + eor x11,x27,x27,ror#23 + and x17,x20,x27 + bic x28,x21,x27 + add x22,x22,x8 // h+=X[i] + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x23,x24 // a^b, b^c in next round + eor x16,x16,x11,ror#18 // Sigma1(e) + ror x11,x23,#28 + add x22,x22,x17 // h+=Ch(e,f,g) + eor x17,x23,x23,ror#5 + add x22,x22,x16 // h+=Sigma1(e) + and x19,x19,x28 // (b^c)&=(a^b) + add x26,x26,x22 // d+=h + eor x19,x19,x24 // Maj(a,b,c) + eor x17,x11,x17,ror#34 // Sigma0(a) + add x22,x22,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + //add x22,x22,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x9,x9 // 6 +#endif + add x22,x22,x17 // h+=Sigma0(a) + ror x16,x26,#14 + add x21,x21,x19 // h+=K[i] + eor x12,x26,x26,ror#23 + and x17,x27,x26 + bic x19,x20,x26 + add x21,x21,x9 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x22,x23 // a^b, b^c in next round + eor x16,x16,x12,ror#18 // Sigma1(e) + ror x12,x22,#28 + add x21,x21,x17 // h+=Ch(e,f,g) + eor x17,x22,x22,ror#5 + add x21,x21,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x25,x25,x21 // d+=h + eor x28,x28,x23 // Maj(a,b,c) + eor x17,x12,x17,ror#34 // Sigma0(a) + add x21,x21,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x21,x21,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x10,x10 // 7 +#endif + ldp x11,x12,[x1],#2*8 + add x21,x21,x17 // h+=Sigma0(a) + ror x16,x25,#14 + add x20,x20,x28 // h+=K[i] + eor x13,x25,x25,ror#23 + and x17,x26,x25 + bic x28,x27,x25 + add x20,x20,x10 // h+=X[i] + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x21,x22 // a^b, b^c in next round + eor x16,x16,x13,ror#18 // Sigma1(e) + ror x13,x21,#28 + add x20,x20,x17 // h+=Ch(e,f,g) + eor x17,x21,x21,ror#5 + add x20,x20,x16 // h+=Sigma1(e) + and x19,x19,x28 // (b^c)&=(a^b) + add x24,x24,x20 // d+=h + eor x19,x19,x22 // Maj(a,b,c) + eor x17,x13,x17,ror#34 // Sigma0(a) + add x20,x20,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + //add x20,x20,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x11,x11 // 8 +#endif + add x20,x20,x17 // h+=Sigma0(a) + ror x16,x24,#14 + add x27,x27,x19 // h+=K[i] + eor x14,x24,x24,ror#23 + and x17,x25,x24 + bic x19,x26,x24 + add x27,x27,x11 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x20,x21 // a^b, b^c in next round + eor x16,x16,x14,ror#18 // Sigma1(e) + ror x14,x20,#28 + add x27,x27,x17 // h+=Ch(e,f,g) + eor x17,x20,x20,ror#5 + add x27,x27,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x23,x23,x27 // d+=h + eor x28,x28,x21 // Maj(a,b,c) + eor x17,x14,x17,ror#34 // Sigma0(a) + add x27,x27,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x27,x27,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x12,x12 // 9 +#endif + ldp x13,x14,[x1],#2*8 + add x27,x27,x17 // h+=Sigma0(a) + ror x16,x23,#14 + add x26,x26,x28 // h+=K[i] + eor x15,x23,x23,ror#23 + and x17,x24,x23 + bic x28,x25,x23 + add x26,x26,x12 // h+=X[i] + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x27,x20 // a^b, b^c in next round + eor x16,x16,x15,ror#18 // Sigma1(e) + ror x15,x27,#28 + add x26,x26,x17 // h+=Ch(e,f,g) + eor x17,x27,x27,ror#5 + add x26,x26,x16 // h+=Sigma1(e) + and x19,x19,x28 // (b^c)&=(a^b) + add x22,x22,x26 // d+=h + eor x19,x19,x20 // Maj(a,b,c) + eor x17,x15,x17,ror#34 // Sigma0(a) + add x26,x26,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + //add x26,x26,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x13,x13 // 10 +#endif + add x26,x26,x17 // h+=Sigma0(a) + ror x16,x22,#14 + add x25,x25,x19 // h+=K[i] + eor x0,x22,x22,ror#23 + and x17,x23,x22 + bic x19,x24,x22 + add x25,x25,x13 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x26,x27 // a^b, b^c in next round + eor x16,x16,x0,ror#18 // Sigma1(e) + ror x0,x26,#28 + add x25,x25,x17 // h+=Ch(e,f,g) + eor x17,x26,x26,ror#5 + add x25,x25,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x21,x21,x25 // d+=h + eor x28,x28,x27 // Maj(a,b,c) + eor x17,x0,x17,ror#34 // Sigma0(a) + add x25,x25,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x25,x25,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x14,x14 // 11 +#endif + ldp x15,x0,[x1],#2*8 + add x25,x25,x17 // h+=Sigma0(a) + str x6,[sp,#24] + ror x16,x21,#14 + add x24,x24,x28 // h+=K[i] + eor x6,x21,x21,ror#23 + and x17,x22,x21 + bic x28,x23,x21 + add x24,x24,x14 // h+=X[i] + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x25,x26 // a^b, b^c in next round + eor x16,x16,x6,ror#18 // Sigma1(e) + ror x6,x25,#28 + add x24,x24,x17 // h+=Ch(e,f,g) + eor x17,x25,x25,ror#5 + add x24,x24,x16 // h+=Sigma1(e) + and x19,x19,x28 // (b^c)&=(a^b) + add x20,x20,x24 // d+=h + eor x19,x19,x26 // Maj(a,b,c) + eor x17,x6,x17,ror#34 // Sigma0(a) + add x24,x24,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + //add x24,x24,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x15,x15 // 12 +#endif + add x24,x24,x17 // h+=Sigma0(a) + str x7,[sp,#0] + ror x16,x20,#14 + add x23,x23,x19 // h+=K[i] + eor x7,x20,x20,ror#23 + and x17,x21,x20 + bic x19,x22,x20 + add x23,x23,x15 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x24,x25 // a^b, b^c in next round + eor x16,x16,x7,ror#18 // Sigma1(e) + ror x7,x24,#28 + add x23,x23,x17 // h+=Ch(e,f,g) + eor x17,x24,x24,ror#5 + add x23,x23,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x27,x27,x23 // d+=h + eor x28,x28,x25 // Maj(a,b,c) + eor x17,x7,x17,ror#34 // Sigma0(a) + add x23,x23,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x23,x23,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x0,x0 // 13 +#endif + ldp x1,x2,[x1] + add x23,x23,x17 // h+=Sigma0(a) + str x8,[sp,#8] + ror x16,x27,#14 + add x22,x22,x28 // h+=K[i] + eor x8,x27,x27,ror#23 + and x17,x20,x27 + bic x28,x21,x27 + add x22,x22,x0 // h+=X[i] + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x23,x24 // a^b, b^c in next round + eor x16,x16,x8,ror#18 // Sigma1(e) + ror x8,x23,#28 + add x22,x22,x17 // h+=Ch(e,f,g) + eor x17,x23,x23,ror#5 + add x22,x22,x16 // h+=Sigma1(e) + and x19,x19,x28 // (b^c)&=(a^b) + add x26,x26,x22 // d+=h + eor x19,x19,x24 // Maj(a,b,c) + eor x17,x8,x17,ror#34 // Sigma0(a) + add x22,x22,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + //add x22,x22,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x1,x1 // 14 +#endif + ldr x6,[sp,#24] + add x22,x22,x17 // h+=Sigma0(a) + str x9,[sp,#16] + ror x16,x26,#14 + add x21,x21,x19 // h+=K[i] + eor x9,x26,x26,ror#23 + and x17,x27,x26 + bic x19,x20,x26 + add x21,x21,x1 // h+=X[i] + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x22,x23 // a^b, b^c in next round + eor x16,x16,x9,ror#18 // Sigma1(e) + ror x9,x22,#28 + add x21,x21,x17 // h+=Ch(e,f,g) + eor x17,x22,x22,ror#5 + add x21,x21,x16 // h+=Sigma1(e) + and x28,x28,x19 // (b^c)&=(a^b) + add x25,x25,x21 // d+=h + eor x28,x28,x23 // Maj(a,b,c) + eor x17,x9,x17,ror#34 // Sigma0(a) + add x21,x21,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + //add x21,x21,x17 // h+=Sigma0(a) +#ifndef __ARMEB__ + rev x2,x2 // 15 +#endif + ldr x7,[sp,#0] + add x21,x21,x17 // h+=Sigma0(a) + str x10,[sp,#24] + ror x16,x25,#14 + add x20,x20,x28 // h+=K[i] + ror x9,x4,#1 + and x17,x26,x25 + ror x8,x1,#19 + bic x28,x27,x25 + ror x10,x21,#28 + add x20,x20,x2 // h+=X[i] + eor x16,x16,x25,ror#18 + eor x9,x9,x4,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x21,x22 // a^b, b^c in next round + eor x16,x16,x25,ror#41 // Sigma1(e) + eor x10,x10,x21,ror#34 + add x20,x20,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x8,x8,x1,ror#61 + eor x9,x9,x4,lsr#7 // sigma0(X[i+1]) + add x20,x20,x16 // h+=Sigma1(e) + eor x19,x19,x22 // Maj(a,b,c) + eor x17,x10,x21,ror#39 // Sigma0(a) + eor x8,x8,x1,lsr#6 // sigma1(X[i+14]) + add x3,x3,x12 + add x24,x24,x20 // d+=h + add x20,x20,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x3,x3,x9 + add x20,x20,x17 // h+=Sigma0(a) + add x3,x3,x8 +.Loop_16_xx: + ldr x8,[sp,#8] + str x11,[sp,#0] + ror x16,x24,#14 + add x27,x27,x19 // h+=K[i] + ror x10,x5,#1 + and x17,x25,x24 + ror x9,x2,#19 + bic x19,x26,x24 + ror x11,x20,#28 + add x27,x27,x3 // h+=X[i] + eor x16,x16,x24,ror#18 + eor x10,x10,x5,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x20,x21 // a^b, b^c in next round + eor x16,x16,x24,ror#41 // Sigma1(e) + eor x11,x11,x20,ror#34 + add x27,x27,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x9,x9,x2,ror#61 + eor x10,x10,x5,lsr#7 // sigma0(X[i+1]) + add x27,x27,x16 // h+=Sigma1(e) + eor x28,x28,x21 // Maj(a,b,c) + eor x17,x11,x20,ror#39 // Sigma0(a) + eor x9,x9,x2,lsr#6 // sigma1(X[i+14]) + add x4,x4,x13 + add x23,x23,x27 // d+=h + add x27,x27,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x4,x4,x10 + add x27,x27,x17 // h+=Sigma0(a) + add x4,x4,x9 + ldr x9,[sp,#16] + str x12,[sp,#8] + ror x16,x23,#14 + add x26,x26,x28 // h+=K[i] + ror x11,x6,#1 + and x17,x24,x23 + ror x10,x3,#19 + bic x28,x25,x23 + ror x12,x27,#28 + add x26,x26,x4 // h+=X[i] + eor x16,x16,x23,ror#18 + eor x11,x11,x6,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x27,x20 // a^b, b^c in next round + eor x16,x16,x23,ror#41 // Sigma1(e) + eor x12,x12,x27,ror#34 + add x26,x26,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x10,x10,x3,ror#61 + eor x11,x11,x6,lsr#7 // sigma0(X[i+1]) + add x26,x26,x16 // h+=Sigma1(e) + eor x19,x19,x20 // Maj(a,b,c) + eor x17,x12,x27,ror#39 // Sigma0(a) + eor x10,x10,x3,lsr#6 // sigma1(X[i+14]) + add x5,x5,x14 + add x22,x22,x26 // d+=h + add x26,x26,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x5,x5,x11 + add x26,x26,x17 // h+=Sigma0(a) + add x5,x5,x10 + ldr x10,[sp,#24] + str x13,[sp,#16] + ror x16,x22,#14 + add x25,x25,x19 // h+=K[i] + ror x12,x7,#1 + and x17,x23,x22 + ror x11,x4,#19 + bic x19,x24,x22 + ror x13,x26,#28 + add x25,x25,x5 // h+=X[i] + eor x16,x16,x22,ror#18 + eor x12,x12,x7,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x26,x27 // a^b, b^c in next round + eor x16,x16,x22,ror#41 // Sigma1(e) + eor x13,x13,x26,ror#34 + add x25,x25,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x11,x11,x4,ror#61 + eor x12,x12,x7,lsr#7 // sigma0(X[i+1]) + add x25,x25,x16 // h+=Sigma1(e) + eor x28,x28,x27 // Maj(a,b,c) + eor x17,x13,x26,ror#39 // Sigma0(a) + eor x11,x11,x4,lsr#6 // sigma1(X[i+14]) + add x6,x6,x15 + add x21,x21,x25 // d+=h + add x25,x25,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x6,x6,x12 + add x25,x25,x17 // h+=Sigma0(a) + add x6,x6,x11 + ldr x11,[sp,#0] + str x14,[sp,#24] + ror x16,x21,#14 + add x24,x24,x28 // h+=K[i] + ror x13,x8,#1 + and x17,x22,x21 + ror x12,x5,#19 + bic x28,x23,x21 + ror x14,x25,#28 + add x24,x24,x6 // h+=X[i] + eor x16,x16,x21,ror#18 + eor x13,x13,x8,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x25,x26 // a^b, b^c in next round + eor x16,x16,x21,ror#41 // Sigma1(e) + eor x14,x14,x25,ror#34 + add x24,x24,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x12,x12,x5,ror#61 + eor x13,x13,x8,lsr#7 // sigma0(X[i+1]) + add x24,x24,x16 // h+=Sigma1(e) + eor x19,x19,x26 // Maj(a,b,c) + eor x17,x14,x25,ror#39 // Sigma0(a) + eor x12,x12,x5,lsr#6 // sigma1(X[i+14]) + add x7,x7,x0 + add x20,x20,x24 // d+=h + add x24,x24,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x7,x7,x13 + add x24,x24,x17 // h+=Sigma0(a) + add x7,x7,x12 + ldr x12,[sp,#8] + str x15,[sp,#0] + ror x16,x20,#14 + add x23,x23,x19 // h+=K[i] + ror x14,x9,#1 + and x17,x21,x20 + ror x13,x6,#19 + bic x19,x22,x20 + ror x15,x24,#28 + add x23,x23,x7 // h+=X[i] + eor x16,x16,x20,ror#18 + eor x14,x14,x9,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x24,x25 // a^b, b^c in next round + eor x16,x16,x20,ror#41 // Sigma1(e) + eor x15,x15,x24,ror#34 + add x23,x23,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x13,x13,x6,ror#61 + eor x14,x14,x9,lsr#7 // sigma0(X[i+1]) + add x23,x23,x16 // h+=Sigma1(e) + eor x28,x28,x25 // Maj(a,b,c) + eor x17,x15,x24,ror#39 // Sigma0(a) + eor x13,x13,x6,lsr#6 // sigma1(X[i+14]) + add x8,x8,x1 + add x27,x27,x23 // d+=h + add x23,x23,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x8,x8,x14 + add x23,x23,x17 // h+=Sigma0(a) + add x8,x8,x13 + ldr x13,[sp,#16] + str x0,[sp,#8] + ror x16,x27,#14 + add x22,x22,x28 // h+=K[i] + ror x15,x10,#1 + and x17,x20,x27 + ror x14,x7,#19 + bic x28,x21,x27 + ror x0,x23,#28 + add x22,x22,x8 // h+=X[i] + eor x16,x16,x27,ror#18 + eor x15,x15,x10,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x23,x24 // a^b, b^c in next round + eor x16,x16,x27,ror#41 // Sigma1(e) + eor x0,x0,x23,ror#34 + add x22,x22,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x14,x14,x7,ror#61 + eor x15,x15,x10,lsr#7 // sigma0(X[i+1]) + add x22,x22,x16 // h+=Sigma1(e) + eor x19,x19,x24 // Maj(a,b,c) + eor x17,x0,x23,ror#39 // Sigma0(a) + eor x14,x14,x7,lsr#6 // sigma1(X[i+14]) + add x9,x9,x2 + add x26,x26,x22 // d+=h + add x22,x22,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x9,x9,x15 + add x22,x22,x17 // h+=Sigma0(a) + add x9,x9,x14 + ldr x14,[sp,#24] + str x1,[sp,#16] + ror x16,x26,#14 + add x21,x21,x19 // h+=K[i] + ror x0,x11,#1 + and x17,x27,x26 + ror x15,x8,#19 + bic x19,x20,x26 + ror x1,x22,#28 + add x21,x21,x9 // h+=X[i] + eor x16,x16,x26,ror#18 + eor x0,x0,x11,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x22,x23 // a^b, b^c in next round + eor x16,x16,x26,ror#41 // Sigma1(e) + eor x1,x1,x22,ror#34 + add x21,x21,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x15,x15,x8,ror#61 + eor x0,x0,x11,lsr#7 // sigma0(X[i+1]) + add x21,x21,x16 // h+=Sigma1(e) + eor x28,x28,x23 // Maj(a,b,c) + eor x17,x1,x22,ror#39 // Sigma0(a) + eor x15,x15,x8,lsr#6 // sigma1(X[i+14]) + add x10,x10,x3 + add x25,x25,x21 // d+=h + add x21,x21,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x10,x10,x0 + add x21,x21,x17 // h+=Sigma0(a) + add x10,x10,x15 + ldr x15,[sp,#0] + str x2,[sp,#24] + ror x16,x25,#14 + add x20,x20,x28 // h+=K[i] + ror x1,x12,#1 + and x17,x26,x25 + ror x0,x9,#19 + bic x28,x27,x25 + ror x2,x21,#28 + add x20,x20,x10 // h+=X[i] + eor x16,x16,x25,ror#18 + eor x1,x1,x12,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x21,x22 // a^b, b^c in next round + eor x16,x16,x25,ror#41 // Sigma1(e) + eor x2,x2,x21,ror#34 + add x20,x20,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x0,x0,x9,ror#61 + eor x1,x1,x12,lsr#7 // sigma0(X[i+1]) + add x20,x20,x16 // h+=Sigma1(e) + eor x19,x19,x22 // Maj(a,b,c) + eor x17,x2,x21,ror#39 // Sigma0(a) + eor x0,x0,x9,lsr#6 // sigma1(X[i+14]) + add x11,x11,x4 + add x24,x24,x20 // d+=h + add x20,x20,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x11,x11,x1 + add x20,x20,x17 // h+=Sigma0(a) + add x11,x11,x0 + ldr x0,[sp,#8] + str x3,[sp,#0] + ror x16,x24,#14 + add x27,x27,x19 // h+=K[i] + ror x2,x13,#1 + and x17,x25,x24 + ror x1,x10,#19 + bic x19,x26,x24 + ror x3,x20,#28 + add x27,x27,x11 // h+=X[i] + eor x16,x16,x24,ror#18 + eor x2,x2,x13,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x20,x21 // a^b, b^c in next round + eor x16,x16,x24,ror#41 // Sigma1(e) + eor x3,x3,x20,ror#34 + add x27,x27,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x1,x1,x10,ror#61 + eor x2,x2,x13,lsr#7 // sigma0(X[i+1]) + add x27,x27,x16 // h+=Sigma1(e) + eor x28,x28,x21 // Maj(a,b,c) + eor x17,x3,x20,ror#39 // Sigma0(a) + eor x1,x1,x10,lsr#6 // sigma1(X[i+14]) + add x12,x12,x5 + add x23,x23,x27 // d+=h + add x27,x27,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x12,x12,x2 + add x27,x27,x17 // h+=Sigma0(a) + add x12,x12,x1 + ldr x1,[sp,#16] + str x4,[sp,#8] + ror x16,x23,#14 + add x26,x26,x28 // h+=K[i] + ror x3,x14,#1 + and x17,x24,x23 + ror x2,x11,#19 + bic x28,x25,x23 + ror x4,x27,#28 + add x26,x26,x12 // h+=X[i] + eor x16,x16,x23,ror#18 + eor x3,x3,x14,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x27,x20 // a^b, b^c in next round + eor x16,x16,x23,ror#41 // Sigma1(e) + eor x4,x4,x27,ror#34 + add x26,x26,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x2,x2,x11,ror#61 + eor x3,x3,x14,lsr#7 // sigma0(X[i+1]) + add x26,x26,x16 // h+=Sigma1(e) + eor x19,x19,x20 // Maj(a,b,c) + eor x17,x4,x27,ror#39 // Sigma0(a) + eor x2,x2,x11,lsr#6 // sigma1(X[i+14]) + add x13,x13,x6 + add x22,x22,x26 // d+=h + add x26,x26,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x13,x13,x3 + add x26,x26,x17 // h+=Sigma0(a) + add x13,x13,x2 + ldr x2,[sp,#24] + str x5,[sp,#16] + ror x16,x22,#14 + add x25,x25,x19 // h+=K[i] + ror x4,x15,#1 + and x17,x23,x22 + ror x3,x12,#19 + bic x19,x24,x22 + ror x5,x26,#28 + add x25,x25,x13 // h+=X[i] + eor x16,x16,x22,ror#18 + eor x4,x4,x15,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x26,x27 // a^b, b^c in next round + eor x16,x16,x22,ror#41 // Sigma1(e) + eor x5,x5,x26,ror#34 + add x25,x25,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x3,x3,x12,ror#61 + eor x4,x4,x15,lsr#7 // sigma0(X[i+1]) + add x25,x25,x16 // h+=Sigma1(e) + eor x28,x28,x27 // Maj(a,b,c) + eor x17,x5,x26,ror#39 // Sigma0(a) + eor x3,x3,x12,lsr#6 // sigma1(X[i+14]) + add x14,x14,x7 + add x21,x21,x25 // d+=h + add x25,x25,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x14,x14,x4 + add x25,x25,x17 // h+=Sigma0(a) + add x14,x14,x3 + ldr x3,[sp,#0] + str x6,[sp,#24] + ror x16,x21,#14 + add x24,x24,x28 // h+=K[i] + ror x5,x0,#1 + and x17,x22,x21 + ror x4,x13,#19 + bic x28,x23,x21 + ror x6,x25,#28 + add x24,x24,x14 // h+=X[i] + eor x16,x16,x21,ror#18 + eor x5,x5,x0,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x25,x26 // a^b, b^c in next round + eor x16,x16,x21,ror#41 // Sigma1(e) + eor x6,x6,x25,ror#34 + add x24,x24,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x4,x4,x13,ror#61 + eor x5,x5,x0,lsr#7 // sigma0(X[i+1]) + add x24,x24,x16 // h+=Sigma1(e) + eor x19,x19,x26 // Maj(a,b,c) + eor x17,x6,x25,ror#39 // Sigma0(a) + eor x4,x4,x13,lsr#6 // sigma1(X[i+14]) + add x15,x15,x8 + add x20,x20,x24 // d+=h + add x24,x24,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x15,x15,x5 + add x24,x24,x17 // h+=Sigma0(a) + add x15,x15,x4 + ldr x4,[sp,#8] + str x7,[sp,#0] + ror x16,x20,#14 + add x23,x23,x19 // h+=K[i] + ror x6,x1,#1 + and x17,x21,x20 + ror x5,x14,#19 + bic x19,x22,x20 + ror x7,x24,#28 + add x23,x23,x15 // h+=X[i] + eor x16,x16,x20,ror#18 + eor x6,x6,x1,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x24,x25 // a^b, b^c in next round + eor x16,x16,x20,ror#41 // Sigma1(e) + eor x7,x7,x24,ror#34 + add x23,x23,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x5,x5,x14,ror#61 + eor x6,x6,x1,lsr#7 // sigma0(X[i+1]) + add x23,x23,x16 // h+=Sigma1(e) + eor x28,x28,x25 // Maj(a,b,c) + eor x17,x7,x24,ror#39 // Sigma0(a) + eor x5,x5,x14,lsr#6 // sigma1(X[i+14]) + add x0,x0,x9 + add x27,x27,x23 // d+=h + add x23,x23,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x0,x0,x6 + add x23,x23,x17 // h+=Sigma0(a) + add x0,x0,x5 + ldr x5,[sp,#16] + str x8,[sp,#8] + ror x16,x27,#14 + add x22,x22,x28 // h+=K[i] + ror x7,x2,#1 + and x17,x20,x27 + ror x6,x15,#19 + bic x28,x21,x27 + ror x8,x23,#28 + add x22,x22,x0 // h+=X[i] + eor x16,x16,x27,ror#18 + eor x7,x7,x2,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x23,x24 // a^b, b^c in next round + eor x16,x16,x27,ror#41 // Sigma1(e) + eor x8,x8,x23,ror#34 + add x22,x22,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x6,x6,x15,ror#61 + eor x7,x7,x2,lsr#7 // sigma0(X[i+1]) + add x22,x22,x16 // h+=Sigma1(e) + eor x19,x19,x24 // Maj(a,b,c) + eor x17,x8,x23,ror#39 // Sigma0(a) + eor x6,x6,x15,lsr#6 // sigma1(X[i+14]) + add x1,x1,x10 + add x26,x26,x22 // d+=h + add x22,x22,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x1,x1,x7 + add x22,x22,x17 // h+=Sigma0(a) + add x1,x1,x6 + ldr x6,[sp,#24] + str x9,[sp,#16] + ror x16,x26,#14 + add x21,x21,x19 // h+=K[i] + ror x8,x3,#1 + and x17,x27,x26 + ror x7,x0,#19 + bic x19,x20,x26 + ror x9,x22,#28 + add x21,x21,x1 // h+=X[i] + eor x16,x16,x26,ror#18 + eor x8,x8,x3,ror#8 + orr x17,x17,x19 // Ch(e,f,g) + eor x19,x22,x23 // a^b, b^c in next round + eor x16,x16,x26,ror#41 // Sigma1(e) + eor x9,x9,x22,ror#34 + add x21,x21,x17 // h+=Ch(e,f,g) + and x28,x28,x19 // (b^c)&=(a^b) + eor x7,x7,x0,ror#61 + eor x8,x8,x3,lsr#7 // sigma0(X[i+1]) + add x21,x21,x16 // h+=Sigma1(e) + eor x28,x28,x23 // Maj(a,b,c) + eor x17,x9,x22,ror#39 // Sigma0(a) + eor x7,x7,x0,lsr#6 // sigma1(X[i+14]) + add x2,x2,x11 + add x25,x25,x21 // d+=h + add x21,x21,x28 // h+=Maj(a,b,c) + ldr x28,[x30],#8 // *K++, x19 in next round + add x2,x2,x8 + add x21,x21,x17 // h+=Sigma0(a) + add x2,x2,x7 + ldr x7,[sp,#0] + str x10,[sp,#24] + ror x16,x25,#14 + add x20,x20,x28 // h+=K[i] + ror x9,x4,#1 + and x17,x26,x25 + ror x8,x1,#19 + bic x28,x27,x25 + ror x10,x21,#28 + add x20,x20,x2 // h+=X[i] + eor x16,x16,x25,ror#18 + eor x9,x9,x4,ror#8 + orr x17,x17,x28 // Ch(e,f,g) + eor x28,x21,x22 // a^b, b^c in next round + eor x16,x16,x25,ror#41 // Sigma1(e) + eor x10,x10,x21,ror#34 + add x20,x20,x17 // h+=Ch(e,f,g) + and x19,x19,x28 // (b^c)&=(a^b) + eor x8,x8,x1,ror#61 + eor x9,x9,x4,lsr#7 // sigma0(X[i+1]) + add x20,x20,x16 // h+=Sigma1(e) + eor x19,x19,x22 // Maj(a,b,c) + eor x17,x10,x21,ror#39 // Sigma0(a) + eor x8,x8,x1,lsr#6 // sigma1(X[i+14]) + add x3,x3,x12 + add x24,x24,x20 // d+=h + add x20,x20,x19 // h+=Maj(a,b,c) + ldr x19,[x30],#8 // *K++, x28 in next round + add x3,x3,x9 + add x20,x20,x17 // h+=Sigma0(a) + add x3,x3,x8 + cbnz x19,.Loop_16_xx + + ldp x0,x2,[x29,#96] + ldr x1,[x29,#112] + sub x30,x30,#648 // rewind + + ldp x3,x4,[x0] + ldp x5,x6,[x0,#2*8] + add x1,x1,#14*8 // advance input pointer + ldp x7,x8,[x0,#4*8] + add x20,x20,x3 + ldp x9,x10,[x0,#6*8] + add x21,x21,x4 + add x22,x22,x5 + add x23,x23,x6 + stp x20,x21,[x0] + add x24,x24,x7 + add x25,x25,x8 + stp x22,x23,[x0,#2*8] + add x26,x26,x9 + add x27,x27,x10 + cmp x1,x2 + stp x24,x25,[x0,#4*8] + stp x26,x27,[x0,#6*8] + b.ne .Loop + + ldp x19,x20,[x29,#16] + add sp,sp,#4*8 + ldp x21,x22,[x29,#32] + ldp x23,x24,[x29,#48] + ldp x25,x26,[x29,#64] + ldp x27,x28,[x29,#80] + ldp x29,x30,[sp],#128 + ret +.size sha512_block_data_order,.-sha512_block_data_order + +.align 6 +.type K512,%object +K512: + .quad 0x428a2f98d728ae22,0x7137449123ef65cd + .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc + .quad 0x3956c25bf348b538,0x59f111f1b605d019 + .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118 + .quad 0xd807aa98a3030242,0x12835b0145706fbe + .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2 + .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1 + .quad 0x9bdc06a725c71235,0xc19bf174cf692694 + .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3 + .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65 + .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483 + .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5 + .quad 0x983e5152ee66dfab,0xa831c66d2db43210 + .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4 + .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725 + .quad 0x06ca6351e003826f,0x142929670a0e6e70 + .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926 + .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df + .quad 0x650a73548baf63de,0x766a0abb3c77b2a8 + .quad 0x81c2c92e47edaee6,0x92722c851482353b + .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001 + .quad 0xc24b8b70d0f89791,0xc76c51a30654be30 + .quad 0xd192e819d6ef5218,0xd69906245565a910 + .quad 0xf40e35855771202a,0x106aa07032bbd1b8 + .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53 + .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8 + .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb + .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3 + .quad 0x748f82ee5defb2fc,0x78a5636f43172f60 + .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec + .quad 0x90befffa23631e28,0xa4506cebde82bde9 + .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b + .quad 0xca273eceea26619c,0xd186b8c721c0c207 + .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178 + .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6 + .quad 0x113f9804bef90dae,0x1b710b35131c471b + .quad 0x28db77f523047d84,0x32caab7b40c72493 + .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c + .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a + .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817 + .quad 0 // terminator +.size K512,.-K512 +.align 3 +.LOPENSSL_armcap_P: + .quad OPENSSL_armcap_P-. +.asciz "SHA512 block transform for ARMv8, CRYPTOGAMS by " +.align 2 +.comm OPENSSL_armcap_P,4,4 Property changes on: stable/11/secure/lib/libcrypto/aarch64/sha512-armv8.S ___________________________________________________________________ Added: svn:eol-style ## -0,0 +1 ## +native \ No newline at end of property Added: svn:keywords ## -0,0 +1 ## +FreeBSD=%H \ No newline at end of property Added: svn:mime-type ## -0,0 +1 ## +text/plain \ No newline at end of property Index: stable/11 =================================================================== --- stable/11 (revision 325332) +++ stable/11 (revision 325333) Property changes on: stable/11 ___________________________________________________________________ Modified: svn:mergeinfo ## -0,0 +0,1 ## Merged /head:r307976