65816-crypto/sha256.macros
2017-07-03 23:05:51 -05:00

465 lines
6.8 KiB
Plaintext

* Copyright (c) 2017 Stephen Heumann
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
* Right-rotate 32-bit value in &loc (DP or 16-bit address) by &n positions
macro
ROTR4 &loc,&n
aif &n>16,.dorotl
lda &loc+2
lcla &i
&i seta &n
.rotrloop
lsr a ;to set carry
ror &loc
ror &loc+2
&i seta &i-1
aif &i>0,.rotrloop
ago .end
.dorotl
ROTL4 &loc,32-&n
.end
mend
* Expects the contents of &loc+2 to be loaded in A already
macro
ROTR4CONT &loc,&n
aif &n>16,.dorotl
lcla &i
&i seta &n
.rotrloop
lsr a ;to set carry
ror &loc
ror &loc+2
&i seta &i-1
aif &i>0,.rotrloop
ago .end
.dorotl
ROTL4 &loc,32-&n
.end
mend
* Left-rotate 32-bit value in &loc (DP or 16-bit address) by &n positions
macro
ROTL4 &loc,&n
aif &n>16,.dorotr2
lda &loc
lcla &i
&i seta &n
.rotlloop2
asl a ;to set carry
rol &loc+2
rol &loc
&i seta &i-1
aif &i>0,.rotlloop2
ago .end2
.dorotr2
ROTR4 &loc,32-&n
.end2
mend
* Expects the contents of &loc to be loaded in A already
macro
ROTL4CONT &loc,&n
aif &n>16,.dorotr2
lcla &i
&i seta &n
.rotlloop2
asl a ;to set carry
rol &loc+2
rol &loc
&i seta &i-1
aif &i>0,.rotlloop2
ago .end2
.dorotr2
ROTR4 &loc,32-&n
.end2
mend
* &to := &from ROTR4 &n
macro
ROTR4MOVE &to,&from,&n
aif &n>16,.dorotl3
lda &from
sta &to
lda &from+2
sta &to+2
lcla &i
&i seta &n
.rotrloop3
lsr a ;to set carry
ror &to
ror &to+2
&i seta &i-1
aif &i>0,.rotrloop3
ago .end3
.dorotl3
ROTL4MOVE &to,&from,32-&n
.end3
mend
* &to := &from ROTL4 &n
macro
ROTL4MOVE &to,&from,&n
aif &n>16,.dorotr4
lda &from+2
sta &to+2
lda &from
sta &to
lcla &i
&i seta &n
.rotlloop4
asl a ;to set carry
rol &to+2
rol &to
&i seta &i-1
aif &i>0,.rotlloop4
ago .end4
.dorotr4
ROTR4MOVE &to,&from,32-&n
.end4
mend
* This makes a function wrapper that is callable from C,
* taking a pointer to the context structure as its argument.
macro
CFunction &fn
phb
plx
ply
tdc
pld
plb
plb
phy
phx
plb
pha
jsl &fn
pld
rtl
mend
* Macros to operate on elements of the message schedule (W)
macro
&lab lda_w &i,&inc
lcla &j
&j seta &i
.modloop1
aif &j<16,.goodidx1
&j seta &j-16
ago .modloop1
.goodidx1
aif C:&inc<>0,.haveinc1
lcla &inc
.haveinc1
&lab lda w+(&j)*4+&inc
mend
macro
&lab sta_w &i,&inc
lcla &j
&j seta &i
.modloop3
aif &j<16,.goodidx3
&j seta &j-16
ago .modloop3
.goodidx3
aif C:&inc<>0,.haveinc3
lcla &inc
.haveinc3
&lab sta w+(&j)*4+&inc
mend
macro
&lab adc_w &i,&inc
lcla &j
&j seta &i
.modloop4
aif &j<16,.goodidx4
&j seta &j-16
ago .modloop4
.goodidx4
aif C:&inc<>0,.haveinc4
lcla &inc
.haveinc4
&lab adc w+(&j)*4+&inc
mend
* Compute one part of the message schedule (16 elements)
macro
ComputeSchedule &part
lcla &i
; Flip the endianness of W_0 to W_15 (the current block of the message)
aif &part<>1,.skippart1
.loop1
lda w+&i*4
xba
ldx w+&i*4+2
sta w+&i*4+2
txa
xba
sta w+&i*4
&i seta &i+1
aif &i<16,.loop1
ago .end
.skippart1
; compute the rest of the message schedule (W_16 to W_63)
&i seta (&part-1)*16
.loop2
; sigma_0 + w[i-16] computation
lda_w &i-15,-1
and #$FF00
sta temp1+2
lda_w &i-15,3
and #$00FF
ora temp1+2
sta temp1+2
lda_w &i-15,1
sta temp1
ROTL4CONT temp1,1
lda_w &i-15,2
sta temp2
lda_w &i-15
sta temp2+2
ROTR4CONT temp2,2
lda_w &i-15,2
lsr a
sta temp3+2
lda_w &i-15
ror a
sta temp3
lsr temp3+2
ror temp3
lsr temp3+2
lda temp3
ror a
eor temp2
eor temp1
clc
adc_w &i-16
sta temp1
lda temp3+2
eor temp2+2
eor temp1+2
adc_w &i-16,2
sta temp1+2
; sigma_1 + w[i-7] computation
lda_w &i-2,2
sta temp2
lda_w &i-2
sta temp2+2
ROTR4CONT temp2,1
ROTR4MOVE temp3,temp2,2
lda_w &i-2,3
and #$00FF
lsr a
tax
lda_w &i-2,1
ror a
tay
txa
lsr a
tax
tya
ror a
eor temp3
eor temp2
clc
adc_w &i-7
tay
txa
eor temp3+2
eor temp2+2
adc_w &i-7,2
tax
clc
tya
adc temp1
sta_w &i
txa
adc temp1+2
sta_w &i,2
&i seta &i+1
aif &i<&part*16,.loop2
.end
mend
* One iteration of the loop for processing blocks.
* The a,b,c,d,e,f,g,h variables are given as parameters so we can avoid
* cycling them.
macro
BlockLoopIter &a,&b,&c,&d,&e,&f,&g,&h,&iter,&k_idx1,&k_idx2
; Sigma_1+w[i] computation
lda &e+1
sta temp1
sta temp2
lda &e-1
ora &e+3
sta temp1+2
sta temp2+2
ROTR4CONT temp2,3
ROTL4 temp1,2
lda &e-1
ora &e+3
sta temp3
lda &e+1
sta temp3+2
ROTR4CONT temp3,1
lda temp1
eor temp2
eor temp3
clc
ldx idx
adc w+&iter*4,x
sta temp1
lda temp1+2
eor temp2+2
eor temp3+2
adc w+&iter*4+2,x
sta temp1+2
; ch+Sigma_1+W[i] computation
lda &f
eor &g
and &e
eor &g
clc
adc temp1
sta temp2
lda &f+2
eor &g+2
and &e+2
eor &g+2
adc temp1+2
sta temp2+2
; T_1 computation
clc
lda &h
adc temp2
tay
lda &h+2
adc temp2+2
tax
clc
tya
ldy k_ptr
adc (&k_idx1),y
sta temp1
txa
adc (&k_idx2),y
sta temp1+2
tax
clc
lda temp1
adc &d
sta &d
txa
adc &d+2
sta &d+2
;Sigma_0+T_1 computation
ROTR4MOVE temp2,&a,2
lda &a
sta temp3+2
lda &a+2
sta temp3
ROTL4CONT temp3,3
lda &a+1
sta temp4+2
lda &a-1
ora &a+3
sta temp4
ROTL4CONT temp4,2
lda temp2
eor temp3
eor temp4
clc
adc temp1
sta temp2
lda temp2+2
eor temp3+2
eor temp4+2
adc temp1+2
sta temp2+2
;maj and T_2 computation (saved to &h)
lda &a
ora &b
and &c
sta temp3
lda &a
and &b
ora temp3
clc
adc temp2
sta &h
lda &a+2
ora &b+2
and &c+2
sta temp3+2
lda &a+2
and &b+2
ora temp3+2
adc temp2+2
sta &h+2
mend
* One part of the loop for processing blocks (16 iterations)
macro
BlockLoopPart &part
stz idx
loop&part anop
BlockLoopIter a_,b,c,d,e,f,g,h,0,zero,two
BlockLoopIter h,a_,b,c,d,e,f,g,1,four,six
BlockLoopIter g,h,a_,b,c,d,e,f,2,eight,ten
BlockLoopIter f,g,h,a_,b,c,d,e,3,twelve,fourteen
BlockLoopIter e,f,g,h,a_,b,c,d,4,sixteen,eighteen
BlockLoopIter d,e,f,g,h,a_,b,c,5,twenty,twentytwo
BlockLoopIter c,d,e,f,g,h,a_,b,6,twentyfour,twentysix
BlockLoopIter b,c,d,e,f,g,h,a_,7,twentyeight,thirty
clc
lda k_ptr
adc #4*8
sta k_ptr
clc
lda idx
adc #4*8
cmp #16*4
bge endloop&part
sta idx
jmp loop&part
endloop&part anop
mend