X-Git-Url: https://git.cryptolib.org/?p=avr-crypto-lib.git;a=blobdiff_plain;f=skein%2Fthreefish1024_dec_asm.S;h=41ddb35cfa20c1b106c737bf9f0c23d78fb45a1f;hp=574382995575dcc7102a6230f247ebb19ecca656;hb=4b5da1dc27a791b5c448274a3db09cd035b33493;hpb=4f50c75ee5a6cc88bf7ea71957ed509e298e6c25

diff --git a/skein/threefish1024_dec_asm.S b/skein/threefish1024_dec_asm.S
index 5743829..41ddb35 100644
--- a/skein/threefish1024_dec_asm.S
+++ b/skein/threefish1024_dec_asm.S
@@ -1,7 +1,7 @@
 /* threefish1024_enc_asm.S */
 /*
     This file is part of the AVR-Crypto-Lib.
-    Copyright (C) 2009  Daniel Otte (daniel.otte@rub.de)
+    Copyright (C) 2006-2015 Daniel Otte (bg@nerilex.org)
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU General Public License as published by
@@ -18,16 +18,16 @@
 */
 /*
  * \author  Daniel Otte
- * \email   daniel.otte@rub.de
+ * \email   bg@nerilex.org
  * \date    2009-03-24
  * \license GPLv3 or later
- */ 
+ */
 
 #include "avr-asm-macros.S"
 
 /******************************************************************************/
 /*
-void permute_inv16(void* data){
+void permute_inv16(void *data){
 	uint64_t t;
 	t = X(15);
 	X(15) = X(7);
@@ -38,7 +38,7 @@ void permute_inv16(void* data){
 	X(11) = X(5);
 	X(5) = X(13);
 	X(13) = X(3);
-	X(3) = t; 		
+	X(3) = t;
 	t = X(4);
 	X(4) = X(6);
 	X(6) = t;
@@ -48,7 +48,7 @@ void permute_inv16(void* data){
 	X(10) = X(8);
 	X(8) = t;
 }
-void add_key_16(void* data, const threefish1024_ctx_t* ctx, uint8_t s){
+void add_key_16(void *data, const threefish1024_ctx_t *ctx, uint8_t s){
 	uint8_t i;
 	for(i=0; i<13; ++i){
 		X(i) -= ctx->k[(s+i)%17];
@@ -57,7 +57,7 @@ void add_key_16(void* data, const threefish1024_ctx_t* ctx, uint8_t s){
 	X(14) -= ctx->k[(s+14)%17] + ctx->t[(s+1)%3];
 	X(15) -= ctx->k[(s+15)%17] + s;
 }
-void threefish1024_dec(void* data, const threefish1024_ctx_t* ctx){
+void threefish1024_dec(void *data, const threefish1024_ctx_t *ctx){
 	uint8_t i=0,s=20;
 	uint8_t r0[8] = {0x69, 0x72, 0x21, 0x34, 0x42, 0x41, 0x31, 0x79};
 	uint8_t r1[8] = {0x61, 0x19, 0x1a, 0x19, 0x53, 0x10, 0x31, 0x53};
@@ -66,8 +66,8 @@ void threefish1024_dec(void* data, const threefish1024_ctx_t* ctx){
 	uint8_t r4[8] = {0x5b, 0x23, 0x53, 0x63, 0x54, 0x3b, 0x2a, 0x20};
 	uint8_t r5[8] = {0x60, 0x22, 0x52, 0x11, 0x11, 0x14, 0x2b, 0x3a};
 	uint8_t r6[8] = {0x7b, 0x02, 0x50, 0x43, 0x73, 0x40, 0x64, 0x5a};
-	uint8_t r7[8] = {0x70, 0x70, 0x29, 0x51, 0x42, 0x7a, 0x71, 0x14}; 
-	
+	uint8_t r7[8] = {0x70, 0x70, 0x29, 0x51, 0x42, 0x7a, 0x71, 0x14};
+
 	do{
 		if(i%4==0){
 			add_key_16(data, ctx, s);
@@ -116,7 +116,7 @@ threefish1024_dec:
 	clr I
 	ldi r26, 20
 	mov S, r26
-1:	
+1:
 	mov r30,  I
 	andi r30, 0x03
 	breq 2f
@@ -263,10 +263,10 @@ exit:
 	pop_range 2, 17
 	pop r29
 	pop r28
-	ret	
+	ret
 3:
 	dec S
-4:	
+4:
 	/* now the permutation */
 	movw r26, DATA0  /* X1 <-> X15 */
 	adiw r26, 1*8
@@ -286,7 +286,7 @@ exit:
 	movw r30, DATA0
 	adiw r30, 7*8
 	rcall xchg_zx8
-	/* --- */	
+	/* --- */
 	movw r26, DATA0  /* X3 <-> X11 */
 	adiw r26, 3*8
 	movw r30, DATA0
@@ -333,7 +333,7 @@ exit:
 	movw r30, DATA0
 	adiw r30, 6*8
 	rcall xchg_zx8
-		
+
 	/* call mix */
 	ldi r30, lo8(threefish1024_rc0)
 	ldi r31, hi8(threefish1024_rc0)
@@ -361,7 +361,7 @@ exit:
 	push IDX4
 	push IDX3
 	push IDX2
-	
+
 	movw r24, DATA0
 	call threefish_invmix_asm /* no rcall? */
 	movw r24, DATA0
@@ -399,8 +399,8 @@ exit:
 	inc I
 9:
 	rjmp 1b
-	
-threefish1024_slut17:	
+
+threefish1024_slut17:
 	.byte 0x00, 0x08, 0x10, 0x18, 0x20, 0x28, 0x30, 0x38
 	.byte 0x40, 0x48, 0x50, 0x58, 0x60, 0x68, 0x70, 0x78
 	.byte 0x80, 0x00, 0x08, 0x10, 0x18, 0x20, 0x28, 0x30
@@ -411,7 +411,8 @@ threefish1024_slut3:
 	.byte 0x10, 0x00, 0x08, 0x10, 0x00, 0x08, 0x10, 0x00
 	.byte 0x08, 0x10, 0x00, 0x08, 0x10, 0x00, 0x08, 0x10
 	.byte 0x00
-	
+
+/* old round constants
 threefish1024_rc0: .byte 0x69, 0x72, 0x21, 0x34, 0x42, 0x41, 0x31, 0x79
 threefish1024_rc1: .byte 0x61, 0x19, 0x1a, 0x19, 0x53, 0x10, 0x31, 0x53
 threefish1024_rc2: .byte 0x33, 0x40, 0x22, 0x69, 0x31, 0x22, 0x6a, 0x5b
@@ -419,7 +420,16 @@ threefish1024_rc3: .byte 0x72, 0x6b, 0x31, 0x60, 0x74, 0x71, 0x2b, 0x50
 threefish1024_rc4: .byte 0x5b, 0x23, 0x53, 0x63, 0x54, 0x3b, 0x2a, 0x20
 threefish1024_rc5: .byte 0x60, 0x22, 0x52, 0x11, 0x11, 0x14, 0x2b, 0x3a
 threefish1024_rc6: .byte 0x7b, 0x02, 0x50, 0x43, 0x73, 0x40, 0x64, 0x5a
-threefish1024_rc7: .byte 0x70, 0x70, 0x29, 0x51, 0x42, 0x7a, 0x71, 0x14 
+threefish1024_rc7: .byte 0x70, 0x70, 0x29, 0x51, 0x42, 0x7a, 0x71, 0x14
+*/
+threefish1024_rc0:  .byte 0x11, 0x49, 0x20, 0x51, 0x1b, 0x41, 0x5a, 0x30
+threefish1024_rc1:  .byte 0x60, 0x54, 0x42, 0x11, 0x24, 0x04, 0x23, 0x2b
+threefish1024_rc2:  .byte 0x43, 0x69, 0x70, 0x5b, 0x60, 0x63, 0x12, 0x10
+threefish1024_rc3:  .byte 0x64, 0x6a, 0x63, 0x49, 0x51, 0x2b, 0x79, 0x69
+threefish1024_rc4:  .byte 0x39, 0x23, 0x04, 0x14, 0x69, 0x42, 0x61, 0x10
+threefish1024_rc5:  .byte 0x49, 0x52, 0x7b, 0x69, 0x34, 0x51, 0x22, 0x21
+threefish1024_rc6:  .byte 0x5b, 0x54, 0x52, 0x54, 0x20, 0x73, 0x39, 0x3a
+threefish1024_rc7:  .byte 0x24, 0x31, 0x51, 0x4a, 0x31, 0x21, 0x64, 0x5b
 
 sub_z_from_x8:
 	ld r0, Z+
@@ -456,16 +466,16 @@ sub_z_from_x8:
 	st X+, r1
 	clr r1
 	ret
-	
+
 T0 = IDX0
 T1 = 0
-CNT = 24	
+CNT = 24
 xchg_zx8:
 	ldi CNT, 8
 1:	ld T0, X
 	ld T1, Z
 	st X+, T1
-	st Z+, T0	
+	st Z+, T0
 	dec CNT
 	brne 1b
 	ret