X-Git-Url: https://git.cryptolib.org/?a=blobdiff_plain;f=aes_enc-asm.S;h=14514f69d83309b7f82a1068dffaa484d4123347;hb=17332291e15183d71d88ed868275e3cb53917180;hp=ed04b6f6ff97a03b248f262e53098db101f36c61;hpb=5e274071cfce142ba67387bea5ad017b42b8001c;p=avr-crypto-lib.git

diff --git a/aes_enc-asm.S b/aes_enc-asm.S
index ed04b6f..14514f6 100644
--- a/aes_enc-asm.S
+++ b/aes_enc-asm.S
@@ -1,6 +1,6 @@
 /* aes_enc-asm.S */
 /*
-    This file is part of the Crypto-avr-lib/microcrypt-lib.
+    This file is part of the This file is part of the AVR-Crypto-Lib.
     Copyright (C) 2008, 2009  Daniel Otte (daniel.otte@rub.de)
 
     This program is free software: you can redistribute it and/or modify
@@ -38,25 +38,6 @@ B = 29
 P = 0
 xREDUCER = 25
 
-gf256mul:
-	clr P
-1:	
-	lsr A
-	breq 4f
-	brcc 2f
-	eor P, B
-2:
-	lsl B
-	brcc 3f
-	eor B, xREDUCER	
-3:
-	rjmp 1b
-4:
-	brcc 2f
-	eor P, B
-2:
-	ret
-
 .global aes256_enc
 aes256_enc:
 	ldi r20, 14
@@ -118,6 +99,10 @@ aes_encrypt_core:
 	.irp param,ST00, ST01, ST02, ST03, ST10, ST11, ST12, ST13, ST20, ST21, ST22, ST23, ST30, ST31, ST32, ST33
 		ld \param, Z+
 	.endr
+	
+	ldi xREDUCER, 0x1b /* load reducer */
+	ldi r31, hi8(aes_sbox)
+	
 	/* key whitening */
 1:
 	.irp param,ST00, ST01, ST02, ST03, ST10, ST11, ST12, ST13, ST20, ST21, ST22, ST23, ST30, ST31, ST32, ST33
@@ -126,323 +111,227 @@ aes_encrypt_core:
 	.endr
 	
 	brtc 2f
-	rjmp exit
+exit:	
+	pop r31
+	pop r30
+	st Z+, ST00
+	st Z+, ST01
+	st Z+, ST02
+	st Z+, ST03
+	st Z+, ST10
+	st Z+, ST11
+	st Z+, ST12
+	st Z+, ST13
+	st Z+, ST20
+	st Z+, ST21
+	st Z+, ST22
+	st Z+, ST23
+	st Z+, ST30
+	st Z+, ST31
+	st Z+, ST32
+	st Z+, ST33
+	pop r29
+	pop r28
+	pop_range 2, 17
+	ret
+
 2:	dec CTR
 	brne 3f
 	set
 3:
 
-	ldi r30, lo8(aes_sbox)
-	ldi r31, hi8(aes_sbox)
-	movw SBOX_SAVE0, r30
 	/* encryption loop */ 
 
 	/* SBOX substitution and shifting */
-	movw r30, SBOX_SAVE0
-	add r30, ST00
-	adc r31, r1
+	mov r30, ST00
 	lpm ST00, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST10
-	adc r31, r1
+	mov r30, ST10
 	lpm ST10, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST20
-	adc r31, r1
+	mov r30, ST20
 	lpm ST20, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST30
-	adc r31, r1
+	mov r30, ST30
 	lpm ST30, Z
 
-	movw r30, SBOX_SAVE0
-	add r30, ST01
-	adc r31, r1
+	mov r30, ST01
 	lpm T0, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST11
-	adc r31, r1
+	mov r30, ST11
 	lpm ST01, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST21
-	adc r31, r1
+	mov r30, ST21
 	lpm ST11, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST31
-	adc r31, r1
+	mov r30, ST31
 	lpm ST21, Z
 	mov ST31, T0
 
-	movw r30, SBOX_SAVE0
-	add r30, ST02
-	adc r31, r1
+	mov r30, ST02
 	lpm T0, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST12
-	adc r31, r1
+	mov r30, ST12
 	lpm T1, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST22
-	adc r31, r1
+	mov r30, ST22
 	lpm ST02, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST32
-	adc r31, r1
+	mov r30, ST32
 	lpm ST12, Z
 	mov ST22, T0
 	mov ST32, T1
 
-	movw r30, SBOX_SAVE0
-	add r30, ST03
-	adc r31, r1
+	mov r30, ST03
 	lpm T0, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST13
-	adc r31, r1
-	lpm T1, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST23
-	adc r31, r1
-	lpm T2, Z
-	movw r30, SBOX_SAVE0
-	add r30, ST33
-	adc r31, r1
+	mov r30, ST33
 	lpm ST03, Z
+	mov r30, ST23
+	lpm ST33, Z
+	mov r30, ST13
+	lpm ST23, Z
 	mov ST13, T0
-	mov ST23, T1
-	mov ST33, T2
-	
+		
 	/* mixcols (or rows in our case) */
 	brtc 2f
 	rjmp 1b
 2:	
-	ldi xREDUCER, 0x1b /* load reducer */
+ /* mixrow 1 */
+	mov r0, ST02
+	eor r0, ST03
+	mov T2, r0
+		
+	mov T0, ST00
+	eor ST00, ST01
+	eor r0, ST00
+	lsl ST00
+	brcc 3f
+	eor ST00, xREDUCER
+3:	eor ST00, r0
+	eor ST00, T0
 	
-	ldi A, 2
-	mov B, ST00
-	rcall gf256mul
-	mov T0, r0
-	ldi A, 3
-	mov B, ST01
-	rcall gf256mul
-	eor T0, r0
-	eor T0, ST02
-	eor T0, ST03
+	mov T1, ST01
+	eor T1, ST02
+	lsl T1
+	brcc 3f
+	eor T1, xREDUCER
+3:	eor T1, r0
+	eor ST01, T1
 	
-	mov T1, ST00
-	ldi A, 2
-	mov B, ST01
-	rcall gf256mul
-	eor T1, r0
-	ldi A, 3
-	mov B, ST02
-	rcall gf256mul
-	eor T1, r0
-	eor T1, ST03
+	lsl T2
+	brcc 3f
+	eor T2, xREDUCER
+3:  eor T2, r0
+	eor ST02, T2
+	
+	eor T0, ST03
+	lsl T0
+	brcc 3f
+	eor T0, xREDUCER
+3:	eor T0, r0
+	eor ST03, T0
+		
+ /* mixrow 2 */
+	mov r0, ST12
+	eor r0, ST13
+	mov T2, r0
+		
+	mov T0, ST10
+	eor ST10, ST11
+	eor r0, ST10
+	lsl ST10
+	brcc 3f
+	eor ST10, xREDUCER
+3:	eor ST10, r0
+	eor ST10, T0
 	
-	mov T2, ST00
-	eor T2, ST01
-	ldi A, 2
-	mov B, ST02
-	rcall gf256mul
-	eor T2, r0
-	ldi A, 3
-	mov B, ST03
-	rcall gf256mul
-	eor T2, r0
+	mov T1, ST11
+	eor T1, ST12
+	lsl T1
+	brcc 3f
+	eor T1, xREDUCER
+3:	eor T1, r0
+	eor ST11, T1
 	
-	ldi A, 3
-	mov B, ST00
-	rcall gf256mul
-	mov T3, r0
-	eor T3, ST01
-	eor T3, ST02
-	ldi A, 2
-	mov B, ST03
-	rcall gf256mul
-	eor T3, r0
+	lsl T2
+	brcc 3f
+	eor T2, xREDUCER
+3:  eor T2, r0
+	eor ST12, T2
 	
-	mov ST00, T0
-	mov ST01, T1
-	mov ST02, T2
-	mov ST03, T3
-			
-	ldi A, 2
-	mov B, ST10
-	rcall gf256mul
-	mov T0, r0
-	ldi A, 3
-	mov B, ST11
-	rcall gf256mul
-	eor T0, r0
-	eor T0, ST12
 	eor T0, ST13
+	lsl T0
+	brcc 3f
+	eor T0, xREDUCER
+3:	eor T0, r0
+	eor ST13, T0
+		
+ /* mixrow 3 */
+	mov r0, ST22
+	eor r0, ST23
+	mov T2, r0
+		
+	mov T0, ST20
+	eor ST20, ST21
+	eor r0, ST20
+	lsl ST20
+	brcc 3f
+	eor ST20, xREDUCER
+3:	eor ST20, r0
+	eor ST20, T0
 	
-	mov T1, ST10
-	ldi A, 2
-	mov B, ST11
-	rcall gf256mul
-	eor T1, r0
-	ldi A, 3
-	mov B, ST12
-	rcall gf256mul
-	eor T1, r0
-	eor T1, ST13
-	
-	mov T2, ST10
-	eor T2, ST11
-	ldi A, 2
-	mov B, ST12
-	rcall gf256mul
-	eor T2, r0
-	ldi A, 3
-	mov B, ST13
-	rcall gf256mul
-	eor T2, r0
+	mov T1, ST21
+	eor T1, ST22
+	lsl T1
+	brcc 3f
+	eor T1, xREDUCER
+3:	eor T1, r0
+	eor ST21, T1
 	
-	ldi A, 3
-	mov B, ST10
-	rcall gf256mul
-	mov T3, r0
-	eor T3, ST11
-	eor T3, ST12
-	ldi A, 2
-	mov B, ST13
-	rcall gf256mul
-	eor T3, r0
+	lsl T2
+	brcc 3f
+	eor T2, xREDUCER
+3:  eor T2, r0
+	eor ST22, T2
 	
-	mov ST10, T0
-	mov ST11, T1
-	mov ST12, T2
-	mov ST13, T3
-
-	ldi A, 2
-	mov B, ST20
-	rcall gf256mul
-	mov T0, r0
-	ldi A, 3
-	mov B, ST21
-	rcall gf256mul
-	eor T0, r0
-	eor T0, ST22
 	eor T0, ST23
+	lsl T0
+	brcc 3f
+	eor T0, xREDUCER
+3:	eor T0, r0
+	eor ST23, T0
+		
+ /* mixrow 4 */
+	mov r0, ST32
+	eor r0, ST33
+	mov T2, r0
+		
+	mov T0, ST30
+	eor ST30, ST31
+	eor r0, ST30
+	lsl ST30
+	brcc 3f
+	eor ST30, xREDUCER
+3:	eor ST30, r0
+	eor ST30, T0
 	
-	mov T1, ST20
-	ldi A, 2
-	mov B, ST21
-	rcall gf256mul
-	eor T1, r0
-	ldi A, 3
-	mov B, ST22
-	rcall gf256mul
-	eor T1, r0
-	eor T1, ST23
-	
-	mov T2, ST20
-	eor T2, ST21
-	ldi A, 2
-	mov B, ST22
-	rcall gf256mul
-	eor T2, r0
-	ldi A, 3
-	mov B, ST23
-	rcall gf256mul
-	eor T2, r0
+	mov T1, ST31
+	eor T1, ST32
+	lsl T1
+	brcc 3f
+	eor T1, xREDUCER
+3:	eor T1, r0
+	eor ST31, T1
 	
-	ldi A, 3
-	mov B, ST20
-	rcall gf256mul
-	mov T3, r0
-	eor T3, ST21
-	eor T3, ST22
-	ldi A, 2
-	mov B, ST23
-	rcall gf256mul
-	eor T3, r0
+	lsl T2
+	brcc 3f
+	eor T2, xREDUCER
+3:  eor T2, r0
+	eor ST32, T2
 	
-	mov ST20, T0
-	mov ST21, T1
-	mov ST22, T2
-	mov ST23, T3
-
-	ldi A, 2
-	mov B, ST30
-	rcall gf256mul
-	mov T0, r0
-	ldi A, 3
-	mov B, ST31
-	rcall gf256mul
-	eor T0, r0
-	eor T0, ST32
 	eor T0, ST33
-	
-	mov T1, ST30
-	ldi A, 2
-	mov B, ST31
-	rcall gf256mul
-	eor T1, r0
-	ldi A, 3
-	mov B, ST32
-	rcall gf256mul
-	eor T1, r0
-	eor T1, ST33
-	
-	mov T2, ST30
-	eor T2, ST31
-	ldi A, 2
-	mov B, ST32
-	rcall gf256mul
-	eor T2, r0
-	ldi A, 3
-	mov B, ST33
-	rcall gf256mul
-	eor T2, r0
-	
-	ldi A, 3
-	mov B, ST30
-	rcall gf256mul
-	mov T3, r0
-	eor T3, ST31
-	eor T3, ST32
-	ldi A, 2
-	mov B, ST33
-	rcall gf256mul
-	eor T3, r0
-	
-	mov ST30, T0
-	mov ST31, T1
-	mov ST32, T2
-	mov ST33, T3
-
+	lsl T0
+	brcc 3f
+	eor T0, xREDUCER
+3:	eor T0, r0
+	eor ST33, T0
 	/* mix colums (rows) done */
 
 	/* add key*/
 	rjmp 1b
 	
-exit:	
-	pop r31
-	pop r30
-	st Z+, ST00
-	st Z+, ST01
-	st Z+, ST02
-	st Z+, ST03
-	st Z+, ST10
-	st Z+, ST11
-	st Z+, ST12
-	st Z+, ST13
-	st Z+, ST20
-	st Z+, ST21
-	st Z+, ST22
-	st Z+, ST23
-	st Z+, ST30
-	st Z+, ST31
-	st Z+, ST32
-	st Z+, ST33
-	
-	pop r29
-	pop r28
-	pop_range 2, 17
-	ret
+