diff options
Diffstat (limited to 'linux-arm/crypto/modes')
| -rw-r--r-- | linux-arm/crypto/modes/ghash-armv4.S | 4 | ||||
| -rw-r--r-- | linux-arm/crypto/modes/ghashv8-armx.S (renamed from linux-arm/crypto/modes/ghashv8-armx32.S) | 26 |
2 files changed, 13 insertions, 17 deletions
diff --git a/linux-arm/crypto/modes/ghash-armv4.S b/linux-arm/crypto/modes/ghash-armv4.S index f868c2d..b6c7e9b 100644 --- a/linux-arm/crypto/modes/ghash-armv4.S +++ b/linux-arm/crypto/modes/ghash-armv4.S @@ -1,6 +1,5 @@ #if defined(__arm__) -#if defined(__arm__) -#include <openssl/arm_arch.h> +#include "arm_arch.h" .syntax unified @@ -538,4 +537,3 @@ gcm_ghash_neon: .align 2 #endif -#endif
\ No newline at end of file diff --git a/linux-arm/crypto/modes/ghashv8-armx32.S b/linux-arm/crypto/modes/ghashv8-armx.S index 9a38ded..71913fb 100644 --- a/linux-arm/crypto/modes/ghashv8-armx32.S +++ b/linux-arm/crypto/modes/ghashv8-armx.S @@ -1,5 +1,4 @@ -#if defined(__arm__) -#include <openssl/arm_arch.h> +#include "arm_arch.h" .text .fpu neon @@ -67,10 +66,10 @@ gcm_gmult_v8: #endif vext.8 q3,q9,q9,#8 -.byte 0x86,0x0e,0xa8,0xf2 @ pmull q0,q12,q3 @ H.lo·Xi.lo +.byte 0x86,0x0e,0xa8,0xf2 @ pmull q0,q12,q3 @ H.lo·Xi.lo veor q9,q9,q3 @ Karatsuba pre-processing -.byte 0x87,0x4e,0xa9,0xf2 @ pmull2 q2,q12,q3 @ H.hi·Xi.hi -.byte 0xa2,0x2e,0xaa,0xf2 @ pmull q1,q13,q9 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) +.byte 0x87,0x4e,0xa9,0xf2 @ pmull2 q2,q12,q3 @ H.hi·Xi.hi +.byte 0xa2,0x2e,0xaa,0xf2 @ pmull q1,q13,q9 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) vext.8 q9,q0,q2,#8 @ Karatsuba post-processing veor q10,q0,q2 @@ -135,7 +134,7 @@ gcm_ghash_v8: #endif vext.8 q7,q9,q9,#8 veor q3,q3,q0 @ I[i]^=Xi -.byte 0x8e,0x8e,0xa8,0xf2 @ pmull q4,q12,q7 @ H·Ii+1 +.byte 0x8e,0x8e,0xa8,0xf2 @ pmull q4,q12,q7 @ H·Ii+1 veor q9,q9,q7 @ Karatsuba pre-processing .byte 0x8f,0xce,0xa9,0xf2 @ pmull2 q6,q12,q7 b .Loop_mod2x_v8 @@ -144,14 +143,14 @@ gcm_ghash_v8: .Loop_mod2x_v8: vext.8 q10,q3,q3,#8 subs r3,r3,#32 @ is there more data? -.byte 0x86,0x0e,0xac,0xf2 @ pmull q0,q14,q3 @ H^2.lo·Xi.lo +.byte 0x86,0x0e,0xac,0xf2 @ pmull q0,q14,q3 @ H^2.lo·Xi.lo movlo r12,#0 @ is it time to zero r12? .byte 0xa2,0xae,0xaa,0xf2 @ pmull q5,q13,q9 veor q10,q10,q3 @ Karatsuba pre-processing -.byte 0x87,0x4e,0xad,0xf2 @ pmull2 q2,q14,q3 @ H^2.hi·Xi.hi +.byte 0x87,0x4e,0xad,0xf2 @ pmull2 q2,q14,q3 @ H^2.hi·Xi.hi veor q0,q0,q4 @ accumulate -.byte 0xa5,0x2e,0xab,0xf2 @ pmull2 q1,q13,q10 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi) +.byte 0xa5,0x2e,0xab,0xf2 @ pmull2 q1,q13,q10 @ (H^2.lo+H^2.hi)·(Xi.lo+Xi.hi) vld1.64 {q8},[r2],r12 @ load [rotated] I[i+2] veor q2,q2,q6 @@ -176,7 +175,7 @@ gcm_ghash_v8: vext.8 q7,q9,q9,#8 vext.8 q3,q8,q8,#8 veor q0,q1,q10 -.byte 0x8e,0x8e,0xa8,0xf2 @ pmull q4,q12,q7 @ H·Ii+1 +.byte 0x8e,0x8e,0xa8,0xf2 @ pmull q4,q12,q7 @ H·Ii+1 veor q3,q3,q2 @ accumulate q3 early vext.8 q10,q0,q0,#8 @ 2nd phase of reduction @@ -197,10 +196,10 @@ gcm_ghash_v8: veor q3,q3,q0 @ inp^=Xi veor q9,q8,q10 @ q9 is rotated inp^Xi -.byte 0x86,0x0e,0xa8,0xf2 @ pmull q0,q12,q3 @ H.lo·Xi.lo +.byte 0x86,0x0e,0xa8,0xf2 @ pmull q0,q12,q3 @ H.lo·Xi.lo veor q9,q9,q3 @ Karatsuba pre-processing -.byte 0x87,0x4e,0xa9,0xf2 @ pmull2 q2,q12,q3 @ H.hi·Xi.hi -.byte 0xa2,0x2e,0xaa,0xf2 @ pmull q1,q13,q9 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) +.byte 0x87,0x4e,0xa9,0xf2 @ pmull2 q2,q12,q3 @ H.hi·Xi.hi +.byte 0xa2,0x2e,0xaa,0xf2 @ pmull q1,q13,q9 @ (H.lo+H.hi)·(Xi.lo+Xi.hi) vext.8 q9,q0,q2,#8 @ Karatsuba post-processing veor q10,q0,q2 @@ -230,4 +229,3 @@ gcm_ghash_v8: .byte 71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0 .align 2 .align 2 -#endif
\ No newline at end of file |