Enable assembler optimizations on earlier ARM cores

* cipher/blowfish-armv6.S => cipher/blowfish-arm.S: adapt to pre-armv6 CPUs.
* cipher/blowfish.c: enable assembly on armv4/armv5 little-endian CPUs.
* cipher/camellia-armv6.S => cipher/camellia-arm.S: adapt to pre-armv6 CPUs.
* cipher/camellia.c, cipher-camellia-glue.c: enable assembly on armv4/armv5
  little-endian CPUs.
* cipher/cast5-armv6.S => cipher/cast5-arm.S: adapt to pre-armv6 CPUs.
* cipher/cast5.c: enable assembly on armv4/armv5 little-endian CPUs.
* cipher/rijndael-armv6.S => cipher/rijndael-arm.S: adapt to pre-armv6 CPUs.
* cipher/rijndael.c: enable assembly on armv4/armv5 little-endian CPUs.
* cipher/twofish-armv6.S => cipher/twofish-arm.S: adapt to pre-armv6 CPUs.
* cipher/twofish.c: enable assembly on armv4/armv5 little-endian CPUs.

--
Our ARMv6 assembly optimized code can be easily adapted to earlier CPUs.
The only incompatible place is rev instruction used to do byte swapping.
Replace it on <= ARMv6 with a series of 4 instructions.

Compare:
                ECB/Stream         CBC             CFB             OFB             CTR
             --------------- --------------- --------------- --------------- ---------------
AES            620ms   610ms   650ms   680ms   620ms   630ms   660ms 660ms   630ms   630ms
CAMELLIA128    720ms   720ms   780ms   790ms   770ms   760ms   780ms 780ms   770ms   760ms
CAMELLIA256    910ms   910ms   970ms   970ms   960ms   950ms   970ms 970ms   960ms   950ms
CAST5          820ms   820ms   930ms   920ms   890ms   860ms   930ms 920ms   880ms   890ms
BLOWFISH       550ms   560ms   650ms   660ms   630ms   600ms   660ms 650ms   610ms   620ms

                ECB/Stream         CBC             CFB             OFB             CTR
             --------------- --------------- --------------- --------------- ---------------
AES            130ms   140ms   180ms   200ms   160ms   170ms   190ms 200ms   170ms   170ms
CAMELLIA128    150ms   160ms   210ms   220ms   200ms   190ms   210ms 220ms   190ms   190ms
CAMELLIA256    180ms   180ms   260ms   240ms   240ms   230ms   250ms 250ms   230ms   230ms
CAST5          170ms   160ms   270ms   120ms   240ms   130ms   260ms 270ms   130ms   120ms
BLOWFISH       160ms   150ms   260ms   110ms   230ms   120ms   250ms 260ms   110ms   120ms

Signed-off-by: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
[ jk: in camellia.h and twofish.c, USE_ARMV6_ASM => USE_ARM_ASM ]
[ jk: fix blowfish-arm.S when __ARM_FEATURE_UNALIGNED defined ]
[ jk: in twofish.S remove defined(HAVE_ARM_ARCH_V6) ]
[ jk: ARMv6 => ARM in comments ]

1 files changed, 19 insertions, 19 deletions

diff --git a/cipher/rijndael.c b/cipher/rijndael.c
index 85c1a41d..e9bb4f68 100644
--- a/cipher/rijndael.c
+++ b/cipher/rijndael.c
@@ -67,11 +67,11 @@
 # define USE_AMD64_ASM 1
 #endif
 
-/* USE_ARMV6_ASM indicates whether to use ARMv6 assembly code. */
-#undef USE_ARMV6_ASM
-#if defined(HAVE_ARM_ARCH_V6) && defined(__ARMEL__)
+/* USE_ARM_ASM indicates whether to use ARM assembly code. */
+#undef USE_ARM_ASM
+#if defined(__ARMEL__)
 # ifdef HAVE_COMPATIBLE_GCC_ARM_PLATFORM_AS
-#  define USE_ARMV6_ASM 1
+#  define USE_ARM_ASM 1
 # endif
 #endif
 
@@ -123,18 +123,18 @@ extern void _gcry_aes_amd64_decrypt_block(const void *keysched_dec,
 					  int rounds);
 #endif /*USE_AMD64_ASM*/
 
-#ifdef USE_ARMV6_ASM
-/* ARMv6 assembly implementations of AES */
-extern void _gcry_aes_armv6_encrypt_block(const void *keysched_enc,
+#ifdef USE_ARM_ASM
+/* ARM assembly implementations of AES */
+extern void _gcry_aes_arm_encrypt_block(const void *keysched_enc,
 					  unsigned char *out,
 					  const unsigned char *in,
 					  int rounds);
 
-extern void _gcry_aes_armv6_decrypt_block(const void *keysched_dec,
+extern void _gcry_aes_arm_decrypt_block(const void *keysched_dec,
 					  unsigned char *out,
 					  const unsigned char *in,
 					  int rounds);
-#endif /*USE_ARMV6_ASM*/
+#endif /*USE_ARM_ASM*/
 
 
 
@@ -567,8 +567,8 @@ do_encrypt_aligned (const RIJNDAEL_context *ctx,
 {
 #ifdef USE_AMD64_ASM
   _gcry_aes_amd64_encrypt_block(ctx->keyschenc, b, a, ctx->rounds);
-#elif defined(USE_ARMV6_ASM)
-  _gcry_aes_armv6_encrypt_block(ctx->keyschenc, b, a, ctx->rounds);
+#elif defined(USE_ARM_ASM)
+  _gcry_aes_arm_encrypt_block(ctx->keyschenc, b, a, ctx->rounds);
 #else
 #define rk (ctx->keyschenc)
   int rounds = ctx->rounds;
@@ -651,7 +651,7 @@ do_encrypt_aligned (const RIJNDAEL_context *ctx,
   *((u32_a_t*)(b+ 8)) ^= *((u32_a_t*)rk[rounds][2]);
   *((u32_a_t*)(b+12)) ^= *((u32_a_t*)rk[rounds][3]);
 #undef rk
-#endif /*!USE_AMD64_ASM && !USE_ARMV6_ASM*/
+#endif /*!USE_AMD64_ASM && !USE_ARM_ASM*/
 }
 
 
@@ -659,7 +659,7 @@ static void
 do_encrypt (const RIJNDAEL_context *ctx,
             unsigned char *bx, const unsigned char *ax)
 {
-#if !defined(USE_AMD64_ASM) && !defined(USE_ARMV6_ASM)
+#if !defined(USE_AMD64_ASM) && !defined(USE_ARM_ASM)
   /* BX and AX are not necessary correctly aligned.  Thus we might
      need to copy them here.  We try to align to a 16 bytes.  */
   if (((size_t)ax & 0x0f) || ((size_t)bx & 0x0f))
@@ -680,7 +680,7 @@ do_encrypt (const RIJNDAEL_context *ctx,
       memcpy (bx, b.b, 16);
     }
   else
-#endif /*!USE_AMD64_ASM && !USE_ARMV6_ASM*/
+#endif /*!USE_AMD64_ASM && !USE_ARM_ASM*/
     {
       do_encrypt_aligned (ctx, bx, ax);
     }
@@ -1694,8 +1694,8 @@ do_decrypt_aligned (RIJNDAEL_context *ctx,
 {
 #ifdef USE_AMD64_ASM
   _gcry_aes_amd64_decrypt_block(ctx->keyschdec, b, a, ctx->rounds);
-#elif defined(USE_ARMV6_ASM)
-  _gcry_aes_armv6_decrypt_block(ctx->keyschdec, b, a, ctx->rounds);
+#elif defined(USE_ARM_ASM)
+  _gcry_aes_arm_decrypt_block(ctx->keyschdec, b, a, ctx->rounds);
 #else
 #define rk  (ctx->keyschdec)
   int rounds = ctx->rounds;
@@ -1779,7 +1779,7 @@ do_decrypt_aligned (RIJNDAEL_context *ctx,
   *((u32_a_t*)(b+ 8)) ^= *((u32_a_t*)rk[0][2]);
   *((u32_a_t*)(b+12)) ^= *((u32_a_t*)rk[0][3]);
 #undef rk
-#endif /*!USE_AMD64_ASM && !USE_ARMV6_ASM*/
+#endif /*!USE_AMD64_ASM && !USE_ARM_ASM*/
 }
 
 
@@ -1794,7 +1794,7 @@ do_decrypt (RIJNDAEL_context *ctx, byte *bx, const byte *ax)
       ctx->decryption_prepared = 1;
     }
 
-#if !defined(USE_AMD64_ASM) && !defined(USE_ARMV6_ASM)
+#if !defined(USE_AMD64_ASM) && !defined(USE_ARM_ASM)
   /* BX and AX are not necessary correctly aligned.  Thus we might
      need to copy them here.  We try to align to a 16 bytes. */
   if (((size_t)ax & 0x0f) || ((size_t)bx & 0x0f))
@@ -1815,7 +1815,7 @@ do_decrypt (RIJNDAEL_context *ctx, byte *bx, const byte *ax)
       memcpy (bx, b.b, 16);
     }
   else
-#endif /*!USE_AMD64_ASM && !USE_ARMV6_ASM*/
+#endif /*!USE_AMD64_ASM && !USE_ARM_ASM*/
     {
       do_decrypt_aligned (ctx, bx, ax);
     }