Add ARIA block cipher

* cipher/Makefile.am: Add 'aria.c'.
* cipher/aria.c: New.
* cipher/cipher.c (cipher_list, cipher_list_algo301): Add ARIA cipher
specs.
* cipher/mac-cmac.c (map_mac_algo_to_cipher): Add GCRY_MAC_CMAC_ARIA.
(_gcry_mac_type_spec_cmac_aria): New.
* cipher/mac-gmac.c (map_mac_algo_to_cipher): Add GCRY_MAC_GMAC_ARIA.
(_gcry_mac_type_spec_gmac_aria): New.
* cipher/mac-internal.h (_gcry_mac_type_spec_cmac_aria)
(_gcry_mac_type_spec_gmac_aria)
(_gcry_mac_type_spec_poly1305mac_aria): New.
* cipher/mac-poly1305.c (poly1305mac_open): Add GCRY_MAC_GMAC_ARIA.
(_gcry_mac_type_spec_poly1305mac_aria): New.
* cipher/mac.c (mac_list, mac_list_algo201, mac_list_algo401)
(mac_list_algo501): Add ARIA MAC specs.
* configure.ac (available_ciphers): Add 'aria'.
(GCRYPT_CIPHERS): Add 'aria.lo'.
(USE_ARIA): New.
* doc/gcrypt.texi: Add GCRY_CIPHER_ARIA128, GCRY_CIPHER_ARIA192,
GCRY_CIPHER_ARIA256, GCRY_MAC_CMAC_ARIA, GCRY_MAC_GMAC_ARIA and
GCRY_MAC_POLY1305_ARIA.
* src/cipher.h (_gcry_cipher_spec_aria128, _gcry_cipher_spec_aria192)
(_gcry_cipher_spec_aria256): New.
* src/gcrypt.h.in (gcry_cipher_algos): Add GCRY_CIPHER_ARIA128,
GCRY_CIPHER_ARIA192 and GCRY_CIPHER_ARIA256.
(gcry_mac_algos): GCRY_MAC_CMAC_ARIA, GCRY_MAC_GMAC_ARIA and
GCRY_MAC_POLY1305_ARIA.
* tests/basic.c (check_ecb_cipher, check_ctr_cipher)
(check_cfb_cipher, check_ocb_cipher) [USE_ARIA]: Add ARIA test-vectors.
(check_ciphers) [USE_ARIA]: Add GCRY_CIPHER_ARIA128, GCRY_CIPHER_ARIA192
and GCRY_CIPHER_ARIA256.
(main): Also run 'check_bulk_cipher_modes' for 'cipher_modes_only'-mode.
* tests/bench-slope.c (bench_mac_init): Add GCRY_MAC_POLY1305_ARIA
setiv-handling.
* tests/benchmark.c (mac_bench): Likewise.
--

This patch adds ARIA block cipher for libgcrypt. This implementation
is based on work by Taehee Yoo, with following notable changes:
 - Integration to libgcrypt, use of bithelp.h and bufhelp.h helper
   functions where possible.
 - Added lookup table prefetching as is done in AES, GCM and SM4
   implementations.
 - Changed `get_u8` to return `u32` as returning `byte` caused
   sub-optimal code generation with gcc-12/x86-64 (zero extending
   from 8-bit to 32-bit register, followed by extraneous sign
   extending from 32-bit to 64-bit register).
 - Changed 'aria_crypt' loop structure a bit for tiny performance
   increase (~1% seen with gcc-12/x86-64/zen4).

Benchmark on AMD Ryzen 9 7900X (x86-64):

 ARIA128        |  nanosecs/byte   mebibytes/sec   cycles/byte  auto Mhz
        ECB enc |      3.99 ns/B     239.1 MiB/s     22.43 c/B      5625
        ECB dec |      4.00 ns/B     238.4 MiB/s     22.50 c/B      5625

Benchmark on AMD Ryzen 9 7900X (win32):

 ARIA128        |  nanosecs/byte   mebibytes/sec   cycles/byte  auto Mhz
        ECB enc |      4.57 ns/B     208.7 MiB/s     25.31 c/B      5538
        ECB dec |      4.66 ns/B     204.8 MiB/s     25.39 c/B      5453

Benchmark on ARM Cortex-A53 (aarch64):

 ARIA128        |  nanosecs/byte   mebibytes/sec   cycles/byte  auto Mhz
        ECB enc |     74.69 ns/B     12.77 MiB/s     48.40 c/B     647.9
        ECB dec |     74.99 ns/B     12.72 MiB/s     48.58 c/B     647.9

Cc: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>

2 files changed, 11 insertions, 2 deletions

diff --git a/src/cipher.h b/src/cipher.h
index 9b890aeb..95ed43d7 100644
--- a/src/cipher.h
+++ b/src/cipher.h
@@ -171,6 +171,9 @@ extern gcry_cipher_spec_t _gcry_cipher_spec_gost28147;
 extern gcry_cipher_spec_t _gcry_cipher_spec_gost28147_mesh;
 extern gcry_cipher_spec_t _gcry_cipher_spec_chacha20;
 extern gcry_cipher_spec_t _gcry_cipher_spec_sm4;
+extern gcry_cipher_spec_t _gcry_cipher_spec_aria128;
+extern gcry_cipher_spec_t _gcry_cipher_spec_aria192;
+extern gcry_cipher_spec_t _gcry_cipher_spec_aria256;
 
 /* Declarations for the digest specifications.  */
 extern const gcry_md_spec_t _gcry_digest_spec_crc32;
diff --git a/src/gcrypt.h.in b/src/gcrypt.h.in
index 47d73339..aba22bfc 100644
--- a/src/gcrypt.h.in
+++ b/src/gcrypt.h.in
@@ -943,7 +943,10 @@ enum gcry_cipher_algos
     GCRY_CIPHER_GOST28147   = 315,
     GCRY_CIPHER_CHACHA20    = 316,
     GCRY_CIPHER_GOST28147_MESH   = 317, /* With CryptoPro key meshing.  */
-    GCRY_CIPHER_SM4         = 318
+    GCRY_CIPHER_SM4         = 318,
+    GCRY_CIPHER_ARIA128     = 319,
+    GCRY_CIPHER_ARIA192     = 320,
+    GCRY_CIPHER_ARIA256     = 321
   };
 
 /* The Rijndael algorithm is basically AES, so provide some macros. */
@@ -1510,6 +1513,7 @@ enum gcry_mac_algos
     GCRY_MAC_CMAC_IDEA          = 210,
     GCRY_MAC_CMAC_GOST28147     = 211,
     GCRY_MAC_CMAC_SM4           = 212,
+    GCRY_MAC_CMAC_ARIA          = 213,
 
     GCRY_MAC_GMAC_AES           = 401,
     GCRY_MAC_GMAC_CAMELLIA      = 402,
@@ -1517,6 +1521,7 @@ enum gcry_mac_algos
     GCRY_MAC_GMAC_SERPENT       = 404,
     GCRY_MAC_GMAC_SEED          = 405,
     GCRY_MAC_GMAC_SM4           = 406,
+    GCRY_MAC_GMAC_ARIA          = 407,
 
     GCRY_MAC_POLY1305           = 501,
     GCRY_MAC_POLY1305_AES       = 502,
@@ -1524,7 +1529,8 @@ enum gcry_mac_algos
     GCRY_MAC_POLY1305_TWOFISH   = 504,
     GCRY_MAC_POLY1305_SERPENT   = 505,
     GCRY_MAC_POLY1305_SEED      = 506,
-    GCRY_MAC_POLY1305_SM4       = 507
+    GCRY_MAC_POLY1305_SM4       = 507,
+    GCRY_MAC_POLY1305_ARIA      = 508
   };
 
 /* Flags used with the open function.  */