crypto: camellia - add AES-NI/AVX/x86_64 assembler implementation of camellia cipher

This patch adds AES-NI/AVX/x86_64 assembler implementation of Camellia block
cipher. Implementation process data in sixteen block chunks, which are
byte-sliced and AES SubBytes is reused for Camellia s-box with help of pre-
and post-filtering.

Patch has been tested with tcrypt and automated filesystem tests.

tcrypt test results:

Intel Core i5-2450M:

camellia-aesni-avx vs camellia-asm-x86_64-2way:
128bit key:                                             (lrw:256bit)    (xts:256bit)
size    ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec lrw-enc lrw-dec xts-enc xts-dec
16B     0.98x   0.96x   0.99x   0.96x   0.96x   0.95x   0.95x   0.94x   0.97x   0.98x
64B     0.99x   0.98x   1.00x   0.98x   0.98x   0.99x   0.98x   0.93x   0.99x   0.98x
256B    2.28x   2.28x   1.01x   2.29x   2.25x   2.24x   1.96x   1.97x   1.91x   1.90x
1024B   2.57x   2.56x   1.00x   2.57x   2.51x   2.53x   2.19x   2.17x   2.19x   2.22x
8192B   2.49x   2.49x   1.00x   2.53x   2.48x   2.49x   2.17x   2.17x   2.22x   2.22x

256bit key:                                             (lrw:384bit)    (xts:512bit)
size    ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec lrw-enc lrw-dec xts-enc xts-dec
16B     0.97x   0.98x   0.99x   0.97x   0.97x   0.96x   0.97x   0.98x   0.98x   0.99x
64B     1.00x   1.00x   1.01x   0.99x   0.98x   0.99x   0.99x   0.99x   0.99x   0.99x
256B    2.37x   2.37x   1.01x   2.39x   2.35x   2.33x   2.10x   2.11x   1.99x   2.02x
1024B   2.58x   2.60x   1.00x   2.58x   2.56x   2.56x   2.28x   2.29x   2.28x   2.29x
8192B   2.50x   2.52x   1.00x   2.56x   2.51x   2.51x   2.24x   2.25x   2.26x   2.29x
Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/Makefile

@@ -12,6 +12,7 @@ obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
 
 obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
 obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
+obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += camellia-aesni-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
@@ -34,6 +35,8 @@ serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
 
 aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
 camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
+camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
+			       camellia_aesni_avx_glue.o
 cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o
 cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o

crypto/Kconfig

@@ -803,6 +803,28 @@ config CRYPTO_CAMELLIA_X86_64
 	  See also:
 	  <https://info.isl.ntt.co.jp/crypt/eng/camellia/index_s.html>
 
+config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
+	tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX)"
+	depends on X86 && 64BIT
+	depends on CRYPTO
+	select CRYPTO_ALGAPI
+	select CRYPTO_CRYPTD
+	select CRYPTO_ABLK_HELPER_X86
+	select CRYPTO_GLUE_HELPER_X86
+	select CRYPTO_CAMELLIA_X86_64
+	select CRYPTO_LRW
+	select CRYPTO_XTS
+	help
+	  Camellia cipher algorithm module (x86_64/AES-NI/AVX).
+
+	  Camellia is a symmetric key block cipher developed jointly
+	  at NTT and Mitsubishi Electric Corporation.
+
+	  The Camellia specifies three key sizes: 128, 192 and 256 bits.
+
+	  See also:
+	  <https://info.isl.ntt.co.jp/crypt/eng/camellia/index_s.html>
+
 config CRYPTO_CAMELLIA_SPARC64
 	tristate "Camellia cipher algorithm (SPARC64)"
 	depends on SPARC64

crypto/testmgr.c

@@ -1726,6 +1726,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "__driver-cbc-camellia-aesni",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "__driver-cbc-cast5-avx",
 		.test = alg_test_null,
@@ -1817,6 +1832,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "__driver-ecb-camellia-aesni",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "__driver-ecb-cast5-avx",
 		.test = alg_test_null,
@@ -2142,6 +2172,22 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "cryptd(__driver-cbc-camellia-aesni)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "cryptd(__driver-ecb-aes-aesni)",
 		.test = alg_test_null,
@@ -2158,6 +2204,22 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "cryptd(__driver-ecb-camellia-aesni)",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "cryptd(__driver-ecb-cast5-avx)",
 		.test = alg_test_null,