crypto: camellia - add AVX2/AES-NI/x86_64 assembler implementation of camellia cipher

Patch adds AVX2/AES-NI/x86-64 implementation of Camellia cipher, requiring
32 parallel blocks for input (512 bytes). Compared to AVX implementation, this
version is extended to use the 256-bit wide YMM registers. For AES-NI
instructions data is split to two 128-bit registers and merged afterwards.
Even with this additional handling, performance should be higher compared
to the AES-NI/AVX implementation.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

2 files changed, 35 insertions, 0 deletions

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 9ad3d78c1075..622d8a48cbe9 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -894,6 +894,29 @@ config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
           See also:
           <https://info.isl.ntt.co.jp/crypt/eng/camellia/index_s.html>
 
+config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64
+        tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX2)"
+        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_CAMELLIA_AESNI_AVX_X86_64
+        select CRYPTO_LRW
+        select CRYPTO_XTS
+        help
+          Camellia cipher algorithm module (x86_64/AES-NI/AVX2).
+
+          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
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f5e13dea8cc9..5823735cf381 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1667,6 +1667,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__driver-cbc-camellia-aesni",
                 .test = alg_test_null,
         }, {
+                .alg = "__driver-cbc-camellia-aesni-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__driver-cbc-cast5-avx",
                 .test = alg_test_null,
         }, {
@@ -1698,6 +1701,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__driver-ecb-camellia-aesni",
                 .test = alg_test_null,
         }, {
+                .alg = "__driver-ecb-camellia-aesni-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__driver-ecb-cast5-avx",
                 .test = alg_test_null,
         }, {
@@ -1978,6 +1984,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "cryptd(__driver-cbc-camellia-aesni)",
                 .test = alg_test_null,
         }, {
+                .alg = "cryptd(__driver-cbc-camellia-aesni-avx2)",
+                .test = alg_test_null,
+        }, {
                 .alg = "cryptd(__driver-cbc-serpent-avx2)",
                 .test = alg_test_null,
         }, {
@@ -1991,6 +2000,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "cryptd(__driver-ecb-camellia-aesni)",
                 .test = alg_test_null,
         }, {
+                .alg = "cryptd(__driver-ecb-camellia-aesni-avx2)",
+                .test = alg_test_null,
+        }, {
                 .alg = "cryptd(__driver-ecb-cast5-avx)",
                 .test = alg_test_null,
         }, {