crypto: twofish - add AVX2/x86_64 assembler implementation of twofish cipher

Patch adds AVX2/x86-64 implementation of Twofish cipher, requiring 16 parallel
blocks for input (256 bytes). Table look-ups are performed using vpgatherdd
instruction directly from vector registers and thus should be faster than
earlier implementations. Implementation also uses 256-bit wide YMM registers,
which should give additional speed up compared to the AVX implementation.

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

2 files changed, 36 insertions, 0 deletions

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 6b9564f91168..1ba48ddd4da1 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1250,6 +1250,30 @@ config CRYPTO_TWOFISH_AVX_X86_64
           See also:
           <http://www.schneier.com/twofish.html>
 
+config CRYPTO_TWOFISH_AVX2_X86_64
+        tristate "Twofish cipher algorithm (x86_64/AVX2)"
+        depends on X86 && 64BIT
+        select CRYPTO_ALGAPI
+        select CRYPTO_CRYPTD
+        select CRYPTO_ABLK_HELPER_X86
+        select CRYPTO_GLUE_HELPER_X86
+        select CRYPTO_TWOFISH_COMMON
+        select CRYPTO_TWOFISH_X86_64
+        select CRYPTO_TWOFISH_X86_64_3WAY
+        select CRYPTO_TWOFISH_AVX_X86_64
+        select CRYPTO_LRW
+        select CRYPTO_XTS
+        help
+          Twofish cipher algorithm (x86_64/AVX2).
+
+          Twofish was submitted as an AES (Advanced Encryption Standard)
+          candidate cipher by researchers at CounterPane Systems.  It is a
+          16 round block cipher supporting key sizes of 128, 192, and 256
+          bits.
+
+          See also:
+          <http://www.schneier.com/twofish.html>
+
 comment "Compression"
 
 config CRYPTO_DEFLATE
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index f3effb42531e..fea7841dd6f3 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -1651,6 +1651,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__cbc-twofish-avx",
                 .test = alg_test_null,
         }, {
+                .alg = "__cbc-twofish-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__driver-cbc-aes-aesni",
                 .test = alg_test_null,
                 .fips_allowed = 1,
@@ -1676,6 +1679,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__driver-cbc-twofish-avx",
                 .test = alg_test_null,
         }, {
+                .alg = "__driver-cbc-twofish-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__driver-ecb-aes-aesni",
                 .test = alg_test_null,
                 .fips_allowed = 1,
@@ -1701,6 +1707,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "__driver-ecb-twofish-avx",
                 .test = alg_test_null,
         }, {
+                .alg = "__driver-ecb-twofish-avx2",
+                .test = alg_test_null,
+        }, {
                 .alg = "__ghash-pclmulqdqni",
                 .test = alg_test_null,
                 .fips_allowed = 1,
@@ -1985,6 +1994,9 @@ static const struct alg_test_desc alg_test_descs[] = {
                 .alg = "cryptd(__driver-ecb-twofish-avx)",
                 .test = alg_test_null,
         }, {
+                .alg = "cryptd(__driver-ecb-twofish-avx2)",
+                .test = alg_test_null,
+        }, {
                 .alg = "cryptd(__driver-gcm-aes-aesni)",
                 .test = alg_test_null,
                 .fips_allowed = 1,