From 4ea1277d301eb776e321684cd4ea95116b4e8847 Mon Sep 17 00:00:00 2001 From: Johannes Goetzfried Date: Wed, 11 Jul 2012 19:38:57 +0200 Subject: crypto: cast6 - add x86_64/avx assembler implementation This patch adds a x86_64/avx assembler implementation of the Cast6 block cipher. The implementation processes eight blocks in parallel (two 4 block chunk AVX operations). The table-lookups are done in general-purpose registers. For small blocksizes the functions from the generic module are called. A good performance increase is provided for blocksizes greater or equal to 128B. Patch has been tested with tcrypt and automated filesystem tests. Tcrypt benchmark results: Intel Core i5-2500 CPU (fam:6, model:42, step:7) cast6-avx-x86_64 vs. cast6-generic 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 0.97x 1.00x 1.01x 1.01x 0.99x 0.97x 0.98x 1.01x 0.96x 0.98x 64B 0.98x 0.99x 1.02x 1.01x 0.99x 1.00x 1.01x 0.99x 1.00x 0.99x 256B 1.77x 1.84x 0.99x 1.85x 1.77x 1.77x 1.70x 1.74x 1.69x 1.72x 1024B 1.93x 1.95x 0.99x 1.96x 1.93x 1.93x 1.84x 1.85x 1.89x 1.87x 8192B 1.91x 1.95x 0.99x 1.97x 1.95x 1.91x 1.86x 1.87x 1.93x 1.90x 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 0.99x 1.02x 1.01x 0.98x 0.99x 1.00x 1.00x 0.98x 0.98x 64B 0.98x 0.99x 1.01x 1.00x 1.00x 1.00x 1.01x 1.01x 0.97x 1.00x 256B 1.77x 1.83x 1.00x 1.86x 1.79x 1.78x 1.70x 1.76x 1.71x 1.69x 1024B 1.92x 1.95x 0.99x 1.96x 1.93x 1.93x 1.83x 1.86x 1.89x 1.87x 8192B 1.94x 1.95x 0.99x 1.97x 1.95x 1.95x 1.87x 1.87x 1.93x 1.91x Signed-off-by: Johannes Goetzfried Signed-off-by: Herbert Xu --- crypto/Kconfig | 17 ++++++++++++++++ crypto/testmgr.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) (limited to 'crypto') diff --git a/crypto/Kconfig b/crypto/Kconfig index cda97fcaa82..fe8ed62efe2 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -713,6 +713,23 @@ config CRYPTO_CAST6 The CAST6 encryption algorithm (synonymous with CAST-256) is described in RFC2612. +config CRYPTO_CAST6_AVX_X86_64 + tristate "CAST6 (CAST-256) cipher algorithm (x86_64/AVX)" + depends on X86 && 64BIT + select CRYPTO_ALGAPI + select CRYPTO_CRYPTD + select CRYPTO_ABLK_HELPER_X86 + select CRYPTO_GLUE_HELPER_X86 + select CRYPTO_CAST6 + select CRYPTO_LRW + select CRYPTO_XTS + help + The CAST6 encryption algorithm (synonymous with CAST-256) is + described in RFC2612. + + This module provides the Cast6 cipher algorithm that processes + eight blocks parallel using the AVX instruction set. + config CRYPTO_DES tristate "DES and Triple DES EDE cipher algorithms" select CRYPTO_ALGAPI diff --git a/crypto/testmgr.c b/crypto/testmgr.c index cff3c1c3f83..575b57c3244 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -1548,6 +1548,21 @@ static const struct alg_test_desc alg_test_descs[] = { } } } + }, { + .alg = "__cbc-cast6-avx", + .test = alg_test_null, + .suite = { + .cipher = { + .enc = { + .vecs = NULL, + .count = 0 + }, + .dec = { + .vecs = NULL, + .count = 0 + } + } + } }, { .alg = "__cbc-serpent-avx", .test = alg_test_null, @@ -1624,6 +1639,21 @@ static const struct alg_test_desc alg_test_descs[] = { } } } + }, { + .alg = "__driver-cbc-cast6-avx", + .test = alg_test_null, + .suite = { + .cipher = { + .enc = { + .vecs = NULL, + .count = 0 + }, + .dec = { + .vecs = NULL, + .count = 0 + } + } + } }, { .alg = "__driver-cbc-serpent-avx", .test = alg_test_null, @@ -1700,6 +1730,21 @@ static const struct alg_test_desc alg_test_descs[] = { } } } + }, { + .alg = "__driver-ecb-cast6-avx", + .test = alg_test_null, + .suite = { + .cipher = { + .enc = { + .vecs = NULL, + .count = 0 + }, + .dec = { + .vecs = NULL, + .count = 0 + } + } + } }, { .alg = "__driver-ecb-serpent-avx", .test = alg_test_null, @@ -2026,6 +2071,21 @@ static const struct alg_test_desc alg_test_descs[] = { } } } + }, { + .alg = "cryptd(__driver-ecb-cast6-avx)", + .test = alg_test_null, + .suite = { + .cipher = { + .enc = { + .vecs = NULL, + .count = 0 + }, + .dec = { + .vecs = NULL, + .count = 0 + } + } + } }, { .alg = "cryptd(__driver-ecb-serpent-avx)", .test = alg_test_null, -- cgit v1.2.3-18-g5258