From 4d6d6a2c850f89bc9283d02519cb536baba72032 Mon Sep 17 00:00:00 2001 From: Johannes Goetzfried Date: Wed, 11 Jul 2012 19:37:37 +0200 Subject: crypto: cast5 - add x86_64/avx assembler implementation This patch adds a x86_64/avx assembler implementation of the Cast5 block cipher. The implementation processes sixteen blocks in parallel (four 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) cast5-avx-x86_64 vs. cast5-generic 64bit key: size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 0.99x 0.99x 1.00x 1.00x 1.02x 1.01x 64B 1.00x 1.00x 0.98x 1.00x 1.01x 1.02x 256B 2.03x 2.01x 0.95x 2.11x 2.12x 2.13x 1024B 2.30x 2.24x 0.95x 2.29x 2.35x 2.35x 8192B 2.31x 2.27x 0.95x 2.31x 2.39x 2.39x 128bit key: size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 0.99x 0.99x 1.00x 1.00x 1.01x 1.01x 64B 1.00x 1.00x 0.98x 1.01x 1.02x 1.01x 256B 2.17x 2.13x 0.96x 2.19x 2.19x 2.19x 1024B 2.29x 2.32x 0.95x 2.34x 2.37x 2.38x 8192B 2.35x 2.32x 0.95x 2.35x 2.39x 2.39x Signed-off-by: Johannes Goetzfried Signed-off-by: Herbert Xu --- crypto/Kconfig | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'crypto/Kconfig') diff --git a/crypto/Kconfig b/crypto/Kconfig index a3238051b03e..cda97fcaa822 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -692,6 +692,20 @@ config CRYPTO_CAST5 The CAST5 encryption algorithm (synonymous with CAST-128) is described in RFC2144. +config CRYPTO_CAST5_AVX_X86_64 + tristate "CAST5 (CAST-128) cipher algorithm (x86_64/AVX)" + depends on X86 && 64BIT + select CRYPTO_ALGAPI + select CRYPTO_CRYPTD + select CRYPTO_ABLK_HELPER_X86 + select CRYPTO_CAST5 + help + The CAST5 encryption algorithm (synonymous with CAST-128) is + described in RFC2144. + + This module provides the Cast5 cipher algorithm that processes + sixteen blocks parallel using the AVX instruction set. + config CRYPTO_CAST6 tristate "CAST6 (CAST-256) cipher algorithm" select CRYPTO_ALGAPI -- cgit v1.2.1 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 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'crypto/Kconfig') diff --git a/crypto/Kconfig b/crypto/Kconfig index cda97fcaa822..fe8ed62efe2f 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 -- cgit v1.2.1 From 35a1fc1873dd6deac6c005ead85424a8ee28183a Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Thu, 19 Jul 2012 09:42:41 -0500 Subject: powerpc/crypto: add 842 crypto driver This patch add the 842 cryptographic API driver that submits compression requests to the 842 hardware compression accelerator driver (nx-compress). If the hardware accelerator goes offline for any reason (dynamic disable, migration, etc...), this driver will use LZO as a software failover for all future compression requests. For decompression requests, the 842 hardware driver contains a software implementation of the 842 decompressor to support the decompression of data that was compressed before the accelerator went offline. Signed-off-by: Robert Jennings Signed-off-by: Seth Jennings Signed-off-by: Herbert Xu --- crypto/Kconfig | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'crypto/Kconfig') diff --git a/crypto/Kconfig b/crypto/Kconfig index fe8ed62efe2f..cbcc0e2eeda0 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1039,6 +1039,15 @@ config CRYPTO_LZO help This is the LZO algorithm. +config CRYPTO_842 + tristate "842 compression algorithm" + depends on CRYPTO_DEV_NX_COMPRESS + # 842 uses lzo if the hardware becomes unavailable + select LZO_COMPRESS + select LZO_DECOMPRESS + help + This is the 842 algorithm. + comment "Random Number Generation" config CRYPTO_ANSI_CPRNG -- cgit v1.2.1 From 023af608254add7ba037cd634cc5f2fb21ff6420 Mon Sep 17 00:00:00 2001 From: Jussi Kivilinna Date: Sun, 22 Jul 2012 18:18:37 +0300 Subject: crypto: aesni_intel - improve lrw and xts performance by utilizing parallel AES-NI hardware pipelines Use parallel LRW and XTS encryption facilities to better utilize AES-NI hardware pipelines and gain extra performance. Tcrypt benchmark results (async), old vs new ratios: Intel Core i5-2450M CPU (fam: 6, model: 42, step: 7) aes:128bit lrw:256bit xts:256bit size lrw-enc lrw-dec xts-dec xts-dec 16B 0.99x 1.00x 1.22x 1.19x 64B 1.38x 1.50x 1.58x 1.61x 256B 2.04x 2.02x 2.27x 2.29x 1024B 2.56x 2.54x 2.89x 2.92x 8192B 2.85x 2.99x 3.40x 3.23x aes:192bit lrw:320bit xts:384bit size lrw-enc lrw-dec xts-dec xts-dec 16B 1.08x 1.08x 1.16x 1.17x 64B 1.48x 1.54x 1.59x 1.65x 256B 2.18x 2.17x 2.29x 2.28x 1024B 2.67x 2.67x 2.87x 3.05x 8192B 2.93x 2.84x 3.28x 3.33x aes:256bit lrw:348bit xts:512bit size lrw-enc lrw-dec xts-dec xts-dec 16B 1.07x 1.07x 1.18x 1.19x 64B 1.56x 1.56x 1.70x 1.71x 256B 2.22x 2.24x 2.46x 2.46x 1024B 2.76x 2.77x 3.13x 3.05x 8192B 2.99x 3.05x 3.40x 3.30x Cc: Huang Ying Signed-off-by: Jussi Kivilinna Reviewed-by: Kim Phillips Signed-off-by: Herbert Xu --- crypto/Kconfig | 2 ++ 1 file changed, 2 insertions(+) (limited to 'crypto/Kconfig') diff --git a/crypto/Kconfig b/crypto/Kconfig index cbcc0e2eeda0..213fb37be51f 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -564,6 +564,8 @@ config CRYPTO_AES_NI_INTEL select CRYPTO_CRYPTD select CRYPTO_ABLK_HELPER_X86 select CRYPTO_ALGAPI + select CRYPTO_LRW + select CRYPTO_XTS help Use Intel AES-NI instructions for AES algorithm. -- cgit v1.2.1 From f0be44f4fb1faee42635ca5ea06dc9c3e820a35d Mon Sep 17 00:00:00 2001 From: David McCullough Date: Fri, 7 Sep 2012 04:17:02 +0800 Subject: arm/crypto: Add optimized AES and SHA1 routines Add assembler versions of AES and SHA1 for ARM platforms. This has provided up to a 50% improvement in IPsec/TCP throughout for tunnels using AES128/SHA1. Platform CPU SPeed Endian Before (bps) After (bps) Improvement IXP425 533 MHz big 11217042 15566294 ~38% KS8695 166 MHz little 3828549 5795373 ~51% Signed-off-by: David McCullough Signed-off-by: Herbert Xu --- crypto/Kconfig | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'crypto/Kconfig') diff --git a/crypto/Kconfig b/crypto/Kconfig index 213fb37be51f..27307981f88e 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -433,6 +433,15 @@ config CRYPTO_SHA1_SSSE3 using Supplemental SSE3 (SSSE3) instructions or Advanced Vector Extensions (AVX), when available. +config CRYPTO_SHA1_ARM + tristate "SHA1 digest algorithm (ARM-asm)" + depends on ARM + select CRYPTO_SHA1 + select CRYPTO_HASH + help + SHA-1 secure hash standard (FIPS 180-1/DFIPS 180-2) implemented + using optimized ARM assembler. + config CRYPTO_SHA256 tristate "SHA224 and SHA256 digest algorithm" select CRYPTO_HASH @@ -590,6 +599,30 @@ config CRYPTO_AES_NI_INTEL ECB, CBC, LRW, PCBC, XTS. The 64 bit version has additional acceleration for CTR. +config CRYPTO_AES_ARM + tristate "AES cipher algorithms (ARM-asm)" + depends on ARM + select CRYPTO_ALGAPI + select CRYPTO_AES + help + Use optimized AES assembler routines for ARM platforms. + + AES cipher algorithms (FIPS-197). AES uses the Rijndael + algorithm. + + Rijndael appears to be consistently a very good performer in + both hardware and software across a wide range of computing + environments regardless of its use in feedback or non-feedback + modes. Its key setup time is excellent, and its key agility is + good. Rijndael's very low memory requirements make it very well + suited for restricted-space environments, in which it also + demonstrates excellent performance. Rijndael's operations are + among the easiest to defend against power and timing attacks. + + The AES specifies three key sizes: 128, 192 and 256 bits + + See for more information. + config CRYPTO_ANUBIS tristate "Anubis cipher algorithm" select CRYPTO_ALGAPI -- cgit v1.2.1