linux_dsm_epyc7002/arch/x86/crypto/Makefile

110 lines
4.7 KiB
Makefile
Raw Normal View History

#
# Arch-specific CryptoAPI modules.
#
avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
$(comma)4)$(comma)%ymm2,yes,no)
sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no)
sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no)
obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
crypto: camellia - add assembler implementation for x86_64 Patch adds x86_64 assembler implementation of Camellia block cipher. Two set of functions are provided. First set is regular 'one-block at time' encrypt/decrypt functions. Second is 'two-block at time' functions that gain performance increase on out-of-order CPUs. Performance of 2-way functions should be equal to 1-way functions with in-order CPUs. Patch has been tested with tcrypt and automated filesystem tests. Tcrypt benchmark results: AMD Phenom II 1055T (fam:16, model:10): camellia-asm vs camellia_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 1.27x 1.22x 1.30x 1.42x 1.30x 1.34x 1.19x 1.05x 1.23x 1.24x 64B 1.74x 1.79x 1.43x 1.87x 1.81x 1.87x 1.48x 1.38x 1.55x 1.62x 256B 1.90x 1.87x 1.43x 1.94x 1.94x 1.95x 1.63x 1.62x 1.67x 1.70x 1024B 1.96x 1.93x 1.43x 1.95x 1.98x 2.01x 1.67x 1.69x 1.74x 1.80x 8192B 1.96x 1.96x 1.39x 1.93x 2.01x 2.03x 1.72x 1.64x 1.71x 1.76x 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 1.23x 1.23x 1.33x 1.39x 1.34x 1.38x 1.04x 1.18x 1.21x 1.29x 64B 1.72x 1.69x 1.42x 1.78x 1.81x 1.89x 1.57x 1.52x 1.56x 1.65x 256B 1.85x 1.88x 1.42x 1.86x 1.93x 1.96x 1.69x 1.65x 1.70x 1.75x 1024B 1.88x 1.86x 1.45x 1.95x 1.96x 1.95x 1.77x 1.71x 1.77x 1.78x 8192B 1.91x 1.86x 1.42x 1.91x 2.03x 1.98x 1.73x 1.71x 1.78x 1.76x camellia-asm vs aes-asm (8kB block): 128bit 256bit ecb-enc 1.15x 1.22x ecb-dec 1.16x 1.16x cbc-enc 0.85x 0.90x cbc-dec 1.20x 1.23x ctr-enc 1.28x 1.30x ctr-dec 1.27x 1.28x lrw-enc 1.12x 1.16x lrw-dec 1.08x 1.10x xts-enc 1.11x 1.15x xts-dec 1.14x 1.15x Intel Core2 T8100 (fam:6, model:23, step:6): camellia-asm vs camellia_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 1.10x 1.12x 1.14x 1.16x 1.16x 1.15x 1.02x 1.02x 1.08x 1.08x 64B 1.61x 1.60x 1.17x 1.68x 1.67x 1.66x 1.43x 1.42x 1.44x 1.42x 256B 1.65x 1.73x 1.17x 1.77x 1.81x 1.80x 1.54x 1.53x 1.58x 1.54x 1024B 1.76x 1.74x 1.18x 1.80x 1.85x 1.85x 1.60x 1.59x 1.65x 1.60x 8192B 1.77x 1.75x 1.19x 1.81x 1.85x 1.86x 1.63x 1.61x 1.66x 1.62x 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 1.10x 1.07x 1.13x 1.16x 1.11x 1.16x 1.03x 1.02x 1.08x 1.07x 64B 1.61x 1.62x 1.15x 1.66x 1.63x 1.68x 1.47x 1.46x 1.47x 1.44x 256B 1.71x 1.70x 1.16x 1.75x 1.69x 1.79x 1.58x 1.57x 1.59x 1.55x 1024B 1.78x 1.72x 1.17x 1.75x 1.80x 1.80x 1.63x 1.62x 1.65x 1.62x 8192B 1.76x 1.73x 1.17x 1.78x 1.80x 1.81x 1.64x 1.62x 1.68x 1.64x camellia-asm vs aes-asm (8kB block): 128bit 256bit ecb-enc 1.17x 1.21x ecb-dec 1.17x 1.20x cbc-enc 0.80x 0.82x cbc-dec 1.22x 1.24x ctr-enc 1.25x 1.26x ctr-dec 1.25x 1.26x lrw-enc 1.14x 1.18x lrw-dec 1.13x 1.17x xts-enc 1.14x 1.18x xts-dec 1.14x 1.17x Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2012-03-06 01:26:47 +07:00
obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
crypto: twofish - add 3-way parallel x86_64 assembler implemention Patch adds 3-way parallel x86_64 assembly implementation of twofish as new module. New assembler functions crypt data in three blocks chunks, improving cipher performance on out-of-order CPUs. Patch has been tested with tcrypt and automated filesystem tests. Summary of the tcrypt benchmarks: Twofish 3-way-asm vs twofish asm (128bit 8kb block ECB) encrypt: 1.3x speed decrypt: 1.3x speed Twofish 3-way-asm vs twofish asm (128bit 8kb block CBC) encrypt: 1.07x speed decrypt: 1.4x speed Twofish 3-way-asm vs twofish asm (128bit 8kb block CTR) encrypt: 1.4x speed Twofish 3-way-asm vs AES asm (128bit 8kb block ECB) encrypt: 1.0x speed decrypt: 1.0x speed Twofish 3-way-asm vs AES asm (128bit 8kb block CBC) encrypt: 0.84x speed decrypt: 1.09x speed Twofish 3-way-asm vs AES asm (128bit 8kb block CTR) encrypt: 1.15x speed Full output: http://koti.mbnet.fi/axh/kernel/crypto/tcrypt-speed-twofish-3way-asm-x86_64.txt http://koti.mbnet.fi/axh/kernel/crypto/tcrypt-speed-twofish-asm-x86_64.txt http://koti.mbnet.fi/axh/kernel/crypto/tcrypt-speed-aes-asm-x86_64.txt Tests were run on: vendor_id : AuthenticAMD cpu family : 16 model : 10 model name : AMD Phenom(tm) II X6 1055T Processor Also userspace test were run on: vendor_id : GenuineIntel cpu family : 6 model : 15 model name : Intel(R) Xeon(R) CPU E7330 @ 2.40GHz stepping : 11 Userspace test results: Encryption/decryption of twofish 3-way vs x86_64-asm on AMD Phenom II: encrypt: 1.27x decrypt: 1.25x Encryption/decryption of twofish 3-way vs x86_64-asm on Intel Xeon E7330: encrypt: 1.36x decrypt: 1.36x Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-09-26 20:47:25 +07:00
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
crypto: chacha20 - Add a SSSE3 SIMD variant for x86_64 Implements an x86_64 assembler driver for the ChaCha20 stream cipher. This single block variant works on a single state matrix using SSE instructions. It requires SSSE3 due the use of pshufb for efficient 8/16-bit rotate operations. For large messages, throughput increases by ~65% compared to chacha20-generic: testing speed of chacha20 (chacha20-generic) encryption test 0 (256 bit key, 16 byte blocks): 45089207 operations in 10 seconds (721427312 bytes) test 1 (256 bit key, 64 byte blocks): 43839521 operations in 10 seconds (2805729344 bytes) test 2 (256 bit key, 256 byte blocks): 12702056 operations in 10 seconds (3251726336 bytes) test 3 (256 bit key, 1024 byte blocks): 3371173 operations in 10 seconds (3452081152 bytes) test 4 (256 bit key, 8192 byte blocks): 422468 operations in 10 seconds (3460857856 bytes) testing speed of chacha20 (chacha20-simd) encryption test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes) test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes) test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes) test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes) test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes) Benchmark results from a Core i5-4670T. Signed-off-by: Martin Willi <martin@strongswan.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:01 +07:00
obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
crypto: serpent - add 8-way parallel x86_64/SSE2 assembler implementation Patch adds x86_64/SSE2 assembler implementation of serpent cipher. Assembler functions crypt data in eigth block chunks (two 4 block chunk SSE2 operations in parallel to improve performance on out-of-order CPUs). Glue code is based on one from AES-NI implementation, so requests from irq context are redirected to cryptd. v2: - add missing include of linux/module.h (appearently crypto.h used to include module.h, which changed for 3.2 by commit 7c926402a7e8c9b279968fd94efec8700ba3859e) Patch has been tested with tcrypt and automated filesystem tests. Tcrypt benchmarks results (serpent-sse2/serpent_generic speed ratios): AMD Phenom II 1055T (fam:16, model:10): size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 1.03x 1.01x 1.03x 1.05x 1.00x 0.99x 64B 1.00x 1.01x 1.02x 1.04x 1.02x 1.01x 256B 2.34x 2.41x 0.99x 2.43x 2.39x 2.40x 1024B 2.51x 2.57x 1.00x 2.59x 2.56x 2.56x 8192B 2.50x 2.54x 1.00x 2.55x 2.57x 2.57x Intel Celeron T1600 (fam:6, model:15, step:13): size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 0.97x 0.97x 1.01x 1.01x 1.01x 1.02x 64B 1.00x 1.00x 1.00x 1.02x 1.01x 1.01x 256B 3.41x 3.35x 1.00x 3.39x 3.42x 3.44x 1024B 3.75x 3.72x 0.99x 3.74x 3.75x 3.75x 8192B 3.70x 3.68x 0.99x 3.68x 3.69x 3.69x Full output: http://koti.mbnet.fi/axh/kernel/crypto/phenom-ii-1055t/serpent-generic.txt http://koti.mbnet.fi/axh/kernel/crypto/phenom-ii-1055t/serpent-sse2.txt http://koti.mbnet.fi/axh/kernel/crypto/celeron-t1600/serpent-generic.txt http://koti.mbnet.fi/axh/kernel/crypto/celeron-t1600/serpent-sse2.txt Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-11-09 21:26:25 +07:00
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
crypto: sha1 - SSSE3 based SHA1 implementation for x86-64 This is an assembler implementation of the SHA1 algorithm using the Supplemental SSE3 (SSSE3) instructions or, when available, the Advanced Vector Extensions (AVX). Testing with the tcrypt module shows the raw hash performance is up to 2.3 times faster than the C implementation, using 8k data blocks on a Core 2 Duo T5500. For the smalest data set (16 byte) it is still 25% faster. Since this implementation uses SSE/YMM registers it cannot safely be used in every situation, e.g. while an IRQ interrupts a kernel thread. The implementation falls back to the generic SHA1 variant, if using the SSE/YMM registers is not possible. With this algorithm I was able to increase the throughput of a single IPsec link from 344 Mbit/s to 464 Mbit/s on a Core 2 Quad CPU using the SSSE3 variant -- a speedup of +34.8%. Saving and restoring SSE/YMM state might make the actual throughput fluctuate when there are FPU intensive userland applications running. For example, meassuring the performance using iperf2 directly on the machine under test gives wobbling numbers because iperf2 uses the FPU for each packet to check if the reporting interval has expired (in the above test I got min/max/avg: 402/484/464 MBit/s). Using this algorithm on a IPsec gateway gives much more reasonable and stable numbers, albeit not as high as in the directly connected case. Here is the result from an RFC 2544 test run with a EXFO Packet Blazer FTB-8510: frame size sha1-generic sha1-ssse3 delta 64 byte 37.5 MBit/s 37.5 MBit/s 0.0% 128 byte 56.3 MBit/s 62.5 MBit/s +11.0% 256 byte 87.5 MBit/s 100.0 MBit/s +14.3% 512 byte 131.3 MBit/s 150.0 MBit/s +14.2% 1024 byte 162.5 MBit/s 193.8 MBit/s +19.3% 1280 byte 175.0 MBit/s 212.5 MBit/s +21.4% 1420 byte 175.0 MBit/s 218.7 MBit/s +25.0% 1518 byte 150.0 MBit/s 181.2 MBit/s +20.8% The throughput for the largest frame size is lower than for the previous size because the IP packets need to be fragmented in this case to make there way through the IPsec tunnel. Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Maxim Locktyukhin <maxim.locktyukhin@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-08-05 01:19:25 +07:00
obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
crypto: poly1305 - Add a SSE2 SIMD variant for x86_64 Implements an x86_64 assembler driver for the Poly1305 authenticator. This single block variant holds the 130-bit integer in 5 32-bit words, but uses SSE to do two multiplications/additions in parallel. When calling updates with small blocks, the overhead for kernel_fpu_begin/ kernel_fpu_end() negates the perfmance gain. We therefore use the poly1305-generic fallback for small updates. For large messages, throughput increases by ~5-10% compared to poly1305-generic: testing speed of poly1305 (poly1305-generic) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 4080026 opers/sec, 391682496 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 6221094 opers/sec, 597225024 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9609750 opers/sec, 922536057 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1459379 opers/sec, 420301267 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2115179 opers/sec, 609171609 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3729874 opers/sec, 1074203856 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 593000 opers/sec, 626208000 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1081536 opers/sec, 1142102332 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 302077 opers/sec, 628320576 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 554384 opers/sec, 1153120176 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 278715 opers/sec, 1150536345 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 140202 opers/sec, 1153022070 bytes/sec testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3790063 opers/sec, 363846076 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5913378 opers/sec, 567684355 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9352574 opers/sec, 897847104 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1362145 opers/sec, 392297990 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2007075 opers/sec, 578037628 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3709811 opers/sec, 1068425798 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 566272 opers/sec, 597984182 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1111657 opers/sec, 1173910108 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 288857 opers/sec, 600823808 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 590746 opers/sec, 1228751888 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 301825 opers/sec, 1245936902 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 153075 opers/sec, 1258896201 bytes/sec Benchmark results from a Core i5-4670T. Signed-off-by: Martin Willi <martin@strongswan.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:06 +07:00
obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
# These modules require assembler to support AVX.
ifeq ($(avx_supported),yes)
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_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
endif
# These modules require assembler to support AVX2.
ifeq ($(avx2_supported),yes)
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
obj-$(CONFIG_CRYPTO_SHA1_MB) += sha1-mb/
obj-$(CONFIG_CRYPTO_SHA256_MB) += sha256-mb/
obj-$(CONFIG_CRYPTO_SHA512_MB) += sha512-mb/
endif
aes-i586-y := aes-i586-asm_32.o aes_glue.o
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
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
des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
crypto: camellia - add assembler implementation for x86_64 Patch adds x86_64 assembler implementation of Camellia block cipher. Two set of functions are provided. First set is regular 'one-block at time' encrypt/decrypt functions. Second is 'two-block at time' functions that gain performance increase on out-of-order CPUs. Performance of 2-way functions should be equal to 1-way functions with in-order CPUs. Patch has been tested with tcrypt and automated filesystem tests. Tcrypt benchmark results: AMD Phenom II 1055T (fam:16, model:10): camellia-asm vs camellia_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 1.27x 1.22x 1.30x 1.42x 1.30x 1.34x 1.19x 1.05x 1.23x 1.24x 64B 1.74x 1.79x 1.43x 1.87x 1.81x 1.87x 1.48x 1.38x 1.55x 1.62x 256B 1.90x 1.87x 1.43x 1.94x 1.94x 1.95x 1.63x 1.62x 1.67x 1.70x 1024B 1.96x 1.93x 1.43x 1.95x 1.98x 2.01x 1.67x 1.69x 1.74x 1.80x 8192B 1.96x 1.96x 1.39x 1.93x 2.01x 2.03x 1.72x 1.64x 1.71x 1.76x 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 1.23x 1.23x 1.33x 1.39x 1.34x 1.38x 1.04x 1.18x 1.21x 1.29x 64B 1.72x 1.69x 1.42x 1.78x 1.81x 1.89x 1.57x 1.52x 1.56x 1.65x 256B 1.85x 1.88x 1.42x 1.86x 1.93x 1.96x 1.69x 1.65x 1.70x 1.75x 1024B 1.88x 1.86x 1.45x 1.95x 1.96x 1.95x 1.77x 1.71x 1.77x 1.78x 8192B 1.91x 1.86x 1.42x 1.91x 2.03x 1.98x 1.73x 1.71x 1.78x 1.76x camellia-asm vs aes-asm (8kB block): 128bit 256bit ecb-enc 1.15x 1.22x ecb-dec 1.16x 1.16x cbc-enc 0.85x 0.90x cbc-dec 1.20x 1.23x ctr-enc 1.28x 1.30x ctr-dec 1.27x 1.28x lrw-enc 1.12x 1.16x lrw-dec 1.08x 1.10x xts-enc 1.11x 1.15x xts-dec 1.14x 1.15x Intel Core2 T8100 (fam:6, model:23, step:6): camellia-asm vs camellia_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 1.10x 1.12x 1.14x 1.16x 1.16x 1.15x 1.02x 1.02x 1.08x 1.08x 64B 1.61x 1.60x 1.17x 1.68x 1.67x 1.66x 1.43x 1.42x 1.44x 1.42x 256B 1.65x 1.73x 1.17x 1.77x 1.81x 1.80x 1.54x 1.53x 1.58x 1.54x 1024B 1.76x 1.74x 1.18x 1.80x 1.85x 1.85x 1.60x 1.59x 1.65x 1.60x 8192B 1.77x 1.75x 1.19x 1.81x 1.85x 1.86x 1.63x 1.61x 1.66x 1.62x 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 1.10x 1.07x 1.13x 1.16x 1.11x 1.16x 1.03x 1.02x 1.08x 1.07x 64B 1.61x 1.62x 1.15x 1.66x 1.63x 1.68x 1.47x 1.46x 1.47x 1.44x 256B 1.71x 1.70x 1.16x 1.75x 1.69x 1.79x 1.58x 1.57x 1.59x 1.55x 1024B 1.78x 1.72x 1.17x 1.75x 1.80x 1.80x 1.63x 1.62x 1.65x 1.62x 8192B 1.76x 1.73x 1.17x 1.78x 1.80x 1.81x 1.64x 1.62x 1.68x 1.64x camellia-asm vs aes-asm (8kB block): 128bit 256bit ecb-enc 1.17x 1.21x ecb-dec 1.17x 1.20x cbc-enc 0.80x 0.82x cbc-dec 1.22x 1.24x ctr-enc 1.25x 1.26x ctr-dec 1.25x 1.26x lrw-enc 1.14x 1.18x lrw-dec 1.13x 1.17x xts-enc 1.14x 1.18x xts-dec 1.14x 1.17x Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2012-03-06 01:26:47 +07:00
camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
crypto: twofish - add 3-way parallel x86_64 assembler implemention Patch adds 3-way parallel x86_64 assembly implementation of twofish as new module. New assembler functions crypt data in three blocks chunks, improving cipher performance on out-of-order CPUs. Patch has been tested with tcrypt and automated filesystem tests. Summary of the tcrypt benchmarks: Twofish 3-way-asm vs twofish asm (128bit 8kb block ECB) encrypt: 1.3x speed decrypt: 1.3x speed Twofish 3-way-asm vs twofish asm (128bit 8kb block CBC) encrypt: 1.07x speed decrypt: 1.4x speed Twofish 3-way-asm vs twofish asm (128bit 8kb block CTR) encrypt: 1.4x speed Twofish 3-way-asm vs AES asm (128bit 8kb block ECB) encrypt: 1.0x speed decrypt: 1.0x speed Twofish 3-way-asm vs AES asm (128bit 8kb block CBC) encrypt: 0.84x speed decrypt: 1.09x speed Twofish 3-way-asm vs AES asm (128bit 8kb block CTR) encrypt: 1.15x speed Full output: http://koti.mbnet.fi/axh/kernel/crypto/tcrypt-speed-twofish-3way-asm-x86_64.txt http://koti.mbnet.fi/axh/kernel/crypto/tcrypt-speed-twofish-asm-x86_64.txt http://koti.mbnet.fi/axh/kernel/crypto/tcrypt-speed-aes-asm-x86_64.txt Tests were run on: vendor_id : AuthenticAMD cpu family : 16 model : 10 model name : AMD Phenom(tm) II X6 1055T Processor Also userspace test were run on: vendor_id : GenuineIntel cpu family : 6 model : 15 model name : Intel(R) Xeon(R) CPU E7330 @ 2.40GHz stepping : 11 Userspace test results: Encryption/decryption of twofish 3-way vs x86_64-asm on AMD Phenom II: encrypt: 1.27x decrypt: 1.25x Encryption/decryption of twofish 3-way vs x86_64-asm on Intel Xeon E7330: encrypt: 1.36x decrypt: 1.36x Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-09-26 20:47:25 +07:00
twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
crypto: chacha20 - Add a SSSE3 SIMD variant for x86_64 Implements an x86_64 assembler driver for the ChaCha20 stream cipher. This single block variant works on a single state matrix using SSE instructions. It requires SSSE3 due the use of pshufb for efficient 8/16-bit rotate operations. For large messages, throughput increases by ~65% compared to chacha20-generic: testing speed of chacha20 (chacha20-generic) encryption test 0 (256 bit key, 16 byte blocks): 45089207 operations in 10 seconds (721427312 bytes) test 1 (256 bit key, 64 byte blocks): 43839521 operations in 10 seconds (2805729344 bytes) test 2 (256 bit key, 256 byte blocks): 12702056 operations in 10 seconds (3251726336 bytes) test 3 (256 bit key, 1024 byte blocks): 3371173 operations in 10 seconds (3452081152 bytes) test 4 (256 bit key, 8192 byte blocks): 422468 operations in 10 seconds (3460857856 bytes) testing speed of chacha20 (chacha20-simd) encryption test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes) test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes) test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes) test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes) test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes) Benchmark results from a Core i5-4670T. Signed-off-by: Martin Willi <martin@strongswan.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:01 +07:00
chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
crypto: serpent - add 8-way parallel x86_64/SSE2 assembler implementation Patch adds x86_64/SSE2 assembler implementation of serpent cipher. Assembler functions crypt data in eigth block chunks (two 4 block chunk SSE2 operations in parallel to improve performance on out-of-order CPUs). Glue code is based on one from AES-NI implementation, so requests from irq context are redirected to cryptd. v2: - add missing include of linux/module.h (appearently crypto.h used to include module.h, which changed for 3.2 by commit 7c926402a7e8c9b279968fd94efec8700ba3859e) Patch has been tested with tcrypt and automated filesystem tests. Tcrypt benchmarks results (serpent-sse2/serpent_generic speed ratios): AMD Phenom II 1055T (fam:16, model:10): size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 1.03x 1.01x 1.03x 1.05x 1.00x 0.99x 64B 1.00x 1.01x 1.02x 1.04x 1.02x 1.01x 256B 2.34x 2.41x 0.99x 2.43x 2.39x 2.40x 1024B 2.51x 2.57x 1.00x 2.59x 2.56x 2.56x 8192B 2.50x 2.54x 1.00x 2.55x 2.57x 2.57x Intel Celeron T1600 (fam:6, model:15, step:13): size ecb-enc ecb-dec cbc-enc cbc-dec ctr-enc ctr-dec 16B 0.97x 0.97x 1.01x 1.01x 1.01x 1.02x 64B 1.00x 1.00x 1.00x 1.02x 1.01x 1.01x 256B 3.41x 3.35x 1.00x 3.39x 3.42x 3.44x 1024B 3.75x 3.72x 0.99x 3.74x 3.75x 3.75x 8192B 3.70x 3.68x 0.99x 3.68x 3.69x 3.69x Full output: http://koti.mbnet.fi/axh/kernel/crypto/phenom-ii-1055t/serpent-generic.txt http://koti.mbnet.fi/axh/kernel/crypto/phenom-ii-1055t/serpent-sse2.txt http://koti.mbnet.fi/axh/kernel/crypto/celeron-t1600/serpent-generic.txt http://koti.mbnet.fi/axh/kernel/crypto/celeron-t1600/serpent-sse2.txt Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-11-09 21:26:25 +07:00
serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
ifeq ($(avx_supported),yes)
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
twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o \
twofish_avx_glue.o
serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o \
serpent_avx_glue.o
endif
ifeq ($(avx2_supported),yes)
camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
chacha20-x86_64-y += chacha20-avx2-x86_64.o
serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
endif
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
crypto: aes - AES CTR x86_64 "by8" AVX optimization This patch introduces "by8" AES CTR mode AVX optimization inspired by Intel Optimized IPSEC Cryptograhpic library. For additional information, please see: http://downloadcenter.intel.com/Detail_Desc.aspx?agr=Y&DwnldID=22972 The functions aes_ctr_enc_128_avx_by8(), aes_ctr_enc_192_avx_by8() and aes_ctr_enc_256_avx_by8() are adapted from Intel Optimized IPSEC Cryptographic library. When both AES and AVX features are enabled in a platform, the glue code in AESNI module overrieds the existing "by4" CTR mode en/decryption with the "by8" AES CTR mode en/decryption. On a Haswell desktop, with turbo disabled and all cpus running at maximum frequency, the "by8" CTR mode optimization shows better performance results across data & key sizes as measured by tcrypt. The average performance improvement of the "by8" version over the "by4" version is as follows: For 128 bit key and data sizes >= 256 bytes, there is a 10-16% improvement. For 192 bit key and data sizes >= 256 bytes, there is a 20-22% improvement. For 256 bit key and data sizes >= 256 bytes, there is a 20-25% improvement. A typical run of tcrypt with AES CTR mode encryption of the "by4" and "by8" optimization shows the following results: tcrypt with "by4" AES CTR mode encryption optimization on a Haswell Desktop: --------------------------------------------------------------------------- testing speed of __ctr-aes-aesni encryption test 0 (128 bit key, 16 byte blocks): 1 operation in 343 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 336 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 491 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1130 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 7309 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 346 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 361 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 543 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 1321 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 9649 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 369 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 366 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 595 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 1531 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 10522 cycles (8192 bytes) testing speed of __ctr-aes-aesni decryption test 0 (128 bit key, 16 byte blocks): 1 operation in 336 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 350 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 487 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1129 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 7287 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 350 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 359 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 635 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 1324 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 9595 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 364 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 377 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 604 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 1527 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 10549 cycles (8192 bytes) tcrypt with "by8" AES CTR mode encryption optimization on a Haswell Desktop: --------------------------------------------------------------------------- testing speed of __ctr-aes-aesni encryption test 0 (128 bit key, 16 byte blocks): 1 operation in 340 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 330 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 450 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1043 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 6597 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 339 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 352 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 539 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 1153 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 8458 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 353 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 360 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 512 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 1277 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 8745 cycles (8192 bytes) testing speed of __ctr-aes-aesni decryption test 0 (128 bit key, 16 byte blocks): 1 operation in 348 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 335 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 451 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1030 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 6611 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 354 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 346 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 488 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 1154 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 8390 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 357 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 362 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 515 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 1284 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 8681 cycles (8192 bytes) crypto: Incorporate feed back to AES CTR mode optimization patch Specifically, the following: a) alignment around main loop in aes_ctrby8_avx_x86_64.S b) .rodata around data constants used in the assembely code. c) the use of CONFIG_AVX in the glue code. d) fix up white space. e) informational message for "by8" AES CTR mode optimization f) "by8" AES CTR mode optimization can be simply enabled if the platform supports both AES and AVX features. The optimization works superbly on Sandybridge as well. Testing on Haswell shows no performance change since the last. Testing on Sandybridge shows that the "by8" AES CTR mode optimization greatly improves performance. tcrypt log with "by4" AES CTR mode optimization on Sandybridge -------------------------------------------------------------- testing speed of __ctr-aes-aesni encryption test 0 (128 bit key, 16 byte blocks): 1 operation in 383 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 408 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 707 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1864 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 12813 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 395 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 432 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 780 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 2132 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 15765 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 416 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 438 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 842 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 2383 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 16945 cycles (8192 bytes) testing speed of __ctr-aes-aesni decryption test 0 (128 bit key, 16 byte blocks): 1 operation in 389 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 409 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 704 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1865 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 12783 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 409 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 434 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 792 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 2151 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 15804 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 421 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 444 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 840 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 2394 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 16928 cycles (8192 bytes) tcrypt log with "by8" AES CTR mode optimization on Sandybridge -------------------------------------------------------------- testing speed of __ctr-aes-aesni encryption test 0 (128 bit key, 16 byte blocks): 1 operation in 383 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 401 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 522 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1136 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 7046 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 394 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 418 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 559 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 1263 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 9072 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 408 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 428 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 595 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 1385 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 9224 cycles (8192 bytes) testing speed of __ctr-aes-aesni decryption test 0 (128 bit key, 16 byte blocks): 1 operation in 390 cycles (16 bytes) test 1 (128 bit key, 64 byte blocks): 1 operation in 402 cycles (64 bytes) test 2 (128 bit key, 256 byte blocks): 1 operation in 530 cycles (256 bytes) test 3 (128 bit key, 1024 byte blocks): 1 operation in 1135 cycles (1024 bytes) test 4 (128 bit key, 8192 byte blocks): 1 operation in 7079 cycles (8192 bytes) test 5 (192 bit key, 16 byte blocks): 1 operation in 414 cycles (16 bytes) test 6 (192 bit key, 64 byte blocks): 1 operation in 417 cycles (64 bytes) test 7 (192 bit key, 256 byte blocks): 1 operation in 572 cycles (256 bytes) test 8 (192 bit key, 1024 byte blocks): 1 operation in 1312 cycles (1024 bytes) test 9 (192 bit key, 8192 byte blocks): 1 operation in 9073 cycles (8192 bytes) test 10 (256 bit key, 16 byte blocks): 1 operation in 415 cycles (16 bytes) test 11 (256 bit key, 64 byte blocks): 1 operation in 454 cycles (64 bytes) test 12 (256 bit key, 256 byte blocks): 1 operation in 598 cycles (256 bytes) test 13 (256 bit key, 1024 byte blocks): 1 operation in 1407 cycles (1024 bytes) test 14 (256 bit key, 8192 byte blocks): 1 operation in 9288 cycles (8192 bytes) crypto: Fix redundant checks a) Fix the redundant check for cpu_has_aes b) Fix the key length check when invoking the CTR mode "by8" encryptor/decryptor. crypto: fix typo in AES ctr mode transform Signed-off-by: Chandramouli Narayanan <mouli@linux.intel.com> Reviewed-by: Mathias Krause <minipli@googlemail.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2014-06-10 23:22:47 +07:00
aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
crypto: sha1 - SSSE3 based SHA1 implementation for x86-64 This is an assembler implementation of the SHA1 algorithm using the Supplemental SSE3 (SSSE3) instructions or, when available, the Advanced Vector Extensions (AVX). Testing with the tcrypt module shows the raw hash performance is up to 2.3 times faster than the C implementation, using 8k data blocks on a Core 2 Duo T5500. For the smalest data set (16 byte) it is still 25% faster. Since this implementation uses SSE/YMM registers it cannot safely be used in every situation, e.g. while an IRQ interrupts a kernel thread. The implementation falls back to the generic SHA1 variant, if using the SSE/YMM registers is not possible. With this algorithm I was able to increase the throughput of a single IPsec link from 344 Mbit/s to 464 Mbit/s on a Core 2 Quad CPU using the SSSE3 variant -- a speedup of +34.8%. Saving and restoring SSE/YMM state might make the actual throughput fluctuate when there are FPU intensive userland applications running. For example, meassuring the performance using iperf2 directly on the machine under test gives wobbling numbers because iperf2 uses the FPU for each packet to check if the reporting interval has expired (in the above test I got min/max/avg: 402/484/464 MBit/s). Using this algorithm on a IPsec gateway gives much more reasonable and stable numbers, albeit not as high as in the directly connected case. Here is the result from an RFC 2544 test run with a EXFO Packet Blazer FTB-8510: frame size sha1-generic sha1-ssse3 delta 64 byte 37.5 MBit/s 37.5 MBit/s 0.0% 128 byte 56.3 MBit/s 62.5 MBit/s +11.0% 256 byte 87.5 MBit/s 100.0 MBit/s +14.3% 512 byte 131.3 MBit/s 150.0 MBit/s +14.2% 1024 byte 162.5 MBit/s 193.8 MBit/s +19.3% 1280 byte 175.0 MBit/s 212.5 MBit/s +21.4% 1420 byte 175.0 MBit/s 218.7 MBit/s +25.0% 1518 byte 150.0 MBit/s 181.2 MBit/s +20.8% The throughput for the largest frame size is lower than for the previous size because the IP packets need to be fragmented in this case to make there way through the IPsec tunnel. Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Maxim Locktyukhin <maxim.locktyukhin@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2011-08-05 01:19:25 +07:00
sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
crypto: poly1305 - Add a SSE2 SIMD variant for x86_64 Implements an x86_64 assembler driver for the Poly1305 authenticator. This single block variant holds the 130-bit integer in 5 32-bit words, but uses SSE to do two multiplications/additions in parallel. When calling updates with small blocks, the overhead for kernel_fpu_begin/ kernel_fpu_end() negates the perfmance gain. We therefore use the poly1305-generic fallback for small updates. For large messages, throughput increases by ~5-10% compared to poly1305-generic: testing speed of poly1305 (poly1305-generic) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 4080026 opers/sec, 391682496 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 6221094 opers/sec, 597225024 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9609750 opers/sec, 922536057 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1459379 opers/sec, 420301267 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2115179 opers/sec, 609171609 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3729874 opers/sec, 1074203856 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 593000 opers/sec, 626208000 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1081536 opers/sec, 1142102332 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 302077 opers/sec, 628320576 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 554384 opers/sec, 1153120176 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 278715 opers/sec, 1150536345 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 140202 opers/sec, 1153022070 bytes/sec testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3790063 opers/sec, 363846076 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5913378 opers/sec, 567684355 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9352574 opers/sec, 897847104 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1362145 opers/sec, 392297990 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2007075 opers/sec, 578037628 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3709811 opers/sec, 1068425798 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 566272 opers/sec, 597984182 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1111657 opers/sec, 1173910108 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 288857 opers/sec, 600823808 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 590746 opers/sec, 1228751888 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 301825 opers/sec, 1245936902 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 153075 opers/sec, 1258896201 bytes/sec Benchmark results from a Core i5-4670T. Signed-off-by: Martin Willi <martin@strongswan.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:06 +07:00
poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o
ifeq ($(avx2_supported),yes)
sha1-ssse3-y += sha1_avx2_x86_64_asm.o
crypto: poly1305 - Add a four block AVX2 variant for x86_64 Extends the x86_64 Poly1305 authenticator by a function processing four consecutive Poly1305 blocks in parallel using AVX2 instructions. For large messages, throughput increases by ~15-45% compared to two block SSE2: testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3809514 opers/sec, 365713411 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5973423 opers/sec, 573448627 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9446779 opers/sec, 906890803 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1364814 opers/sec, 393066691 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2045780 opers/sec, 589184697 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3711946 opers/sec, 1069040592 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 573686 opers/sec, 605812732 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1647802 opers/sec, 1740079440 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 292970 opers/sec, 609378224 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 943229 opers/sec, 1961916528 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 494623 opers/sec, 2041804569 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 254045 opers/sec, 2089271014 bytes/sec testing speed of poly1305 (poly1305-simd) test 0 ( 96 byte blocks, 16 bytes per update, 6 updates): 3826224 opers/sec, 367317552 bytes/sec test 1 ( 96 byte blocks, 32 bytes per update, 3 updates): 5948638 opers/sec, 571069267 bytes/sec test 2 ( 96 byte blocks, 96 bytes per update, 1 updates): 9439110 opers/sec, 906154627 bytes/sec test 3 ( 288 byte blocks, 16 bytes per update, 18 updates): 1367756 opers/sec, 393913872 bytes/sec test 4 ( 288 byte blocks, 32 bytes per update, 9 updates): 2056881 opers/sec, 592381958 bytes/sec test 5 ( 288 byte blocks, 288 bytes per update, 1 updates): 3711153 opers/sec, 1068812179 bytes/sec test 6 ( 1056 byte blocks, 32 bytes per update, 33 updates): 574940 opers/sec, 607136745 bytes/sec test 7 ( 1056 byte blocks, 1056 bytes per update, 1 updates): 1948830 opers/sec, 2057964585 bytes/sec test 8 ( 2080 byte blocks, 32 bytes per update, 65 updates): 293308 opers/sec, 610082096 bytes/sec test 9 ( 2080 byte blocks, 2080 bytes per update, 1 updates): 1235224 opers/sec, 2569267792 bytes/sec test 10 ( 4128 byte blocks, 4128 bytes per update, 1 updates): 684405 opers/sec, 2825226316 bytes/sec test 11 ( 8224 byte blocks, 8224 bytes per update, 1 updates): 367101 opers/sec, 3019039446 bytes/sec Benchmark results from a Core i5-4670T. Signed-off-by: Martin Willi <martin@strongswan.org> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:08 +07:00
poly1305-x86_64-y += poly1305-avx2-x86_64.o
endif
ifeq ($(sha1_ni_supported),yes)
sha1-ssse3-y += sha1_ni_asm.o
endif
crc32c-intel-y := crc32c-intel_glue.o
crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
ifeq ($(sha256_ni_supported),yes)
sha256-ssse3-y += sha256_ni_asm.o
endif
sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o