forked from luck/tmp_suning_uos_patched
d7d7b85356
These x86_64 vectorized implementations support AVX, AVX-2, and AVX512F.
The AVX-512F implementation is disabled on Skylake, due to throttling,
but it is quite fast on >= Cannonlake.
On the left is cycle counts on a Core i7 6700HQ using the AVX-2
codepath, comparing this implementation ("new") to the implementation in
the current crypto api ("old"). On the right are benchmarks on a Xeon
Gold 5120 using the AVX-512 codepath. The new implementation is faster
on all benchmarks.
AVX-2 AVX-512
--------- -----------
size old new size old new
---- ---- ---- ---- ---- ----
0 70 68 0 74 70
16 92 90 16 96 92
32 134 104 32 136 106
48 172 120 48 184 124
64 218 136 64 218 138
80 254 158 80 260 160
96 298 174 96 300 176
112 342 192 112 342 194
128 388 212 128 384 212
144 428 228 144 420 226
160 466 246 160 464 248
176 510 264 176 504 264
192 550 282 192 544 282
208 594 302 208 582 300
224 628 316 224 624 318
240 676 334 240 662 338
256 716 354 256 708 358
272 764 374 272 748 372
288 802 352 288 788 358
304 420 366 304 422 370
320 428 360 320 432 364
336 484 378 336 486 380
352 426 384 352 434 390
368 478 400 368 480 408
384 488 394 384 490 398
400 542 408 400 542 412
416 486 416 416 492 426
432 534 430 432 538 436
448 544 422 448 546 432
464 600 438 464 600 448
480 540 448 480 548 456
496 594 464 496 594 476
512 602 456 512 606 470
528 656 476 528 656 480
544 600 480 544 606 498
560 650 494 560 652 512
576 664 490 576 662 508
592 714 508 592 716 522
608 656 514 608 664 538
624 708 532 624 710 552
640 716 524 640 720 516
656 770 536 656 772 526
672 716 548 672 722 544
688 770 562 688 768 556
704 774 552 704 778 556
720 826 568 720 832 568
736 768 574 736 780 584
752 822 592 752 826 600
768 830 584 768 836 560
784 884 602 784 888 572
800 828 610 800 838 588
816 884 628 816 884 604
832 888 618 832 894 598
848 942 632 848 946 612
864 884 644 864 896 628
880 936 660 880 942 644
896 948 652 896 952 608
912 1000 664 912 1004 616
928 942 676 928 954 634
944 994 690 944 1000 646
960 1002 680 960 1008 646
976 1054 694 976 1062 658
992 1002 706 992 1012 674
1008 1052 720 1008 1058 690
This commit wires in the prior implementation from Andy, and makes the
following changes to be suitable for kernel land.
- Some cosmetic and structural changes, like renaming labels to
.Lname, constants, and other Linux conventions, as well as making
the code easy for us to maintain moving forward.
- CPU feature checking is done in C by the glue code.
- We avoid jumping into the middle of functions, to appease objtool,
and instead parameterize shared code.
- We maintain frame pointers so that stack traces make sense.
- We remove the dependency on the perl xlate code, which transforms
the output into things that assemblers we don't care about use.
Importantly, none of our changes affect the arithmetic or core code, but
just involve the differing environment of kernel space.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Samuel Neves <sneves@dei.uc.pt>
Co-developed-by: Samuel Neves <sneves@dei.uc.pt>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
128 lines
5.1 KiB
Makefile
128 lines
5.1 KiB
Makefile
# SPDX-License-Identifier: GPL-2.0
|
|
#
|
|
# Arch-specific CryptoAPI modules.
|
|
#
|
|
|
|
OBJECT_FILES_NON_STANDARD := y
|
|
|
|
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)
|
|
avx512_supported :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,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_TWOFISH_586) += twofish-i586.o
|
|
obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
|
|
|
|
obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
|
|
obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
|
|
obj-$(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-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
|
|
obj-$(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
|
|
obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
|
|
|
|
obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
|
|
|
|
obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
|
|
obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
|
|
obj-$(CONFIG_CRYPTO_CURVE25519_X86) += curve25519-x86_64.o
|
|
|
|
# These modules require assembler to support AVX.
|
|
ifeq ($(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-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
|
|
obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += blake2s-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-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
|
|
endif
|
|
|
|
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
|
|
serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
|
|
|
|
des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
|
|
camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
|
|
blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
|
|
twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
|
|
twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
|
|
chacha-x86_64-y := chacha-ssse3-x86_64.o chacha_glue.o
|
|
serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
|
|
|
|
aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
|
|
|
|
nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
|
|
blake2s-x86_64-y := blake2s-core.o blake2s-glue.o
|
|
poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o
|
|
ifneq ($(CONFIG_CRYPTO_POLY1305_X86_64),)
|
|
targets += poly1305-x86_64-cryptogams.S
|
|
endif
|
|
|
|
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
|
|
chacha-x86_64-y += chacha-avx2-x86_64.o
|
|
serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
|
|
|
|
nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o
|
|
endif
|
|
|
|
ifeq ($(avx512_supported),yes)
|
|
chacha-x86_64-y += chacha-avx512vl-x86_64.o
|
|
endif
|
|
|
|
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
|
|
aesni-intel-$(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
|
|
sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
|
|
ifeq ($(avx2_supported),yes)
|
|
sha1-ssse3-y += sha1_avx2_x86_64_asm.o
|
|
endif
|
|
ifeq ($(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
|
|
|
|
quiet_cmd_perlasm = PERLASM $@
|
|
cmd_perlasm = $(PERL) $< > $@
|
|
$(obj)/%.S: $(src)/%.pl FORCE
|
|
$(call if_changed,perlasm)
|