| Message ID | 20221207135855.459181-1-ap420073@gmail.com |
|---|---|
| Headers | show |
| Series | crypto: aria: implement aria-avx2 and aria-avx512 | expand |
> -----Original Message----- > From: Taehee Yoo <ap420073@gmail.com> > Sent: Wednesday, December 7, 2022 7:59 AM > Subject: [PATCH v7 3/4] crypto: aria: implement aria-avx2 > ... > diff --git a/arch/x86/crypto/aria-avx.h b/arch/x86/crypto/aria-avx.h > index 01e9a01dc157..b997c4888fb7 100644 > --- a/arch/x86/crypto/aria-avx.h > +++ b/arch/x86/crypto/aria-avx.h > @@ -7,10 +7,48 @@ > #define ARIA_AESNI_PARALLEL_BLOCKS 16 > #define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * 16) > > +#define ARIA_AESNI_AVX2_PARALLEL_BLOCKS 32 > +#define ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * 32) I think those _SIZE macros should use the _BLOCKS macros rather than hardcode those numbers: #define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_PARALLEL_BLOCKS) #define ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_AVX2_PARALLEL_BLOCKS)
Hi Elliott, Thank you so much for the review! On 12/10/22 04:16, Elliott, Robert (Servers) wrote: > > >> -----Original Message----- >> From: Taehee Yoo <ap420073@gmail.com> >> Sent: Wednesday, December 7, 2022 7:59 AM >> Subject: [PATCH v7 3/4] crypto: aria: implement aria-avx2 >> > ... >> diff --git a/arch/x86/crypto/aria-avx.h b/arch/x86/crypto/aria-avx.h >> index 01e9a01dc157..b997c4888fb7 100644 >> --- a/arch/x86/crypto/aria-avx.h >> +++ b/arch/x86/crypto/aria-avx.h >> @@ -7,10 +7,48 @@ >> #define ARIA_AESNI_PARALLEL_BLOCKS 16 >> #define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * 16) >> >> +#define ARIA_AESNI_AVX2_PARALLEL_BLOCKS 32 >> +#define ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * 32) > > I think those _SIZE macros should use the _BLOCKS macros rather > than hardcode those numbers: > > #define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_PARALLEL_BLOCKS) > #define ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_AVX2_PARALLEL_BLOCKS) > I agree with it. I will replace the magic numbers with the _BLOCK macros in the v8 patch. Thanks a lot! Taehee Yoo
This patchset is to implement aria-avx2 and aria-avx512. There are some differences between aria-avx, aria-avx2, and aria-avx512, but they are not core logic(s-box, diffusion layer). ARIA-AVX2 It supports 32way parallel processing using 256bit registers. Like ARIA-AVX, it supports both AES-NI based s-box layer algorithm and GFNI based s-box layer algorithm. These algorithms are the same as ARIA-AVX except that AES-NI doesn't support 256bit registers, so it is used twice. ARIA-AVX512 It supports 64way parallel processing using 512bit registers. It supports only GFNI based s-box layer algorithm. Benchmarks with i3-12100 commands: modprobe tcrypt mode=610 num_mb=8192 ARIA-AVX512(128bit and 256bit) testing speed of multibuffer ecb(aria) (ecb-aria-avx512) encryption tcrypt: 1 operation in 1504 cycles (1024 bytes) tcrypt: 1 operation in 4595 cycles (4096 bytes) tcrypt: 1 operation in 1763 cycles (1024 bytes) tcrypt: 1 operation in 5540 cycles (4096 bytes) testing speed of multibuffer ecb(aria) (ecb-aria-avx512) decryption tcrypt: 1 operation in 1502 cycles (1024 bytes) tcrypt: 1 operation in 4615 cycles (4096 bytes) tcrypt: 1 operation in 1759 cycles (1024 bytes) tcrypt: 1 operation in 5554 cycles (4096 bytes) ARIA-AVX2 with GFNI(128bit and 256bit) testing speed of multibuffer ecb(aria) (ecb-aria-avx2) encryption tcrypt: 1 operation in 2003 cycles (1024 bytes) tcrypt: 1 operation in 5867 cycles (4096 bytes) tcrypt: 1 operation in 2358 cycles (1024 bytes) tcrypt: 1 operation in 7295 cycles (4096 bytes) testing speed of multibuffer ecb(aria) (ecb-aria-avx2) decryption tcrypt: 1 operation in 2004 cycles (1024 bytes) tcrypt: 1 operation in 5956 cycles (4096 bytes) tcrypt: 1 operation in 2409 cycles (1024 bytes) tcrypt: 1 operation in 7564 cycles (4096 bytes) ARIA-AVX with GFNI(128bit and 256bit) testing speed of multibuffer ecb(aria) (ecb-aria-avx) encryption tcrypt: 1 operation in 2761 cycles (1024 bytes) tcrypt: 1 operation in 9390 cycles (4096 bytes) tcrypt: 1 operation in 3401 cycles (1024 bytes) tcrypt: 1 operation in 11876 cycles (4096 bytes) testing speed of multibuffer ecb(aria) (ecb-aria-avx) decryption tcrypt: 1 operation in 2735 cycles (1024 bytes) tcrypt: 1 operation in 9424 cycles (4096 bytes) tcrypt: 1 operation in 3369 cycles (1024 bytes) tcrypt: 1 operation in 11954 cycles (4096 bytes) This patchset will not successfully be merged before applying CFI fixes because of conflict. v7: - Use IS_ENABLED() instead of defined() v6: - Rebase for "CFI fixes" patchset. - Use SYM_TYPED_FUNC_START instead of SYM_FUNC_START. v5: - Set CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE flag to avx2, and avx512. v4: - Use keystream array in the request ctx. v3: - Use ARIA_CTX_enc_key, ARIA_CTX_dec_key, and ARIA_CTX_rounds defines. v2: - Add new "add keystream array into struct aria_ctx" patch. - Use keystream array in the aria_ctx instead of stack memory Taehee Yoo (4): crypto: aria: add keystream array into request ctx crypto: aria: do not use magic number offsets of aria_ctx crypto: aria: implement aria-avx2 crypto: aria: implement aria-avx512 arch/x86/crypto/Kconfig | 38 + arch/x86/crypto/Makefile | 6 + arch/x86/crypto/aria-aesni-avx-asm_64.S | 26 +- arch/x86/crypto/aria-aesni-avx2-asm_64.S | 1433 +++++++++++++++++++++ arch/x86/crypto/aria-avx.h | 46 + arch/x86/crypto/aria-gfni-avx512-asm_64.S | 1020 +++++++++++++++ arch/x86/crypto/aria_aesni_avx2_glue.c | 252 ++++ arch/x86/crypto/aria_aesni_avx_glue.c | 45 +- arch/x86/crypto/aria_gfni_avx512_glue.c | 250 ++++ arch/x86/kernel/asm-offsets.c | 9 + crypto/aria_generic.c | 4 + 11 files changed, 3101 insertions(+), 28 deletions(-) create mode 100644 arch/x86/crypto/aria-aesni-avx2-asm_64.S create mode 100644 arch/x86/crypto/aria-gfni-avx512-asm_64.S create mode 100644 arch/x86/crypto/aria_aesni_avx2_glue.c create mode 100644 arch/x86/crypto/aria_gfni_avx512_glue.c