diff options
| author |  Taehee Yoo <ap420073@gmail.com>
| 2023-01-01 09:12:51 +0000 |
|---|---|---|
| committer |  Herbert Xu <herbert@gondor.apana.org.au>
| 2023-01-06 17:15:47 +0800 |
| commit | 37d8d3ae7a58cb16fa3f4f1992d2ee36bc621438 (patch) | |
| tree | 18640f13c534066a7b185ffd2a84f63be34f1ee2 /arch/x86/crypto/aria-avx.h | |
| parent | crypto: x86/aria - do not use magic number offsets of aria_ctx (diff) | |
| download | linux-37d8d3ae7a58cb16fa3f4f1992d2ee36bc621438.tar.gz linux-37d8d3ae7a58cb16fa3f4f1992d2ee36bc621438.tar.bz2 linux-37d8d3ae7a58cb16fa3f4f1992d2ee36bc621438.zip | |
crypto: x86/aria - implement aria-avx2
aria-avx2 implementation uses AVX2, AES-NI, and GFNI.
It supports 32way parallel processing.
So, byteslicing code is changed to support 32way parallel.
And it exports some aria-avx functions such as encrypt() and decrypt().
There are two main logics, s-box layer and diffusion layer.
These codes are the same as aria-avx implementation.
But some instruction are exchanged because they don't support 256bit
registers.
Also, AES-NI doesn't support 256bit register.
So, aesenclast and aesdeclast are used twice like below:
vextracti128 $1, ymm0, xmm6;
vaesenclast xmm7, xmm0, xmm0;
vaesenclast xmm7, xmm6, xmm6;
vinserti128 $1, xmm6, ymm0, ymm0;
Benchmark with modprobe tcrypt mode=610 num_mb=8192, i3-12100:
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)
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/x86/crypto/aria-avx.h')
| -rw-r--r-- | arch/x86/crypto/aria-avx.h | 40 |
1 files changed, 39 insertions, 1 deletions
diff --git a/arch/x86/crypto/aria-avx.h b/arch/x86/crypto/aria-avx.h index 01e9a01dc157..9f2d847c460a 100644 --- a/arch/x86/crypto/aria-avx.h +++ b/arch/x86/crypto/aria-avx.h @@ -5,12 +5,50 @@ #include <linux/types.h> #define ARIA_AESNI_PARALLEL_BLOCKS 16 -#define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * 16) +#define ARIA_AESNI_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_PARALLEL_BLOCKS) + +#define ARIA_AESNI_AVX2_PARALLEL_BLOCKS 32 +#define ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE (ARIA_BLOCK_SIZE * ARIA_AESNI_AVX2_PARALLEL_BLOCKS) + +asmlinkage void aria_aesni_avx_encrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_decrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_ctr_crypt_16way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); +asmlinkage void aria_aesni_avx_gfni_encrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_gfni_decrypt_16way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx_gfni_ctr_crypt_16way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); + +asmlinkage void aria_aesni_avx2_encrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_decrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_ctr_crypt_32way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); +asmlinkage void aria_aesni_avx2_gfni_encrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_gfni_decrypt_32way(const void *ctx, u8 *dst, + const u8 *src); +asmlinkage void aria_aesni_avx2_gfni_ctr_crypt_32way(const void *ctx, u8 *dst, + const u8 *src, + u8 *keystream, u8 *iv); struct aria_avx_ops { void (*aria_encrypt_16way)(const void *ctx, u8 *dst, const u8 *src); void (*aria_decrypt_16way)(const void *ctx, u8 *dst, const u8 *src); void (*aria_ctr_crypt_16way)(const void *ctx, u8 *dst, const u8 *src, u8 *keystream, u8 *iv); + void (*aria_encrypt_32way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_decrypt_32way)(const void *ctx, u8 *dst, const u8 *src); + void (*aria_ctr_crypt_32way)(const void *ctx, u8 *dst, const u8 *src, + u8 *keystream, u8 *iv); + }; #endif |