Commit 37d8d3ae authored by Taehee Yoo's avatar Taehee Yoo Committed by Herbert Xu

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: default avatarTaehee Yoo <ap420073@gmail.com>
Signed-off-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
parent 35344cf3
......@@ -304,6 +304,25 @@ config CRYPTO_ARIA_AESNI_AVX_X86_64
Processes 16 blocks in parallel.
config CRYPTO_ARIA_AESNI_AVX2_X86_64
tristate "Ciphers: ARIA with modes: ECB, CTR (AES-NI/AVX2/GFNI)"
depends on X86 && 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_SIMD
select CRYPTO_ALGAPI
select CRYPTO_ARIA
select CRYPTO_ARIA_AESNI_AVX_X86_64
help
Length-preserving cipher: ARIA cipher algorithms
(RFC 5794) with ECB and CTR modes
Architecture: x86_64 using:
- AES-NI (AES New Instructions)
- AVX2 (Advanced Vector Extensions)
- GFNI (Galois Field New Instructions)
Processes 32 blocks in parallel.
config CRYPTO_CHACHA20_X86_64
tristate "Ciphers: ChaCha20, XChaCha20, XChaCha12 (SSSE3/AVX2/AVX-512VL)"
depends on X86 && 64BIT
......
......@@ -103,6 +103,9 @@ sm4-aesni-avx2-x86_64-y := sm4-aesni-avx2-asm_64.o sm4_aesni_avx2_glue.o
obj-$(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) += aria-aesni-avx-x86_64.o
aria-aesni-avx-x86_64-y := aria-aesni-avx-asm_64.o aria_aesni_avx_glue.o
obj-$(CONFIG_CRYPTO_ARIA_AESNI_AVX2_X86_64) += aria-aesni-avx2-x86_64.o
aria-aesni-avx2-x86_64-y := aria-aesni-avx2-asm_64.o aria_aesni_avx2_glue.o
quiet_cmd_perlasm = PERLASM $@
cmd_perlasm = $(PERL) $< > $@
$(obj)/%.S: $(src)/%.pl FORCE
......
This diff is collapsed.
......@@ -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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Glue Code for the AVX2/AES-NI/GFNI assembler implementation of the ARIA Cipher
*
* Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com>
*/
#include <crypto/algapi.h>
#include <crypto/internal/simd.h>
#include <crypto/aria.h>
#include <linux/crypto.h>
#include <linux/err.h>
#include <linux/module.h>
#include <linux/types.h>
#include "ecb_cbc_helpers.h"
#include "aria-avx.h"
asmlinkage void aria_aesni_avx2_encrypt_32way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx2_encrypt_32way);
asmlinkage void aria_aesni_avx2_decrypt_32way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx2_decrypt_32way);
asmlinkage void aria_aesni_avx2_ctr_crypt_32way(const void *ctx, u8 *dst,
const u8 *src,
u8 *keystream, u8 *iv);
EXPORT_SYMBOL_GPL(aria_aesni_avx2_ctr_crypt_32way);
asmlinkage void aria_aesni_avx2_gfni_encrypt_32way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_encrypt_32way);
asmlinkage void aria_aesni_avx2_gfni_decrypt_32way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_decrypt_32way);
asmlinkage void aria_aesni_avx2_gfni_ctr_crypt_32way(const void *ctx, u8 *dst,
const u8 *src,
u8 *keystream, u8 *iv);
EXPORT_SYMBOL_GPL(aria_aesni_avx2_gfni_ctr_crypt_32way);
static struct aria_avx_ops aria_ops;
struct aria_avx2_request_ctx {
u8 keystream[ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE];
};
static int ecb_do_encrypt(struct skcipher_request *req, const u32 *rkey)
{
ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS);
ECB_BLOCK(ARIA_AESNI_AVX2_PARALLEL_BLOCKS, aria_ops.aria_encrypt_32way);
ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_encrypt_16way);
ECB_BLOCK(1, aria_encrypt);
ECB_WALK_END();
}
static int ecb_do_decrypt(struct skcipher_request *req, const u32 *rkey)
{
ECB_WALK_START(req, ARIA_BLOCK_SIZE, ARIA_AESNI_PARALLEL_BLOCKS);
ECB_BLOCK(ARIA_AESNI_AVX2_PARALLEL_BLOCKS, aria_ops.aria_decrypt_32way);
ECB_BLOCK(ARIA_AESNI_PARALLEL_BLOCKS, aria_ops.aria_decrypt_16way);
ECB_BLOCK(1, aria_decrypt);
ECB_WALK_END();
}
static int aria_avx2_ecb_encrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct aria_ctx *ctx = crypto_skcipher_ctx(tfm);
return ecb_do_encrypt(req, ctx->enc_key[0]);
}
static int aria_avx2_ecb_decrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct aria_ctx *ctx = crypto_skcipher_ctx(tfm);
return ecb_do_decrypt(req, ctx->dec_key[0]);
}
static int aria_avx2_set_key(struct crypto_skcipher *tfm, const u8 *key,
unsigned int keylen)
{
return aria_set_key(&tfm->base, key, keylen);
}
static int aria_avx2_ctr_encrypt(struct skcipher_request *req)
{
struct aria_avx2_request_ctx *req_ctx = skcipher_request_ctx(req);
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct aria_ctx *ctx = crypto_skcipher_ctx(tfm);
struct skcipher_walk walk;
unsigned int nbytes;
int err;
err = skcipher_walk_virt(&walk, req, false);
while ((nbytes = walk.nbytes) > 0) {
const u8 *src = walk.src.virt.addr;
u8 *dst = walk.dst.virt.addr;
while (nbytes >= ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE) {
kernel_fpu_begin();
aria_ops.aria_ctr_crypt_32way(ctx, dst, src,
&req_ctx->keystream[0],
walk.iv);
kernel_fpu_end();
dst += ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE;
src += ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE;
nbytes -= ARIA_AESNI_AVX2_PARALLEL_BLOCK_SIZE;
}
while (nbytes >= ARIA_AESNI_PARALLEL_BLOCK_SIZE) {
kernel_fpu_begin();
aria_ops.aria_ctr_crypt_16way(ctx, dst, src,
&req_ctx->keystream[0],
walk.iv);
kernel_fpu_end();
dst += ARIA_AESNI_PARALLEL_BLOCK_SIZE;
src += ARIA_AESNI_PARALLEL_BLOCK_SIZE;
nbytes -= ARIA_AESNI_PARALLEL_BLOCK_SIZE;
}
while (nbytes >= ARIA_BLOCK_SIZE) {
memcpy(&req_ctx->keystream[0], walk.iv, ARIA_BLOCK_SIZE);
crypto_inc(walk.iv, ARIA_BLOCK_SIZE);
aria_encrypt(ctx, &req_ctx->keystream[0],
&req_ctx->keystream[0]);
crypto_xor_cpy(dst, src, &req_ctx->keystream[0],
ARIA_BLOCK_SIZE);
dst += ARIA_BLOCK_SIZE;
src += ARIA_BLOCK_SIZE;
nbytes -= ARIA_BLOCK_SIZE;
}
if (walk.nbytes == walk.total && nbytes > 0) {
memcpy(&req_ctx->keystream[0], walk.iv,
ARIA_BLOCK_SIZE);
crypto_inc(walk.iv, ARIA_BLOCK_SIZE);
aria_encrypt(ctx, &req_ctx->keystream[0],
&req_ctx->keystream[0]);
crypto_xor_cpy(dst, src, &req_ctx->keystream[0],
nbytes);
dst += nbytes;
src += nbytes;
nbytes = 0;
}
err = skcipher_walk_done(&walk, nbytes);
}
return err;
}
static int aria_avx2_init_tfm(struct crypto_skcipher *tfm)
{
crypto_skcipher_set_reqsize(tfm, sizeof(struct aria_avx2_request_ctx));
return 0;
}
static struct skcipher_alg aria_algs[] = {
{
.base.cra_name = "__ecb(aria)",
.base.cra_driver_name = "__ecb-aria-avx2",
.base.cra_priority = 500,
.base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = ARIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = ARIA_MIN_KEY_SIZE,
.max_keysize = ARIA_MAX_KEY_SIZE,
.setkey = aria_avx2_set_key,
.encrypt = aria_avx2_ecb_encrypt,
.decrypt = aria_avx2_ecb_decrypt,
}, {
.base.cra_name = "__ctr(aria)",
.base.cra_driver_name = "__ctr-aria-avx2",
.base.cra_priority = 500,
.base.cra_flags = CRYPTO_ALG_INTERNAL |
CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = ARIA_MIN_KEY_SIZE,
.max_keysize = ARIA_MAX_KEY_SIZE,
.ivsize = ARIA_BLOCK_SIZE,
.chunksize = ARIA_BLOCK_SIZE,
.setkey = aria_avx2_set_key,
.encrypt = aria_avx2_ctr_encrypt,
.decrypt = aria_avx2_ctr_encrypt,
.init = aria_avx2_init_tfm,
}
};
static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)];
static int __init aria_avx2_init(void)
{
const char *feature_name;
if (!boot_cpu_has(X86_FEATURE_AVX) ||
!boot_cpu_has(X86_FEATURE_AVX2) ||
!boot_cpu_has(X86_FEATURE_AES) ||
!boot_cpu_has(X86_FEATURE_OSXSAVE)) {
pr_info("AVX2 or AES-NI instructions are not detected.\n");
return -ENODEV;
}
if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM,
&feature_name)) {
pr_info("CPU feature '%s' is not supported.\n", feature_name);
return -ENODEV;
}
if (boot_cpu_has(X86_FEATURE_GFNI)) {
aria_ops.aria_encrypt_16way = aria_aesni_avx_gfni_encrypt_16way;
aria_ops.aria_decrypt_16way = aria_aesni_avx_gfni_decrypt_16way;
aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_gfni_ctr_crypt_16way;
aria_ops.aria_encrypt_32way = aria_aesni_avx2_gfni_encrypt_32way;
aria_ops.aria_decrypt_32way = aria_aesni_avx2_gfni_decrypt_32way;
aria_ops.aria_ctr_crypt_32way = aria_aesni_avx2_gfni_ctr_crypt_32way;
} else {
aria_ops.aria_encrypt_16way = aria_aesni_avx_encrypt_16way;
aria_ops.aria_decrypt_16way = aria_aesni_avx_decrypt_16way;
aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_ctr_crypt_16way;
aria_ops.aria_encrypt_32way = aria_aesni_avx2_encrypt_32way;
aria_ops.aria_decrypt_32way = aria_aesni_avx2_decrypt_32way;
aria_ops.aria_ctr_crypt_32way = aria_aesni_avx2_ctr_crypt_32way;
}
return simd_register_skciphers_compat(aria_algs,
ARRAY_SIZE(aria_algs),
aria_simd_algs);
}
static void __exit aria_avx2_exit(void)
{
simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs),
aria_simd_algs);
}
module_init(aria_avx2_init);
module_exit(aria_avx2_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Taehee Yoo <ap420073@gmail.com>");
MODULE_DESCRIPTION("ARIA Cipher Algorithm, AVX2/AES-NI/GFNI optimized");
MODULE_ALIAS_CRYPTO("aria");
MODULE_ALIAS_CRYPTO("aria-aesni-avx2");
......@@ -18,18 +18,24 @@
asmlinkage void aria_aesni_avx_encrypt_16way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx_encrypt_16way);
asmlinkage void aria_aesni_avx_decrypt_16way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx_decrypt_16way);
asmlinkage void aria_aesni_avx_ctr_crypt_16way(const void *ctx, u8 *dst,
const u8 *src,
u8 *keystream, u8 *iv);
EXPORT_SYMBOL_GPL(aria_aesni_avx_ctr_crypt_16way);
asmlinkage void aria_aesni_avx_gfni_encrypt_16way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_encrypt_16way);
asmlinkage void aria_aesni_avx_gfni_decrypt_16way(const void *ctx, u8 *dst,
const u8 *src);
EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_decrypt_16way);
asmlinkage void aria_aesni_avx_gfni_ctr_crypt_16way(const void *ctx, u8 *dst,
const u8 *src,
u8 *keystream, u8 *iv);
EXPORT_SYMBOL_GPL(aria_aesni_avx_gfni_ctr_crypt_16way);
static struct aria_avx_ops aria_ops;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment