openssl/providers/implementations/ciphers/ciphercommon_hw.c

195 lines
5.3 KiB
C
Raw Normal View History

/*
* Copyright 2019-2020 The OpenSSL Project Authors. All Rights Reserved.
*
* Licensed under the Apache License 2.0 (the "License"). You may not use
* this file except in compliance with the License. You can obtain a copy
* in the file LICENSE in the source distribution or at
* https://www.openssl.org/source/license.html
*/
#include "prov/ciphercommon.h"
/*-
* The generic cipher functions for cipher modes cbc, ecb, ofb, cfb and ctr.
* Used if there is no special hardware implementations.
*/
int ossl_cipher_hw_generic_cbc(PROV_CIPHER_CTX *dat, unsigned char *out,
const unsigned char *in, size_t len)
{
if (dat->stream.cbc)
(*dat->stream.cbc) (in, out, len, dat->ks, dat->iv, dat->enc);
else if (dat->enc)
CRYPTO_cbc128_encrypt(in, out, len, dat->ks, dat->iv, dat->block);
else
CRYPTO_cbc128_decrypt(in, out, len, dat->ks, dat->iv, dat->block);
return 1;
}
int ossl_cipher_hw_generic_ecb(PROV_CIPHER_CTX *dat, unsigned char *out,
const unsigned char *in, size_t len)
{
size_t i, bl = dat->blocksize;
if (len < bl)
return 1;
Optimize AES-ECB mode in OpenSSL for both aarch64 and aarch32 Aes-ecb mode can be optimized by inverleaving cipher operation on several blocks and loop unrolling. Interleaving needs one ideal unrolling factor, here we adopt the same factor with aes-cbc, which is described as below: If blocks number > 5, select 5 blocks as one iteration,every loop, decrease the blocks number by 5. If 3 < left blocks < 5 select 3 blocks as one iteration, every loop, decrease the block number by 3. If left blocks < 3, treat them as tail blocks. Detailed implementation will have a little adjustment for squeezing code space. With this way, for small size such as 16 bytes, the performance is similar as before, but for big size such as 16k bytes, the performance improves a lot, even reaches to 100%, for some arches such as A57, the improvement even exceeds 100%. The following table will list the encryption performance data on aarch64, take a72 and a57 as examples. Performance value takes the unit of cycles per byte, takes the format as comparision of values. List them as below: A72: Before optimization After optimization Improve evp-aes-128-ecb@16 17.26538237 16.82663866 2.61% evp-aes-128-ecb@64 5.50528499 5.222637557 5.41% evp-aes-128-ecb@256 2.632700213 1.908442892 37.95% evp-aes-128-ecb@1024 1.876102047 1.078018868 74.03% evp-aes-128-ecb@8192 1.6550392 0.853982929 93.80% evp-aes-128-ecb@16384 1.636871283 0.847623957 93.11% evp-aes-192-ecb@16 17.73104961 17.09692468 3.71% evp-aes-192-ecb@64 5.78984398 5.418545192 6.85% evp-aes-192-ecb@256 2.872005308 2.081815274 37.96% evp-aes-192-ecb@1024 2.083226672 1.25095642 66.53% evp-aes-192-ecb@8192 1.831992057 0.995916251 83.95% evp-aes-192-ecb@16384 1.821590009 0.993820525 83.29% evp-aes-256-ecb@16 18.0606306 17.96963317 0.51% evp-aes-256-ecb@64 6.19651997 5.762465812 7.53% evp-aes-256-ecb@256 3.176991394 2.24642538 41.42% evp-aes-256-ecb@1024 2.385991919 1.396018192 70.91% evp-aes-256-ecb@8192 2.147862636 1.142222597 88.04% evp-aes-256-ecb@16384 2.131361787 1.135944617 87.63% A57: Before optimization After optimization Improve evp-aes-128-ecb@16 18.61045121 18.36456218 1.34% evp-aes-128-ecb@64 6.438628994 5.467959461 17.75% evp-aes-128-ecb@256 2.957452881 1.97238604 49.94% evp-aes-128-ecb@1024 2.117096219 1.099665054 92.52% evp-aes-128-ecb@8192 1.868385973 0.837440804 123.11% evp-aes-128-ecb@16384 1.853078526 0.822420027 125.32% evp-aes-192-ecb@16 19.07021756 18.50018552 3.08% evp-aes-192-ecb@64 6.672351486 5.696088921 17.14% evp-aes-192-ecb@256 3.260427769 2.131449916 52.97% evp-aes-192-ecb@1024 2.410522832 1.250529718 92.76% evp-aes-192-ecb@8192 2.17921605 0.973225504 123.92% evp-aes-192-ecb@16384 2.162250997 0.95919871 125.42% evp-aes-256-ecb@16 19.3008384 19.12743654 0.91% evp-aes-256-ecb@64 6.992950658 5.92149541 18.09% evp-aes-256-ecb@256 3.576361743 2.287619504 56.34% evp-aes-256-ecb@1024 2.726671027 1.381267599 97.40% evp-aes-256-ecb@8192 2.493583657 1.110959913 124.45% evp-aes-256-ecb@16384 2.473916816 1.099967073 124.91% Change-Id: Iccd23d972e0d52d22dc093f4c208f69c9d5a0ca7 Reviewed-by: Shane Lontis <shane.lontis@oracle.com> Reviewed-by: Richard Levitte <levitte@openssl.org> (Merged from https://github.com/openssl/openssl/pull/10518)
2019-11-07 10:36:45 +08:00
if (dat->stream.ecb) {
(*dat->stream.ecb) (in, out, len, dat->ks, dat->enc);
}
else {
for (i = 0, len -= bl; i <= len; i += bl)
(*dat->block) (in + i, out + i, dat->ks);
}
return 1;
}
int ossl_cipher_hw_generic_ofb128(PROV_CIPHER_CTX *dat, unsigned char *out,
const unsigned char *in, size_t len)
{
int num = dat->num;
CRYPTO_ofb128_encrypt(in, out, len, dat->ks, dat->iv, &num, dat->block);
dat->num = num;
return 1;
}
int ossl_cipher_hw_generic_cfb128(PROV_CIPHER_CTX *dat, unsigned char *out,
const unsigned char *in, size_t len)
{
int num = dat->num;
CRYPTO_cfb128_encrypt(in, out, len, dat->ks, dat->iv, &num, dat->enc,
dat->block);
dat->num = num;
return 1;
}
int ossl_cipher_hw_generic_cfb8(PROV_CIPHER_CTX *dat, unsigned char *out,
const unsigned char *in, size_t len)
{
int num = dat->num;
CRYPTO_cfb128_8_encrypt(in, out, len, dat->ks, dat->iv, &num, dat->enc,
dat->block);
dat->num = num;
return 1;
}
int ossl_cipher_hw_generic_cfb1(PROV_CIPHER_CTX *dat, unsigned char *out,
const unsigned char *in, size_t len)
{
int num = dat->num;
if (dat->use_bits) {
CRYPTO_cfb128_1_encrypt(in, out, len, dat->ks, dat->iv, &num,
dat->enc, dat->block);
dat->num = num;
return 1;
}
while (len >= MAXBITCHUNK) {
CRYPTO_cfb128_1_encrypt(in, out, MAXBITCHUNK * 8, dat->ks,
dat->iv, &num, dat->enc, dat->block);
len -= MAXBITCHUNK;
out += MAXBITCHUNK;
in += MAXBITCHUNK;
}
if (len)
CRYPTO_cfb128_1_encrypt(in, out, len * 8, dat->ks, dat->iv, &num,
dat->enc, dat->block);
dat->num = num;
return 1;
}
int ossl_cipher_hw_generic_ctr(PROV_CIPHER_CTX *dat, unsigned char *out,
const unsigned char *in, size_t len)
{
unsigned int num = dat->num;
if (dat->stream.ctr)
CRYPTO_ctr128_encrypt_ctr32(in, out, len, dat->ks, dat->iv, dat->buf,
&num, dat->stream.ctr);
else
CRYPTO_ctr128_encrypt(in, out, len, dat->ks, dat->iv, dat->buf,
&num, dat->block);
dat->num = num;
return 1;
}
/*-
* The chunked cipher functions for cipher modes cbc, ecb, ofb, cfb and ctr.
* Used if there is no special hardware implementations.
*/
int ossl_cipher_hw_chunked_cbc(PROV_CIPHER_CTX *ctx, unsigned char *out,
const unsigned char *in, size_t inl)
{
while (inl >= MAXCHUNK) {
ossl_cipher_hw_generic_cbc(ctx, out, in, MAXCHUNK);
inl -= MAXCHUNK;
in += MAXCHUNK;
out += MAXCHUNK;
}
if (inl > 0)
ossl_cipher_hw_generic_cbc(ctx, out, in, inl);
return 1;
}
int ossl_cipher_hw_chunked_cfb8(PROV_CIPHER_CTX *ctx, unsigned char *out,
const unsigned char *in, size_t inl)
{
size_t chunk = MAXCHUNK;
if (inl < chunk)
chunk = inl;
while (inl > 0 && inl >= chunk) {
ossl_cipher_hw_generic_cfb8(ctx, out, in, inl);
inl -= chunk;
in += chunk;
out += chunk;
if (inl < chunk)
chunk = inl;
}
return 1;
}
int ossl_cipher_hw_chunked_cfb128(PROV_CIPHER_CTX *ctx, unsigned char *out,
const unsigned char *in, size_t inl)
{
size_t chunk = MAXCHUNK;
if (inl < chunk)
chunk = inl;
while (inl > 0 && inl >= chunk) {
ossl_cipher_hw_generic_cfb128(ctx, out, in, inl);
inl -= chunk;
in += chunk;
out += chunk;
if (inl < chunk)
chunk = inl;
}
return 1;
}
int ossl_cipher_hw_chunked_ofb128(PROV_CIPHER_CTX *ctx, unsigned char *out,
const unsigned char *in, size_t inl)
{
while (inl >= MAXCHUNK) {
ossl_cipher_hw_generic_ofb128(ctx, out, in, MAXCHUNK);
inl -= MAXCHUNK;
in += MAXCHUNK;
out += MAXCHUNK;
}
if (inl > 0)
ossl_cipher_hw_generic_ofb128(ctx, out, in, inl);
return 1;
}