kernel_optimize_test/crypto/poly1305_generic.c

150 lines
3.7 KiB
C
Raw Normal View History

/*
* Poly1305 authenticator algorithm, RFC7539
*
* Copyright (C) 2015 Martin Willi
*
* Based on public domain code by Andrew Moon and Daniel J. Bernstein.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/poly1305.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <asm/unaligned.h>
static int crypto_poly1305_init(struct shash_desc *desc)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
poly1305_core_init(&dctx->h);
dctx->buflen = 0;
dctx->rset = 0;
dctx->sset = false;
return 0;
}
crypto: poly1305 - add new 32 and 64-bit generic versions These two C implementations from Zinc -- a 32x32 one and a 64x64 one, depending on the platform -- come from Andrew Moon's public domain poly1305-donna portable code, modified for usage in the kernel. The precomputation in the 32-bit version and the use of 64x64 multiplies in the 64-bit version make these perform better than the code it replaces. Moon's code is also very widespread and has received many eyeballs of scrutiny. There's a bit of interference between the x86 implementation, which relies on internal details of the old scalar implementation. In the next commit, the x86 implementation will be replaced with a faster one that doesn't rely on this, so none of this matters much. But for now, to keep this passing the tests, we inline the bits of the old implementation that the x86 implementation relied on. Also, since we now support a slightly larger key space, via the union, some offsets had to be fixed up. Nonce calculation was folded in with the emit function, to take advantage of 64x64 arithmetic. However, Adiantum appeared to rely on no nonce handling in emit, so this path was conditionalized. We also introduced a new struct, poly1305_core_key, to represent the precise amount of space that particular implementation uses. Testing with kbench9000, depending on the CPU, the update function for the 32x32 version has been improved by 4%-7%, and for the 64x64 by 19%-30%. The 32x32 gains are small, but I think there's great value in having a parallel implementation to the 64x64 one so that the two can be compared side-by-side as nice stand-alone units. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2020-01-06 11:40:46 +08:00
static unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
const u8 *src, unsigned int srclen)
{
if (!dctx->sset) {
if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) {
poly1305_core_setkey(&dctx->core_r, src);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->rset = 2;
}
if (srclen >= POLY1305_BLOCK_SIZE) {
dctx->s[0] = get_unaligned_le32(src + 0);
dctx->s[1] = get_unaligned_le32(src + 4);
dctx->s[2] = get_unaligned_le32(src + 8);
dctx->s[3] = get_unaligned_le32(src + 12);
src += POLY1305_BLOCK_SIZE;
srclen -= POLY1305_BLOCK_SIZE;
dctx->sset = true;
}
}
return srclen;
}
static void poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
unsigned int srclen)
{
unsigned int datalen;
if (unlikely(!dctx->sset)) {
datalen = crypto_poly1305_setdesckey(dctx, src, srclen);
src += srclen - datalen;
srclen = datalen;
}
crypto: poly1305 - add new 32 and 64-bit generic versions These two C implementations from Zinc -- a 32x32 one and a 64x64 one, depending on the platform -- come from Andrew Moon's public domain poly1305-donna portable code, modified for usage in the kernel. The precomputation in the 32-bit version and the use of 64x64 multiplies in the 64-bit version make these perform better than the code it replaces. Moon's code is also very widespread and has received many eyeballs of scrutiny. There's a bit of interference between the x86 implementation, which relies on internal details of the old scalar implementation. In the next commit, the x86 implementation will be replaced with a faster one that doesn't rely on this, so none of this matters much. But for now, to keep this passing the tests, we inline the bits of the old implementation that the x86 implementation relied on. Also, since we now support a slightly larger key space, via the union, some offsets had to be fixed up. Nonce calculation was folded in with the emit function, to take advantage of 64x64 arithmetic. However, Adiantum appeared to rely on no nonce handling in emit, so this path was conditionalized. We also introduced a new struct, poly1305_core_key, to represent the precise amount of space that particular implementation uses. Testing with kbench9000, depending on the CPU, the update function for the 32x32 version has been improved by 4%-7%, and for the 64x64 by 19%-30%. The 32x32 gains are small, but I think there's great value in having a parallel implementation to the 64x64 one so that the two can be compared side-by-side as nice stand-alone units. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2020-01-06 11:40:46 +08:00
poly1305_core_blocks(&dctx->h, &dctx->core_r, src,
srclen / POLY1305_BLOCK_SIZE, 1);
}
static int crypto_poly1305_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
unsigned int bytes;
if (unlikely(dctx->buflen)) {
bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
memcpy(dctx->buf + dctx->buflen, src, bytes);
src += bytes;
srclen -= bytes;
dctx->buflen += bytes;
if (dctx->buflen == POLY1305_BLOCK_SIZE) {
poly1305_blocks(dctx, dctx->buf,
POLY1305_BLOCK_SIZE);
dctx->buflen = 0;
}
}
if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
poly1305_blocks(dctx, src, srclen);
src += srclen - (srclen % POLY1305_BLOCK_SIZE);
srclen %= POLY1305_BLOCK_SIZE;
}
if (unlikely(srclen)) {
dctx->buflen = srclen;
memcpy(dctx->buf, src, srclen);
}
return 0;
}
static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
{
struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
if (unlikely(!dctx->sset))
return -ENOKEY;
poly1305_final_generic(dctx, dst);
return 0;
}
static struct shash_alg poly1305_alg = {
.digestsize = POLY1305_DIGEST_SIZE,
.init = crypto_poly1305_init,
.update = crypto_poly1305_update,
.final = crypto_poly1305_final,
.descsize = sizeof(struct poly1305_desc_ctx),
.base = {
.cra_name = "poly1305",
.cra_driver_name = "poly1305-generic",
.cra_priority = 100,
.cra_blocksize = POLY1305_BLOCK_SIZE,
.cra_module = THIS_MODULE,
},
};
static int __init poly1305_mod_init(void)
{
return crypto_register_shash(&poly1305_alg);
}
static void __exit poly1305_mod_exit(void)
{
crypto_unregister_shash(&poly1305_alg);
}
subsys_initcall(poly1305_mod_init);
module_exit(poly1305_mod_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
MODULE_DESCRIPTION("Poly1305 authenticator");
MODULE_ALIAS_CRYPTO("poly1305");
MODULE_ALIAS_CRYPTO("poly1305-generic");