kernel_optimize_test/arch/arm64/crypto/chacha-neon-glue.c
Jason A. Donenfeld 706024a52c crypto: arch/lib - limit simd usage to 4k chunks
The initial Zinc patchset, after some mailing list discussion, contained
code to ensure that kernel_fpu_enable would not be kept on for more than
a 4k chunk, since it disables preemption. The choice of 4k isn't totally
scientific, but it's not a bad guess either, and it's what's used in
both the x86 poly1305, blake2s, and nhpoly1305 code already (in the form
of PAGE_SIZE, which this commit corrects to be explicitly 4k for the
former two).

Ard did some back of the envelope calculations and found that
at 5 cycles/byte (overestimate) on a 1ghz processor (pretty slow), 4k
means we have a maximum preemption disabling of 20us, which Sebastian
confirmed was probably a good limit.

Unfortunately the chunking appears to have been left out of the final
patchset that added the glue code. So, this commit adds it back in.

Fixes: 84e03fa39f ("crypto: x86/chacha - expose SIMD ChaCha routine as library function")
Fixes: b3aad5bad2 ("crypto: arm64/chacha - expose arm64 ChaCha routine as library function")
Fixes: a44a3430d7 ("crypto: arm/chacha - expose ARM ChaCha routine as library function")
Fixes: d7d7b85356 ("crypto: x86/poly1305 - wire up faster implementations for kernel")
Fixes: f569ca1647 ("crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation")
Fixes: a6b803b3dd ("crypto: arm/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation")
Fixes: ed0356eda1 ("crypto: blake2s - x86_64 SIMD implementation")
Cc: Eric Biggers <ebiggers@google.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2020-04-30 15:16:59 +10:00

244 lines
6.6 KiB
C

/*
* ARM NEON and scalar accelerated ChaCha and XChaCha stream ciphers,
* including ChaCha20 (RFC7539)
*
* Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* Based on:
* ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
*
* Copyright (C) 2015 Martin Willi
*
* 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/chacha.h>
#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <linux/jump_label.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <asm/hwcap.h>
#include <asm/neon.h>
#include <asm/simd.h>
asmlinkage void chacha_block_xor_neon(u32 *state, u8 *dst, const u8 *src,
int nrounds);
asmlinkage void chacha_4block_xor_neon(u32 *state, u8 *dst, const u8 *src,
int nrounds, int bytes);
asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
int bytes, int nrounds)
{
while (bytes > 0) {
int l = min(bytes, CHACHA_BLOCK_SIZE * 5);
if (l <= CHACHA_BLOCK_SIZE) {
u8 buf[CHACHA_BLOCK_SIZE];
memcpy(buf, src, l);
chacha_block_xor_neon(state, buf, buf, nrounds);
memcpy(dst, buf, l);
state[12] += 1;
break;
}
chacha_4block_xor_neon(state, dst, src, nrounds, l);
bytes -= l;
src += l;
dst += l;
state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
}
}
void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
{
if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
hchacha_block_generic(state, stream, nrounds);
} else {
kernel_neon_begin();
hchacha_block_neon(state, stream, nrounds);
kernel_neon_end();
}
}
EXPORT_SYMBOL(hchacha_block_arch);
void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
{
chacha_init_generic(state, key, iv);
}
EXPORT_SYMBOL(chacha_init_arch);
void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
int nrounds)
{
if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
!crypto_simd_usable())
return chacha_crypt_generic(state, dst, src, bytes, nrounds);
do {
unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
kernel_neon_begin();
chacha_doneon(state, dst, src, todo, nrounds);
kernel_neon_end();
bytes -= todo;
src += todo;
dst += todo;
} while (bytes);
}
EXPORT_SYMBOL(chacha_crypt_arch);
static int chacha_neon_stream_xor(struct skcipher_request *req,
const struct chacha_ctx *ctx, const u8 *iv)
{
struct skcipher_walk walk;
u32 state[16];
int err;
err = skcipher_walk_virt(&walk, req, false);
chacha_init_generic(state, ctx->key, iv);
while (walk.nbytes > 0) {
unsigned int nbytes = walk.nbytes;
if (nbytes < walk.total)
nbytes = rounddown(nbytes, walk.stride);
if (!static_branch_likely(&have_neon) ||
!crypto_simd_usable()) {
chacha_crypt_generic(state, walk.dst.virt.addr,
walk.src.virt.addr, nbytes,
ctx->nrounds);
} else {
kernel_neon_begin();
chacha_doneon(state, walk.dst.virt.addr,
walk.src.virt.addr, nbytes, ctx->nrounds);
kernel_neon_end();
}
err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
}
return err;
}
static int chacha_neon(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
return chacha_neon_stream_xor(req, ctx, req->iv);
}
static int xchacha_neon(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
struct chacha_ctx subctx;
u32 state[16];
u8 real_iv[16];
chacha_init_generic(state, ctx->key, req->iv);
hchacha_block_arch(state, subctx.key, ctx->nrounds);
subctx.nrounds = ctx->nrounds;
memcpy(&real_iv[0], req->iv + 24, 8);
memcpy(&real_iv[8], req->iv + 16, 8);
return chacha_neon_stream_xor(req, &subctx, real_iv);
}
static struct skcipher_alg algs[] = {
{
.base.cra_name = "chacha20",
.base.cra_driver_name = "chacha20-neon",
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA_KEY_SIZE,
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = CHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
.walksize = 5 * CHACHA_BLOCK_SIZE,
.setkey = chacha20_setkey,
.encrypt = chacha_neon,
.decrypt = chacha_neon,
}, {
.base.cra_name = "xchacha20",
.base.cra_driver_name = "xchacha20-neon",
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA_KEY_SIZE,
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = XCHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
.walksize = 5 * CHACHA_BLOCK_SIZE,
.setkey = chacha20_setkey,
.encrypt = xchacha_neon,
.decrypt = xchacha_neon,
}, {
.base.cra_name = "xchacha12",
.base.cra_driver_name = "xchacha12-neon",
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA_KEY_SIZE,
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = XCHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
.walksize = 5 * CHACHA_BLOCK_SIZE,
.setkey = chacha12_setkey,
.encrypt = xchacha_neon,
.decrypt = xchacha_neon,
}
};
static int __init chacha_simd_mod_init(void)
{
if (!cpu_have_named_feature(ASIMD))
return 0;
static_branch_enable(&have_neon);
return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
}
static void __exit chacha_simd_mod_fini(void)
{
if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && cpu_have_named_feature(ASIMD))
crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
}
module_init(chacha_simd_mod_init);
module_exit(chacha_simd_mod_fini);
MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_CRYPTO("chacha20");
MODULE_ALIAS_CRYPTO("chacha20-neon");
MODULE_ALIAS_CRYPTO("xchacha20");
MODULE_ALIAS_CRYPTO("xchacha20-neon");
MODULE_ALIAS_CRYPTO("xchacha12");
MODULE_ALIAS_CRYPTO("xchacha12-neon");