linux/lib/crypto/arm64/chacha-neon-glue.c

120 lines
3.2 KiB
C
Raw Permalink Normal View History

/*
* ChaCha and HChaCha functions (ARM64 optimized)
*
* 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/chacha.h>
#include <crypto/internal/simd.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(const struct chacha_state *state,
u8 *dst, const u8 *src, int nrounds);
asmlinkage void chacha_4block_xor_neon(const struct chacha_state *state,
u8 *dst, const u8 *src,
int nrounds, int bytes);
asmlinkage void hchacha_block_neon(const struct chacha_state *state,
u32 out[HCHACHA_OUT_WORDS], int nrounds);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
static void chacha_doneon(struct chacha_state *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->x[12] += 1;
break;
}
chacha_4block_xor_neon(state, dst, src, nrounds, l);
bytes -= l;
src += l;
dst += l;
state->x[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
}
}
void hchacha_block_arch(const struct chacha_state *state,
u32 out[HCHACHA_OUT_WORDS], int nrounds)
{
if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
hchacha_block_generic(state, out, nrounds);
} else {
kernel_neon_begin();
hchacha_block_neon(state, out, nrounds);
kernel_neon_end();
}
}
EXPORT_SYMBOL(hchacha_block_arch);
void chacha_crypt_arch(struct chacha_state *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);
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: 84e03fa39fbe ("crypto: x86/chacha - expose SIMD ChaCha routine as library function") Fixes: b3aad5bad26a ("crypto: arm64/chacha - expose arm64 ChaCha routine as library function") Fixes: a44a3430d71b ("crypto: arm/chacha - expose ARM ChaCha routine as library function") Fixes: d7d7b8535662 ("crypto: x86/poly1305 - wire up faster implementations for kernel") Fixes: f569ca164751 ("crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") Fixes: a6b803b3ddc7 ("crypto: arm/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") Fixes: ed0356eda153 ("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>
2020-04-22 17:18:53 -06:00
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);
bool chacha_is_arch_optimized(void)
{
return static_key_enabled(&have_neon);
}
EXPORT_SYMBOL(chacha_is_arch_optimized);
static int __init chacha_simd_mod_init(void)
{
if (cpu_have_named_feature(ASIMD))
static_branch_enable(&have_neon);
return 0;
}
subsys_initcall(chacha_simd_mod_init);
static void __exit chacha_simd_mod_exit(void)
{
}
module_exit(chacha_simd_mod_exit);
MODULE_DESCRIPTION("ChaCha and HChaCha functions (ARM64 optimized)");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");