mirror of
https://github.com/torvalds/linux.git
synced 2025-08-15 14:11:42 +02:00
ef93f15628
This reverts commit c4741b2305.
Crypto API self-tests no longer run at registration time and now
occur either at late_initcall or upon the first use.
Therefore the premise of the above commit no longer exists. Revert
it and subsequent additions of subsys_initcall and arch_initcall.
Note that lib/crypto calls will stay at subsys_initcall (or rather
downgraded from arch_initcall) because they may need to occur
before Crypto API registration.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
134 lines
3.4 KiB
C
134 lines
3.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* ChaCha and HChaCha functions (ARM optimized)
|
|
*
|
|
* Copyright (C) 2016-2019 Linaro, Ltd. <ard.biesheuvel@linaro.org>
|
|
* Copyright (C) 2015 Martin Willi
|
|
*/
|
|
|
|
#include <crypto/chacha.h>
|
|
#include <crypto/internal/simd.h>
|
|
#include <linux/jump_label.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
|
|
#include <asm/cputype.h>
|
|
#include <asm/hwcap.h>
|
|
#include <asm/neon.h>
|
|
#include <asm/simd.h>
|
|
|
|
asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
|
|
int nrounds);
|
|
asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src,
|
|
int nrounds, unsigned int nbytes);
|
|
asmlinkage void hchacha_block_arm(const u32 *state, u32 *out, int nrounds);
|
|
asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
|
|
|
|
asmlinkage void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
|
|
const u32 *state, int nrounds);
|
|
|
|
static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_neon);
|
|
|
|
static inline bool neon_usable(void)
|
|
{
|
|
return static_branch_likely(&use_neon) && crypto_simd_usable();
|
|
}
|
|
|
|
static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
|
|
unsigned int bytes, int nrounds)
|
|
{
|
|
u8 buf[CHACHA_BLOCK_SIZE];
|
|
|
|
while (bytes > CHACHA_BLOCK_SIZE) {
|
|
unsigned int l = min(bytes, CHACHA_BLOCK_SIZE * 4U);
|
|
|
|
chacha_4block_xor_neon(state, dst, src, nrounds, l);
|
|
bytes -= l;
|
|
src += l;
|
|
dst += l;
|
|
state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
|
|
}
|
|
if (bytes) {
|
|
const u8 *s = src;
|
|
u8 *d = dst;
|
|
|
|
if (bytes != CHACHA_BLOCK_SIZE)
|
|
s = d = memcpy(buf, src, bytes);
|
|
chacha_block_xor_neon(state, d, s, nrounds);
|
|
if (d != dst)
|
|
memcpy(dst, buf, bytes);
|
|
state[12]++;
|
|
}
|
|
}
|
|
|
|
void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
|
|
{
|
|
if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable()) {
|
|
hchacha_block_arm(state, stream, nrounds);
|
|
} else {
|
|
kernel_neon_begin();
|
|
hchacha_block_neon(state, stream, nrounds);
|
|
kernel_neon_end();
|
|
}
|
|
}
|
|
EXPORT_SYMBOL(hchacha_block_arch);
|
|
|
|
void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
|
|
int nrounds)
|
|
{
|
|
if (!IS_ENABLED(CONFIG_KERNEL_MODE_NEON) || !neon_usable() ||
|
|
bytes <= CHACHA_BLOCK_SIZE) {
|
|
chacha_doarm(dst, src, bytes, state, nrounds);
|
|
state[12] += DIV_ROUND_UP(bytes, CHACHA_BLOCK_SIZE);
|
|
return;
|
|
}
|
|
|
|
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)
|
|
{
|
|
/* We always can use at least the ARM scalar implementation. */
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL(chacha_is_arch_optimized);
|
|
|
|
static int __init chacha_arm_mod_init(void)
|
|
{
|
|
if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_NEON)) {
|
|
switch (read_cpuid_part()) {
|
|
case ARM_CPU_PART_CORTEX_A7:
|
|
case ARM_CPU_PART_CORTEX_A5:
|
|
/*
|
|
* The Cortex-A7 and Cortex-A5 do not perform well with
|
|
* the NEON implementation but do incredibly with the
|
|
* scalar one and use less power.
|
|
*/
|
|
break;
|
|
default:
|
|
static_branch_enable(&use_neon);
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
subsys_initcall(chacha_arm_mod_init);
|
|
|
|
static void __exit chacha_arm_mod_exit(void)
|
|
{
|
|
}
|
|
module_exit(chacha_arm_mod_exit);
|
|
|
|
MODULE_DESCRIPTION("ChaCha and HChaCha functions (ARM optimized)");
|
|
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
|
|
MODULE_LICENSE("GPL v2");
|