mirror of
https://github.com/torvalds/linux.git
synced 2026-03-08 04:04:43 +01:00
a229d83235
Migrate the x86_64 implementations of NH into lib/crypto/. This makes the nh() function be optimized on x86_64 kernels. Note: this temporarily makes the adiantum template not utilize the x86_64 optimized NH code. This is resolved in a later commit that converts the adiantum template to use nh() instead of "nhpoly1305". Link: https://lore.kernel.org/r/20251211011846.8179-6-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers@kernel.org>
45 lines
1.2 KiB
C
45 lines
1.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* x86_64 accelerated implementation of NH
|
|
*
|
|
* Copyright 2018 Google LLC
|
|
*/
|
|
|
|
#include <asm/fpu/api.h>
|
|
#include <linux/static_call.h>
|
|
|
|
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_sse2);
|
|
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_avx2);
|
|
|
|
asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
|
|
__le64 hash[NH_NUM_PASSES]);
|
|
asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
|
|
__le64 hash[NH_NUM_PASSES]);
|
|
|
|
static bool nh_arch(const u32 *key, const u8 *message, size_t message_len,
|
|
__le64 hash[NH_NUM_PASSES])
|
|
{
|
|
if (message_len >= 64 && static_branch_likely(&have_sse2) &&
|
|
irq_fpu_usable()) {
|
|
kernel_fpu_begin();
|
|
if (static_branch_likely(&have_avx2))
|
|
nh_avx2(key, message, message_len, hash);
|
|
else
|
|
nh_sse2(key, message, message_len, hash);
|
|
kernel_fpu_end();
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
#define nh_mod_init_arch nh_mod_init_arch
|
|
static void nh_mod_init_arch(void)
|
|
{
|
|
if (boot_cpu_has(X86_FEATURE_XMM2)) {
|
|
static_branch_enable(&have_sse2);
|
|
if (boot_cpu_has(X86_FEATURE_AVX2) &&
|
|
cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM,
|
|
NULL))
|
|
static_branch_enable(&have_avx2);
|
|
}
|
|
}
|