linux/lib/crypto/powerpc/poly1305-p10-glue.c
Eric Biggers 676d45aba8 lib/crypto: powerpc: Move arch/powerpc/lib/crypto/ into lib/crypto/
Move the contents of arch/powerpc/lib/crypto/ into lib/crypto/powerpc/.

The new code organization makes a lot more sense for how this code
actually works and is developed.  In particular, it makes it possible to
build each algorithm as a single module, with better inlining and dead
code elimination.  For a more detailed explanation, see the patchset
which did this for the CRC library code:
https://lore.kernel.org/r/20250607200454.73587-1-ebiggers@kernel.org/.
Also see the patchset which did this for SHA-512:
https://lore.kernel.org/linux-crypto/20250616014019.415791-1-ebiggers@kernel.org/

This is just a preparatory commit, which does the move to get the files
into their new location but keeps them building the same way as before.
Later commits will make the actual improvements to the way the
arch-optimized code is integrated for each algorithm.

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Link: https://lore.kernel.org/r/20250619191908.134235-5-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
2025-06-30 09:26:20 -07:00

96 lines
2.6 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Poly1305 authenticator algorithm, RFC7539.
*
* Copyright 2023- IBM Corp. All rights reserved.
*/
#include <asm/switch_to.h>
#include <crypto/internal/poly1305.h>
#include <linux/cpufeature.h>
#include <linux/jump_label.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/unaligned.h>
asmlinkage void poly1305_p10le_4blocks(struct poly1305_block_state *state, const u8 *m, u32 mlen);
asmlinkage void poly1305_64s(struct poly1305_block_state *state, const u8 *m, u32 mlen, int highbit);
asmlinkage void poly1305_emit_64(const struct poly1305_state *state, const u32 nonce[4], u8 digest[POLY1305_DIGEST_SIZE]);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
static void vsx_begin(void)
{
preempt_disable();
enable_kernel_vsx();
}
static void vsx_end(void)
{
disable_kernel_vsx();
preempt_enable();
}
void poly1305_block_init_arch(struct poly1305_block_state *dctx,
const u8 raw_key[POLY1305_BLOCK_SIZE])
{
if (!static_key_enabled(&have_p10))
return poly1305_block_init_generic(dctx, raw_key);
dctx->h = (struct poly1305_state){};
dctx->core_r.key.r64[0] = get_unaligned_le64(raw_key + 0);
dctx->core_r.key.r64[1] = get_unaligned_le64(raw_key + 8);
}
EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
unsigned int len, u32 padbit)
{
if (!static_key_enabled(&have_p10))
return poly1305_blocks_generic(state, src, len, padbit);
vsx_begin();
if (len >= POLY1305_BLOCK_SIZE * 4) {
poly1305_p10le_4blocks(state, src, len);
src += len - (len % (POLY1305_BLOCK_SIZE * 4));
len %= POLY1305_BLOCK_SIZE * 4;
}
while (len >= POLY1305_BLOCK_SIZE) {
poly1305_64s(state, src, POLY1305_BLOCK_SIZE, padbit);
len -= POLY1305_BLOCK_SIZE;
src += POLY1305_BLOCK_SIZE;
}
vsx_end();
}
EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
void poly1305_emit_arch(const struct poly1305_state *state,
u8 digest[POLY1305_DIGEST_SIZE],
const u32 nonce[4])
{
if (!static_key_enabled(&have_p10))
return poly1305_emit_generic(state, digest, nonce);
poly1305_emit_64(state, nonce, digest);
}
EXPORT_SYMBOL_GPL(poly1305_emit_arch);
bool poly1305_is_arch_optimized(void)
{
return static_key_enabled(&have_p10);
}
EXPORT_SYMBOL(poly1305_is_arch_optimized);
static int __init poly1305_p10_init(void)
{
if (cpu_has_feature(CPU_FTR_ARCH_31))
static_branch_enable(&have_p10);
return 0;
}
subsys_initcall(poly1305_p10_init);
static void __exit poly1305_p10_exit(void)
{
}
module_exit(poly1305_p10_exit);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Danny Tsen <dtsen@linux.ibm.com>");
MODULE_DESCRIPTION("Optimized Poly1305 for P10");