mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-08-05 16:54:27 +00:00
e96cb9507f
Consolidate the CPU-based SHA-256 code into a single module, following what I did with SHA-512: - Each arch now provides a header file lib/crypto/$(SRCARCH)/sha256.h, replacing lib/crypto/$(SRCARCH)/sha256.c. The header defines sha256_blocks() and optionally sha256_mod_init_arch(). It is included by lib/crypto/sha256.c, and thus the code gets built into the single libsha256 module, with proper inlining and dead code elimination. - sha256_blocks_generic() is moved from lib/crypto/sha256-generic.c into lib/crypto/sha256.c. It's now a static function marked with __maybe_unused, so the compiler automatically eliminates it in any cases where it's not used. - Whether arch-optimized SHA-256 is buildable is now controlled centrally by lib/crypto/Kconfig instead of by lib/crypto/$(SRCARCH)/Kconfig. The conditions for enabling it remain the same as before, and it remains enabled by default. - Any additional arch-specific translation units for the optimized SHA-256 code (such as assembly files) are now compiled by lib/crypto/Makefile instead of lib/crypto/$(SRCARCH)/Makefile. Acked-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20250630160645.3198-13-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers@kernel.org>
58 lines
1.6 KiB
C
58 lines
1.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
* SHA-256 Secure Hash Algorithm, SPE optimized
|
|
*
|
|
* Based on generic implementation. The assembler module takes care
|
|
* about the SPE registers so it can run from interrupt context.
|
|
*
|
|
* Copyright (c) 2015 Markus Stockhausen <stockhausen@collogia.de>
|
|
*/
|
|
|
|
#include <asm/switch_to.h>
|
|
#include <linux/preempt.h>
|
|
|
|
/*
|
|
* MAX_BYTES defines the number of bytes that are allowed to be processed
|
|
* between preempt_disable() and preempt_enable(). SHA256 takes ~2,000
|
|
* operations per 64 bytes. e500 cores can issue two arithmetic instructions
|
|
* per clock cycle using one 32/64 bit unit (SU1) and one 32 bit unit (SU2).
|
|
* Thus 1KB of input data will need an estimated maximum of 18,000 cycles.
|
|
* Headroom for cache misses included. Even with the low end model clocked
|
|
* at 667 MHz this equals to a critical time window of less than 27us.
|
|
*
|
|
*/
|
|
#define MAX_BYTES 1024
|
|
|
|
extern void ppc_spe_sha256_transform(struct sha256_block_state *state,
|
|
const u8 *src, u32 blocks);
|
|
|
|
static void spe_begin(void)
|
|
{
|
|
/* We just start SPE operations and will save SPE registers later. */
|
|
preempt_disable();
|
|
enable_kernel_spe();
|
|
}
|
|
|
|
static void spe_end(void)
|
|
{
|
|
disable_kernel_spe();
|
|
/* reenable preemption */
|
|
preempt_enable();
|
|
}
|
|
|
|
static void sha256_blocks(struct sha256_block_state *state,
|
|
const u8 *data, size_t nblocks)
|
|
{
|
|
do {
|
|
/* cut input data into smaller blocks */
|
|
u32 unit = min_t(size_t, nblocks,
|
|
MAX_BYTES / SHA256_BLOCK_SIZE);
|
|
|
|
spe_begin();
|
|
ppc_spe_sha256_transform(state, data, unit);
|
|
spe_end();
|
|
|
|
data += unit * SHA256_BLOCK_SIZE;
|
|
nblocks -= unit;
|
|
} while (nblocks);
|
|
}
|