linux/arch/x86/crypto/sha1_ssse3_glue.c
Roxana Nicolescu 1c43c0f1f8 crypto: x86/sha - load modules based on CPU features
x86 optimized crypto modules are built as modules rather than build-in and
they are not loaded when the crypto API is initialized, resulting in the
generic builtin module (sha1-generic) being used instead.

It was discovered when creating a sha1/sha256 checksum of a 2Gb file by
using kcapi-tools because it would take significantly longer than creating
a sha512 checksum of the same file. trace-cmd showed that for sha1/256 the
generic module was used, whereas for sha512 the optimized module was used
instead.

Add module aliases() for these x86 optimized crypto modules based on CPU
feature bits so udev gets a chance to load them later in the boot
process. This resulted in ~3x decrease in the real-time execution of
kcapi-dsg.

Fix is inspired from commit
aa031b8f70 ("crypto: x86/sha512 - load based on CPU features")
where a similar fix was done for sha512.

Cc: stable@vger.kernel.org # 5.15+
Suggested-by: Dimitri John Ledkov <dimitri.ledkov@canonical.com>
Suggested-by: Julian Andres Klode <julian.klode@canonical.com>
Signed-off-by: Roxana Nicolescu <roxana.nicolescu@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2023-09-20 13:15:54 +08:00

363 lines
8.5 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Cryptographic API.
*
* Glue code for the SHA1 Secure Hash Algorithm assembler implementation using
* Supplemental SSE3 instructions.
*
* This file is based on sha1_generic.c
*
* Copyright (c) Alan Smithee.
* Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
* Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
* Copyright (c) Mathias Krause <minipli@googlemail.com>
* Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/types.h>
#include <crypto/sha1.h>
#include <crypto/sha1_base.h>
#include <asm/cpu_device_id.h>
#include <asm/simd.h>
static const struct x86_cpu_id module_cpu_ids[] = {
X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
{}
};
MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
static int sha1_update(struct shash_desc *desc, const u8 *data,
unsigned int len, sha1_block_fn *sha1_xform)
{
struct sha1_state *sctx = shash_desc_ctx(desc);
if (!crypto_simd_usable() ||
(sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
return crypto_sha1_update(desc, data, len);
/*
* Make sure struct sha1_state begins directly with the SHA1
* 160-bit internal state, as this is what the asm functions expect.
*/
BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0);
kernel_fpu_begin();
sha1_base_do_update(desc, data, len, sha1_xform);
kernel_fpu_end();
return 0;
}
static int sha1_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out, sha1_block_fn *sha1_xform)
{
if (!crypto_simd_usable())
return crypto_sha1_finup(desc, data, len, out);
kernel_fpu_begin();
if (len)
sha1_base_do_update(desc, data, len, sha1_xform);
sha1_base_do_finalize(desc, sha1_xform);
kernel_fpu_end();
return sha1_base_finish(desc, out);
}
asmlinkage void sha1_transform_ssse3(struct sha1_state *state,
const u8 *data, int blocks);
static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha1_update(desc, data, len, sha1_transform_ssse3);
}
static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha1_finup(desc, data, len, out, sha1_transform_ssse3);
}
/* Add padding and return the message digest. */
static int sha1_ssse3_final(struct shash_desc *desc, u8 *out)
{
return sha1_ssse3_finup(desc, NULL, 0, out);
}
static struct shash_alg sha1_ssse3_alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_base_init,
.update = sha1_ssse3_update,
.final = sha1_ssse3_final,
.finup = sha1_ssse3_finup,
.descsize = sizeof(struct sha1_state),
.base = {
.cra_name = "sha1",
.cra_driver_name = "sha1-ssse3",
.cra_priority = 150,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
};
static int register_sha1_ssse3(void)
{
if (boot_cpu_has(X86_FEATURE_SSSE3))
return crypto_register_shash(&sha1_ssse3_alg);
return 0;
}
static void unregister_sha1_ssse3(void)
{
if (boot_cpu_has(X86_FEATURE_SSSE3))
crypto_unregister_shash(&sha1_ssse3_alg);
}
asmlinkage void sha1_transform_avx(struct sha1_state *state,
const u8 *data, int blocks);
static int sha1_avx_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha1_update(desc, data, len, sha1_transform_avx);
}
static int sha1_avx_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha1_finup(desc, data, len, out, sha1_transform_avx);
}
static int sha1_avx_final(struct shash_desc *desc, u8 *out)
{
return sha1_avx_finup(desc, NULL, 0, out);
}
static struct shash_alg sha1_avx_alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_base_init,
.update = sha1_avx_update,
.final = sha1_avx_final,
.finup = sha1_avx_finup,
.descsize = sizeof(struct sha1_state),
.base = {
.cra_name = "sha1",
.cra_driver_name = "sha1-avx",
.cra_priority = 160,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
};
static bool avx_usable(void)
{
if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
if (boot_cpu_has(X86_FEATURE_AVX))
pr_info("AVX detected but unusable.\n");
return false;
}
return true;
}
static int register_sha1_avx(void)
{
if (avx_usable())
return crypto_register_shash(&sha1_avx_alg);
return 0;
}
static void unregister_sha1_avx(void)
{
if (avx_usable())
crypto_unregister_shash(&sha1_avx_alg);
}
#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */
asmlinkage void sha1_transform_avx2(struct sha1_state *state,
const u8 *data, int blocks);
static bool avx2_usable(void)
{
if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
&& boot_cpu_has(X86_FEATURE_BMI1)
&& boot_cpu_has(X86_FEATURE_BMI2))
return true;
return false;
}
static void sha1_apply_transform_avx2(struct sha1_state *state,
const u8 *data, int blocks)
{
/* Select the optimal transform based on data block size */
if (blocks >= SHA1_AVX2_BLOCK_OPTSIZE)
sha1_transform_avx2(state, data, blocks);
else
sha1_transform_avx(state, data, blocks);
}
static int sha1_avx2_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha1_update(desc, data, len, sha1_apply_transform_avx2);
}
static int sha1_avx2_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha1_finup(desc, data, len, out, sha1_apply_transform_avx2);
}
static int sha1_avx2_final(struct shash_desc *desc, u8 *out)
{
return sha1_avx2_finup(desc, NULL, 0, out);
}
static struct shash_alg sha1_avx2_alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_base_init,
.update = sha1_avx2_update,
.final = sha1_avx2_final,
.finup = sha1_avx2_finup,
.descsize = sizeof(struct sha1_state),
.base = {
.cra_name = "sha1",
.cra_driver_name = "sha1-avx2",
.cra_priority = 170,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
};
static int register_sha1_avx2(void)
{
if (avx2_usable())
return crypto_register_shash(&sha1_avx2_alg);
return 0;
}
static void unregister_sha1_avx2(void)
{
if (avx2_usable())
crypto_unregister_shash(&sha1_avx2_alg);
}
#ifdef CONFIG_AS_SHA1_NI
asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data,
int rounds);
static int sha1_ni_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
return sha1_update(desc, data, len, sha1_ni_transform);
}
static int sha1_ni_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
return sha1_finup(desc, data, len, out, sha1_ni_transform);
}
static int sha1_ni_final(struct shash_desc *desc, u8 *out)
{
return sha1_ni_finup(desc, NULL, 0, out);
}
static struct shash_alg sha1_ni_alg = {
.digestsize = SHA1_DIGEST_SIZE,
.init = sha1_base_init,
.update = sha1_ni_update,
.final = sha1_ni_final,
.finup = sha1_ni_finup,
.descsize = sizeof(struct sha1_state),
.base = {
.cra_name = "sha1",
.cra_driver_name = "sha1-ni",
.cra_priority = 250,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
};
static int register_sha1_ni(void)
{
if (boot_cpu_has(X86_FEATURE_SHA_NI))
return crypto_register_shash(&sha1_ni_alg);
return 0;
}
static void unregister_sha1_ni(void)
{
if (boot_cpu_has(X86_FEATURE_SHA_NI))
crypto_unregister_shash(&sha1_ni_alg);
}
#else
static inline int register_sha1_ni(void) { return 0; }
static inline void unregister_sha1_ni(void) { }
#endif
static int __init sha1_ssse3_mod_init(void)
{
if (!x86_match_cpu(module_cpu_ids))
return -ENODEV;
if (register_sha1_ssse3())
goto fail;
if (register_sha1_avx()) {
unregister_sha1_ssse3();
goto fail;
}
if (register_sha1_avx2()) {
unregister_sha1_avx();
unregister_sha1_ssse3();
goto fail;
}
if (register_sha1_ni()) {
unregister_sha1_avx2();
unregister_sha1_avx();
unregister_sha1_ssse3();
goto fail;
}
return 0;
fail:
return -ENODEV;
}
static void __exit sha1_ssse3_mod_fini(void)
{
unregister_sha1_ni();
unregister_sha1_avx2();
unregister_sha1_avx();
unregister_sha1_ssse3();
}
module_init(sha1_ssse3_mod_init);
module_exit(sha1_ssse3_mod_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
MODULE_ALIAS_CRYPTO("sha1");
MODULE_ALIAS_CRYPTO("sha1-ssse3");
MODULE_ALIAS_CRYPTO("sha1-avx");
MODULE_ALIAS_CRYPTO("sha1-avx2");
#ifdef CONFIG_AS_SHA1_NI
MODULE_ALIAS_CRYPTO("sha1-ni");
#endif