mirror of
https://github.com/torvalds/linux.git
synced 2026-03-08 01:04:41 +01:00
lib/crypto: x86/polyval: Migrate optimized code into library
Migrate the x86_64 implementation of POLYVAL into lib/crypto/, wiring it up to the POLYVAL library interface. This makes the POLYVAL library be properly optimized on x86_64. This drops the x86_64 optimizations of polyval in the crypto_shash API. That's fine, since polyval will be removed from crypto_shash entirely since it is unneeded there. But even if it comes back, the crypto_shash API could just be implemented on top of the library API, as usual. Adjust the names and prototypes of the assembly functions to align more closely with the rest of the library code. Also replace a movaps instruction with movups to remove the assumption that the key struct is 16-byte aligned. Users can still align the key if they want (and at least in this case, movups is just as fast as movaps), but it's inconvenient to require it. Reviewed-by: Ard Biesheuvel <ardb@kernel.org> Link: https://lore.kernel.org/r/20251109234726.638437-6-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers@kernel.org>
This commit is contained in:
Eric Biggers
parent
37919e239e
commit
4d8da35579
8 changed files with 107 additions and 214 deletions
|
|
@ -353,16 +353,6 @@ config CRYPTO_NHPOLY1305_AVX2
|
|||
Architecture: x86_64 using:
|
||||
- AVX2 (Advanced Vector Extensions 2)
|
||||
|
||||
config CRYPTO_POLYVAL_CLMUL_NI
|
||||
tristate "Hash functions: POLYVAL (CLMUL-NI)"
|
||||
depends on 64BIT
|
||||
select CRYPTO_POLYVAL
|
||||
help
|
||||
POLYVAL hash function for HCTR2
|
||||
|
||||
Architecture: x86_64 using:
|
||||
- CLMUL-NI (carry-less multiplication new instructions)
|
||||
|
||||
config CRYPTO_SM3_AVX_X86_64
|
||||
tristate "Hash functions: SM3 (AVX)"
|
||||
depends on 64BIT
|
||||
|
|
|
|||
|
|
@ -52,9 +52,6 @@ aesni-intel-$(CONFIG_64BIT) += aes-ctr-avx-x86_64.o \
|
|||
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
|
||||
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
|
||||
|
||||
obj-$(CONFIG_CRYPTO_POLYVAL_CLMUL_NI) += polyval-clmulni.o
|
||||
polyval-clmulni-y := polyval-clmulni_asm.o polyval-clmulni_glue.o
|
||||
|
||||
obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
|
||||
nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
|
||||
obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
|
||||
|
|
|
|||
|
|
@ -1,180 +0,0 @@
|
|||
// SPDX-License-Identifier: GPL-2.0-only
|
||||
/*
|
||||
* Glue code for POLYVAL using PCMULQDQ-NI
|
||||
*
|
||||
* Copyright (c) 2007 Nokia Siemens Networks - Mikko Herranen <mh1@iki.fi>
|
||||
* Copyright (c) 2009 Intel Corp.
|
||||
* Author: Huang Ying <ying.huang@intel.com>
|
||||
* Copyright 2021 Google LLC
|
||||
*/
|
||||
|
||||
/*
|
||||
* Glue code based on ghash-clmulni-intel_glue.c.
|
||||
*
|
||||
* This implementation of POLYVAL uses montgomery multiplication
|
||||
* accelerated by PCLMULQDQ-NI to implement the finite field
|
||||
* operations.
|
||||
*/
|
||||
|
||||
#include <asm/cpu_device_id.h>
|
||||
#include <asm/fpu/api.h>
|
||||
#include <crypto/internal/hash.h>
|
||||
#include <crypto/polyval.h>
|
||||
#include <crypto/utils.h>
|
||||
#include <linux/errno.h>
|
||||
#include <linux/kernel.h>
|
||||
#include <linux/module.h>
|
||||
#include <linux/string.h>
|
||||
|
||||
#define POLYVAL_ALIGN 16
|
||||
#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
|
||||
#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
|
||||
#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA)
|
||||
#define NUM_KEY_POWERS 8
|
||||
|
||||
struct polyval_tfm_ctx {
|
||||
/*
|
||||
* These powers must be in the order h^8, ..., h^1.
|
||||
*/
|
||||
u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR;
|
||||
};
|
||||
|
||||
struct polyval_desc_ctx {
|
||||
u8 buffer[POLYVAL_BLOCK_SIZE];
|
||||
};
|
||||
|
||||
asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
|
||||
const u8 *in, size_t nblocks, u8 *accumulator);
|
||||
asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2);
|
||||
|
||||
static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
|
||||
{
|
||||
return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN);
|
||||
}
|
||||
|
||||
static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
|
||||
const u8 *in, size_t nblocks, u8 *accumulator)
|
||||
{
|
||||
kernel_fpu_begin();
|
||||
clmul_polyval_update(keys, in, nblocks, accumulator);
|
||||
kernel_fpu_end();
|
||||
}
|
||||
|
||||
static void internal_polyval_mul(u8 *op1, const u8 *op2)
|
||||
{
|
||||
kernel_fpu_begin();
|
||||
clmul_polyval_mul(op1, op2);
|
||||
kernel_fpu_end();
|
||||
}
|
||||
|
||||
static int polyval_x86_setkey(struct crypto_shash *tfm,
|
||||
const u8 *key, unsigned int keylen)
|
||||
{
|
||||
struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(tfm);
|
||||
int i;
|
||||
|
||||
if (keylen != POLYVAL_BLOCK_SIZE)
|
||||
return -EINVAL;
|
||||
|
||||
memcpy(tctx->key_powers[NUM_KEY_POWERS-1], key, POLYVAL_BLOCK_SIZE);
|
||||
|
||||
for (i = NUM_KEY_POWERS-2; i >= 0; i--) {
|
||||
memcpy(tctx->key_powers[i], key, POLYVAL_BLOCK_SIZE);
|
||||
internal_polyval_mul(tctx->key_powers[i],
|
||||
tctx->key_powers[i+1]);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int polyval_x86_init(struct shash_desc *desc)
|
||||
{
|
||||
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
|
||||
|
||||
memset(dctx, 0, sizeof(*dctx));
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int polyval_x86_update(struct shash_desc *desc,
|
||||
const u8 *src, unsigned int srclen)
|
||||
{
|
||||
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
|
||||
const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
|
||||
unsigned int nblocks;
|
||||
|
||||
do {
|
||||
/* Allow rescheduling every 4K bytes. */
|
||||
nblocks = min(srclen, 4096U) / POLYVAL_BLOCK_SIZE;
|
||||
internal_polyval_update(tctx, src, nblocks, dctx->buffer);
|
||||
srclen -= nblocks * POLYVAL_BLOCK_SIZE;
|
||||
src += nblocks * POLYVAL_BLOCK_SIZE;
|
||||
} while (srclen >= POLYVAL_BLOCK_SIZE);
|
||||
|
||||
return srclen;
|
||||
}
|
||||
|
||||
static int polyval_x86_finup(struct shash_desc *desc, const u8 *src,
|
||||
unsigned int len, u8 *dst)
|
||||
{
|
||||
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
|
||||
const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
|
||||
|
||||
if (len) {
|
||||
crypto_xor(dctx->buffer, src, len);
|
||||
internal_polyval_mul(dctx->buffer,
|
||||
tctx->key_powers[NUM_KEY_POWERS-1]);
|
||||
}
|
||||
|
||||
memcpy(dst, dctx->buffer, POLYVAL_BLOCK_SIZE);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static struct shash_alg polyval_alg = {
|
||||
.digestsize = POLYVAL_DIGEST_SIZE,
|
||||
.init = polyval_x86_init,
|
||||
.update = polyval_x86_update,
|
||||
.finup = polyval_x86_finup,
|
||||
.setkey = polyval_x86_setkey,
|
||||
.descsize = sizeof(struct polyval_desc_ctx),
|
||||
.base = {
|
||||
.cra_name = "polyval",
|
||||
.cra_driver_name = "polyval-clmulni",
|
||||
.cra_priority = 200,
|
||||
.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
|
||||
.cra_blocksize = POLYVAL_BLOCK_SIZE,
|
||||
.cra_ctxsize = POLYVAL_CTX_SIZE,
|
||||
.cra_module = THIS_MODULE,
|
||||
},
|
||||
};
|
||||
|
||||
__maybe_unused static const struct x86_cpu_id pcmul_cpu_id[] = {
|
||||
X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL),
|
||||
{}
|
||||
};
|
||||
MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id);
|
||||
|
||||
static int __init polyval_clmulni_mod_init(void)
|
||||
{
|
||||
if (!x86_match_cpu(pcmul_cpu_id))
|
||||
return -ENODEV;
|
||||
|
||||
if (!boot_cpu_has(X86_FEATURE_AVX))
|
||||
return -ENODEV;
|
||||
|
||||
return crypto_register_shash(&polyval_alg);
|
||||
}
|
||||
|
||||
static void __exit polyval_clmulni_mod_exit(void)
|
||||
{
|
||||
crypto_unregister_shash(&polyval_alg);
|
||||
}
|
||||
|
||||
module_init(polyval_clmulni_mod_init);
|
||||
module_exit(polyval_clmulni_mod_exit);
|
||||
|
||||
MODULE_LICENSE("GPL");
|
||||
MODULE_DESCRIPTION("POLYVAL hash function accelerated by PCLMULQDQ-NI");
|
||||
MODULE_ALIAS_CRYPTO("polyval");
|
||||
MODULE_ALIAS_CRYPTO("polyval-clmulni");
|
||||
|
|
@ -48,6 +48,9 @@ struct polyval_key {
|
|||
#ifdef CONFIG_ARM64
|
||||
/** @h_powers: Powers of the hash key H^8 through H^1 */
|
||||
struct polyval_elem h_powers[8];
|
||||
#elif defined(CONFIG_X86)
|
||||
/** @h_powers: Powers of the hash key H^8 through H^1 */
|
||||
struct polyval_elem h_powers[8];
|
||||
#else
|
||||
#error "Unhandled arch"
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -145,6 +145,7 @@ config CRYPTO_LIB_POLYVAL_ARCH
|
|||
bool
|
||||
depends on CRYPTO_LIB_POLYVAL && !UML
|
||||
default y if ARM64 && KERNEL_MODE_NEON
|
||||
default y if X86_64
|
||||
|
||||
config CRYPTO_LIB_CHACHA20POLY1305
|
||||
tristate
|
||||
|
|
|
|||
|
|
@ -203,6 +203,7 @@ libpolyval-y := polyval.o
|
|||
ifeq ($(CONFIG_CRYPTO_LIB_POLYVAL_ARCH),y)
|
||||
CFLAGS_polyval.o += -I$(src)/$(SRCARCH)
|
||||
libpolyval-$(CONFIG_ARM64) += arm64/polyval-ce-core.o
|
||||
libpolyval-$(CONFIG_X86) += x86/polyval-pclmul-avx.o
|
||||
endif
|
||||
|
||||
################################################################################
|
||||
|
|
|
|||
|
|
@ -36,10 +36,10 @@
|
|||
#define MI %xmm14
|
||||
#define SUM %xmm15
|
||||
|
||||
#define KEY_POWERS %rdi
|
||||
#define MSG %rsi
|
||||
#define BLOCKS_LEFT %rdx
|
||||
#define ACCUMULATOR %rcx
|
||||
#define ACCUMULATOR %rdi
|
||||
#define KEY_POWERS %rsi
|
||||
#define MSG %rdx
|
||||
#define BLOCKS_LEFT %rcx
|
||||
#define TMP %rax
|
||||
|
||||
.section .rodata.cst16.gstar, "aM", @progbits, 16
|
||||
|
|
@ -234,7 +234,7 @@
|
|||
|
||||
movups (MSG), %xmm0
|
||||
pxor SUM, %xmm0
|
||||
movaps (KEY_POWERS), %xmm1
|
||||
movups (KEY_POWERS), %xmm1
|
||||
schoolbook1_noload
|
||||
dec BLOCKS_LEFT
|
||||
addq $16, MSG
|
||||
|
|
@ -261,15 +261,12 @@
|
|||
.endm
|
||||
|
||||
/*
|
||||
* Perform montgomery multiplication in GF(2^128) and store result in op1.
|
||||
* Computes a = a * b * x^{-128} mod x^128 + x^127 + x^126 + x^121 + 1.
|
||||
*
|
||||
* Computes op1*op2*x^{-128} mod x^128 + x^127 + x^126 + x^121 + 1
|
||||
* If op1, op2 are in montgomery form, this computes the montgomery
|
||||
* form of op1*op2.
|
||||
*
|
||||
* void clmul_polyval_mul(u8 *op1, const u8 *op2);
|
||||
* void polyval_mul_pclmul_avx(struct polyval_elem *a,
|
||||
* const struct polyval_elem *b);
|
||||
*/
|
||||
SYM_FUNC_START(clmul_polyval_mul)
|
||||
SYM_FUNC_START(polyval_mul_pclmul_avx)
|
||||
FRAME_BEGIN
|
||||
vmovdqa .Lgstar(%rip), GSTAR
|
||||
movups (%rdi), %xmm0
|
||||
|
|
@ -280,22 +277,23 @@ SYM_FUNC_START(clmul_polyval_mul)
|
|||
movups SUM, (%rdi)
|
||||
FRAME_END
|
||||
RET
|
||||
SYM_FUNC_END(clmul_polyval_mul)
|
||||
SYM_FUNC_END(polyval_mul_pclmul_avx)
|
||||
|
||||
/*
|
||||
* Perform polynomial evaluation as specified by POLYVAL. This computes:
|
||||
* h^n * accumulator + h^n * m_0 + ... + h^1 * m_{n-1}
|
||||
* where n=nblocks, h is the hash key, and m_i are the message blocks.
|
||||
*
|
||||
* rdi - pointer to precomputed key powers h^8 ... h^1
|
||||
* rsi - pointer to message blocks
|
||||
* rdx - number of blocks to hash
|
||||
* rcx - pointer to the accumulator
|
||||
* rdi - pointer to the accumulator
|
||||
* rsi - pointer to precomputed key powers h^8 ... h^1
|
||||
* rdx - pointer to message blocks
|
||||
* rcx - number of blocks to hash
|
||||
*
|
||||
* void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
|
||||
* const u8 *in, size_t nblocks, u8 *accumulator);
|
||||
* void polyval_blocks_pclmul_avx(struct polyval_elem *acc,
|
||||
* const struct polyval_key *key,
|
||||
* const u8 *data, size_t nblocks);
|
||||
*/
|
||||
SYM_FUNC_START(clmul_polyval_update)
|
||||
SYM_FUNC_START(polyval_blocks_pclmul_avx)
|
||||
FRAME_BEGIN
|
||||
vmovdqa .Lgstar(%rip), GSTAR
|
||||
movups (ACCUMULATOR), SUM
|
||||
|
|
@ -318,4 +316,4 @@ SYM_FUNC_START(clmul_polyval_update)
|
|||
movups SUM, (ACCUMULATOR)
|
||||
FRAME_END
|
||||
RET
|
||||
SYM_FUNC_END(clmul_polyval_update)
|
||||
SYM_FUNC_END(polyval_blocks_pclmul_avx)
|
||||
83
lib/crypto/x86/polyval.h
Normal file
83
lib/crypto/x86/polyval.h
Normal file
|
|
@ -0,0 +1,83 @@
|
|||
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
||||
/*
|
||||
* POLYVAL library functions, x86_64 optimized
|
||||
*
|
||||
* Copyright 2025 Google LLC
|
||||
*/
|
||||
#include <asm/fpu/api.h>
|
||||
#include <linux/cpufeature.h>
|
||||
|
||||
#define NUM_H_POWERS 8
|
||||
|
||||
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pclmul_avx);
|
||||
|
||||
asmlinkage void polyval_mul_pclmul_avx(struct polyval_elem *a,
|
||||
const struct polyval_elem *b);
|
||||
asmlinkage void polyval_blocks_pclmul_avx(struct polyval_elem *acc,
|
||||
const struct polyval_key *key,
|
||||
const u8 *data, size_t nblocks);
|
||||
|
||||
static void polyval_preparekey_arch(struct polyval_key *key,
|
||||
const u8 raw_key[POLYVAL_BLOCK_SIZE])
|
||||
{
|
||||
static_assert(ARRAY_SIZE(key->h_powers) == NUM_H_POWERS);
|
||||
memcpy(&key->h_powers[NUM_H_POWERS - 1], raw_key, POLYVAL_BLOCK_SIZE);
|
||||
if (static_branch_likely(&have_pclmul_avx) && irq_fpu_usable()) {
|
||||
kernel_fpu_begin();
|
||||
for (int i = NUM_H_POWERS - 2; i >= 0; i--) {
|
||||
key->h_powers[i] = key->h_powers[i + 1];
|
||||
polyval_mul_pclmul_avx(
|
||||
&key->h_powers[i],
|
||||
&key->h_powers[NUM_H_POWERS - 1]);
|
||||
}
|
||||
kernel_fpu_end();
|
||||
} else {
|
||||
for (int i = NUM_H_POWERS - 2; i >= 0; i--) {
|
||||
key->h_powers[i] = key->h_powers[i + 1];
|
||||
polyval_mul_generic(&key->h_powers[i],
|
||||
&key->h_powers[NUM_H_POWERS - 1]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static void polyval_mul_arch(struct polyval_elem *acc,
|
||||
const struct polyval_key *key)
|
||||
{
|
||||
if (static_branch_likely(&have_pclmul_avx) && irq_fpu_usable()) {
|
||||
kernel_fpu_begin();
|
||||
polyval_mul_pclmul_avx(acc, &key->h_powers[NUM_H_POWERS - 1]);
|
||||
kernel_fpu_end();
|
||||
} else {
|
||||
polyval_mul_generic(acc, &key->h_powers[NUM_H_POWERS - 1]);
|
||||
}
|
||||
}
|
||||
|
||||
static void polyval_blocks_arch(struct polyval_elem *acc,
|
||||
const struct polyval_key *key,
|
||||
const u8 *data, size_t nblocks)
|
||||
{
|
||||
if (static_branch_likely(&have_pclmul_avx) && irq_fpu_usable()) {
|
||||
do {
|
||||
/* Allow rescheduling every 4 KiB. */
|
||||
size_t n = min_t(size_t, nblocks,
|
||||
4096 / POLYVAL_BLOCK_SIZE);
|
||||
|
||||
kernel_fpu_begin();
|
||||
polyval_blocks_pclmul_avx(acc, key, data, n);
|
||||
kernel_fpu_end();
|
||||
data += n * POLYVAL_BLOCK_SIZE;
|
||||
nblocks -= n;
|
||||
} while (nblocks);
|
||||
} else {
|
||||
polyval_blocks_generic(acc, &key->h_powers[NUM_H_POWERS - 1],
|
||||
data, nblocks);
|
||||
}
|
||||
}
|
||||
|
||||
#define polyval_mod_init_arch polyval_mod_init_arch
|
||||
static void polyval_mod_init_arch(void)
|
||||
{
|
||||
if (boot_cpu_has(X86_FEATURE_PCLMULQDQ) &&
|
||||
boot_cpu_has(X86_FEATURE_AVX))
|
||||
static_branch_enable(&have_pclmul_avx);
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue