linux_dsm_epyc7002/arch/x86/crypto/chacha_glue.c
Ard Biesheuvel e79a317151 crypto: x86/chacha-sse3 - use unaligned loads for state array
Due to the fact that the x86 port does not support allocating objects
on the stack with an alignment that exceeds 8 bytes, we have a rather
ugly hack in the x86 code for ChaCha to ensure that the state array is
aligned to 16 bytes, allowing the SSE3 implementation of the algorithm
to use aligned loads.

Given that the performance benefit of using of aligned loads appears to
be limited (~0.25% for 1k blocks using tcrypt on a Corei7-8650U), and
the fact that this hack has leaked into generic ChaCha code, let's just
remove it.

Cc: Martin Willi <martin@strongswan.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Martin Willi <martin@strongswan.org>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2020-07-16 21:49:04 +10:00

317 lines
9.1 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* x64 SIMD accelerated ChaCha and XChaCha stream ciphers,
* including ChaCha20 (RFC7539)
*
* Copyright (C) 2015 Martin Willi
*/
#include <crypto/algapi.h>
#include <crypto/internal/chacha.h>
#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <asm/simd.h>
asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds);
asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
unsigned int len, int nrounds);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
{
len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
}
static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
unsigned int bytes, int nrounds)
{
if (IS_ENABLED(CONFIG_AS_AVX512) &&
static_branch_likely(&chacha_use_avx512vl)) {
while (bytes >= CHACHA_BLOCK_SIZE * 8) {
chacha_8block_xor_avx512vl(state, dst, src, bytes,
nrounds);
bytes -= CHACHA_BLOCK_SIZE * 8;
src += CHACHA_BLOCK_SIZE * 8;
dst += CHACHA_BLOCK_SIZE * 8;
state[12] += 8;
}
if (bytes > CHACHA_BLOCK_SIZE * 4) {
chacha_8block_xor_avx512vl(state, dst, src, bytes,
nrounds);
state[12] += chacha_advance(bytes, 8);
return;
}
if (bytes > CHACHA_BLOCK_SIZE * 2) {
chacha_4block_xor_avx512vl(state, dst, src, bytes,
nrounds);
state[12] += chacha_advance(bytes, 4);
return;
}
if (bytes) {
chacha_2block_xor_avx512vl(state, dst, src, bytes,
nrounds);
state[12] += chacha_advance(bytes, 2);
return;
}
}
if (static_branch_likely(&chacha_use_avx2)) {
while (bytes >= CHACHA_BLOCK_SIZE * 8) {
chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
bytes -= CHACHA_BLOCK_SIZE * 8;
src += CHACHA_BLOCK_SIZE * 8;
dst += CHACHA_BLOCK_SIZE * 8;
state[12] += 8;
}
if (bytes > CHACHA_BLOCK_SIZE * 4) {
chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
state[12] += chacha_advance(bytes, 8);
return;
}
if (bytes > CHACHA_BLOCK_SIZE * 2) {
chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
state[12] += chacha_advance(bytes, 4);
return;
}
if (bytes > CHACHA_BLOCK_SIZE) {
chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
state[12] += chacha_advance(bytes, 2);
return;
}
}
while (bytes >= CHACHA_BLOCK_SIZE * 4) {
chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
bytes -= CHACHA_BLOCK_SIZE * 4;
src += CHACHA_BLOCK_SIZE * 4;
dst += CHACHA_BLOCK_SIZE * 4;
state[12] += 4;
}
if (bytes > CHACHA_BLOCK_SIZE) {
chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
state[12] += chacha_advance(bytes, 4);
return;
}
if (bytes) {
chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
state[12]++;
}
}
void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
{
if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
hchacha_block_generic(state, stream, nrounds);
} else {
kernel_fpu_begin();
hchacha_block_ssse3(state, stream, nrounds);
kernel_fpu_end();
}
}
EXPORT_SYMBOL(hchacha_block_arch);
void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
{
chacha_init_generic(state, key, iv);
}
EXPORT_SYMBOL(chacha_init_arch);
void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
int nrounds)
{
if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
bytes <= CHACHA_BLOCK_SIZE)
return chacha_crypt_generic(state, dst, src, bytes, nrounds);
do {
unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
kernel_fpu_begin();
chacha_dosimd(state, dst, src, todo, nrounds);
kernel_fpu_end();
bytes -= todo;
src += todo;
dst += todo;
} while (bytes);
}
EXPORT_SYMBOL(chacha_crypt_arch);
static int chacha_simd_stream_xor(struct skcipher_request *req,
const struct chacha_ctx *ctx, const u8 *iv)
{
u32 state[CHACHA_STATE_WORDS] __aligned(8);
struct skcipher_walk walk;
int err;
err = skcipher_walk_virt(&walk, req, false);
chacha_init_generic(state, ctx->key, iv);
while (walk.nbytes > 0) {
unsigned int nbytes = walk.nbytes;
if (nbytes < walk.total)
nbytes = round_down(nbytes, walk.stride);
if (!static_branch_likely(&chacha_use_simd) ||
!crypto_simd_usable()) {
chacha_crypt_generic(state, walk.dst.virt.addr,
walk.src.virt.addr, nbytes,
ctx->nrounds);
} else {
kernel_fpu_begin();
chacha_dosimd(state, walk.dst.virt.addr,
walk.src.virt.addr, nbytes,
ctx->nrounds);
kernel_fpu_end();
}
err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
}
return err;
}
static int chacha_simd(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
return chacha_simd_stream_xor(req, ctx, req->iv);
}
static int xchacha_simd(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
u32 state[CHACHA_STATE_WORDS] __aligned(8);
struct chacha_ctx subctx;
u8 real_iv[16];
chacha_init_generic(state, ctx->key, req->iv);
if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
kernel_fpu_begin();
hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
kernel_fpu_end();
} else {
hchacha_block_generic(state, subctx.key, ctx->nrounds);
}
subctx.nrounds = ctx->nrounds;
memcpy(&real_iv[0], req->iv + 24, 8);
memcpy(&real_iv[8], req->iv + 16, 8);
return chacha_simd_stream_xor(req, &subctx, real_iv);
}
static struct skcipher_alg algs[] = {
{
.base.cra_name = "chacha20",
.base.cra_driver_name = "chacha20-simd",
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA_KEY_SIZE,
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = CHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
.setkey = chacha20_setkey,
.encrypt = chacha_simd,
.decrypt = chacha_simd,
}, {
.base.cra_name = "xchacha20",
.base.cra_driver_name = "xchacha20-simd",
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA_KEY_SIZE,
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = XCHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
.setkey = chacha20_setkey,
.encrypt = xchacha_simd,
.decrypt = xchacha_simd,
}, {
.base.cra_name = "xchacha12",
.base.cra_driver_name = "xchacha12-simd",
.base.cra_priority = 300,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct chacha_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = CHACHA_KEY_SIZE,
.max_keysize = CHACHA_KEY_SIZE,
.ivsize = XCHACHA_IV_SIZE,
.chunksize = CHACHA_BLOCK_SIZE,
.setkey = chacha12_setkey,
.encrypt = xchacha_simd,
.decrypt = xchacha_simd,
},
};
static int __init chacha_simd_mod_init(void)
{
if (!boot_cpu_has(X86_FEATURE_SSSE3))
return 0;
static_branch_enable(&chacha_use_simd);
if (boot_cpu_has(X86_FEATURE_AVX) &&
boot_cpu_has(X86_FEATURE_AVX2) &&
cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
static_branch_enable(&chacha_use_avx2);
if (IS_ENABLED(CONFIG_AS_AVX512) &&
boot_cpu_has(X86_FEATURE_AVX512VL) &&
boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
static_branch_enable(&chacha_use_avx512vl);
}
return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
}
static void __exit chacha_simd_mod_fini(void)
{
if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && boot_cpu_has(X86_FEATURE_SSSE3))
crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
}
module_init(chacha_simd_mod_init);
module_exit(chacha_simd_mod_fini);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (x64 SIMD accelerated)");
MODULE_ALIAS_CRYPTO("chacha20");
MODULE_ALIAS_CRYPTO("chacha20-simd");
MODULE_ALIAS_CRYPTO("xchacha20");
MODULE_ALIAS_CRYPTO("xchacha20-simd");
MODULE_ALIAS_CRYPTO("xchacha12");
MODULE_ALIAS_CRYPTO("xchacha12-simd");