crypto: chacha20 - Add a SSSE3 SIMD variant for x86_64
Implements an x86_64 assembler driver for the ChaCha20 stream cipher. This
single block variant works on a single state matrix using SSE instructions.
It requires SSSE3 due the use of pshufb for efficient 8/16-bit rotate
operations.
For large messages, throughput increases by ~65% compared to
chacha20-generic:
testing speed of chacha20 (chacha20-generic) encryption
test 0 (256 bit key, 16 byte blocks): 45089207 operations in 10 seconds (721427312 bytes)
test 1 (256 bit key, 64 byte blocks): 43839521 operations in 10 seconds (2805729344 bytes)
test 2 (256 bit key, 256 byte blocks): 12702056 operations in 10 seconds (3251726336 bytes)
test 3 (256 bit key, 1024 byte blocks): 3371173 operations in 10 seconds (3452081152 bytes)
test 4 (256 bit key, 8192 byte blocks): 422468 operations in 10 seconds (3460857856 bytes)
testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes)
test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes)
test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes)
test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes)
test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes)
Benchmark results from a Core i5-4670T.
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:01 +07:00
|
|
|
/*
|
|
|
|
* ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
|
|
|
|
*
|
|
|
|
* Copyright (C) 2015 Martin Willi
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License as published by
|
|
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
|
|
* (at your option) any later version.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <crypto/algapi.h>
|
|
|
|
#include <crypto/chacha20.h>
|
|
|
|
#include <linux/crypto.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <asm/fpu/api.h>
|
|
|
|
#include <asm/simd.h>
|
|
|
|
|
|
|
|
#define CHACHA20_STATE_ALIGN 16
|
|
|
|
|
|
|
|
asmlinkage void chacha20_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src);
|
crypto: chacha20 - Add a four block SSSE3 variant for x86_64
Extends the x86_64 SSSE3 ChaCha20 implementation by a function processing
four ChaCha20 blocks in parallel. This avoids the word shuffling needed
in the single block variant, further increasing throughput.
For large messages, throughput increases by ~110% compared to single block
SSSE3:
testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes)
test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes)
test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes)
test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes)
test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes)
testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 42249230 operations in 10 seconds (675987680 bytes)
test 1 (256 bit key, 64 byte blocks): 46441641 operations in 10 seconds (2972265024 bytes)
test 2 (256 bit key, 256 byte blocks): 33028112 operations in 10 seconds (8455196672 bytes)
test 3 (256 bit key, 1024 byte blocks): 11568759 operations in 10 seconds (11846409216 bytes)
test 4 (256 bit key, 8192 byte blocks): 1448761 operations in 10 seconds (11868250112 bytes)
Benchmark results from a Core i5-4670T.
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:02 +07:00
|
|
|
asmlinkage void chacha20_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src);
|
crypto: chacha20 - Add a SSSE3 SIMD variant for x86_64
Implements an x86_64 assembler driver for the ChaCha20 stream cipher. This
single block variant works on a single state matrix using SSE instructions.
It requires SSSE3 due the use of pshufb for efficient 8/16-bit rotate
operations.
For large messages, throughput increases by ~65% compared to
chacha20-generic:
testing speed of chacha20 (chacha20-generic) encryption
test 0 (256 bit key, 16 byte blocks): 45089207 operations in 10 seconds (721427312 bytes)
test 1 (256 bit key, 64 byte blocks): 43839521 operations in 10 seconds (2805729344 bytes)
test 2 (256 bit key, 256 byte blocks): 12702056 operations in 10 seconds (3251726336 bytes)
test 3 (256 bit key, 1024 byte blocks): 3371173 operations in 10 seconds (3452081152 bytes)
test 4 (256 bit key, 8192 byte blocks): 422468 operations in 10 seconds (3460857856 bytes)
testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes)
test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes)
test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes)
test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes)
test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes)
Benchmark results from a Core i5-4670T.
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:01 +07:00
|
|
|
|
|
|
|
static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src,
|
|
|
|
unsigned int bytes)
|
|
|
|
{
|
|
|
|
u8 buf[CHACHA20_BLOCK_SIZE];
|
|
|
|
|
crypto: chacha20 - Add a four block SSSE3 variant for x86_64
Extends the x86_64 SSSE3 ChaCha20 implementation by a function processing
four ChaCha20 blocks in parallel. This avoids the word shuffling needed
in the single block variant, further increasing throughput.
For large messages, throughput increases by ~110% compared to single block
SSSE3:
testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes)
test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes)
test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes)
test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes)
test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes)
testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 42249230 operations in 10 seconds (675987680 bytes)
test 1 (256 bit key, 64 byte blocks): 46441641 operations in 10 seconds (2972265024 bytes)
test 2 (256 bit key, 256 byte blocks): 33028112 operations in 10 seconds (8455196672 bytes)
test 3 (256 bit key, 1024 byte blocks): 11568759 operations in 10 seconds (11846409216 bytes)
test 4 (256 bit key, 8192 byte blocks): 1448761 operations in 10 seconds (11868250112 bytes)
Benchmark results from a Core i5-4670T.
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:02 +07:00
|
|
|
while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
|
|
|
|
chacha20_4block_xor_ssse3(state, dst, src);
|
|
|
|
bytes -= CHACHA20_BLOCK_SIZE * 4;
|
|
|
|
src += CHACHA20_BLOCK_SIZE * 4;
|
|
|
|
dst += CHACHA20_BLOCK_SIZE * 4;
|
|
|
|
state[12] += 4;
|
|
|
|
}
|
crypto: chacha20 - Add a SSSE3 SIMD variant for x86_64
Implements an x86_64 assembler driver for the ChaCha20 stream cipher. This
single block variant works on a single state matrix using SSE instructions.
It requires SSSE3 due the use of pshufb for efficient 8/16-bit rotate
operations.
For large messages, throughput increases by ~65% compared to
chacha20-generic:
testing speed of chacha20 (chacha20-generic) encryption
test 0 (256 bit key, 16 byte blocks): 45089207 operations in 10 seconds (721427312 bytes)
test 1 (256 bit key, 64 byte blocks): 43839521 operations in 10 seconds (2805729344 bytes)
test 2 (256 bit key, 256 byte blocks): 12702056 operations in 10 seconds (3251726336 bytes)
test 3 (256 bit key, 1024 byte blocks): 3371173 operations in 10 seconds (3452081152 bytes)
test 4 (256 bit key, 8192 byte blocks): 422468 operations in 10 seconds (3460857856 bytes)
testing speed of chacha20 (chacha20-simd) encryption
test 0 (256 bit key, 16 byte blocks): 43141886 operations in 10 seconds (690270176 bytes)
test 1 (256 bit key, 64 byte blocks): 46845874 operations in 10 seconds (2998135936 bytes)
test 2 (256 bit key, 256 byte blocks): 18458512 operations in 10 seconds (4725379072 bytes)
test 3 (256 bit key, 1024 byte blocks): 5360533 operations in 10 seconds (5489185792 bytes)
test 4 (256 bit key, 8192 byte blocks): 692846 operations in 10 seconds (5675794432 bytes)
Benchmark results from a Core i5-4670T.
Signed-off-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2015-07-17 00:14:01 +07:00
|
|
|
while (bytes >= CHACHA20_BLOCK_SIZE) {
|
|
|
|
chacha20_block_xor_ssse3(state, dst, src);
|
|
|
|
bytes -= CHACHA20_BLOCK_SIZE;
|
|
|
|
src += CHACHA20_BLOCK_SIZE;
|
|
|
|
dst += CHACHA20_BLOCK_SIZE;
|
|
|
|
state[12]++;
|
|
|
|
}
|
|
|
|
if (bytes) {
|
|
|
|
memcpy(buf, src, bytes);
|
|
|
|
chacha20_block_xor_ssse3(state, buf, buf);
|
|
|
|
memcpy(dst, buf, bytes);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst,
|
|
|
|
struct scatterlist *src, unsigned int nbytes)
|
|
|
|
{
|
|
|
|
u32 *state, state_buf[16 + (CHACHA20_STATE_ALIGN / sizeof(u32)) - 1];
|
|
|
|
struct blkcipher_walk walk;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
if (!may_use_simd())
|
|
|
|
return crypto_chacha20_crypt(desc, dst, src, nbytes);
|
|
|
|
|
|
|
|
state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN);
|
|
|
|
|
|
|
|
blkcipher_walk_init(&walk, dst, src, nbytes);
|
|
|
|
err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE);
|
|
|
|
|
|
|
|
crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv);
|
|
|
|
|
|
|
|
kernel_fpu_begin();
|
|
|
|
|
|
|
|
while (walk.nbytes >= CHACHA20_BLOCK_SIZE) {
|
|
|
|
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
|
|
|
|
rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE));
|
|
|
|
err = blkcipher_walk_done(desc, &walk,
|
|
|
|
walk.nbytes % CHACHA20_BLOCK_SIZE);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (walk.nbytes) {
|
|
|
|
chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr,
|
|
|
|
walk.nbytes);
|
|
|
|
err = blkcipher_walk_done(desc, &walk, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
kernel_fpu_end();
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct crypto_alg alg = {
|
|
|
|
.cra_name = "chacha20",
|
|
|
|
.cra_driver_name = "chacha20-simd",
|
|
|
|
.cra_priority = 300,
|
|
|
|
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
|
|
|
|
.cra_blocksize = 1,
|
|
|
|
.cra_type = &crypto_blkcipher_type,
|
|
|
|
.cra_ctxsize = sizeof(struct chacha20_ctx),
|
|
|
|
.cra_alignmask = sizeof(u32) - 1,
|
|
|
|
.cra_module = THIS_MODULE,
|
|
|
|
.cra_u = {
|
|
|
|
.blkcipher = {
|
|
|
|
.min_keysize = CHACHA20_KEY_SIZE,
|
|
|
|
.max_keysize = CHACHA20_KEY_SIZE,
|
|
|
|
.ivsize = CHACHA20_IV_SIZE,
|
|
|
|
.geniv = "seqiv",
|
|
|
|
.setkey = crypto_chacha20_setkey,
|
|
|
|
.encrypt = chacha20_simd,
|
|
|
|
.decrypt = chacha20_simd,
|
|
|
|
},
|
|
|
|
},
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init chacha20_simd_mod_init(void)
|
|
|
|
{
|
|
|
|
if (!cpu_has_ssse3)
|
|
|
|
return -ENODEV;
|
|
|
|
|
|
|
|
return crypto_register_alg(&alg);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit chacha20_simd_mod_fini(void)
|
|
|
|
{
|
|
|
|
crypto_unregister_alg(&alg);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(chacha20_simd_mod_init);
|
|
|
|
module_exit(chacha20_simd_mod_fini);
|
|
|
|
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
|
|
|
|
MODULE_DESCRIPTION("chacha20 cipher algorithm, SIMD accelerated");
|
|
|
|
MODULE_ALIAS_CRYPTO("chacha20");
|
|
|
|
MODULE_ALIAS_CRYPTO("chacha20-simd");
|