aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/crypto/chacha_glue.c
diff options
context:
space:
mode:
authorArd Biesheuvel2020-07-08 12:11:18 +0300
committerHerbert Xu2020-07-16 21:49:04 +1000
commite79a31715193686e92dadb4caedfbb1f5de3659c (patch)
treefe9d960b52083a72242d8c1a5ecbd0db8b90ff3d /arch/x86/crypto/chacha_glue.c
parent06cc2afbbdf9a9e8df3e2f8db724997dd6e1b4ac (diff)
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>
Diffstat (limited to 'arch/x86/crypto/chacha_glue.c')
-rw-r--r--arch/x86/crypto/chacha_glue.c17
1 files changed, 2 insertions, 15 deletions
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 22250091cdbe..e67a59130025 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -14,8 +14,6 @@
#include <linux/module.h>
#include <asm/simd.h>
-#define CHACHA_STATE_ALIGN 16
-
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,
@@ -124,8 +122,6 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
{
- state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
-
if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
hchacha_block_generic(state, stream, nrounds);
} else {
@@ -138,8 +134,6 @@ EXPORT_SYMBOL(hchacha_block_arch);
void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
{
- state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
-
chacha_init_generic(state, key, iv);
}
EXPORT_SYMBOL(chacha_init_arch);
@@ -147,8 +141,6 @@ EXPORT_SYMBOL(chacha_init_arch);
void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
int nrounds)
{
- state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
-
if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
bytes <= CHACHA_BLOCK_SIZE)
return chacha_crypt_generic(state, dst, src, bytes, nrounds);
@@ -170,15 +162,12 @@ 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, state_buf[16 + 2] __aligned(8);
+ u32 state[CHACHA_STATE_WORDS] __aligned(8);
struct skcipher_walk walk;
int err;
err = skcipher_walk_virt(&walk, req, false);
- BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
- state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
-
chacha_init_generic(state, ctx->key, iv);
while (walk.nbytes > 0) {
@@ -217,12 +206,10 @@ 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, state_buf[16 + 2] __aligned(8);
+ u32 state[CHACHA_STATE_WORDS] __aligned(8);
struct chacha_ctx subctx;
u8 real_iv[16];
- BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
- state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
chacha_init_generic(state, ctx->key, req->iv);
if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {