From: Eric Biggers <ebiggers@xxxxxxxxxx>
For chacha20_block(), use the existing 32-bit left-rotate function
instead of defining one ourselves.
Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx>
---
lib/chacha20.c | 69 +++++++++++++++++++++++++++-------------------------------
1 file changed, 32 insertions(+), 37 deletions(-)
diff --git a/lib/chacha20.c b/lib/chacha20.c
index 29d3801dee24..c1cc50fb68c9 100644
--- a/lib/chacha20.c
+++ b/lib/chacha20.c
@@ -16,11 +16,6 @@
#include <asm/unaligned.h>
#include <crypto/chacha20.h>
-static inline u32 rotl32(u32 v, u8 n)
-{
- return (v << n) | (v >> (sizeof(v) * 8 - n));
-}
-
void chacha20_block(u32 *state, u32 *stream)
{
u32 x[16], *out = stream;
@@ -30,45 +25,45 @@ void chacha20_block(u32 *state, u32 *stream)
x[i] = state[i];
for (i = 0; i < 20; i += 2) {
- x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 16);
- x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 16);
- x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 16);
- x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 16);
+ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16);
+ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16);
+ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16);
+ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16);
- x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 12);
- x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 12);
- x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 12);
- x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 12);
+ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12);
+ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12);
+ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12);
+ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12);
- x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 8);
- x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 8);
- x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 8);
- x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 8);
+ x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8);
+ x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8);
+ x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8);
+ x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8);
- x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 7);
- x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 7);
- x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 7);
- x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 7);
+ x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7);
+ x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7);
+ x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7);
+ x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7);
- x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 16);
- x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 16);
- x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 16);
- x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 16);
+ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16);
+ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16);
+ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16);
+ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16);
- x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 12);
- x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 12);
- x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 12);
- x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 12);
+ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12);
+ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12);
+ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12);
+ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12);
- x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 8);
- x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 8);
- x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 8);
- x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 8);
+ x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8);
+ x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8);
+ x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8);
+ x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8);
- x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 7);
- x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 7);
- x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 7);
- x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 7);
+ x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7);
+ x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7);
+ x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7);
+ x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7);
}
for (i = 0; i < ARRAY_SIZE(x); i++)
--
2.15.1
