This patch converts the relevant code in the rmd implementations to
use the pointer form of the endian swapping operations. This allows
certain architectures to generate more optimised code. For example,
on sparc64 this more than halves the CPU cycles on a typical hashing
operation.
Based on a patch by David Miller.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
#define F4(x, y, z) (y ^ (z & (x ^ y))) /* z ? x : y */
#define ROUND(a, b, c, d, f, k, x, s) { \
#define F4(x, y, z) (y ^ (z & (x ^ y))) /* z ? x : y */
#define ROUND(a, b, c, d, f, k, x, s) { \
- (a) += f((b), (c), (d)) + le32_to_cpu(x) + (k); \
+ (a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
(a) = rol32((a), (s)); \
}
(a) = rol32((a), (s)); \
}
/* Store state in digest */
for (i = 0; i < 4; i++)
/* Store state in digest */
for (i = 0; i < 4; i++)
- dst[i] = cpu_to_le32(rctx->state[i]);
+ dst[i] = cpu_to_le32p(&rctx->state[i]);
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));
#define F5(x, y, z) (x ^ (y | ~z))
#define ROUND(a, b, c, d, e, f, k, x, s) { \
#define F5(x, y, z) (x ^ (y | ~z))
#define ROUND(a, b, c, d, e, f, k, x, s) { \
- (a) += f((b), (c), (d)) + le32_to_cpu(x) + (k); \
+ (a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
(a) = rol32((a), (s)) + (e); \
(c) = rol32((c), 10); \
}
(a) = rol32((a), (s)) + (e); \
(c) = rol32((c), 10); \
}
/* Store state in digest */
for (i = 0; i < 5; i++)
/* Store state in digest */
for (i = 0; i < 5; i++)
- dst[i] = cpu_to_le32(rctx->state[i]);
+ dst[i] = cpu_to_le32p(&rctx->state[i]);
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));
#define F4(x, y, z) (y ^ (z & (x ^ y))) /* z ? x : y */
#define ROUND(a, b, c, d, f, k, x, s) { \
#define F4(x, y, z) (y ^ (z & (x ^ y))) /* z ? x : y */
#define ROUND(a, b, c, d, f, k, x, s) { \
- (a) += f((b), (c), (d)) + le32_to_cpu(x) + (k); \
+ (a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
(a) = rol32((a), (s)); \
}
(a) = rol32((a), (s)); \
}
/* Store state in digest */
for (i = 0; i < 8; i++)
/* Store state in digest */
for (i = 0; i < 8; i++)
- dst[i] = cpu_to_le32(rctx->state[i]);
+ dst[i] = cpu_to_le32p(&rctx->state[i]);
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));
#define F5(x, y, z) (x ^ (y | ~z))
#define ROUND(a, b, c, d, e, f, k, x, s) { \
#define F5(x, y, z) (x ^ (y | ~z))
#define ROUND(a, b, c, d, e, f, k, x, s) { \
- (a) += f((b), (c), (d)) + le32_to_cpu(x) + (k); \
+ (a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \
(a) = rol32((a), (s)) + (e); \
(c) = rol32((c), 10); \
}
(a) = rol32((a), (s)) + (e); \
(c) = rol32((c), 10); \
}
/* Store state in digest */
for (i = 0; i < 10; i++)
/* Store state in digest */
for (i = 0; i < 10; i++)
- dst[i] = cpu_to_le32(rctx->state[i]);
+ dst[i] = cpu_to_le32p(&rctx->state[i]);
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));
/* Wipe context */
memset(rctx, 0, sizeof(*rctx));