[CRYPTO] rmd: Use pointer form of endian swapping operations

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>

crypto/rmd128.c

@@ -44,7 +44,7 @@ struct rmd128_ctx {
 #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)); \
 }
 
@@ -285,7 +285,7 @@ static void rmd128_final(struct crypto_tfm *tfm, u8 *out)
 
 	/* 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));

crypto/rmd160.c

@@ -47,7 +47,7 @@ struct rmd160_ctx {
 #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); \
 }
@@ -329,7 +329,7 @@ static void rmd160_final(struct crypto_tfm *tfm, u8 *out)
 
 	/* 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));

crypto/rmd256.c

@@ -44,7 +44,7 @@ struct rmd256_ctx {
 #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)); \
 }
 
@@ -304,7 +304,7 @@ static void rmd256_final(struct crypto_tfm *tfm, u8 *out)
 
 	/* 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));

crypto/rmd320.c

@@ -47,7 +47,7 @@ struct rmd320_ctx {
 #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); \
 }
@@ -353,7 +353,7 @@ static void rmd320_final(struct crypto_tfm *tfm, u8 *out)
 
 	/* 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));