crypto: lib/sha256 - Clear W[] in sha256_update() instead of sha256_transform()

The temporary W[] array is currently zeroed out once every call to
sha256_transform(), i.e. once every 64 bytes of input data. Moving it to
sha256_update() instead so that it is cleared only once per update can
save about 2-3% of the total time taken to compute the digest, with a
reasonable memset() implementation, and considerably more (~20%) with a
bad one (eg the x86 purgatory currently uses a memset() coded in C).
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

lib/crypto/sha256.c

@@ -43,10 +43,9 @@ static inline void BLEND_OP(int I, u32 *W)
 	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
 }
 
-static void sha256_transform(u32 *state, const u8 *input)
+static void sha256_transform(u32 *state, const u8 *input, u32 *W)
 {
 	u32 a, b, c, d, e, f, g, h, t1, t2;
-	u32 W[64];
 	int i;
 
 	/* load the input */
@@ -200,15 +199,13 @@ static void sha256_transform(u32 *state, const u8 *input)
 
 	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
 	state[4] += e; state[5] += f; state[6] += g; state[7] += h;
-
-	/* clear any sensitive info... */
-	memzero_explicit(W, 64 * sizeof(u32));
 }
 
 void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 {
 	unsigned int partial, done;
 	const u8 *src;
+	u32 W[64];
 
 	partial = sctx->count & 0x3f;
 	sctx->count += len;
@@ -223,11 +220,13 @@ void sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
 		}
 
 		do {
-			sha256_transform(sctx->state, src);
+			sha256_transform(sctx->state, src, W);
 			done += 64;
 			src = data + done;
 		} while (done + 63 < len);
 
+		memzero_explicit(W, sizeof(W));
+
 		partial = 0;
 	}
 	memcpy(sctx->buf + partial, src, len - done);