crypto: blake2s - optimize blake2s initialization

If no key was provided, then don't waste time initializing the block
buffer, as its initial contents won't be used.

Also, make crypto_blake2s_init() and blake2s() call a single internal
function __blake2s_init() which treats the key as optional, rather than
conditionally calling blake2s_init() or blake2s_init_key().  This
reduces the compiled code size, as previously both blake2s_init() and
blake2s_init_key() were being inlined into these two callers, except
when the key size passed to blake2s() was a compile-time constant.

These optimizations aren't that significant for BLAKE2s.  However, the
equivalent optimizations will be more significant for BLAKE2b, as
everything is twice as big in BLAKE2b.  And it's good to keep things
consistent rather than making optimizations for BLAKE2b but not BLAKE2s.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 27 insertions, 26 deletions

diff --git a/include/crypto/blake2s.h b/include/crypto/blake2s.h
index b471deac28ff..734ed22b7a6a 100644
--- a/include/crypto/blake2s.h
+++ b/include/crypto/blake2s.h
@@ -43,29 +43,34 @@ enum blake2s_iv {
 	BLAKE2S_IV7 = 0x5BE0CD19UL,
 };
 
-void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen);
-void blake2s_final(struct blake2s_state *state, u8 *out);
-
-static inline void blake2s_init_param(struct blake2s_state *state,
-				      const u32 param)
+static inline void __blake2s_init(struct blake2s_state *state, size_t outlen,
+				  const void *key, size_t keylen)
 {
-	*state = (struct blake2s_state){{
-		BLAKE2S_IV0 ^ param,
-		BLAKE2S_IV1,
-		BLAKE2S_IV2,
-		BLAKE2S_IV3,
-		BLAKE2S_IV4,
-		BLAKE2S_IV5,
-		BLAKE2S_IV6,
-		BLAKE2S_IV7,
-	}};
+	state->h[0] = BLAKE2S_IV0 ^ (0x01010000 | keylen << 8 | outlen);
+	state->h[1] = BLAKE2S_IV1;
+	state->h[2] = BLAKE2S_IV2;
+	state->h[3] = BLAKE2S_IV3;
+	state->h[4] = BLAKE2S_IV4;
+	state->h[5] = BLAKE2S_IV5;
+	state->h[6] = BLAKE2S_IV6;
+	state->h[7] = BLAKE2S_IV7;
+	state->t[0] = 0;
+	state->t[1] = 0;
+	state->f[0] = 0;
+	state->f[1] = 0;
+	state->buflen = 0;
+	state->outlen = outlen;
+	if (keylen) {
+		memcpy(state->buf, key, keylen);
+		memset(&state->buf[keylen], 0, BLAKE2S_BLOCK_SIZE - keylen);
+		state->buflen = BLAKE2S_BLOCK_SIZE;
+	}
 }
 
 static inline void blake2s_init(struct blake2s_state *state,
 				const size_t outlen)
 {
-	blake2s_init_param(state, 0x01010000 | outlen);
-	state->outlen = outlen;
+	__blake2s_init(state, outlen, NULL, 0);
 }
 
 static inline void blake2s_init_key(struct blake2s_state *state,
@@ -75,12 +80,12 @@ static inline void blake2s_init_key(struct blake2s_state *state,
 	WARN_ON(IS_ENABLED(DEBUG) && (!outlen || outlen > BLAKE2S_HASH_SIZE ||
 		!key || !keylen || keylen > BLAKE2S_KEY_SIZE));
 
-	blake2s_init_param(state, 0x01010000 | keylen << 8 | outlen);
-	memcpy(state->buf, key, keylen);
-	state->buflen = BLAKE2S_BLOCK_SIZE;
-	state->outlen = outlen;
+	__blake2s_init(state, outlen, key, keylen);
 }
 
+void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen);
+void blake2s_final(struct blake2s_state *state, u8 *out);
+
 static inline void blake2s(u8 *out, const u8 *in, const u8 *key,
 			   const size_t outlen, const size_t inlen,
 			   const size_t keylen)
@@ -91,11 +96,7 @@ static inline void blake2s(u8 *out, const u8 *in, const u8 *key,
 		outlen > BLAKE2S_HASH_SIZE || keylen > BLAKE2S_KEY_SIZE ||
 		(!key && keylen)));
 
-	if (keylen)
-		blake2s_init_key(&state, outlen, key, keylen);
-	else
-		blake2s_init(&state, outlen);
-
+	__blake2s_init(&state, outlen, key, keylen);
 	blake2s_update(&state, in, inlen);
 	blake2s_final(&state, out);
 }