crypto: chacha20-generic - refactor to allow varying number of rounds

In preparation for adding XChaCha12 support, rename/refactor
chacha20-generic to support different numbers of rounds.  The
justification for needing XChaCha12 support is explained in more detail
in the patch "crypto: chacha - add XChaCha12 support".

The only difference between ChaCha{8,12,20} are the number of rounds
itself; all other parts of the algorithm are the same.  Therefore,
remove the "20" from all definitions, structures, functions, files, etc.
that will be shared by all ChaCha versions.

Also make ->setkey() store the round count in the chacha_ctx (previously
chacha20_ctx).  The generic code then passes the round count through to
chacha_block().  There will be a ->setkey() function for each explicitly
allowed round count; the encrypt/decrypt functions will be the same.  I
decided not to do it the opposite way (same ->setkey() function for all
round counts, with different encrypt/decrypt functions) because that
would have required more boilerplate code in architecture-specific
implementations of ChaCha and XChaCha.

Reviewed-by: Ard Biesheuvel <[email protected]>
Acked-by: Martin Willi <[email protected]>
Signed-off-by: Eric Biggers <[email protected]>
Signed-off-by: Herbert Xu <[email protected]>

lib/chacha.c

@@ -0,0 +1,117 @@
+/*
+ * The "hash function" used as the core of the ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/bitops.h>
+#include <linux/cryptohash.h>
+#include <asm/unaligned.h>
+#include <crypto/chacha.h>
+
+static void chacha_permute(u32 *x, int nrounds)
+{
+	int i;
+
+	/* whitelist the allowed round counts */
+	WARN_ON_ONCE(nrounds != 20);
+
+	for (i = 0; i < nrounds; i += 2) {
+		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]  = 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] = 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]  = 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] = 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]  = 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] = 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]  = 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);
+	}
+}
+
+/**
+ * chacha_block - generate one keystream block and increment block counter
+ * @state: input state matrix (16 32-bit words)
+ * @stream: output keystream block (64 bytes)
+ * @nrounds: number of rounds (currently must be 20)
+ *
+ * This is the ChaCha core, a function from 64-byte strings to 64-byte strings.
+ * The caller has already converted the endianness of the input.  This function
+ * also handles incrementing the block counter in the input matrix.
+ */
+void chacha_block(u32 *state, u8 *stream, int nrounds)
+{
+	u32 x[16];
+	int i;
+
+	memcpy(x, state, 64);
+
+	chacha_permute(x, nrounds);
+
+	for (i = 0; i < ARRAY_SIZE(x); i++)
+		put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]);
+
+	state[12]++;
+}
+EXPORT_SYMBOL(chacha_block);
+
+/**
+ * hchacha_block - abbreviated ChaCha core, for XChaCha
+ * @in: input state matrix (16 32-bit words)
+ * @out: output (8 32-bit words)
+ * @nrounds: number of rounds (currently must be 20)
+ *
+ * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step
+ * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf).  HChaCha
+ * skips the final addition of the initial state, and outputs only certain words
+ * of the state.  It should not be used for streaming directly.
+ */
+void hchacha_block(const u32 *in, u32 *out, int nrounds)
+{
+	u32 x[16];
+
+	memcpy(x, in, 64);
+
+	chacha_permute(x, nrounds);
+
+	memcpy(&out[0], &x[0], 16);
+	memcpy(&out[4], &x[12], 16);
+}
+EXPORT_SYMBOL(hchacha_block);