crypto: chacha - move existing library code into lib/crypto

Currently, our generic ChaCha implementation consists of a permute
function in lib/chacha.c that operates on the 64-byte ChaCha state
directly [and which is always included into the core kernel since it
is used by the /dev/random driver], and the crypto API plumbing to
expose it as a skcipher.

In order to support in-kernel users that need the ChaCha streamcipher
but have no need [or tolerance] for going through the abstractions of
the crypto API, let's expose the streamcipher bits via a library API
as well, in a way that permits the implementation to be superseded by
an architecture specific one if provided.

So move the streamcipher code into a separate module in lib/crypto,
and expose the init() and crypt() routines to users of the library.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

4 files changed, 180 insertions, 0 deletions

diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index 261430051595..6a11931ae105 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -8,6 +8,32 @@ config CRYPTO_LIB_AES
 config CRYPTO_LIB_ARC4
 	tristate
 
+config CRYPTO_ARCH_HAVE_LIB_CHACHA
+	tristate
+	help
+	  Declares whether the architecture provides an arch-specific
+	  accelerated implementation of the ChaCha library interface,
+	  either builtin or as a module.
+
+config CRYPTO_LIB_CHACHA_GENERIC
+	tristate
+	select CRYPTO_ALGAPI
+	help
+	  This symbol can be depended upon by arch implementations of the
+	  ChaCha library interface that require the generic code as a
+	  fallback, e.g., for SIMD implementations. If no arch specific
+	  implementation is enabled, this implementation serves the users
+	  of CRYPTO_LIB_CHACHA.
+
+config CRYPTO_LIB_CHACHA
+	tristate "ChaCha library interface"
+	depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
+	select CRYPTO_LIB_CHACHA_GENERIC if CRYPTO_ARCH_HAVE_LIB_CHACHA=n
+	help
+	  Enable the ChaCha library interface. This interface may be fulfilled
+	  by either the generic implementation or an arch-specific one, if one
+	  is available and enabled.
+
 config CRYPTO_LIB_DES
 	tristate
 
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 63de4cb3fcf8..0ce40604e104 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -1,5 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 
+# chacha is used by the /dev/random driver which is always builtin
+obj-y						+= chacha.o
+obj-$(CONFIG_CRYPTO_LIB_CHACHA_GENERIC)		+= libchacha.o
+
 obj-$(CONFIG_CRYPTO_LIB_AES)			+= libaes.o
 libaes-y					:= aes.o
 
diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c
new file mode 100644
index 000000000000..65ead6b0c7e0
--- /dev/null
+++ b/lib/crypto/chacha.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The "hash function" used as the core of the ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/bitops.h>
+#include <linux/string.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 && nrounds != 12);
+
+	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 (20 or 12; 20 is recommended)
+ *
+ * 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_generic(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_generic);
+
+/**
+ * hchacha_block_generic - abbreviated ChaCha core, for XChaCha
+ * @state: input state matrix (16 32-bit words)
+ * @out: output (8 32-bit words)
+ * @nrounds: number of rounds (20 or 12; 20 is recommended)
+ *
+ * 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_generic(const u32 *state, u32 *stream, int nrounds)
+{
+	u32 x[16];
+
+	memcpy(x, state, 64);
+
+	chacha_permute(x, nrounds);
+
+	memcpy(&stream[0], &x[0], 16);
+	memcpy(&stream[4], &x[12], 16);
+}
+EXPORT_SYMBOL(hchacha_block_generic);
diff --git a/lib/crypto/libchacha.c b/lib/crypto/libchacha.c
new file mode 100644
index 000000000000..dabc3accae05
--- /dev/null
+++ b/lib/crypto/libchacha.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include <crypto/algapi.h> // for crypto_xor_cpy
+#include <crypto/chacha.h>
+
+void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds)
+{
+	/* aligned to potentially speed up crypto_xor() */
+	u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
+
+	while (bytes >= CHACHA_BLOCK_SIZE) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE);
+		bytes -= CHACHA_BLOCK_SIZE;
+		dst += CHACHA_BLOCK_SIZE;
+		src += CHACHA_BLOCK_SIZE;
+	}
+	if (bytes) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, bytes);
+	}
+}
+EXPORT_SYMBOL(chacha_crypt_generic);
+
+MODULE_LICENSE("GPL");