UPSTREAM: 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as well, in a way that permits the implementation to be superseded by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>
(cherry picked from commit 5fb8ef25803ef33e2eb60b626435828b937bed75)
Bug: 152722841
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I7fe321d1fcbaea1dc3f9f65dec74a6f40da2d489

lib/Makefile

@@ -31,7 +31,7 @@ endif
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o\
 	 idr.o int_sqrt.o extable.o \
-	 sha1.o chacha.o irq_regs.o argv_split.o \
+	 sha1.o irq_regs.o argv_split.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \

lib/crypto/Kconfig

@@ -1,3 +1,29 @@
 # SPDX-License-Identifier: GPL-2.0
 
 comment "Crypto library routines"
+
+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.

lib/crypto/Makefile

@@ -1 +1,5 @@
 # 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

lib/crypto/chacha.c

@@ -9,9 +9,11 @@
  * (at your option) any later version.
  */
 
+#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>
@@ -76,7 +78,7 @@ static void chacha_permute(u32 *x, int nrounds)
  * 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)
+void chacha_block_generic(u32 *state, u8 *stream, int nrounds)
 {
 	u32 x[16];
 	int i;
@@ -90,11 +92,11 @@ void chacha_block(u32 *state, u8 *stream, int nrounds)
 
 	state[12]++;
 }
-EXPORT_SYMBOL(chacha_block);
+EXPORT_SYMBOL(chacha_block_generic);
 
 /**
- * hchacha_block - abbreviated ChaCha core, for XChaCha
- * @in: input state matrix (16 32-bit words)
+ * 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)
  *
@@ -103,15 +105,15 @@ EXPORT_SYMBOL(chacha_block);
  * 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)
+void hchacha_block_generic(const u32 *state, u32 *stream, int nrounds)
 {
 	u32 x[16];
 
-	memcpy(x, in, 64);
+	memcpy(x, state, 64);
 
 	chacha_permute(x, nrounds);
 
-	memcpy(&out[0], &x[0], 16);
-	memcpy(&out[4], &x[12], 16);
+	memcpy(&stream[0], &x[0], 16);
+	memcpy(&stream[4], &x[12], 16);
 }
-EXPORT_SYMBOL(hchacha_block);
+EXPORT_SYMBOL(hchacha_block_generic);

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");