[RFC PATCH 01/20] crypto: chacha - move existing library code into lib/crypto

@@ -20,7 +20,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>

@@ -20,7 +20,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>

@@ -7,7 +7,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>

@@ -1374,6 +1374,14 @@ config CRYPTO_SALSA20
 	  The Salsa20 stream cipher algorithm is designed by Daniel J.
 	  Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html>
 
+config CRYPTO_ARCH_HAVE_LIB_CHACHA
+	tristate
+
+config CRYPTO_LIB_CHACHA
+	tristate
+	default y
+	depends on CRYPTO_ARCH_HAVE_LIB_CHACHA || !CRYPTO_ARCH_HAVE_LIB_CHACHA
+
 config CRYPTO_CHACHA20
 	tristate "ChaCha stream cipher algorithms"
 	select CRYPTO_BLKCIPHER

@@ -8,29 +8,10 @@
 
 #include <asm/unaligned.h>
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/module.h>
 
-static void chacha_docrypt(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(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(state, stream, nrounds);
-		crypto_xor_cpy(dst, src, stream, bytes);
-	}
-}
-
 static int chacha_stream_xor(struct skcipher_request *req,
 			     const struct chacha_ctx *ctx, const u8 *iv)
 {

@@ -48,8 +29,8 @@ static int chacha_stream_xor(struct skcipher_request *req,
 		if (nbytes < walk.total)
 			nbytes = round_down(nbytes, CHACHA_BLOCK_SIZE);
 
-		chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
-			       nbytes, ctx->nrounds);
+		chacha_crypt_generic(state, walk.dst.virt.addr,
+				     walk.src.virt.addr, nbytes, ctx->nrounds);
 		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 

@@ -58,22 +39,7 @@ static int chacha_stream_xor(struct skcipher_request *req,
 
 void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv)
 {
-	state[0]  = 0x61707865; /* "expa" */
-	state[1]  = 0x3320646e; /* "nd 3" */
-	state[2]  = 0x79622d32; /* "2-by" */
-	state[3]  = 0x6b206574; /* "te k" */
-	state[4]  = ctx->key[0];
-	state[5]  = ctx->key[1];
-	state[6]  = ctx->key[2];
-	state[7]  = ctx->key[3];
-	state[8]  = ctx->key[4];
-	state[9]  = ctx->key[5];
-	state[10] = ctx->key[6];
-	state[11] = ctx->key[7];
-	state[12] = get_unaligned_le32(iv +  0);
-	state[13] = get_unaligned_le32(iv +  4);
-	state[14] = get_unaligned_le32(iv +  8);
-	state[15] = get_unaligned_le32(iv + 12);
+	chacha_init_generic(state, ctx->key, iv);
 }
 EXPORT_SYMBOL_GPL(crypto_chacha_init);
 

@@ -126,7 +92,7 @@ int crypto_xchacha_crypt(struct skcipher_request *req)
 
 	/* Compute the subkey given the original key and first 128 nonce bits */
 	crypto_chacha_init(state, ctx, req->iv);
-	hchacha_block(state, subctx.key, ctx->nrounds);
+	hchacha_block_generic(state, subctx.key, ctx->nrounds);
 	subctx.nrounds = ctx->nrounds;
 
 	/* Build the real IV */

@@ -15,9 +15,8 @@
 #ifndef _CRYPTO_CHACHA_H
 #define _CRYPTO_CHACHA_H
 
-#include <crypto/skcipher.h>
+#include <asm/unaligned.h>
 #include <linux/types.h>
-#include <linux/crypto.h>
 
 /* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */
 #define CHACHA_IV_SIZE		16

@@ -29,26 +28,42 @@
 /* 192-bit nonce, then 64-bit stream position */
 #define XCHACHA_IV_SIZE		32
 
-struct chacha_ctx {
-	u32 key[8];
-	int nrounds;
-};
-
-void chacha_block(u32 *state, u8 *stream, int nrounds);
+void chacha_block_generic(u32 *state, u8 *stream, int nrounds);
 static inline void chacha20_block(u32 *state, u8 *stream)
 {
-	chacha_block(state, stream, 20);
+	chacha_block_generic(state, stream, 20);
+}
+void hchacha_block_generic(const u32 *in, u32 *out, int nrounds);
+
+static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv)
+{
+	state[0]  = 0x61707865; /* "expa" */
+	state[1]  = 0x3320646e; /* "nd 3" */
+	state[2]  = 0x79622d32; /* "2-by" */
+	state[3]  = 0x6b206574; /* "te k" */
+	state[4]  = key[0];
+	state[5]  = key[1];
+	state[6]  = key[2];
+	state[7]  = key[3];
+	state[8]  = key[4];
+	state[9]  = key[5];
+	state[10] = key[6];
+	state[11] = key[7];
+	state[12] = get_unaligned_le32(iv +  0);
+	state[13] = get_unaligned_le32(iv +  4);
+	state[14] = get_unaligned_le32(iv +  8);
+	state[15] = get_unaligned_le32(iv + 12);
 }
-void hchacha_block(const u32 *in, u32 *out, int nrounds);
 
-void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv);
+static inline void chacha_init(u32 *state, const u32 *key, const u8 *iv)
+{
+	chacha_init_generic(state, key, iv);
+}
 
-int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize);
-int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
-			   unsigned int keysize);
+void chacha_crypt(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		  int nrounds);
 
-int crypto_chacha_crypt(struct skcipher_request *req);
-int crypto_xchacha_crypt(struct skcipher_request *req);
+void chacha_crypt_generic(u32 *state, u8 *dst, const u8 *src,
+			  unsigned int bytes, int nrounds);
 
 #endif /* _CRYPTO_CHACHA_H */

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _CRYPTO_INTERNAL_CHACHA_H
+#define _CRYPTO_INTERNAL_CHACHA_H
+
+#include <crypto/chacha.h>
+#include <crypto/skcipher.h>
+#include <linux/crypto.h>
+
+struct chacha_ctx {
+	u32 key[8];
+	int nrounds;
+};
+
+void crypto_chacha_init(u32 *state, const struct chacha_ctx *ctx, const u8 *iv);
+
+int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			   unsigned int keysize);
+int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			   unsigned int keysize);
+
+int crypto_chacha_crypt(struct skcipher_request *req);
+int crypto_xchacha_crypt(struct skcipher_request *req);
+
+#endif /* _CRYPTO_CHACHA_H */

@@ -30,8 +30,7 @@ endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
-	 idr.o extable.o \
-	 sha1.o chacha.o irq_regs.o argv_split.o \
+	 idr.o extable.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 \

@@ -1,13 +1,16 @@
 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_CRYPTO_LIB_AES) += libaes.o
-libaes-y := aes.o
+# chacha is used by the /dev/random driver which is always builtin
+obj-y						+= chacha.o
 
-obj-$(CONFIG_CRYPTO_LIB_ARC4) += libarc4.o
-libarc4-y := arc4.o
+obj-$(CONFIG_CRYPTO_LIB_AES)			+= libaes.o
+libaes-y					:= aes.o
 
-obj-$(CONFIG_CRYPTO_LIB_DES) += libdes.o
-libdes-y := des.o
+obj-$(CONFIG_CRYPTO_LIB_ARC4)			+= libarc4.o
+libarc4-y					:= arc4.o
 
-obj-$(CONFIG_CRYPTO_LIB_SHA256) += libsha256.o
-libsha256-y := sha256.o
+obj-$(CONFIG_CRYPTO_LIB_DES)			+= libdes.o
+libdes-y					:= des.o
+
+obj-$(CONFIG_CRYPTO_LIB_SHA256)			+= libsha256.o
+libsha256-y					:= sha256.o

@@ -5,11 +5,14 @@
  * 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/algapi.h> // for crypto_xor_cpy
 #include <crypto/chacha.h>
 
 static void chacha_permute(u32 *x, int nrounds)

@@ -72,7 +75,7 @@ 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;

@@ -86,7 +89,7 @@ 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

@@ -99,7 +102,7 @@ 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 *in, u32 *out, int nrounds)
 {
 	u32 x[16];
 

@@ -110,4 +113,30 @@ void hchacha_block(const u32 *in, u32 *out, int nrounds)
 	memcpy(&out[0], &x[0], 16);
 	memcpy(&out[4], &x[12], 16);
 }
-EXPORT_SYMBOL(hchacha_block);
+EXPORT_SYMBOL(hchacha_block_generic);
+
+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);
+
+#ifndef CONFIG_CRYPTO_ARCH_HAVE_LIB_CHACHA
+extern void chacha_crypt(u32 *, u8 *, const u8 *,  unsigned int, int)
+	__alias(chacha_crypt_generic);
+EXPORT_SYMBOL(chacha_crypt);
+#endif