crypto: arm/speck - add NEON-accelerated implementation of Speck-XTS

Add an ARM NEON-accelerated implementation of Speck-XTS.  It operates on
128-byte chunks at a time, i.e. 8 blocks for Speck128 or 16 blocks for
Speck64.  Each 128-byte chunk goes through XTS preprocessing, then is
encrypted/decrypted (doing one cipher round for all the blocks, then the
next round, etc.), then goes through XTS postprocessing.

The performance depends on the processor but can be about 3 times faster
than the generic code.  For example, on an ARMv7 processor we observe
the following performance with Speck128/256-XTS:

    xts-speck128-neon:     Encryption 107.9 MB/s, Decryption 108.1 MB/s
    xts(speck128-generic): Encryption  32.1 MB/s, Decryption  36.6 MB/s

In comparison to AES-256-XTS without the Cryptography Extensions:

    xts-aes-neonbs:        Encryption  41.2 MB/s, Decryption  36.7 MB/s
    xts(aes-asm):          Encryption  31.7 MB/s, Decryption  30.8 MB/s
    xts(aes-generic):      Encryption  21.2 MB/s, Decryption  20.9 MB/s

Speck64/128-XTS is even faster:

    xts-speck64-neon:      Encryption 138.6 MB/s, Decryption 139.1 MB/s

Note that as with the generic code, only the Speck128 and Speck64
variants are supported.  Also, for now only the XTS mode of operation is
supported, to target the disk and file encryption use cases.  The NEON
code also only handles the portion of the data that is evenly divisible
into 128-byte chunks, with any remainder handled by a C fallback.  Of
course, other modes of operation could be added later if needed, and/or
the NEON code could be updated to handle other buffer sizes.

The XTS specification is only defined for AES which has a 128-bit block
size, so for the GF(2^64) math needed for Speck64-XTS we use the
reducing polynomial 'x^64 + x^4 + x^3 + x + 1' given by the original XEX
paper.  Of course, when possible users should use Speck128-XTS, but even
that may be too slow on some processors; Speck64-XTS can be faster.
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm/crypto/Kconfig

@@ -121,4 +121,10 @@ config CRYPTO_CHACHA20_NEON
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 
+config CRYPTO_SPECK_NEON
+	tristate "NEON accelerated Speck cipher algorithms"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_SPECK
+
 endif

arch/arm/crypto/Makefile

@@ -10,6 +10,7 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o
+obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -53,6 +54,7 @@ ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
 crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
 chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
+speck-neon-y := speck-neon-core.o speck-neon-glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)

arch/arm/crypto/speck-neon-glue.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
+ *
+ * Copyright (c) 2018 Google, Inc
+ *
+ * Note: the NIST recommendation for XTS only specifies a 128-bit block size,
+ * but a 64-bit version (needed for Speck64) is fairly straightforward; the math
+ * is just done in GF(2^64) instead of GF(2^128), with the reducing polynomial
+ * x^64 + x^4 + x^3 + x + 1 from the original XEX paper (Rogaway, 2004:
+ * "Efficient Instantiations of Tweakable Blockciphers and Refinements to Modes
+ * OCB and PMAC"), represented as 0x1B.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/algapi.h>
+#include <crypto/gf128mul.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/speck.h>
+#include <crypto/xts.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/* The assembly functions only handle multiples of 128 bytes */
+#define SPECK_NEON_CHUNK_SIZE	128
+
+/* Speck128 */
+
+struct speck128_xts_tfm_ctx {
+	struct speck128_tfm_ctx main_key;
+	struct speck128_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
+					  void *dst, const void *src,
+					  unsigned int nbytes, void *tweak);
+
+asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
+					  void *dst, const void *src,
+					  unsigned int nbytes, void *tweak);
+
+typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
+				     u8 *, const u8 *);
+typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
+					  const void *, unsigned int, void *);
+
+static __always_inline int
+__speck128_xts_crypt(struct skcipher_request *req,
+		     speck128_crypt_one_t crypt_one,
+		     speck128_xts_crypt_many_t crypt_many)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	le128 tweak;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+		u8 *dst = walk.dst.virt.addr;
+		const u8 *src = walk.src.virt.addr;
+
+		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+			unsigned int count;
+
+			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+			kernel_neon_begin();
+			(*crypt_many)(ctx->main_key.round_keys,
+				      ctx->main_key.nrounds,
+				      dst, src, count, &tweak);
+			kernel_neon_end();
+			dst += count;
+			src += count;
+			nbytes -= count;
+		}
+
+		/* Handle any remainder with generic code */
+		while (nbytes >= sizeof(tweak)) {
+			le128_xor((le128 *)dst, (const le128 *)src, &tweak);
+			(*crypt_one)(&ctx->main_key, dst, dst);
+			le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
+			gf128mul_x_ble(&tweak, &tweak);
+
+			dst += sizeof(tweak);
+			src += sizeof(tweak);
+			nbytes -= sizeof(tweak);
+		}
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+
+static int speck128_xts_encrypt(struct skcipher_request *req)
+{
+	return __speck128_xts_crypt(req, crypto_speck128_encrypt,
+				    speck128_xts_encrypt_neon);
+}
+
+static int speck128_xts_decrypt(struct skcipher_request *req)
+{
+	return __speck128_xts_crypt(req, crypto_speck128_decrypt,
+				    speck128_xts_decrypt_neon);
+}
+
+static int speck128_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			       unsigned int keylen)
+{
+	struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	keylen /= 2;
+
+	err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
+	if (err)
+		return err;
+
+	return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+/* Speck64 */
+
+struct speck64_xts_tfm_ctx {
+	struct speck64_tfm_ctx main_key;
+	struct speck64_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
+					 void *dst, const void *src,
+					 unsigned int nbytes, void *tweak);
+
+asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
+					 void *dst, const void *src,
+					 unsigned int nbytes, void *tweak);
+
+typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
+				    u8 *, const u8 *);
+typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
+					 const void *, unsigned int, void *);
+
+static __always_inline int
+__speck64_xts_crypt(struct skcipher_request *req, speck64_crypt_one_t crypt_one,
+		    speck64_xts_crypt_many_t crypt_many)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	__le64 tweak;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, true);
+
+	crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+		u8 *dst = walk.dst.virt.addr;
+		const u8 *src = walk.src.virt.addr;
+
+		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+			unsigned int count;
+
+			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+			kernel_neon_begin();
+			(*crypt_many)(ctx->main_key.round_keys,
+				      ctx->main_key.nrounds,
+				      dst, src, count, &tweak);
+			kernel_neon_end();
+			dst += count;
+			src += count;
+			nbytes -= count;
+		}
+
+		/* Handle any remainder with generic code */
+		while (nbytes >= sizeof(tweak)) {
+			*(__le64 *)dst = *(__le64 *)src ^ tweak;
+			(*crypt_one)(&ctx->main_key, dst, dst);
+			*(__le64 *)dst ^= tweak;
+			tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
+					    ((tweak & cpu_to_le64(1ULL << 63)) ?
+					     0x1B : 0));
+			dst += sizeof(tweak);
+			src += sizeof(tweak);
+			nbytes -= sizeof(tweak);
+		}
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	return err;
+}
+
+static int speck64_xts_encrypt(struct skcipher_request *req)
+{
+	return __speck64_xts_crypt(req, crypto_speck64_encrypt,
+				   speck64_xts_encrypt_neon);
+}
+
+static int speck64_xts_decrypt(struct skcipher_request *req)
+{
+	return __speck64_xts_crypt(req, crypto_speck64_decrypt,
+				   speck64_xts_decrypt_neon);
+}
+
+static int speck64_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = xts_verify_key(tfm, key, keylen);
+	if (err)
+		return err;
+
+	keylen /= 2;
+
+	err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
+	if (err)
+		return err;
+
+	return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+static struct skcipher_alg speck_algs[] = {
+	{
+		.base.cra_name		= "xts(speck128)",
+		.base.cra_driver_name	= "xts-speck128-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= SPECK128_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct speck128_xts_tfm_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SPECK128_128_KEY_SIZE,
+		.max_keysize		= 2 * SPECK128_256_KEY_SIZE,
+		.ivsize			= SPECK128_BLOCK_SIZE,
+		.walksize		= SPECK_NEON_CHUNK_SIZE,
+		.setkey			= speck128_xts_setkey,
+		.encrypt		= speck128_xts_encrypt,
+		.decrypt		= speck128_xts_decrypt,
+	}, {
+		.base.cra_name		= "xts(speck64)",
+		.base.cra_driver_name	= "xts-speck64-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= SPECK64_BLOCK_SIZE,
+		.base.cra_ctxsize	= sizeof(struct speck64_xts_tfm_ctx),
+		.base.cra_alignmask	= 7,
+		.base.cra_module	= THIS_MODULE,
+		.min_keysize		= 2 * SPECK64_96_KEY_SIZE,
+		.max_keysize		= 2 * SPECK64_128_KEY_SIZE,
+		.ivsize			= SPECK64_BLOCK_SIZE,
+		.walksize		= SPECK_NEON_CHUNK_SIZE,
+		.setkey			= speck64_xts_setkey,
+		.encrypt		= speck64_xts_encrypt,
+		.decrypt		= speck64_xts_decrypt,
+	}
+};
+
+static int __init speck_neon_module_init(void)
+{
+	if (!(elf_hwcap & HWCAP_NEON))
+		return -ENODEV;
+	return crypto_register_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+static void __exit speck_neon_module_exit(void)
+{
+	crypto_unregister_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+module_init(speck_neon_module_init);
+module_exit(speck_neon_module_exit);
+
+MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("xts(speck128)");
+MODULE_ALIAS_CRYPTO("xts-speck128-neon");
+MODULE_ALIAS_CRYPTO("xts(speck64)");
+MODULE_ALIAS_CRYPTO("xts-speck64-neon");