crypto: arm64/crct10dif - port x86 SSE implementation to arm64

This is a transliteration of the Intel algorithm implemented
using SSE and PCLMULQDQ instructions that resides in the file
arch/x86/crypto/crct10dif-pcl-asm_64.S, but simplified to only
operate on buffers that are 16 byte aligned (but of any size)
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm64/crypto/Kconfig

@@ -31,6 +31,11 @@ config CRYPTO_GHASH_ARM64_CE
 	depends on ARM64 && KERNEL_MODE_NEON
 	select CRYPTO_HASH
 
+config CRYPTO_CRCT10DIF_ARM64_CE
+	tristate "CRCT10DIF digest algorithm using PMULL instructions"
+	depends on KERNEL_MODE_NEON && CRC_T10DIF
+	select CRYPTO_HASH
+
 config CRYPTO_AES_ARM64_CE
 	tristate "AES core cipher using ARMv8 Crypto Extensions"
 	depends on ARM64 && KERNEL_MODE_NEON

arch/arm64/crypto/Makefile

@@ -17,6 +17,9 @@ sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
 obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
 ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
 
+obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM64_CE) += crct10dif-ce.o
+crct10dif-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o
+
 obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
 CFLAGS_aes-ce-cipher.o += -march=armv8-a+crypto
 

arch/arm64/crypto/crct10dif-ce-glue.c

+/*
+ * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/cpufeature.h>
+#include <linux/crc-t10dif.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/hash.h>
+
+#include <asm/neon.h>
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
+
+asmlinkage u16 crc_t10dif_pmull(u16 init_crc, const u8 buf[], u64 len);
+
+static int crct10dif_init(struct shash_desc *desc)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	*crc = 0;
+	return 0;
+}
+
+static int crct10dif_update(struct shash_desc *desc, const u8 *data,
+			    unsigned int length)
+{
+	u16 *crc = shash_desc_ctx(desc);
+	unsigned int l;
+
+	if (unlikely((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE)) {
+		l = min_t(u32, length, CRC_T10DIF_PMULL_CHUNK_SIZE -
+			  ((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE));
+
+		*crc = crc_t10dif_generic(*crc, data, l);
+
+		length -= l;
+		data += l;
+	}
+
+	if (length > 0) {
+		kernel_neon_begin_partial(14);
+		*crc = crc_t10dif_pmull(*crc, data, length);
+		kernel_neon_end();
+	}
+
+	return 0;
+}
+
+static int crct10dif_final(struct shash_desc *desc, u8 *out)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	*(u16 *)out = *crc;
+	return 0;
+}
+
+static struct shash_alg crc_t10dif_alg = {
+	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
+	.init			= crct10dif_init,
+	.update			= crct10dif_update,
+	.final			= crct10dif_final,
+	.descsize		= CRC_T10DIF_DIGEST_SIZE,
+
+	.base.cra_name		= "crct10dif",
+	.base.cra_driver_name	= "crct10dif-arm64-ce",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+};
+
+static int __init crc_t10dif_mod_init(void)
+{
+	return crypto_register_shash(&crc_t10dif_alg);
+}
+
+static void __exit crc_t10dif_mod_exit(void)
+{
+	crypto_unregister_shash(&crc_t10dif_alg);
+}
+
+module_cpu_feature_match(PMULL, crc_t10dif_mod_init);
+module_exit(crc_t10dif_mod_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");