crypto: arm/crct10dif - port x86 SSE implementation to ARM

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/arm/crypto/Kconfig

@@ -120,4 +120,9 @@ config CRYPTO_GHASH_ARM_CE
 	  that uses the 64x64 to 128 bit polynomial multiplication (vmull.p64)
 	  that is part of the ARMv8 Crypto Extensions
 
+config CRYPTO_CRCT10DIF_ARM_CE
+	tristate "CRCT10DIF digest algorithm using PMULL instructions"
+	depends on KERNEL_MODE_NEON && CRC_T10DIF
+	select CRYPTO_HASH
+
 endif

arch/arm/crypto/Makefile

@@ -13,6 +13,7 @@ ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA2_ARM_CE) += sha2-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_GHASH_ARM_CE) += ghash-arm-ce.o
+ce-obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM_CE) += crct10dif-arm-ce.o
 
 ifneq ($(ce-obj-y)$(ce-obj-m),)
 ifeq ($(call as-instr,.fpu crypto-neon-fp-armv8,y,n),y)
@@ -36,6 +37,7 @@ sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
+crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)

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

+/*
+ * Accelerated CRC-T10DIF using ARM 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/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>
+#include <asm/simd.h>
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
+
+asmlinkage u16 crc_t10dif_pmull(u16 init_crc, const u8 buf[], u32 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 (!may_use_simd()) {
+		*crc = crc_t10dif_generic(*crc, data, length);
+	} else {
+		if (unlikely((u32)data % CRC_T10DIF_PMULL_CHUNK_SIZE)) {
+			l = min_t(u32, length, CRC_T10DIF_PMULL_CHUNK_SIZE -
+				  ((u32)data % CRC_T10DIF_PMULL_CHUNK_SIZE));
+
+			*crc = crc_t10dif_generic(*crc, data, l);
+
+			length -= l;
+			data += l;
+		}
+		if (length > 0) {
+			kernel_neon_begin();
+			*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-arm-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)
+{
+	if (!(elf_hwcap2 & HWCAP2_PMULL))
+		return -ENODEV;
+
+	return crypto_register_shash(&crc_t10dif_alg);
+}
+
+static void __exit crc_t10dif_mod_exit(void)
+{
+	crypto_unregister_shash(&crc_t10dif_alg);
+}
+
+module_init(crc_t10dif_mod_init);
+module_exit(crc_t10dif_mod_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("crct10dif");