From 1d481f1cd8925bd92387983ea1245a0ea0f16d32 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 5 Dec 2016 18:42:26 +0000 Subject: 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 Signed-off-by: Herbert Xu --- arch/arm/crypto/crct10dif-ce-glue.c | 101 ++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 arch/arm/crypto/crct10dif-ce-glue.c (limited to 'arch/arm/crypto/crct10dif-ce-glue.c') diff --git a/arch/arm/crypto/crct10dif-ce-glue.c b/arch/arm/crypto/crct10dif-ce-glue.c new file mode 100644 index 000000000000..d428355cf38d --- /dev/null +++ b/arch/arm/crypto/crct10dif-ce-glue.c @@ -0,0 +1,101 @@ +/* + * Accelerated CRC-T10DIF using ARM NEON and Crypto Extensions instructions + * + * Copyright (C) 2016 Linaro Ltd + * + * 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 +#include +#include +#include +#include + +#include + +#include +#include + +#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 "); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("crct10dif"); -- cgit v1.2.3