The arm64 kernel will shortly disallow nested kernel mode NEON, so add a fallback to scalar C code that can be invoked in that case. Signed-off-by: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx> --- arch/arm64/crypto/Kconfig | 3 +- arch/arm64/crypto/ghash-ce-glue.c | 49 ++++++++++++++++---- 2 files changed, 43 insertions(+), 9 deletions(-) diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index d92293747d63..7d75a363e317 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -28,8 +28,9 @@ config CRYPTO_SHA2_ARM64_CE config CRYPTO_GHASH_ARM64_CE tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions" - depends on ARM64 && KERNEL_MODE_NEON + depends on KERNEL_MODE_NEON select CRYPTO_HASH + select CRYPTO_GF128MUL config CRYPTO_CRCT10DIF_ARM64_CE tristate "CRCT10DIF digest algorithm using PMULL instructions" diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 833ec1e3f3e9..3e1a778b181a 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -1,7 +1,7 @@ /* * Accelerated GHASH implementation with ARMv8 PMULL instructions. * - * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@xxxxxxxxxx> + * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@xxxxxxxxxx> * * 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 @@ -9,7 +9,9 @@ */ #include <asm/neon.h> +#include <asm/simd.h> #include <asm/unaligned.h> +#include <crypto/gf128mul.h> #include <crypto/internal/hash.h> #include <linux/cpufeature.h> #include <linux/crypto.h> @@ -25,6 +27,7 @@ MODULE_LICENSE("GPL v2"); struct ghash_key { u64 a; u64 b; + be128 k; }; struct ghash_desc_ctx { @@ -44,6 +47,36 @@ static int ghash_init(struct shash_desc *desc) return 0; } +static void ghash_do_update(int blocks, u64 dg[], const char *src, + struct ghash_key *key, const char *head) +{ + if (may_use_simd()) { + kernel_neon_begin(); + pmull_ghash_update(blocks, dg, src, key, head); + kernel_neon_end(); + } else { + be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) }; + + do { + const u8 *in = src; + + if (head) { + in = head; + blocks++; + head = NULL; + } else { + src += GHASH_BLOCK_SIZE; + } + + crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE); + gf128mul_lle(&dst, &key->k); + } while (--blocks); + + dg[0] = be64_to_cpu(dst.b); + dg[1] = be64_to_cpu(dst.a); + } +} + static int ghash_update(struct shash_desc *desc, const u8 *src, unsigned int len) { @@ -67,10 +100,9 @@ static int ghash_update(struct shash_desc *desc, const u8 *src, blocks = len / GHASH_BLOCK_SIZE; len %= GHASH_BLOCK_SIZE; - kernel_neon_begin_partial(8); - pmull_ghash_update(blocks, ctx->digest, src, key, - partial ? ctx->buf : NULL); - kernel_neon_end(); + ghash_do_update(blocks, ctx->digest, src, key, + partial ? ctx->buf : NULL); + src += blocks * GHASH_BLOCK_SIZE; partial = 0; } @@ -89,9 +121,7 @@ static int ghash_final(struct shash_desc *desc, u8 *dst) memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial); - kernel_neon_begin_partial(8); - pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL); - kernel_neon_end(); + ghash_do_update(1, ctx->digest, ctx->buf, key, NULL); } put_unaligned_be64(ctx->digest[1], dst); put_unaligned_be64(ctx->digest[0], dst + 8); @@ -111,6 +141,9 @@ static int ghash_setkey(struct crypto_shash *tfm, return -EINVAL; } + /* needed for the fallback */ + memcpy(&key->k, inkey, GHASH_BLOCK_SIZE); + /* perform multiplication by 'x' in GF(2^128) */ b = get_unaligned_be64(inkey); a = get_unaligned_be64(inkey + 8); -- 2.7.4