Commit 5d3d9c8b authored by Ard Biesheuvel's avatar Ard Biesheuvel Committed by Herbert Xu

crypto: arm64/crc32 - merge CRC32 and PMULL instruction based drivers

The PMULL based CRC32 implementation already contains code based on the
separate, optional CRC32 instructions to fallback to when operating on
small quantities of data. We can expose these routines directly on systems
that lack the 64x64 PMULL instructions but do implement the CRC32 ones,
which makes the driver that is based solely on those CRC32 instructions
redundant. So remove it.

Note that this aligns arm64 with ARM, whose accelerated CRC32 driver
also combines the CRC32 extension based and the PMULL based versions.
Signed-off-by: default avatarArd Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: default avatarMatthias Brugger <mbrugger@suse.com>
Signed-off-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
parent 1a20b966
...@@ -516,4 +516,3 @@ CONFIG_CRYPTO_GHASH_ARM64_CE=y ...@@ -516,4 +516,3 @@ CONFIG_CRYPTO_GHASH_ARM64_CE=y
CONFIG_CRYPTO_AES_ARM64_CE_CCM=y CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
CONFIG_CRYPTO_AES_ARM64_CE_BLK=y CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
# CONFIG_CRYPTO_AES_ARM64_NEON_BLK is not set # CONFIG_CRYPTO_AES_ARM64_NEON_BLK is not set
CONFIG_CRYPTO_CRC32_ARM64=y
...@@ -37,8 +37,8 @@ config CRYPTO_CRCT10DIF_ARM64_CE ...@@ -37,8 +37,8 @@ config CRYPTO_CRCT10DIF_ARM64_CE
select CRYPTO_HASH select CRYPTO_HASH
config CRYPTO_CRC32_ARM64_CE config CRYPTO_CRC32_ARM64_CE
tristate "CRC32 and CRC32C digest algorithms using PMULL instructions" tristate "CRC32 and CRC32C digest algorithms using ARMv8 extensions"
depends on KERNEL_MODE_NEON && CRC32 depends on CRC32
select CRYPTO_HASH select CRYPTO_HASH
config CRYPTO_AES_ARM64 config CRYPTO_AES_ARM64
...@@ -71,11 +71,6 @@ config CRYPTO_AES_ARM64_NEON_BLK ...@@ -71,11 +71,6 @@ config CRYPTO_AES_ARM64_NEON_BLK
select CRYPTO_AES select CRYPTO_AES
select CRYPTO_SIMD select CRYPTO_SIMD
config CRYPTO_CRC32_ARM64
tristate "CRC32 and CRC32C using optional ARMv8 instructions"
depends on ARM64
select CRYPTO_HASH
config CRYPTO_CHACHA20_NEON config CRYPTO_CHACHA20_NEON
tristate "NEON accelerated ChaCha20 symmetric cipher" tristate "NEON accelerated ChaCha20 symmetric cipher"
depends on KERNEL_MODE_NEON depends on KERNEL_MODE_NEON
......
...@@ -55,10 +55,6 @@ AFLAGS_aes-neon.o := -DINTERLEAVE=4 ...@@ -55,10 +55,6 @@ AFLAGS_aes-neon.o := -DINTERLEAVE=4
CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS
obj-$(CONFIG_CRYPTO_CRC32_ARM64) += crc32-arm64.o
CFLAGS_crc32-arm64.o := -mcpu=generic+crc
$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE $(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
$(call if_changed_rule,cc_o_c) $(call if_changed_rule,cc_o_c)
......
/*
* crc32-arm64.c - CRC32 and CRC32C using optional ARMv8 instructions
*
* Module based on crypto/crc32c_generic.c
*
* CRC32 loop taken from Ed Nevill's Hadoop CRC patch
* http://mail-archives.apache.org/mod_mbox/hadoop-common-dev/201406.mbox/%3C1403687030.3355.19.camel%40localhost.localdomain%3E
*
* Using inline assembly instead of intrinsics in order to be backwards
* compatible with older compilers.
*
* Copyright (C) 2014 Linaro Ltd <yazen.ghannam@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/unaligned/access_ok.h>
#include <linux/cpufeature.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/string.h>
#include <crypto/internal/hash.h>
MODULE_AUTHOR("Yazen Ghannam <yazen.ghannam@linaro.org>");
MODULE_DESCRIPTION("CRC32 and CRC32C using optional ARMv8 instructions");
MODULE_LICENSE("GPL v2");
#define CRC32X(crc, value) __asm__("crc32x %w[c], %w[c], %x[v]":[c]"+r"(crc):[v]"r"(value))
#define CRC32W(crc, value) __asm__("crc32w %w[c], %w[c], %w[v]":[c]"+r"(crc):[v]"r"(value))
#define CRC32H(crc, value) __asm__("crc32h %w[c], %w[c], %w[v]":[c]"+r"(crc):[v]"r"(value))
#define CRC32B(crc, value) __asm__("crc32b %w[c], %w[c], %w[v]":[c]"+r"(crc):[v]"r"(value))
#define CRC32CX(crc, value) __asm__("crc32cx %w[c], %w[c], %x[v]":[c]"+r"(crc):[v]"r"(value))
#define CRC32CW(crc, value) __asm__("crc32cw %w[c], %w[c], %w[v]":[c]"+r"(crc):[v]"r"(value))
#define CRC32CH(crc, value) __asm__("crc32ch %w[c], %w[c], %w[v]":[c]"+r"(crc):[v]"r"(value))
#define CRC32CB(crc, value) __asm__("crc32cb %w[c], %w[c], %w[v]":[c]"+r"(crc):[v]"r"(value))
static u32 crc32_arm64_le_hw(u32 crc, const u8 *p, unsigned int len)
{
s64 length = len;
while ((length -= sizeof(u64)) >= 0) {
CRC32X(crc, get_unaligned_le64(p));
p += sizeof(u64);
}
/* The following is more efficient than the straight loop */
if (length & sizeof(u32)) {
CRC32W(crc, get_unaligned_le32(p));
p += sizeof(u32);
}
if (length & sizeof(u16)) {
CRC32H(crc, get_unaligned_le16(p));
p += sizeof(u16);
}
if (length & sizeof(u8))
CRC32B(crc, *p);
return crc;
}
static u32 crc32c_arm64_le_hw(u32 crc, const u8 *p, unsigned int len)
{
s64 length = len;
while ((length -= sizeof(u64)) >= 0) {
CRC32CX(crc, get_unaligned_le64(p));
p += sizeof(u64);
}
/* The following is more efficient than the straight loop */
if (length & sizeof(u32)) {
CRC32CW(crc, get_unaligned_le32(p));
p += sizeof(u32);
}
if (length & sizeof(u16)) {
CRC32CH(crc, get_unaligned_le16(p));
p += sizeof(u16);
}
if (length & sizeof(u8))
CRC32CB(crc, *p);
return crc;
}
#define CHKSUM_BLOCK_SIZE 1
#define CHKSUM_DIGEST_SIZE 4
struct chksum_ctx {
u32 key;
};
struct chksum_desc_ctx {
u32 crc;
};
static int chksum_init(struct shash_desc *desc)
{
struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
ctx->crc = mctx->key;
return 0;
}
/*
* Setting the seed allows arbitrary accumulators and flexible XOR policy
* If your algorithm starts with ~0, then XOR with ~0 before you set
* the seed.
*/
static int chksum_setkey(struct crypto_shash *tfm, const u8 *key,
unsigned int keylen)
{
struct chksum_ctx *mctx = crypto_shash_ctx(tfm);
if (keylen != sizeof(mctx->key)) {
crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
return -EINVAL;
}
mctx->key = get_unaligned_le32(key);
return 0;
}
static int chksum_update(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
ctx->crc = crc32_arm64_le_hw(ctx->crc, data, length);
return 0;
}
static int chksumc_update(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
ctx->crc = crc32c_arm64_le_hw(ctx->crc, data, length);
return 0;
}
static int chksum_final(struct shash_desc *desc, u8 *out)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
put_unaligned_le32(ctx->crc, out);
return 0;
}
static int chksumc_final(struct shash_desc *desc, u8 *out)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
put_unaligned_le32(~ctx->crc, out);
return 0;
}
static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out)
{
put_unaligned_le32(crc32_arm64_le_hw(crc, data, len), out);
return 0;
}
static int __chksumc_finup(u32 crc, const u8 *data, unsigned int len, u8 *out)
{
put_unaligned_le32(~crc32c_arm64_le_hw(crc, data, len), out);
return 0;
}
static int chksum_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
return __chksum_finup(ctx->crc, data, len, out);
}
static int chksumc_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
return __chksumc_finup(ctx->crc, data, len, out);
}
static int chksum_digest(struct shash_desc *desc, const u8 *data,
unsigned int length, u8 *out)
{
struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
return __chksum_finup(mctx->key, data, length, out);
}
static int chksumc_digest(struct shash_desc *desc, const u8 *data,
unsigned int length, u8 *out)
{
struct chksum_ctx *mctx = crypto_shash_ctx(desc->tfm);
return __chksumc_finup(mctx->key, data, length, out);
}
static int crc32_cra_init(struct crypto_tfm *tfm)
{
struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
mctx->key = 0;
return 0;
}
static int crc32c_cra_init(struct crypto_tfm *tfm)
{
struct chksum_ctx *mctx = crypto_tfm_ctx(tfm);
mctx->key = ~0;
return 0;
}
static struct shash_alg crc32_alg = {
.digestsize = CHKSUM_DIGEST_SIZE,
.setkey = chksum_setkey,
.init = chksum_init,
.update = chksum_update,
.final = chksum_final,
.finup = chksum_finup,
.digest = chksum_digest,
.descsize = sizeof(struct chksum_desc_ctx),
.base = {
.cra_name = "crc32",
.cra_driver_name = "crc32-arm64-hw",
.cra_priority = 300,
.cra_blocksize = CHKSUM_BLOCK_SIZE,
.cra_alignmask = 0,
.cra_ctxsize = sizeof(struct chksum_ctx),
.cra_module = THIS_MODULE,
.cra_init = crc32_cra_init,
}
};
static struct shash_alg crc32c_alg = {
.digestsize = CHKSUM_DIGEST_SIZE,
.setkey = chksum_setkey,
.init = chksum_init,
.update = chksumc_update,
.final = chksumc_final,
.finup = chksumc_finup,
.digest = chksumc_digest,
.descsize = sizeof(struct chksum_desc_ctx),
.base = {
.cra_name = "crc32c",
.cra_driver_name = "crc32c-arm64-hw",
.cra_priority = 300,
.cra_blocksize = CHKSUM_BLOCK_SIZE,
.cra_alignmask = 0,
.cra_ctxsize = sizeof(struct chksum_ctx),
.cra_module = THIS_MODULE,
.cra_init = crc32c_cra_init,
}
};
static int __init crc32_mod_init(void)
{
int err;
err = crypto_register_shash(&crc32_alg);
if (err)
return err;
err = crypto_register_shash(&crc32c_alg);
if (err) {
crypto_unregister_shash(&crc32_alg);
return err;
}
return 0;
}
static void __exit crc32_mod_exit(void)
{
crypto_unregister_shash(&crc32_alg);
crypto_unregister_shash(&crc32c_alg);
}
module_cpu_feature_match(CRC32, crc32_mod_init);
module_exit(crc32_mod_exit);
...@@ -72,6 +72,24 @@ static int crc32_pmull_init(struct shash_desc *desc) ...@@ -72,6 +72,24 @@ static int crc32_pmull_init(struct shash_desc *desc)
return 0; return 0;
} }
static int crc32_update(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
u32 *crc = shash_desc_ctx(desc);
*crc = crc32_armv8_le(*crc, data, length);
return 0;
}
static int crc32c_update(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
u32 *crc = shash_desc_ctx(desc);
*crc = crc32c_armv8_le(*crc, data, length);
return 0;
}
static int crc32_pmull_update(struct shash_desc *desc, const u8 *data, static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
unsigned int length) unsigned int length)
{ {
...@@ -156,7 +174,7 @@ static int crc32c_pmull_final(struct shash_desc *desc, u8 *out) ...@@ -156,7 +174,7 @@ static int crc32c_pmull_final(struct shash_desc *desc, u8 *out)
static struct shash_alg crc32_pmull_algs[] = { { static struct shash_alg crc32_pmull_algs[] = { {
.setkey = crc32_pmull_setkey, .setkey = crc32_pmull_setkey,
.init = crc32_pmull_init, .init = crc32_pmull_init,
.update = crc32_pmull_update, .update = crc32_update,
.final = crc32_pmull_final, .final = crc32_pmull_final,
.descsize = sizeof(u32), .descsize = sizeof(u32),
.digestsize = sizeof(u32), .digestsize = sizeof(u32),
...@@ -171,7 +189,7 @@ static struct shash_alg crc32_pmull_algs[] = { { ...@@ -171,7 +189,7 @@ static struct shash_alg crc32_pmull_algs[] = { {
}, { }, {
.setkey = crc32_pmull_setkey, .setkey = crc32_pmull_setkey,
.init = crc32_pmull_init, .init = crc32_pmull_init,
.update = crc32c_pmull_update, .update = crc32c_update,
.final = crc32c_pmull_final, .final = crc32c_pmull_final,
.descsize = sizeof(u32), .descsize = sizeof(u32),
.digestsize = sizeof(u32), .digestsize = sizeof(u32),
...@@ -187,6 +205,10 @@ static struct shash_alg crc32_pmull_algs[] = { { ...@@ -187,6 +205,10 @@ static struct shash_alg crc32_pmull_algs[] = { {
static int __init crc32_pmull_mod_init(void) static int __init crc32_pmull_mod_init(void)
{ {
if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_PMULL)) {
crc32_pmull_algs[0].update = crc32_pmull_update;
crc32_pmull_algs[1].update = crc32c_pmull_update;
if (elf_hwcap & HWCAP_CRC32) { if (elf_hwcap & HWCAP_CRC32) {
fallback_crc32 = crc32_armv8_le; fallback_crc32 = crc32_armv8_le;
fallback_crc32c = crc32c_armv8_le; fallback_crc32c = crc32c_armv8_le;
...@@ -194,7 +216,9 @@ static int __init crc32_pmull_mod_init(void) ...@@ -194,7 +216,9 @@ static int __init crc32_pmull_mod_init(void)
fallback_crc32 = crc32_le; fallback_crc32 = crc32_le;
fallback_crc32c = __crc32c_le; fallback_crc32c = __crc32c_le;
} }
} else if (!(elf_hwcap & HWCAP_CRC32)) {
return -ENODEV;
}
return crypto_register_shashes(crc32_pmull_algs, return crypto_register_shashes(crc32_pmull_algs,
ARRAY_SIZE(crc32_pmull_algs)); ARRAY_SIZE(crc32_pmull_algs));
} }
...@@ -205,7 +229,12 @@ static void __exit crc32_pmull_mod_exit(void) ...@@ -205,7 +229,12 @@ static void __exit crc32_pmull_mod_exit(void)
ARRAY_SIZE(crc32_pmull_algs)); ARRAY_SIZE(crc32_pmull_algs));
} }
module_cpu_feature_match(PMULL, crc32_pmull_mod_init); static const struct cpu_feature crc32_cpu_feature[] = {
{ cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { }
};
MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature);
module_init(crc32_pmull_mod_init);
module_exit(crc32_pmull_mod_exit); module_exit(crc32_pmull_mod_exit);
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment