crypto: arm64/crc32 - accelerated support based on x86 SSE implementation

This is a combination of the the Intel algorithm implemented using SSE
and PCLMULQDQ instructions from arch/x86/crypto/crc32-pclmul_asm.S, and
the new CRC32 extensions introduced for both 32-bit and 64-bit ARM in
version 8 of the architecture. Two versions of the above combo are
provided, one for CRC32 and one for CRC32C.

The PMULL/NEON algorithm is faster, but operates on blocks of at least
64 bytes, and on multiples of 16 bytes only. For the remaining input,
or for all input on systems that lack the PMULL 64x64->128 instructions,
the CRC32 instructions will be used.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 212 insertions, 0 deletions

diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c
new file mode 100644
index 000000000000..8594127d5e01
--- /dev/null
+++ b/arch/arm64/crypto/crc32-ce-glue.c
@@ -0,0 +1,212 @@
+/*
+ * Accelerated CRC32(C) 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/crc32.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/hash.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/unaligned.h>
+
+#define PMULL_MIN_LEN		64L	/* minimum size of buffer
+					 * for crc32_pmull_le_16 */
+#define SCALE_F			16L	/* size of NEON register */
+
+asmlinkage u32 crc32_pmull_le(const u8 buf[], u64 len, u32 init_crc);
+asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], size_t len);
+
+asmlinkage u32 crc32c_pmull_le(const u8 buf[], u64 len, u32 init_crc);
+asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], size_t len);
+
+static u32 (*fallback_crc32)(u32 init_crc, const u8 buf[], size_t len);
+static u32 (*fallback_crc32c)(u32 init_crc, const u8 buf[], size_t len);
+
+static int crc32_pmull_cra_init(struct crypto_tfm *tfm)
+{
+	u32 *key = crypto_tfm_ctx(tfm);
+
+	*key = 0;
+	return 0;
+}
+
+static int crc32c_pmull_cra_init(struct crypto_tfm *tfm)
+{
+	u32 *key = crypto_tfm_ctx(tfm);
+
+	*key = ~0;
+	return 0;
+}
+
+static int crc32_pmull_setkey(struct crypto_shash *hash, const u8 *key,
+			      unsigned int keylen)
+{
+	u32 *mctx = crypto_shash_ctx(hash);
+
+	if (keylen != sizeof(u32)) {
+		crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	*mctx = le32_to_cpup((__le32 *)key);
+	return 0;
+}
+
+static int crc32_pmull_init(struct shash_desc *desc)
+{
+	u32 *mctx = crypto_shash_ctx(desc->tfm);
+	u32 *crc = shash_desc_ctx(desc);
+
+	*crc = *mctx;
+	return 0;
+}
+
+static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int length)
+{
+	u32 *crc = shash_desc_ctx(desc);
+	unsigned int l;
+
+	if ((u64)data % SCALE_F) {
+		l = min_t(u32, length, SCALE_F - ((u64)data % SCALE_F));
+
+		*crc = fallback_crc32(*crc, data, l);
+
+		data += l;
+		length -= l;
+	}
+
+	if (length >= PMULL_MIN_LEN) {
+		l = round_down(length, SCALE_F);
+
+		kernel_neon_begin_partial(10);
+		*crc = crc32_pmull_le(data, l, *crc);
+		kernel_neon_end();
+
+		data += l;
+		length -= l;
+	}
+
+	if (length > 0)
+		*crc = fallback_crc32(*crc, data, length);
+
+	return 0;
+}
+
+static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int length)
+{
+	u32 *crc = shash_desc_ctx(desc);
+	unsigned int l;
+
+	if ((u64)data % SCALE_F) {
+		l = min_t(u32, length, SCALE_F - ((u64)data % SCALE_F));
+
+		*crc = fallback_crc32c(*crc, data, l);
+
+		data += l;
+		length -= l;
+	}
+
+	if (length >= PMULL_MIN_LEN) {
+		l = round_down(length, SCALE_F);
+
+		kernel_neon_begin_partial(10);
+		*crc = crc32c_pmull_le(data, l, *crc);
+		kernel_neon_end();
+
+		data += l;
+		length -= l;
+	}
+
+	if (length > 0) {
+		*crc = fallback_crc32c(*crc, data, length);
+	}
+
+	return 0;
+}
+
+static int crc32_pmull_final(struct shash_desc *desc, u8 *out)
+{
+	u32 *crc = shash_desc_ctx(desc);
+
+	put_unaligned_le32(*crc, out);
+	return 0;
+}
+
+static int crc32c_pmull_final(struct shash_desc *desc, u8 *out)
+{
+	u32 *crc = shash_desc_ctx(desc);
+
+	put_unaligned_le32(~*crc, out);
+	return 0;
+}
+
+static struct shash_alg crc32_pmull_algs[] = { {
+	.setkey			= crc32_pmull_setkey,
+	.init			= crc32_pmull_init,
+	.update			= crc32_pmull_update,
+	.final			= crc32_pmull_final,
+	.descsize		= sizeof(u32),
+	.digestsize		= sizeof(u32),
+
+	.base.cra_ctxsize	= sizeof(u32),
+	.base.cra_init		= crc32_pmull_cra_init,
+	.base.cra_name		= "crc32",
+	.base.cra_driver_name	= "crc32-arm64-ce",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= 1,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.setkey			= crc32_pmull_setkey,
+	.init			= crc32_pmull_init,
+	.update			= crc32c_pmull_update,
+	.final			= crc32c_pmull_final,
+	.descsize		= sizeof(u32),
+	.digestsize		= sizeof(u32),
+
+	.base.cra_ctxsize	= sizeof(u32),
+	.base.cra_init		= crc32c_pmull_cra_init,
+	.base.cra_name		= "crc32c",
+	.base.cra_driver_name	= "crc32c-arm64-ce",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= 1,
+	.base.cra_module	= THIS_MODULE,
+} };
+
+static int __init crc32_pmull_mod_init(void)
+{
+	if (elf_hwcap & HWCAP_CRC32) {
+		fallback_crc32 = crc32_armv8_le;
+		fallback_crc32c = crc32c_armv8_le;
+	} else {
+		fallback_crc32 = crc32_le;
+		fallback_crc32c = __crc32c_le;
+	}
+
+	return crypto_register_shashes(crc32_pmull_algs,
+				       ARRAY_SIZE(crc32_pmull_algs));
+}
+
+static void __exit crc32_pmull_mod_exit(void)
+{
+	crypto_unregister_shashes(crc32_pmull_algs,
+				  ARRAY_SIZE(crc32_pmull_algs));
+}
+
+module_cpu_feature_match(PMULL, crc32_pmull_mod_init);
+module_exit(crc32_pmull_mod_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");