crypto: riscv - add vector crypto accelerated SM3

Add an implementation of SM3 using the Zvksh extension.  The assembly
code is derived from OpenSSL code (openssl/openssl#21923) that was
dual-licensed so that it could be reused in the kernel.  Nevertheless,
the assembly has been significantly reworked for integration with the
kernel, for example by using a regular .S file instead of the so-called
perlasm, using the assembler instead of bare '.inst', and greatly
reducing code duplication.

Co-developed-by: Christoph Müllner <christoph.muellner@vrull.eu>
Signed-off-by: Christoph Müllner <christoph.muellner@vrull.eu>
Co-developed-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Signed-off-by: Heiko Stuebner <heiko.stuebner@vrull.eu>
Signed-off-by: Jerry Shih <jerry.shih@sifive.com>
Co-developed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Link: https://lore.kernel.org/r/20240122002024.27477-10-ebiggers@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/crypto/Kconfig

@@ -61,4 +61,16 @@ config CRYPTO_SHA512_RISCV64
 	  - Zvknhb vector crypto extension
 	  - Zvkb vector crypto extension
 
+config CRYPTO_SM3_RISCV64
+	tristate "Hash functions: SM3 (ShangMi 3)"
+	depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO
+	select CRYPTO_HASH
+	select CRYPTO_SM3
+	help
+	  SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012)
+
+	  Architecture: riscv64 using:
+	  - Zvksh vector crypto extension
+	  - Zvkb vector crypto extension
+
 endmenu

arch/riscv/crypto/Makefile

@@ -15,3 +15,6 @@ sha256-riscv64-y := sha256-riscv64-glue.o sha256-riscv64-zvknha_or_zvknhb-zvkb.o
 
 obj-$(CONFIG_CRYPTO_SHA512_RISCV64) += sha512-riscv64.o
 sha512-riscv64-y := sha512-riscv64-glue.o sha512-riscv64-zvknhb-zvkb.o
+
+obj-$(CONFIG_CRYPTO_SM3_RISCV64) += sm3-riscv64.o
+sm3-riscv64-y := sm3-riscv64-glue.o sm3-riscv64-zvksh-zvkb.o

arch/riscv/crypto/sm3-riscv64-glue.c

@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SM3 using the RISC-V vector crypto extensions
+ *
+ * Copyright (C) 2023 VRULL GmbH
+ * Author: Heiko Stuebner <heiko.stuebner@vrull.eu>
+ *
+ * Copyright (C) 2023 SiFive, Inc.
+ * Author: Jerry Shih <jerry.shih@sifive.com>
+ */
+
+#include <asm/simd.h>
+#include <asm/vector.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sm3_base.h>
+#include <linux/linkage.h>
+#include <linux/module.h>
+
+/*
+ * Note: the asm function only uses the 'state' field of struct sm3_state.
+ * It is assumed to be the first field.
+ */
+asmlinkage void sm3_transform_zvksh_zvkb(
+	struct sm3_state *state, const u8 *data, int num_blocks);
+
+static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
+{
+	/*
+	 * Ensure struct sm3_state begins directly with the SM3
+	 * 256-bit internal state, as this is what the asm function expects.
+	 */
+	BUILD_BUG_ON(offsetof(struct sm3_state, state) != 0);
+
+	if (crypto_simd_usable()) {
+		kernel_vector_begin();
+		sm3_base_do_update(desc, data, len, sm3_transform_zvksh_zvkb);
+		kernel_vector_end();
+	} else {
+		sm3_update(shash_desc_ctx(desc), data, len);
+	}
+	return 0;
+}
+
+static int riscv64_sm3_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out)
+{
+	struct sm3_state *ctx;
+
+	if (crypto_simd_usable()) {
+		kernel_vector_begin();
+		if (len)
+			sm3_base_do_update(desc, data, len,
+					   sm3_transform_zvksh_zvkb);
+		sm3_base_do_finalize(desc, sm3_transform_zvksh_zvkb);
+		kernel_vector_end();
+
+		return sm3_base_finish(desc, out);
+	}
+
+	ctx = shash_desc_ctx(desc);
+	if (len)
+		sm3_update(ctx, data, len);
+	sm3_final(ctx, out);
+
+	return 0;
+}
+
+static int riscv64_sm3_final(struct shash_desc *desc, u8 *out)
+{
+	return riscv64_sm3_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg riscv64_sm3_alg = {
+	.init = sm3_base_init,
+	.update = riscv64_sm3_update,
+	.final = riscv64_sm3_final,
+	.finup = riscv64_sm3_finup,
+	.descsize = sizeof(struct sm3_state),
+	.digestsize = SM3_DIGEST_SIZE,
+	.base = {
+		.cra_blocksize = SM3_BLOCK_SIZE,
+		.cra_priority = 300,
+		.cra_name = "sm3",
+		.cra_driver_name = "sm3-riscv64-zvksh-zvkb",
+		.cra_module = THIS_MODULE,
+	},
+};
+
+static int __init riscv64_sm3_mod_init(void)
+{
+	if (riscv_isa_extension_available(NULL, ZVKSH) &&
+	    riscv_isa_extension_available(NULL, ZVKB) &&
+	    riscv_vector_vlen() >= 128)
+		return crypto_register_shash(&riscv64_sm3_alg);
+
+	return -ENODEV;
+}
+
+static void __exit riscv64_sm3_mod_exit(void)
+{
+	crypto_unregister_shash(&riscv64_sm3_alg);
+}
+
+module_init(riscv64_sm3_mod_init);
+module_exit(riscv64_sm3_mod_exit);
+
+MODULE_DESCRIPTION("SM3 (RISC-V accelerated)");
+MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("sm3");

arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S

@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */
+//
+// This file is dual-licensed, meaning that you can use it under your
+// choice of either of the following two licenses:
+//
+// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved.
+//
+// Licensed under the Apache License 2.0 (the "License"). You can obtain
+// a copy in the file LICENSE in the source distribution or at
+// https://www.openssl.org/source/license.html
+//
+// or
+//
+// Copyright (c) 2023, Christoph Müllner <christoph.muellner@vrull.eu>
+// Copyright (c) 2023, Jerry Shih <jerry.shih@sifive.com>
+// Copyright 2024 Google LLC
+// All rights reserved.
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions
+// are met:
+// 1. Redistributions of source code must retain the above copyright
+//    notice, this list of conditions and the following disclaimer.
+// 2. Redistributions in binary form must reproduce the above copyright
+//    notice, this list of conditions and the following disclaimer in the
+//    documentation and/or other materials provided with the distribution.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+// The generated code of this file depends on the following RISC-V extensions:
+// - RV64I
+// - RISC-V Vector ('V') with VLEN >= 128
+// - RISC-V Vector SM3 Secure Hash extension ('Zvksh')
+// - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb')
+
+#include <linux/cfi_types.h>
+
+.text
+.option arch, +zvksh, +zvkb
+
+#define STATEP		a0
+#define DATA		a1
+#define NUM_BLOCKS	a2
+
+#define STATE		v0	// LMUL=2
+#define PREV_STATE	v2	// LMUL=2
+#define W0		v4	// LMUL=2
+#define W1		v6	// LMUL=2
+#define VTMP		v8	// LMUL=2
+
+.macro	sm3_8rounds	i, w0, w1
+	// Do 4 rounds using W_{0+i}..W_{7+i}.
+	vsm3c.vi	STATE, \w0, \i + 0
+	vslidedown.vi	VTMP, \w0, 2
+	vsm3c.vi	STATE, VTMP, \i + 1
+
+	// Compute W_{4+i}..W_{11+i}.
+	vslidedown.vi	VTMP, \w0, 4
+	vslideup.vi	VTMP, \w1, 4
+
+	// Do 4 rounds using W_{4+i}..W_{11+i}.
+	vsm3c.vi	STATE, VTMP, \i + 2
+	vslidedown.vi	VTMP, VTMP, 2
+	vsm3c.vi	STATE, VTMP, \i + 3
+
+.if \i < 28
+	// Compute W_{16+i}..W_{23+i}.
+	vsm3me.vv	\w0, \w1, \w0
+.endif
+	// For the next 8 rounds, w0 and w1 are swapped.
+.endm
+
+// void sm3_transform_zvksh_zvkb(u32 state[8], const u8 *data, int num_blocks);
+SYM_TYPED_FUNC_START(sm3_transform_zvksh_zvkb)
+
+	// Load the state and endian-swap each 32-bit word.
+	vsetivli	zero, 8, e32, m2, ta, ma
+	vle32.v		STATE, (STATEP)
+	vrev8.v		STATE, STATE
+
+.Lnext_block:
+	addi		NUM_BLOCKS, NUM_BLOCKS, -1
+
+	// Save the previous state, as it's needed later.
+	vmv.v.v		PREV_STATE, STATE
+
+	// Load the next 512-bit message block into W0-W1.
+	vle32.v		W0, (DATA)
+	addi		DATA, DATA, 32
+	vle32.v		W1, (DATA)
+	addi		DATA, DATA, 32
+
+	// Do the 64 rounds of SM3.
+	sm3_8rounds	0, W0, W1
+	sm3_8rounds	4, W1, W0
+	sm3_8rounds	8, W0, W1
+	sm3_8rounds	12, W1, W0
+	sm3_8rounds	16, W0, W1
+	sm3_8rounds	20, W1, W0
+	sm3_8rounds	24, W0, W1
+	sm3_8rounds	28, W1, W0
+
+	// XOR in the previous state.
+	vxor.vv		STATE, STATE, PREV_STATE
+
+	// Repeat if more blocks remain.
+	bnez		NUM_BLOCKS, .Lnext_block
+
+	// Store the new state and return.
+	vrev8.v		STATE, STATE
+	vse32.v		STATE, (STATEP)
+	ret
+SYM_FUNC_END(sm3_transform_zvksh_zvkb)