diff mbox series

[v2,5/5] armv8 SHA-256 using ARMv8 Crypto Extensions

Message ID 1654107991-598-6-git-send-email-loic.poulain@linaro.org
State Accepted
Commit 0fcc1c76d1acaa68a0675f0baa0e5d9a25908bae
Headers show
Series Add ARMv8 CE sha1/sha256 support | expand

Commit Message

Loic Poulain June 1, 2022, 6:26 p.m. UTC
This patch adds support for the SHA-256 Secure Hash Algorithm for CPUs
that have support for the SHA-256 part of the ARM v8 Crypto Extensions.

It greatly improves sha-256 based operations, about 17x faster on iMX8M
evk board. ~12ms vs ~208ms for a 20MiB kernel sha-256 verification.

asm implementation is a simplified version of the Linux version (from
Ard Biesheuvel).

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
---
 arch/arm/cpu/armv8/Kconfig          |   4 ++
 arch/arm/cpu/armv8/Makefile         |   1 +
 arch/arm/cpu/armv8/sha256_ce_core.S | 134 ++++++++++++++++++++++++++++++++++++
 arch/arm/cpu/armv8/sha256_ce_glue.c |  21 ++++++
 4 files changed, 160 insertions(+)
 create mode 100644 arch/arm/cpu/armv8/sha256_ce_core.S
 create mode 100644 arch/arm/cpu/armv8/sha256_ce_glue.c

Comments

Tom Rini June 27, 2022, 9:31 p.m. UTC | #1
On Wed, Jun 01, 2022 at 08:26:31PM +0200, Loic Poulain wrote:

> This patch adds support for the SHA-256 Secure Hash Algorithm for CPUs
> that have support for the SHA-256 part of the ARM v8 Crypto Extensions.
> 
> It greatly improves sha-256 based operations, about 17x faster on iMX8M
> evk board. ~12ms vs ~208ms for a 20MiB kernel sha-256 verification.
> 
> asm implementation is a simplified version of the Linux version (from
> Ard Biesheuvel).
> 
> Signed-off-by: Loic Poulain <loic.poulain@linaro.org>

Applied to u-boot/next, thanks!
Tom Rini June 27, 2022, 9:31 p.m. UTC | #2
On Thu, Jun 23, 2022 at 03:51:31PM -0400, Tom Rini wrote:

> Now that we can make use of CPU features for sha1/sha256, enable in QEMU
> so that we get some test coverage.
> 
> Cc: Loic Poulain <loic.poulain@linaro.org>
> Cc: Tuomas Tynkkynen <tuomas.tynkkynen@iki.fi>
> Signed-off-by: Tom Rini <trini@konsulko.com>

Applied to u-boot/next, thanks!
diff mbox series

Patch

diff --git a/arch/arm/cpu/armv8/Kconfig b/arch/arm/cpu/armv8/Kconfig
index 0b11ca8..0494a08 100644
--- a/arch/arm/cpu/armv8/Kconfig
+++ b/arch/arm/cpu/armv8/Kconfig
@@ -180,6 +180,10 @@  config ARMV8_CE_SHA1
 	bool "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
 	default y if SHA1
 
+config ARMV8_CE_SHA256
+	bool "SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
+	default y if SHA256
+
 endif
 
 endif
diff --git a/arch/arm/cpu/armv8/Makefile b/arch/arm/cpu/armv8/Makefile
index ff2495c..2e4bf9e 100644
--- a/arch/arm/cpu/armv8/Makefile
+++ b/arch/arm/cpu/armv8/Makefile
@@ -45,3 +45,4 @@  obj-$(CONFIG_ARMV8_PSCI) += psci.o
 obj-$(CONFIG_TARGET_BCMNS3) += bcmns3/
 obj-$(CONFIG_XEN) += xen/
 obj-$(CONFIG_ARMV8_CE_SHA1) += sha1_ce_glue.o sha1_ce_core.o
+obj-$(CONFIG_ARMV8_CE_SHA256) += sha256_ce_glue.o sha256_ce_core.o
diff --git a/arch/arm/cpu/armv8/sha256_ce_core.S b/arch/arm/cpu/armv8/sha256_ce_core.S
new file mode 100644
index 0000000..fbae3ca
--- /dev/null
+++ b/arch/arm/cpu/armv8/sha256_ce_core.S
@@ -0,0 +1,134 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sha256-ce-core.S - core SHA-256 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2022 Linaro Ltd <loic.poulain@linaro.org>
+ */
+
+ #include <config.h>
+ #include <linux/linkage.h>
+ #include <asm/system.h>
+ #include <asm/macro.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	dga		.req	q20
+	dgav		.req	v20
+	dgb		.req	q21
+	dgbv		.req	v21
+
+	t0		.req	v22
+	t1		.req	v23
+
+	dg0q		.req	q24
+	dg0v		.req	v24
+	dg1q		.req	q25
+	dg1v		.req	v25
+	dg2q		.req	q26
+	dg2v		.req	v26
+
+	.macro		add_only, ev, rc, s0
+	mov		dg2v.16b, dg0v.16b
+	.ifeq		\ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha256h		dg0q, dg1q, t0.4s
+	sha256h2	dg1q, dg2q, t0.4s
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha256h		dg0q, dg1q, t1.4s
+	sha256h2	dg1q, dg2q, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, ev, rc, s0, s1, s2, s3
+	sha256su0	v\s0\().4s, v\s1\().4s
+	add_only	\ev, \rc, \s1
+	sha256su1	v\s0\().4s, v\s2\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA-256 round constants
+	 */
+	.align		4
+.Lsha2_rcon:
+	.word		0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+	.word		0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+	.word		0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+	.word		0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+	.word		0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+	.word		0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+	.word		0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+	.word		0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+	.word		0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+	.word		0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+	.word		0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+	.word		0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+	.word		0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+	.word		0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+	.word		0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+	/*
+	 * void sha256_armv8_ce_process(struct sha256_ce_state *sst,
+	 * 				uint8_t const *src, uint32_t blocks)
+	 */
+ENTRY(sha256_armv8_ce_process)
+	/* load round constants */
+	adr		x8, .Lsha2_rcon
+	ld1		{ v0.4s- v3.4s}, [x8], #64
+	ld1		{ v4.4s- v7.4s}, [x8], #64
+	ld1		{ v8.4s-v11.4s}, [x8], #64
+	ld1		{v12.4s-v15.4s}, [x8]
+
+	/* load state */
+	ldp		dga, dgb, [x0]
+
+	/* load input */
+0:	ld1		{v16.4s-v19.4s}, [x1], #64
+	sub		w2, w2, #1
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+	rev32		v16.16b, v16.16b
+	rev32		v17.16b, v17.16b
+	rev32		v18.16b, v18.16b
+	rev32		v19.16b, v19.16b
+#endif
+
+1:	add		t0.4s, v16.4s, v0.4s
+	mov		dg0v.16b, dgav.16b
+	mov		dg1v.16b, dgbv.16b
+
+	add_update	0,  v1, 16, 17, 18, 19
+	add_update	1,  v2, 17, 18, 19, 16
+	add_update	0,  v3, 18, 19, 16, 17
+	add_update	1,  v4, 19, 16, 17, 18
+
+	add_update	0,  v5, 16, 17, 18, 19
+	add_update	1,  v6, 17, 18, 19, 16
+	add_update	0,  v7, 18, 19, 16, 17
+	add_update	1,  v8, 19, 16, 17, 18
+
+	add_update	0,  v9, 16, 17, 18, 19
+	add_update	1, v10, 17, 18, 19, 16
+	add_update	0, v11, 18, 19, 16, 17
+	add_update	1, v12, 19, 16, 17, 18
+
+	add_only	0, v13, 17
+	add_only	1, v14, 18
+	add_only	0, v15, 19
+	add_only	1
+
+	/* update state */
+	add		dgav.4s, dgav.4s, dg0v.4s
+	add		dgbv.4s, dgbv.4s, dg1v.4s
+
+	/* handled all input blocks? */
+	cbnz		w2, 0b
+
+	/* store new state */
+3:	stp		dga, dgb, [x0]
+	ret
+ENDPROC(sha256_armv8_ce_process)
diff --git a/arch/arm/cpu/armv8/sha256_ce_glue.c b/arch/arm/cpu/armv8/sha256_ce_glue.c
new file mode 100644
index 0000000..67dd796
--- /dev/null
+++ b/arch/arm/cpu/armv8/sha256_ce_glue.c
@@ -0,0 +1,21 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sha256_ce_glue.c - SHA-256 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2022 Linaro Ltd <loic.poulain@linaro.org>
+ */
+
+#include <common.h>
+#include <u-boot/sha256.h>
+
+extern void sha256_armv8_ce_process(uint32_t state[8], uint8_t const *src,
+				    uint32_t blocks);
+
+void sha256_process(sha256_context *ctx, const unsigned char *data,
+		    unsigned int blocks)
+{
+	if (!blocks)
+		return;
+
+	sha256_armv8_ce_process(ctx->state, data, blocks);
+}