arm64/crypto: GHASH secure hash using ARMv8 Crypto Extensions

This is a port to ARMv8 (Crypto Extensions) of the Intel implementation of the
GHASH Secure Hash (used in the Galois/Counter chaining mode). It relies on the
optional PMULL/PMULL2 instruction (polynomial multiply long, what Intel call
carry-less multiply).

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

1 files changed, 95 insertions, 0 deletions

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
new file mode 100644
index 000000000000..b9e6eaf41c9b
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -0,0 +1,95 @@
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Based on arch/x86/crypto/ghash-pmullni-intel_asm.S
+ *
+ * Copyright (c) 2009 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *           Vinodh Gopal
+ *           Erdinc Ozturk
+ *           Deniz Karakoyunlu
+ *
+ * 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/linkage.h>
+#include <asm/assembler.h>
+
+	DATA	.req	v0
+	SHASH	.req	v1
+	IN1	.req	v2
+	T1	.req	v2
+	T2	.req	v3
+	T3	.req	v4
+	VZR	.req	v5
+
+	.text
+	.arch		armv8-a+crypto
+
+	/*
+	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+	 *			   struct ghash_key const *k, const char *head)
+	 */
+ENTRY(pmull_ghash_update)
+	ld1		{DATA.16b}, [x1]
+	ld1		{SHASH.16b}, [x3]
+	eor		VZR.16b, VZR.16b, VZR.16b
+
+	/* do the head block first, if supplied */
+	cbz		x4, 0f
+	ld1		{IN1.2d}, [x4]
+	b		1f
+
+0:	ld1		{IN1.2d}, [x2], #16
+	sub		w0, w0, #1
+1:	ext		IN1.16b, IN1.16b, IN1.16b, #8
+CPU_LE(	rev64		IN1.16b, IN1.16b	)
+	eor		DATA.16b, DATA.16b, IN1.16b
+
+	/* multiply DATA by SHASH in GF(2^128) */
+	ext		T2.16b, DATA.16b, DATA.16b, #8
+	ext		T3.16b, SHASH.16b, SHASH.16b, #8
+	eor		T2.16b, T2.16b, DATA.16b
+	eor		T3.16b, T3.16b, SHASH.16b
+
+	pmull2		T1.1q, SHASH.2d, DATA.2d	// a1 * b1
+	pmull		DATA.1q, SHASH.1d, DATA.1d	// a0 * b0
+	pmull		T2.1q, T2.1d, T3.1d		// (a1 + a0)(b1 + b0)
+	eor		T2.16b, T2.16b, T1.16b		// (a0 * b1) + (a1 * b0)
+	eor		T2.16b, T2.16b, DATA.16b
+
+	ext		T3.16b, VZR.16b, T2.16b, #8
+	ext		T2.16b, T2.16b, VZR.16b, #8
+	eor		DATA.16b, DATA.16b, T3.16b
+	eor		T1.16b, T1.16b, T2.16b	// <T1:DATA> is result of
+						// carry-less multiplication
+
+	/* first phase of the reduction */
+	shl		T3.2d, DATA.2d, #1
+	eor		T3.16b, T3.16b, DATA.16b
+	shl		T3.2d, T3.2d, #5
+	eor		T3.16b, T3.16b, DATA.16b
+	shl		T3.2d, T3.2d, #57
+	ext		T2.16b, VZR.16b, T3.16b, #8
+	ext		T3.16b, T3.16b, VZR.16b, #8
+	eor		DATA.16b, DATA.16b, T2.16b
+	eor		T1.16b, T1.16b, T3.16b
+
+	/* second phase of the reduction */
+	ushr		T2.2d, DATA.2d, #5
+	eor		T2.16b, T2.16b, DATA.16b
+	ushr		T2.2d, T2.2d, #1
+	eor		T2.16b, T2.16b, DATA.16b
+	ushr		T2.2d, T2.2d, #1
+	eor		T1.16b, T1.16b, T2.16b
+	eor		DATA.16b, DATA.16b, T1.16b
+
+	cbnz		w0, 0b
+
+	st1		{DATA.16b}, [x1]
+	ret
+ENDPROC(pmull_ghash_update)