ARM: crypto: add NEON accelerated XOR implementation

Add a source file xor-neon.c (which is really just the reference
C implementation passed through the GCC vectorizer) and hook it
up to the XOR framework.

Signed-off-by: Ard Biesheuvel <[e-mail]>
Acked-by: Nicolas Pitre <[e-mail]>

arch/arm/include/asm/xor.h

···
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/hardirq.h>
 #include <asm-generic/xor.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
 
 #define __XOR(a1, a2) a1 ^= a2
 
···
 		xor_speed(&xor_block_arm4regs);	\
 		xor_speed(&xor_block_8regs);	\
 		xor_speed(&xor_block_32regs);	\
+		NEON_TEMPLATES;			\
 	} while (0)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+extern struct xor_block_template const xor_block_neon_inner;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_2(bytes, p1, p2);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_2(bytes, p1, p2);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_3(bytes, p1, p2, p3);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_3(bytes, p1, p2, p3);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_4(bytes, p1, p2, p3, p4);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4);
+		kernel_neon_end();
+	}
+}
+
+static void
+xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+		unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	if (in_interrupt()) {
+		xor_arm4regs_5(bytes, p1, p2, p3, p4, p5);
+	} else {
+		kernel_neon_begin();
+		xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5);
+		kernel_neon_end();
+	}
+}
+
+static struct xor_block_template xor_block_neon = {
+	.name	= "neon",
+	.do_2	= xor_neon_2,
+	.do_3	= xor_neon_3,
+	.do_4	= xor_neon_4,
+	.do_5	= xor_neon_5
+};
+
+#define NEON_TEMPLATES	\
+	do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0)
+#else
+#define NEON_TEMPLATES
+#endif

arch/arm/lib/Makefile

···
 
 $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
+
+ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
+  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon
+  CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
+  lib-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
+endif

arch/arm/lib/xor-neon.c

···
+/*
+ * linux/arch/arm/lib/xor-neon.c
+ *
+ * Copyright (C) 2013 Linaro Ltd <[e-mail]>
+ *
+ * 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/raid/xor.h>
+
+#ifndef __ARM_NEON__
+#error You should compile this file with '-mfloat-abi=softfp -mfpu=neon'
+#endif
+
+/*
+ * Pull in the reference implementations while instructing GCC (through
+ * -ftree-vectorize) to attempt to exploit implicit parallelism and emit
+ * NEON instructions.
+ */
+#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6)
+#pragma GCC optimize "tree-vectorize"
+#else
+/*
+ * While older versions of GCC do not generate incorrect code, they fail to
+ * recognize the parallel nature of these functions, and emit plain ARM code,
+ * which is known to be slower than the optimized ARM code in asm-arm/xor.h.
+ */
+#warning This code requires at least version 4.6 of GCC
+#endif
+
+#pragma GCC diagnostic ignored "-Wunused-variable"
+#include <asm-generic/xor.h>
+
+struct xor_block_template const xor_block_neon_inner = {
+	.name	= "__inner_neon__",
+	.do_2	= xor_8regs_2,
+	.do_3	= xor_8regs_3,
+	.do_4	= xor_8regs_4,
+	.do_5	= xor_8regs_5,
+};