Revert "arm64: remove assembly code string functions"

This reverts commit 00263d0d8e
to reintroduce optimized string handling functions.

BUG=chrome-os-partner:41185
BRANCH=None
TEST=Compiles successfully and boots to kernel prompt on Smaug

Change-Id: I47f8d8afa5c9ff3fca67d4d0f393336fef03402b
Signed-off-by: Patrick Georgi <pgeorgi@chromium.org>
Original-Commit-Id: eeb38afea828a2727d815e4fb5762cfdd09a2b3a
Original-Change-Id: Id053cbcea8b5e7ae29bdd6bb8b6f5e5011c42b00
Original-Signed-off-by: Furquan Shaikh <furquan@google.com>
Original-Reviewed-on: https://chromium-review.googlesource.com/275865
Original-Trybot-Ready: Furquan Shaikh <furquan@chromium.org>
Original-Tested-by: Furquan Shaikh <furquan@chromium.org>
Original-Reviewed-by: Aaron Durbin <adurbin@chromium.org>
Original-Commit-Queue: Furquan Shaikh <furquan@chromium.org>
Reviewed-on: http://review.coreboot.org/10564
Tested-by: build bot (Jenkins)
Reviewed-by: Marc Jones <marc.jones@se-eng.com>

src/arch/arm64/memcpy.S

@@ -0,0 +1,52 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <arch/asm.h>
+
+/*
+ * Copy a buffer from src to dest (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - dest
+ *	x1 - src
+ *	x2 - n
+ * Returns:
+ *	x0 - dest
+ */
+ENTRY(memcpy)
+	mov	x4, x0
+	subs	x2, x2, #8
+	b.mi	2f
+1:	ldr	x3, [x1], #8
+	subs	x2, x2, #8
+	str	x3, [x4], #8
+	b.pl	1b
+2:	adds	x2, x2, #4
+	b.mi	3f
+	ldr	w3, [x1], #4
+	sub	x2, x2, #4
+	str	w3, [x4], #4
+3:	adds	x2, x2, #2
+	b.mi	4f
+	ldrh	w3, [x1], #2
+	sub	x2, x2, #2
+	strh	w3, [x4], #2
+4:	adds	x2, x2, #1
+	b.mi	5f
+	ldrb	w3, [x1]
+	strb	w3, [x4]
+5:	ret
+ENDPROC(memcpy)