35 files changed, 739 insertions, 31 deletions
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 2cf5febeb4..2b056afd67 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -291,13 +291,29 @@ MACH :=
 endif
 
 common-y += $(BOARD) arch/arm/boards/ $(MACH)
-common-y += arch/arm/lib/ arch/arm/cpu/
-common-y += arch/arm/crypto/
+common-y += arch/arm/cpu/
+common-y += arch/arm/lib/
+
+ifeq ($(CONFIG_CPU_V8), y)
+common-y += arch/arm/lib64/
+else
+common-y += arch/arm/lib32/ arch/arm/crypto/
+endif
 
 common-$(CONFIG_OFTREE) += arch/arm/dts/
 
-lds-y	:= arch/arm/lib/barebox.lds
+ifeq ($(CONFIG_CPU_V8), y)
+lds-y	:= arch/arm/lib64/barebox.lds
+else
+lds-y	:= arch/arm/lib32/barebox.lds
+endif
 
 common- += $(patsubst %,arch/arm/boards/%/,$(board-))
 
-CLEAN_FILES += include/generated/mach-types.h arch/arm/lib/barebox.lds barebox-flash-image
+CLEAN_FILES += include/generated/mach-types.h barebox-flash-image
+
+ifeq ($(CONFIG_CPU_V8), y)
+CLEAN_FILES += arch/arm/lib64/barebox.lds
+else
+CLEAN_FILES += arch/arm/lib32/barebox.lds
+endif
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index e1c6f5bfd3..33db7350f8 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -1,29 +1,2 @@
-obj-$(CONFIG_ARM_LINUX)	+= armlinux.o
 obj-$(CONFIG_BOOTM)	+= bootm.o
-obj-$(CONFIG_CMD_BOOTZ)	+= bootz.o
 obj-$(CONFIG_CMD_BOOTU)	+= bootu.o
-obj-y	+= div0.o
-obj-y	+= findbit.o
-obj-y	+= io.o
-obj-y	+= io-readsb.o
-obj-y	+= io-readsw-armv4.o
-obj-y	+= io-readsl.o
-obj-y	+= io-writesb.o
-obj-y	+= io-writesw-armv4.o
-obj-y	+= io-writesl.o
-obj-y	+= lib1funcs.o
-obj-y	+= ashrdi3.o
-obj-y	+= ashldi3.o
-obj-y	+= lshrdi3.o
-obj-y	+= runtime-offset.o
-pbl-y	+= runtime-offset.o
-obj-$(CONFIG_ARM_OPTIMZED_STRING_FUNCTIONS)	+= memcpy.o
-obj-$(CONFIG_ARM_OPTIMZED_STRING_FUNCTIONS)	+= memset.o
-obj-$(CONFIG_ARM_UNWIND) += unwind.o
-obj-$(CONFIG_ARM_SEMIHOSTING) += semihosting-trap.o semihosting.o
-obj-$(CONFIG_MODULES) += module.o
-extra-y += barebox.lds
-
-pbl-y	+= lib1funcs.o
-pbl-y	+= ashldi3.o
-pbl-y	+= div0.o
diff --git a/arch/arm/lib/.gitignore b/arch/arm/lib32/.gitignore
index d1165788c9..d1165788c9 100644
--- a/arch/arm/lib/.gitignore
+++ b/arch/arm/lib32/.gitignore
diff --git a/arch/arm/lib32/Makefile b/arch/arm/lib32/Makefile
new file mode 100644
index 0000000000..cdd07322cf
--- /dev/null
+++ b/arch/arm/lib32/Makefile
@@ -0,0 +1,27 @@
+obj-$(CONFIG_ARM_LINUX)	+= armlinux.o
+obj-$(CONFIG_CMD_BOOTZ)	+= bootz.o
+obj-y	+= div0.o
+obj-y	+= findbit.o
+obj-y	+= io.o
+obj-y	+= io-readsb.o
+obj-y	+= io-readsw-armv4.o
+obj-y	+= io-readsl.o
+obj-y	+= io-writesb.o
+obj-y	+= io-writesw-armv4.o
+obj-y	+= io-writesl.o
+obj-y	+= lib1funcs.o
+obj-y	+= ashrdi3.o
+obj-y	+= ashldi3.o
+obj-y	+= lshrdi3.o
+obj-y	+= runtime-offset.o
+pbl-y	+= runtime-offset.o
+obj-$(CONFIG_ARM_OPTIMZED_STRING_FUNCTIONS)	+= memcpy.o
+obj-$(CONFIG_ARM_OPTIMZED_STRING_FUNCTIONS)	+= memset.o
+obj-$(CONFIG_ARM_UNWIND) += unwind.o
+obj-$(CONFIG_ARM_SEMIHOSTING) += semihosting-trap.o semihosting.o
+obj-$(CONFIG_MODULES) += module.o
+extra-y += barebox.lds
+
+pbl-y	+= lib1funcs.o
+pbl-y	+= ashldi3.o
+pbl-y	+= div0.o
diff --git a/arch/arm/lib/armlinux.c b/arch/arm/lib32/armlinux.c
index 47b9bd33ed..47b9bd33ed 100644
--- a/arch/arm/lib/armlinux.c
+++ b/arch/arm/lib32/armlinux.c
diff --git a/arch/arm/lib/ashldi3.S b/arch/arm/lib32/ashldi3.S
index b62e06f602..b62e06f602 100644
--- a/arch/arm/lib/ashldi3.S
+++ b/arch/arm/lib32/ashldi3.S
diff --git a/arch/arm/lib/ashrdi3.S b/arch/arm/lib32/ashrdi3.S
index db849b65fc..db849b65fc 100644
--- a/arch/arm/lib/ashrdi3.S
+++ b/arch/arm/lib32/ashrdi3.S
diff --git a/arch/arm/lib/barebox.lds.S b/arch/arm/lib32/barebox.lds.S
index 6dc8bd2f3c..6dc8bd2f3c 100644
--- a/arch/arm/lib/barebox.lds.S
+++ b/arch/arm/lib32/barebox.lds.S
diff --git a/arch/arm/lib/bootz.c b/arch/arm/lib32/bootz.c
index 5167c9d20d..5167c9d20d 100644
--- a/arch/arm/lib/bootz.c
+++ b/arch/arm/lib32/bootz.c
diff --git a/arch/arm/lib/copy_template.S b/arch/arm/lib32/copy_template.S
index d8eb06328a..d8eb06328a 100644
--- a/arch/arm/lib/copy_template.S
+++ b/arch/arm/lib32/copy_template.S
diff --git a/arch/arm/lib/div0.c b/arch/arm/lib32/div0.c
index 852cb72331..852cb72331 100644
--- a/arch/arm/lib/div0.c
+++ b/arch/arm/lib32/div0.c
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib32/findbit.S
index ef4caff1ad..ef4caff1ad 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib32/findbit.S
diff --git a/arch/arm/lib/io-readsb.S b/arch/arm/lib32/io-readsb.S
index 963c455175..963c455175 100644
--- a/arch/arm/lib/io-readsb.S
+++ b/arch/arm/lib32/io-readsb.S
diff --git a/arch/arm/lib/io-readsl.S b/arch/arm/lib32/io-readsl.S
index 47a29744e9..47a29744e9 100644
--- a/arch/arm/lib/io-readsl.S
+++ b/arch/arm/lib32/io-readsl.S
diff --git a/arch/arm/lib/io-readsw-armv4.S b/arch/arm/lib32/io-readsw-armv4.S
index f5b34a3479..f5b34a3479 100644
--- a/arch/arm/lib/io-readsw-armv4.S
+++ b/arch/arm/lib32/io-readsw-armv4.S
diff --git a/arch/arm/lib/io-writesb.S b/arch/arm/lib32/io-writesb.S
index 1ab8e47cb4..1ab8e47cb4 100644
--- a/arch/arm/lib/io-writesb.S
+++ b/arch/arm/lib32/io-writesb.S
diff --git a/arch/arm/lib/io-writesl.S b/arch/arm/lib32/io-writesl.S
index 8a3bcd6456..8a3bcd6456 100644
--- a/arch/arm/lib/io-writesl.S
+++ b/arch/arm/lib32/io-writesl.S
diff --git a/arch/arm/lib/io-writesw-armv4.S b/arch/arm/lib32/io-writesw-armv4.S
index 9e8308dd77..9e8308dd77 100644
--- a/arch/arm/lib/io-writesw-armv4.S
+++ b/arch/arm/lib32/io-writesw-armv4.S
diff --git a/arch/arm/lib/io.c b/arch/arm/lib32/io.c
index abfd887aac..abfd887aac 100644
--- a/arch/arm/lib/io.c
+++ b/arch/arm/lib32/io.c
diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib32/lib1funcs.S
index bf1d0192d6..bf1d0192d6 100644
--- a/arch/arm/lib/lib1funcs.S
+++ b/arch/arm/lib32/lib1funcs.S
diff --git a/arch/arm/lib/lshrdi3.S b/arch/arm/lib32/lshrdi3.S
index e77e96c7bc..e77e96c7bc 100644
--- a/arch/arm/lib/lshrdi3.S
+++ b/arch/arm/lib32/lshrdi3.S
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib32/memcpy.S
index 5123691ca9..5123691ca9 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib32/memcpy.S
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib32/memset.S
index c4d2672038..c4d2672038 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib32/memset.S
diff --git a/arch/arm/lib/module.c b/arch/arm/lib32/module.c
index be7965d59c..be7965d59c 100644
--- a/arch/arm/lib/module.c
+++ b/arch/arm/lib32/module.c
diff --git a/arch/arm/lib/runtime-offset.S b/arch/arm/lib32/runtime-offset.S
index f10c4c8469..f10c4c8469 100644
--- a/arch/arm/lib/runtime-offset.S
+++ b/arch/arm/lib32/runtime-offset.S
diff --git a/arch/arm/lib/semihosting-trap.S b/arch/arm/lib32/semihosting-trap.S
index 9e40ebfe21..9e40ebfe21 100644
--- a/arch/arm/lib/semihosting-trap.S
+++ b/arch/arm/lib32/semihosting-trap.S
diff --git a/arch/arm/lib/semihosting.c b/arch/arm/lib32/semihosting.c
index a7351961dc..a7351961dc 100644
--- a/arch/arm/lib/semihosting.c
+++ b/arch/arm/lib32/semihosting.c
diff --git a/arch/arm/lib/unwind.c b/arch/arm/lib32/unwind.c
index c3dca5b61d..c3dca5b61d 100644
--- a/arch/arm/lib/unwind.c
+++ b/arch/arm/lib32/unwind.c
diff --git a/arch/arm/lib64/Makefile b/arch/arm/lib64/Makefile
new file mode 100644
index 0000000000..87e26f6afa
--- /dev/null
+++ b/arch/arm/lib64/Makefile
@@ -0,0 +1,9 @@
+obj-$(CONFIG_ARM_LINUX)	+= armlinux.o
+obj-y	+= div0.o
+obj-$(CONFIG_ARM_OPTIMZED_STRING_FUNCTIONS)	+= memcpy.o
+obj-$(CONFIG_ARM_OPTIMZED_STRING_FUNCTIONS)	+= memset.o
+extra-y += barebox.lds
+
+pbl-y	+= lib1funcs.o
+pbl-y	+= ashldi3.o
+pbl-y	+= div0.o
diff --git a/arch/arm/lib64/armlinux.c b/arch/arm/lib64/armlinux.c
new file mode 100644
index 0000000000..020e6d70ff
--- /dev/null
+++ b/arch/arm/lib64/armlinux.c
@@ -0,0 +1,50 @@
+/*
+ * (C) Copyright 2002
+ * Sysgo Real-Time Solutions, GmbH <www.elinos.com>
+ * Marius Groeger <mgroeger@sysgo.de>
+ *
+ * Copyright (C) 2001  Erik Mouw (J.A.K.Mouw@its.tudelft.nl)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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.
+ */
+
+#include <boot.h>
+#include <common.h>
+#include <command.h>
+#include <driver.h>
+#include <environment.h>
+#include <image.h>
+#include <init.h>
+#include <fs.h>
+#include <linux/list.h>
+#include <xfuncs.h>
+#include <malloc.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <memory.h>
+#include <of.h>
+#include <magicvar.h>
+
+#include <asm/byteorder.h>
+#include <asm/setup.h>
+#include <asm/barebox-arm.h>
+#include <asm/armlinux.h>
+#include <asm/system.h>
+
+void start_linux(void *adr, int swap, unsigned long initrd_address,
+		unsigned long initrd_size, void *oftree)
+{
+	void (*kernel)(void *dtb) = adr;
+
+	shutdown_barebox();
+
+	kernel(oftree);
+}
diff --git a/arch/arm/lib64/barebox.lds.S b/arch/arm/lib64/barebox.lds.S
new file mode 100644
index 0000000000..240699f1a6
--- /dev/null
+++ b/arch/arm/lib64/barebox.lds.S
@@ -0,0 +1,125 @@
+/*
+ * (C) Copyright 2000-2004
+ * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
+ *
+ * See file CREDITS for list of people who contributed to this
+ * project.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * 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.
+ *
+ *
+ */
+
+#include <asm-generic/barebox.lds.h>
+
+OUTPUT_FORMAT("elf64-littleaarch64", "elf64-littleaarch64", "elf64-littleaarch64")
+OUTPUT_ARCH(aarch64)
+ENTRY(start)
+SECTIONS
+{
+#ifdef CONFIG_RELOCATABLE
+	. = 0x0;
+#else
+	. = TEXT_BASE;
+#endif
+
+#ifndef CONFIG_PBL_IMAGE
+	PRE_IMAGE
+#endif
+	. = ALIGN(4);
+	.text      :
+	{
+		_stext = .;
+		_text = .;
+		*(.text_entry*)
+		__bare_init_start = .;
+		*(.text_bare_init*)
+		__bare_init_end = .;
+		__exceptions_start = .;
+		KEEP(*(.text_exceptions*))
+		__exceptions_stop = .;
+		*(.text*)
+	}
+	BAREBOX_BARE_INIT_SIZE
+
+	. = ALIGN(4);
+	.rodata : { *(.rodata*) }
+
+#ifdef CONFIG_ARM_UNWIND
+	/*
+	 * Stack unwinding tables
+	 */
+	. = ALIGN(8);
+	.ARM.unwind_idx : {
+		__start_unwind_idx = .;
+		*(.ARM.exidx*)
+		__stop_unwind_idx = .;
+	}
+	.ARM.unwind_tab : {
+		__start_unwind_tab = .;
+		*(.ARM.extab*)
+		__stop_unwind_tab = .;
+	}
+#endif
+	_etext = .;			/* End of text and rodata section */
+	_sdata = .;
+
+	. = ALIGN(4);
+	.data : { *(.data*) }
+
+	.barebox_imd : { BAREBOX_IMD }
+
+	. = .;
+	__barebox_cmd_start = .;
+	.barebox_cmd : { BAREBOX_CMDS }
+	__barebox_cmd_end = .;
+
+	__barebox_magicvar_start = .;
+	.barebox_magicvar : { BAREBOX_MAGICVARS }
+	__barebox_magicvar_end = .;
+
+	__barebox_initcalls_start = .;
+	.barebox_initcalls : { INITCALLS }
+	__barebox_initcalls_end = .;
+
+	__barebox_exitcalls_start = .;
+	.barebox_exitcalls : { EXITCALLS }
+	__barebox_exitcalls_end = .;
+
+	__usymtab_start = .;
+	__usymtab : { BAREBOX_SYMS }
+	__usymtab_end = .;
+
+	.oftables : { BAREBOX_CLK_TABLE() }
+
+	.dtb : { BAREBOX_DTB() }
+
+	.rel.dyn : {
+		__rel_dyn_start = .;
+		*(.rel*)
+		__rel_dyn_end = .;
+	}
+
+	.dynsym : {
+		__dynsym_start = .;
+		*(.dynsym)
+		__dynsym_end = .;
+	}
+
+	_edata = .;
+
+	. = ALIGN(4);
+	__bss_start = .;
+	.bss : { *(.bss*) }
+	__bss_stop = .;
+	_end = .;
+	_barebox_image_size = __bss_start - TEXT_BASE;
+}
diff --git a/arch/arm/lib64/copy_template.S b/arch/arm/lib64/copy_template.S
new file mode 100644
index 0000000000..cc9a84260d
--- /dev/null
+++ b/arch/arm/lib64/copy_template.S
@@ -0,0 +1,192 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * 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/>.
+ */
+
+
+/*
+ * Copy a buffer from src to dest (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - dest
+ *	x1 - src
+ *	x2 - n
+ * Returns:
+ *	x0 - dest
+ */
+dstin	.req	x0
+src	.req	x1
+count	.req	x2
+tmp1	.req	x3
+tmp1w	.req	w3
+tmp2	.req	x4
+tmp2w	.req	w4
+dst	.req	x6
+
+A_l	.req	x7
+A_h	.req	x8
+B_l	.req	x9
+B_h	.req	x10
+C_l	.req	x11
+C_h	.req	x12
+D_l	.req	x13
+D_h	.req	x14
+
+	mov	dst, dstin
+	cmp	count, #16
+	/*When memory length is less than 16, the accessed are not aligned.*/
+	b.lo	.Ltiny15
+
+	neg	tmp2, src
+	ands	tmp2, tmp2, #15/* Bytes to reach alignment. */
+	b.eq	.LSrcAligned
+	sub	count, count, tmp2
+	/*
+	* Copy the leading memory data from src to dst in an increasing
+	* address order.By this way,the risk of overwritting the source
+	* memory data is eliminated when the distance between src and
+	* dst is less than 16. The memory accesses here are alignment.
+	*/
+	tbz	tmp2, #0, 1f
+	ldrb1	tmp1w, src, #1
+	strb1	tmp1w, dst, #1
+1:
+	tbz	tmp2, #1, 2f
+	ldrh1	tmp1w, src, #2
+	strh1	tmp1w, dst, #2
+2:
+	tbz	tmp2, #2, 3f
+	ldr1	tmp1w, src, #4
+	str1	tmp1w, dst, #4
+3:
+	tbz	tmp2, #3, .LSrcAligned
+	ldr1	tmp1, src, #8
+	str1	tmp1, dst, #8
+
+.LSrcAligned:
+	cmp	count, #64
+	b.ge	.Lcpy_over64
+	/*
+	* Deal with small copies quickly by dropping straight into the
+	* exit block.
+	*/
+.Ltail63:
+	/*
+	* Copy up to 48 bytes of data. At this point we only need the
+	* bottom 6 bits of count to be accurate.
+	*/
+	ands	tmp1, count, #0x30
+	b.eq	.Ltiny15
+	cmp	tmp1w, #0x20
+	b.eq	1f
+	b.lt	2f
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+1:
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+2:
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+.Ltiny15:
+	/*
+	* Prefer to break one ldp/stp into several load/store to access
+	* memory in an increasing address order,rather than to load/store 16
+	* bytes from (src-16) to (dst-16) and to backward the src to aligned
+	* address,which way is used in original cortex memcpy. If keeping
+	* the original memcpy process here, memmove need to satisfy the
+	* precondition that src address is at least 16 bytes bigger than dst
+	* address,otherwise some source data will be overwritten when memove
+	* call memcpy directly. To make memmove simpler and decouple the
+	* memcpy's dependency on memmove, withdrew the original process.
+	*/
+	tbz	count, #3, 1f
+	ldr1	tmp1, src, #8
+	str1	tmp1, dst, #8
+1:
+	tbz	count, #2, 2f
+	ldr1	tmp1w, src, #4
+	str1	tmp1w, dst, #4
+2:
+	tbz	count, #1, 3f
+	ldrh1	tmp1w, src, #2
+	strh1	tmp1w, dst, #2
+3:
+	tbz	count, #0, .Lexitfunc
+	ldrb1	tmp1w, src, #1
+	strb1	tmp1w, dst, #1
+
+	b	.Lexitfunc
+
+.Lcpy_over64:
+	subs	count, count, #128
+	b.ge	.Lcpy_body_large
+	/*
+	* Less than 128 bytes to copy, so handle 64 here and then jump
+	* to the tail.
+	*/
+	ldp1	A_l, A_h, src, #16
+	stp1	A_l, A_h, dst, #16
+	ldp1	B_l, B_h, src, #16
+	ldp1	C_l, C_h, src, #16
+	stp1	B_l, B_h, dst, #16
+	stp1	C_l, C_h, dst, #16
+	ldp1	D_l, D_h, src, #16
+	stp1	D_l, D_h, dst, #16
+
+	tst	count, #0x3f
+	b.ne	.Ltail63
+	b	.Lexitfunc
+
+	/*
+	* Critical loop.  Start at a new cache line boundary.  Assuming
+	* 64 bytes per line this ensures the entire loop is in one line.
+	*/
+.Lcpy_body_large:
+	/* pre-get 64 bytes data. */
+	ldp1	A_l, A_h, src, #16
+	ldp1	B_l, B_h, src, #16
+	ldp1	C_l, C_h, src, #16
+	ldp1	D_l, D_h, src, #16
+1:
+	/*
+	* interlace the load of next 64 bytes data block with store of the last
+	* loaded 64 bytes data.
+	*/
+	stp1	A_l, A_h, dst, #16
+	ldp1	A_l, A_h, src, #16
+	stp1	B_l, B_h, dst, #16
+	ldp1	B_l, B_h, src, #16
+	stp1	C_l, C_h, dst, #16
+	ldp1	C_l, C_h, src, #16
+	stp1	D_l, D_h, dst, #16
+	ldp1	D_l, D_h, src, #16
+	subs	count, count, #64
+	b.ge	1b
+	stp1	A_l, A_h, dst, #16
+	stp1	B_l, B_h, dst, #16
+	stp1	C_l, C_h, dst, #16
+	stp1	D_l, D_h, dst, #16
+
+	tst	count, #0x3f
+	b.ne	.Ltail63
+.Lexitfunc:
diff --git a/arch/arm/lib64/div0.c b/arch/arm/lib64/div0.c
new file mode 100644
index 0000000000..852cb72331
--- /dev/null
+++ b/arch/arm/lib64/div0.c
@@ -0,0 +1,27 @@
+/*
+ * (C) Copyright 2002
+ * Wolfgang Denk, DENX Software Engineering, wd@denx.de.
+ *
+ * See file CREDITS for list of people who contributed to this
+ * project.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * 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.
+ *
+ */
+#include <common.h>
+
+extern void __div0(void);
+
+/* Replacement (=dummy) for GNU/Linux division-by zero handler */
+void __div0 (void)
+{
+	panic("division by zero\n");
+}
diff --git a/arch/arm/lib64/memcpy.S b/arch/arm/lib64/memcpy.S
new file mode 100644
index 0000000000..cfed3191c5
--- /dev/null
+++ b/arch/arm/lib64/memcpy.S
@@ -0,0 +1,74 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * 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 <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Copy a buffer from src to dest (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - dest
+ *	x1 - src
+ *	x2 - n
+ * Returns:
+ *	x0 - dest
+ */
+	.macro ldrb1 ptr, regB, val
+	ldrb  \ptr, [\regB], \val
+	.endm
+
+	.macro strb1 ptr, regB, val
+	strb \ptr, [\regB], \val
+	.endm
+
+	.macro ldrh1 ptr, regB, val
+	ldrh  \ptr, [\regB], \val
+	.endm
+
+	.macro strh1 ptr, regB, val
+	strh \ptr, [\regB], \val
+	.endm
+
+	.macro ldr1 ptr, regB, val
+	ldr \ptr, [\regB], \val
+	.endm
+
+	.macro str1 ptr, regB, val
+	str \ptr, [\regB], \val
+	.endm
+
+	.macro ldp1 ptr, regB, regC, val
+	ldp \ptr, \regB, [\regC], \val
+	.endm
+
+	.macro stp1 ptr, regB, regC, val
+	stp \ptr, \regB, [\regC], \val
+	.endm
+
+	.weak memcpy
+ENTRY(memcpy)
+#include "copy_template.S"
+	ret
+ENDPROC(memcpy)
diff --git a/arch/arm/lib64/memset.S b/arch/arm/lib64/memset.S
new file mode 100644
index 0000000000..380a54097e
--- /dev/null
+++ b/arch/arm/lib64/memset.S
@@ -0,0 +1,215 @@
+/*
+ * Copyright (C) 2013 ARM Ltd.
+ * Copyright (C) 2013 Linaro.
+ *
+ * This code is based on glibc cortex strings work originally authored by Linaro
+ * and re-licensed under GPLv2 for the Linux kernel. The original code can
+ * be found @
+ *
+ * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
+ * files/head:/src/aarch64/
+ *
+ * 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 <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Fill in the buffer with character c (alignment handled by the hardware)
+ *
+ * Parameters:
+ *	x0 - buf
+ *	x1 - c
+ *	x2 - n
+ * Returns:
+ *	x0 - buf
+ */
+
+dstin		.req	x0
+val		.req	w1
+count		.req	x2
+tmp1		.req	x3
+tmp1w		.req	w3
+tmp2		.req	x4
+tmp2w		.req	w4
+zva_len_x	.req	x5
+zva_len		.req	w5
+zva_bits_x	.req	x6
+
+A_l		.req	x7
+A_lw		.req	w7
+dst		.req	x8
+tmp3w		.req	w9
+tmp3		.req	x9
+
+	.weak memset
+ENTRY(memset)
+	mov	dst, dstin	/* Preserve return value.  */
+	and	A_lw, val, #255
+	orr	A_lw, A_lw, A_lw, lsl #8
+	orr	A_lw, A_lw, A_lw, lsl #16
+	orr	A_l, A_l, A_l, lsl #32
+
+	cmp	count, #15
+	b.hi	.Lover16_proc
+	/*All store maybe are non-aligned..*/
+	tbz	count, #3, 1f
+	str	A_l, [dst], #8
+1:
+	tbz	count, #2, 2f
+	str	A_lw, [dst], #4
+2:
+	tbz	count, #1, 3f
+	strh	A_lw, [dst], #2
+3:
+	tbz	count, #0, 4f
+	strb	A_lw, [dst]
+4:
+	ret
+
+.Lover16_proc:
+	/*Whether  the start address is aligned with 16.*/
+	neg	tmp2, dst
+	ands	tmp2, tmp2, #15
+	b.eq	.Laligned
+/*
+* The count is not less than 16, we can use stp to store the start 16 bytes,
+* then adjust the dst aligned with 16.This process will make the current
+* memory address at alignment boundary.
+*/
+	stp	A_l, A_l, [dst] /*non-aligned store..*/
+	/*make the dst aligned..*/
+	sub	count, count, tmp2
+	add	dst, dst, tmp2
+
+.Laligned:
+	cbz	A_l, .Lzero_mem
+
+.Ltail_maybe_long:
+	cmp	count, #64
+	b.ge	.Lnot_short
+.Ltail63:
+	ands	tmp1, count, #0x30
+	b.eq	3f
+	cmp	tmp1w, #0x20
+	b.eq	1f
+	b.lt	2f
+	stp	A_l, A_l, [dst], #16
+1:
+	stp	A_l, A_l, [dst], #16
+2:
+	stp	A_l, A_l, [dst], #16
+/*
+* The last store length is less than 16,use stp to write last 16 bytes.
+* It will lead some bytes written twice and the access is non-aligned.
+*/
+3:
+	ands	count, count, #15
+	cbz	count, 4f
+	add	dst, dst, count
+	stp	A_l, A_l, [dst, #-16]	/* Repeat some/all of last store. */
+4:
+	ret
+
+	/*
+	* Critical loop. Start at a new cache line boundary. Assuming
+	* 64 bytes per line, this ensures the entire loop is in one line.
+	*/
+.Lnot_short:
+	sub	dst, dst, #16/* Pre-bias.  */
+	sub	count, count, #64
+1:
+	stp	A_l, A_l, [dst, #16]
+	stp	A_l, A_l, [dst, #32]
+	stp	A_l, A_l, [dst, #48]
+	stp	A_l, A_l, [dst, #64]!
+	subs	count, count, #64
+	b.ge	1b
+	tst	count, #0x3f
+	add	dst, dst, #16
+	b.ne	.Ltail63
+.Lexitfunc:
+	ret
+
+	/*
+	* For zeroing memory, check to see if we can use the ZVA feature to
+	* zero entire 'cache' lines.
+	*/
+.Lzero_mem:
+	cmp	count, #63
+	b.le	.Ltail63
+	/*
+	* For zeroing small amounts of memory, it's not worth setting up
+	* the line-clear code.
+	*/
+	cmp	count, #128
+	b.lt	.Lnot_short /*count is at least  128 bytes*/
+
+	mrs	tmp1, dczid_el0
+	tbnz	tmp1, #4, .Lnot_short
+	mov	tmp3w, #4
+	and	zva_len, tmp1w, #15	/* Safety: other bits reserved.  */
+	lsl	zva_len, tmp3w, zva_len
+
+	ands	tmp3w, zva_len, #63
+	/*
+	* ensure the zva_len is not less than 64.
+	* It is not meaningful to use ZVA if the block size is less than 64.
+	*/
+	b.ne	.Lnot_short
+.Lzero_by_line:
+	/*
+	* Compute how far we need to go to become suitably aligned. We're
+	* already at quad-word alignment.
+	*/
+	cmp	count, zva_len_x
+	b.lt	.Lnot_short		/* Not enough to reach alignment.  */
+	sub	zva_bits_x, zva_len_x, #1
+	neg	tmp2, dst
+	ands	tmp2, tmp2, zva_bits_x
+	b.eq	2f			/* Already aligned.  */
+	/* Not aligned, check that there's enough to copy after alignment.*/
+	sub	tmp1, count, tmp2
+	/*
+	* grantee the remain length to be ZVA is bigger than 64,
+	* avoid to make the 2f's process over mem range.*/
+	cmp	tmp1, #64
+	ccmp	tmp1, zva_len_x, #8, ge	/* NZCV=0b1000 */
+	b.lt	.Lnot_short
+	/*
+	* We know that there's at least 64 bytes to zero and that it's safe
+	* to overrun by 64 bytes.
+	*/
+	mov	count, tmp1
+1:
+	stp	A_l, A_l, [dst]
+	stp	A_l, A_l, [dst, #16]
+	stp	A_l, A_l, [dst, #32]
+	subs	tmp2, tmp2, #64
+	stp	A_l, A_l, [dst, #48]
+	add	dst, dst, #64
+	b.ge	1b
+	/* We've overrun a bit, so adjust dst downwards.*/
+	add	dst, dst, tmp2
+2:
+	sub	count, count, zva_len_x
+3:
+	dc	zva, dst
+	add	dst, dst, zva_len_x
+	subs	count, count, zva_len_x
+	b.ge	3b
+	ands	count, count, zva_bits_x
+	b.ne	.Ltail_maybe_long
+	ret
+ENDPROC(memset)