arm: rework lib directory to support arm64

This commit create a common directory, lib/,
for arm and arm64 common code.

It also create lib32/ and lib64/ for 32bit
and 64bit code respectively.

Signed-off-by: Raphael Poggi <poggi.raph@gmail.com>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>

26 files changed, 3162 insertions, 0 deletions

diff --git a/arch/arm/lib32/.gitignore b/arch/arm/lib32/.gitignore
new file mode 100644
index 0000000000..d1165788c9
--- /dev/null
+++ b/arch/arm/lib32/.gitignore
@@ -0,0 +1 @@
+barebox.lds
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/lib32/armlinux.c b/arch/arm/lib32/armlinux.c
new file mode 100644
index 0000000000..47b9bd33ed
--- /dev/null
+++ b/arch/arm/lib32/armlinux.c
@@ -0,0 +1,281 @@
+/*
+ * (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>
+
+static struct tag *params;
+static void *armlinux_bootparams = NULL;
+
+static int armlinux_architecture;
+static u32 armlinux_system_rev;
+static u64 armlinux_system_serial;
+
+BAREBOX_MAGICVAR(armlinux_architecture, "ARM machine ID");
+BAREBOX_MAGICVAR(armlinux_system_rev, "ARM system revision");
+BAREBOX_MAGICVAR(armlinux_system_serial, "ARM system serial");
+
+void armlinux_set_architecture(int architecture)
+{
+	export_env_ull("armlinux_architecture", architecture);
+	armlinux_architecture = architecture;
+}
+
+int armlinux_get_architecture(void)
+{
+	getenv_uint("armlinux_architecture", &armlinux_architecture);
+
+	return armlinux_architecture;
+}
+
+void armlinux_set_revision(unsigned int rev)
+{
+	export_env_ull("armlinux_system_rev", rev);
+	armlinux_system_rev = rev;
+}
+
+unsigned int armlinux_get_revision(void)
+{
+	getenv_uint("armlinux_system_rev", &armlinux_system_rev);
+
+	return armlinux_system_rev;
+}
+
+void armlinux_set_serial(u64 serial)
+{
+	export_env_ull("armlinux_system_serial", serial);
+	armlinux_system_serial = serial;
+}
+
+u64 armlinux_get_serial(void)
+{
+	getenv_ull("armlinux_system_serial", &armlinux_system_serial);
+
+	return armlinux_system_serial;
+}
+
+void armlinux_set_bootparams(void *params)
+{
+	armlinux_bootparams = params;
+}
+
+static struct tag *armlinux_get_bootparams(void)
+{
+	struct memory_bank *mem;
+
+	if (armlinux_bootparams)
+		return armlinux_bootparams;
+
+	for_each_memory_bank(mem)
+		return (void *)mem->start + 0x100;
+
+	BUG();
+}
+
+#ifdef CONFIG_ARM_BOARD_APPEND_ATAG
+static struct tag *(*atag_appender)(struct tag *);
+void armlinux_set_atag_appender(struct tag *(*func)(struct tag *))
+{
+	atag_appender = func;
+}
+#endif
+
+static void setup_start_tag(void)
+{
+	params = armlinux_get_bootparams();
+
+	params->hdr.tag = ATAG_CORE;
+	params->hdr.size = tag_size(tag_core);
+
+	params->u.core.flags = 0;
+	params->u.core.pagesize = 0;
+	params->u.core.rootdev = 0;
+
+	params = tag_next(params);
+}
+
+static void setup_memory_tags(void)
+{
+	struct memory_bank *bank;
+
+	for_each_memory_bank(bank) {
+		params->hdr.tag = ATAG_MEM;
+		params->hdr.size = tag_size(tag_mem32);
+
+		params->u.mem.start = bank->start;
+		params->u.mem.size = bank->size;
+
+		params = tag_next(params);
+	}
+}
+
+static void setup_commandline_tag(const char *commandline, int swap)
+{
+	const char *p;
+	size_t words;
+
+	if (!commandline)
+		return;
+
+	/* eat leading white space */
+	for (p = commandline; *p == ' '; p++) ;
+
+	/*
+	 * skip non-existent command lines so the kernel will still
+	 * use its default command line.
+	 */
+	if (*p == '\0')
+		return;
+
+	words = (strlen(p) + 1 /* NUL */ + 3 /* round up */) >> 2;
+	params->hdr.tag = ATAG_CMDLINE;
+	params->hdr.size = (sizeof(struct tag_header) >> 2) + words;
+
+	strcpy(params->u.cmdline.cmdline, p);
+
+#ifdef CONFIG_BOOT_ENDIANNESS_SWITCH
+	if (swap) {
+		u32 *cmd = (u32 *)params->u.cmdline.cmdline;
+		while (words--)
+			cmd[words] = swab32(cmd[words]);
+	}
+#endif
+
+	params = tag_next(params);
+}
+
+static void setup_revision_tag(void)
+{
+	u32 system_rev = armlinux_get_revision();
+
+	if (system_rev) {
+		params->hdr.tag = ATAG_REVISION;
+		params->hdr.size = tag_size(tag_revision);
+
+		params->u.revision.rev = system_rev;
+
+		params = tag_next(params);
+	}
+}
+
+static void setup_serial_tag(void)
+{
+	u64 system_serial = armlinux_get_serial();
+
+	if (system_serial) {
+		params->hdr.tag = ATAG_SERIAL;
+		params->hdr.size = tag_size(tag_serialnr);
+
+		params->u.serialnr.low  = system_serial & 0xffffffff;
+		params->u.serialnr.high = system_serial >> 32;
+
+		params = tag_next(params);
+	}
+}
+
+static void setup_initrd_tag(unsigned long start, unsigned long size)
+{
+	/* an ATAG_INITRD node tells the kernel where the compressed
+	 * ramdisk can be found. ATAG_RDIMG is a better name, actually.
+	 */
+	params->hdr.tag = ATAG_INITRD2;
+	params->hdr.size = tag_size(tag_initrd);
+
+	params->u.initrd.start = start;
+	params->u.initrd.size = size;
+
+	params = tag_next(params);
+}
+
+static void setup_end_tag (void)
+{
+	params->hdr.tag = ATAG_NONE;
+	params->hdr.size = 0;
+}
+
+static void setup_tags(unsigned long initrd_address,
+		unsigned long initrd_size, int swap)
+{
+	const char *commandline = linux_bootargs_get();
+
+	setup_start_tag();
+	setup_memory_tags();
+	setup_commandline_tag(commandline, swap);
+
+	if (initrd_size)
+		setup_initrd_tag(initrd_address, initrd_size);
+
+	setup_revision_tag();
+	setup_serial_tag();
+#ifdef CONFIG_ARM_BOARD_APPEND_ATAG
+	if (atag_appender != NULL)
+		params = atag_appender(params);
+#endif
+	setup_end_tag();
+
+	printf("commandline: %s\n"
+	       "arch_number: %d\n", commandline, armlinux_get_architecture());
+
+}
+
+void start_linux(void *adr, int swap, unsigned long initrd_address,
+		unsigned long initrd_size, void *oftree)
+{
+	void (*kernel)(int zero, int arch, void *params) = adr;
+	void *params = NULL;
+	int architecture;
+
+	if (oftree) {
+		pr_debug("booting kernel with devicetree\n");
+		params = oftree;
+	} else {
+		setup_tags(initrd_address, initrd_size, swap);
+		params = armlinux_get_bootparams();
+	}
+	architecture = armlinux_get_architecture();
+
+	shutdown_barebox();
+	if (swap) {
+		u32 reg;
+		__asm__ __volatile__("mrc p15, 0, %0, c1, c0" : "=r" (reg));
+		reg ^= CR_B; /* swap big-endian flag */
+		__asm__ __volatile__("mcr p15, 0, %0, c1, c0" :: "r" (reg));
+	}
+
+	kernel(0, architecture, params);
+}
diff --git a/arch/arm/lib32/ashldi3.S b/arch/arm/lib32/ashldi3.S
new file mode 100644
index 0000000000..b62e06f602
--- /dev/null
+++ b/arch/arm/lib32/ashldi3.S
@@ -0,0 +1,50 @@
+/* Copyright 1995, 1996, 1998, 1999, 2000, 2003, 2004, 2005
+   Free Software Foundation, Inc.
+
+This file 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, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file 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 <linux/linkage.h>
+
+#ifdef __ARMEB__
+#define al r1
+#define ah r0
+#else
+#define al r0
+#define ah r1
+#endif
+
+.section .text.__ashldi3
+ENTRY(__ashldi3)
+ENTRY(__aeabi_llsl)
+
+	subs	r3, r2, #32
+	rsb	ip, r2, #32
+	movmi	ah, ah, lsl r2
+	movpl	ah, al, lsl r3
+ ARM(	orrmi	ah, ah, al, lsr ip	)
+ THUMB(	lsrmi	r3, al, ip		)
+ THUMB(	orrmi	ah, ah, r3		)
+	mov	al, al, lsl r2
+	mov	pc, lr
+
+ENDPROC(__ashldi3)
+ENDPROC(__aeabi_llsl)
diff --git a/arch/arm/lib32/ashrdi3.S b/arch/arm/lib32/ashrdi3.S
new file mode 100644
index 0000000000..db849b65fc
--- /dev/null
+++ b/arch/arm/lib32/ashrdi3.S
@@ -0,0 +1,50 @@
+/* Copyright 1995, 1996, 1998, 1999, 2000, 2003, 2004, 2005
+   Free Software Foundation, Inc.
+
+This file 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, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file 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 <linux/linkage.h>
+
+#ifdef __ARMEB__
+#define al r1
+#define ah r0
+#else
+#define al r0
+#define ah r1
+#endif
+
+.section .text.__ashrdi3
+ENTRY(__ashrdi3)
+ENTRY(__aeabi_lasr)
+
+	subs	r3, r2, #32
+	rsb	ip, r2, #32
+	movmi	al, al, lsr r2
+	movpl	al, ah, asr r3
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
+	mov	ah, ah, asr r2
+	mov	pc, lr
+
+ENDPROC(__ashrdi3)
+ENDPROC(__aeabi_lasr)
diff --git a/arch/arm/lib32/barebox.lds.S b/arch/arm/lib32/barebox.lds.S
new file mode 100644
index 0000000000..6dc8bd2f3c
--- /dev/null
+++ b/arch/arm/lib32/barebox.lds.S
@@ -0,0 +1,126 @@
+/*
+ * (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("elf32-littlearm", "elf32-littlearm", "elf32-littlearm")
+OUTPUT_ARCH(arm)
+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 = .;
+		. = ALIGN(4);
+		__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/lib32/bootz.c b/arch/arm/lib32/bootz.c
new file mode 100644
index 0000000000..5167c9d20d
--- /dev/null
+++ b/arch/arm/lib32/bootz.c
@@ -0,0 +1,136 @@
+#include <common.h>
+#include <command.h>
+#include <fs.h>
+#include <of.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <malloc.h>
+#include <linux/sizes.h>
+#include <asm/byteorder.h>
+#include <asm/armlinux.h>
+#include <asm/system.h>
+#include <asm-generic/memory_layout.h>
+#include <memory.h>
+
+struct zimage_header {
+	u32	unused[9];
+	u32	magic;
+	u32	start;
+	u32	end;
+};
+
+#define ZIMAGE_MAGIC 0x016F2818
+
+static int do_bootz(int argc, char *argv[])
+{
+	int fd, ret, swap = 0;
+	struct zimage_header __header, *header;
+	void *zimage;
+	void *oftree = NULL;
+	u32 end;
+	int usemap = 0;
+	struct memory_bank *bank = list_first_entry(&memory_banks, struct memory_bank, list);
+	struct resource *res = NULL;
+
+	if (argc != 2)
+		return COMMAND_ERROR_USAGE;
+
+	fd = open(argv[1], O_RDONLY);
+	if (fd < 0) {
+		perror("open");
+		return 1;
+	}
+
+	/*
+	 * We can save the memcpy of the zImage if it already is in
+	 * the first 128MB of SDRAM.
+	 */
+	zimage = memmap(fd, PROT_READ);
+	if (zimage && (unsigned long)zimage  >= bank->start &&
+			(unsigned long)zimage < bank->start + SZ_128M) {
+		usemap = 1;
+		header = zimage;
+	}
+
+	if (!usemap) {
+		header = &__header;
+		ret = read(fd, header, sizeof(*header));
+		if (ret < sizeof(*header)) {
+			printf("could not read %s\n", argv[1]);
+			goto err_out;
+		}
+	}
+
+	switch (header->magic) {
+#ifdef CONFIG_BOOT_ENDIANNESS_SWITCH
+	case swab32(ZIMAGE_MAGIC):
+		swap = 1;
+		/* fall through */
+#endif
+	case ZIMAGE_MAGIC:
+		break;
+	default:
+		printf("invalid magic 0x%08x\n", header->magic);
+		goto err_out;
+	}
+
+	end = header->end;
+
+	if (swap)
+		end = swab32(end);
+
+	if (!usemap) {
+		if (bank->size <= SZ_128M) {
+			zimage = xmalloc(end);
+		} else {
+			zimage = (void *)bank->start + SZ_8M;
+			res = request_sdram_region("zimage",
+					bank->start + SZ_8M, end);
+			if (!res) {
+				printf("can't request region for kernel\n");
+				goto err_out1;
+			}
+		}
+
+		memcpy(zimage, header, sizeof(*header));
+
+		ret = read(fd, zimage + sizeof(*header), end - sizeof(*header));
+		if (ret < end - sizeof(*header)) {
+			printf("could not read %s\n", argv[1]);
+			goto err_out2;
+		}
+	}
+
+	if (swap) {
+		void *ptr;
+		for (ptr = zimage; ptr < zimage + end; ptr += 4)
+			*(u32 *)ptr = swab32(*(u32 *)ptr);
+	}
+
+	printf("loaded zImage from %s with size %d\n", argv[1], end);
+#ifdef CONFIG_OFTREE
+	oftree = of_get_fixed_tree(NULL);
+#endif
+
+	start_linux(zimage, swap, 0, 0, oftree);
+
+	return 0;
+
+err_out2:
+	if (res)
+		release_sdram_region(res);
+err_out1:
+	free(zimage);
+err_out:
+	close(fd);
+
+	return 1;
+}
+
+BAREBOX_CMD_START(bootz)
+	.cmd            = do_bootz,
+	BAREBOX_CMD_DESC("boot Linux zImage")
+	BAREBOX_CMD_OPTS("FILE")
+	BAREBOX_CMD_GROUP(CMD_GRP_BOOT)
+BAREBOX_CMD_END
+
diff --git a/arch/arm/lib32/copy_template.S b/arch/arm/lib32/copy_template.S
new file mode 100644
index 0000000000..d8eb06328a
--- /dev/null
+++ b/arch/arm/lib32/copy_template.S
@@ -0,0 +1,268 @@
+/*
+ *  linux/arch/arm/lib/copy_template.s
+ *
+ *  Code template for optimized memory copy functions
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	Sep 28, 2005
+ *  Copyright:	MontaVista Software, Inc.
+ *
+ *  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.
+ */
+
+/*
+ * Theory of operation
+ * -------------------
+ *
+ * This file provides the core code for a forward memory copy used in
+ * the implementation of memcopy(), copy_to_user() and copy_from_user().
+ *
+ * The including file must define the following accessor macros
+ * according to the need of the given function:
+ *
+ * ldr1w ptr reg abort
+ *
+ *	This loads one word from 'ptr', stores it in 'reg' and increments
+ *	'ptr' to the next word. The 'abort' argument is used for fixup tables.
+ *
+ * ldr4w ptr reg1 reg2 reg3 reg4 abort
+ * ldr8w ptr, reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
+ *
+ *	This loads four or eight words starting from 'ptr', stores them
+ *	in provided registers and increments 'ptr' past those words.
+ *	The'abort' argument is used for fixup tables.
+ *
+ * ldr1b ptr reg cond abort
+ *
+ *	Similar to ldr1w, but it loads a byte and increments 'ptr' one byte.
+ *	It also must apply the condition code if provided, otherwise the
+ *	"al" condition is assumed by default.
+ *
+ * str1w ptr reg abort
+ * str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
+ * str1b ptr reg cond abort
+ *
+ *	Same as their ldr* counterparts, but data is stored to 'ptr' location
+ *	rather than being loaded.
+ *
+ * enter reg1 reg2
+ *
+ *	Preserve the provided registers on the stack plus any additional
+ *	data as needed by the implementation including this code. Called
+ *	upon code entry.
+ *
+ * exit reg1 reg2
+ *
+ *	Restore registers with the values previously saved with the
+ *	'preserv' macro. Called upon code termination.
+ *
+ * LDR1W_SHIFT
+ * STR1W_SHIFT
+ *
+ *	Correction to be applied to the "ip" register when branching into
+ *	the ldr1w or str1w instructions (some of these macros may expand to
+ *	than one 32bit instruction in Thumb-2)
+ */
+
+
+		enter	r4, lr
+
+		subs	r2, r2, #4
+		blt	8f
+		ands	ip, r0, #3
+	PLD(	pld	[r1, #0]		)
+		bne	9f
+		ands	ip, r1, #3
+		bne	10f
+
+1:		subs	r2, r2, #(28)
+		stmfd	sp!, {r5 - r8}
+		blt	5f
+
+	CALGN(	ands	ip, r0, #31		)
+	CALGN(	rsb	r3, ip, #32		)
+	CALGN(	sbcnes	r4, r3, r2		)  @ C is always set here
+	CALGN(	bcs	2f			)
+	CALGN(	adr	r4, 6f			)
+	CALGN(	subs	r2, r2, r3		)  @ C gets set
+	CALGN(	add	pc, r4, ip		)
+
+	PLD(	pld	[r1, #0]		)
+2:	PLD(	subs	r2, r2, #96		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	blt	4f			)
+	PLD(	pld	[r1, #60]		)
+	PLD(	pld	[r1, #92]		)
+
+3:	PLD(	pld	[r1, #124]		)
+4:		ldr8w	r1, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
+		subs	r2, r2, #32
+		str8w	r0, r3, r4, r5, r6, r7, r8, ip, lr, abort=20f
+		bge	3b
+	PLD(	cmn	r2, #96			)
+	PLD(	bge	4b			)
+
+5:		ands	ip, r2, #28
+		rsb	ip, ip, #32
+#if LDR1W_SHIFT > 0
+		lsl	ip, ip, #LDR1W_SHIFT
+#endif
+		addne	pc, pc, ip		@ C is always clear here
+		b	7f
+6:
+		.rept	(1 << LDR1W_SHIFT)
+		W(nop)
+		.endr
+		ldr1w	r1, r3, abort=20f
+		ldr1w	r1, r4, abort=20f
+		ldr1w	r1, r5, abort=20f
+		ldr1w	r1, r6, abort=20f
+		ldr1w	r1, r7, abort=20f
+		ldr1w	r1, r8, abort=20f
+		ldr1w	r1, lr, abort=20f
+
+#if LDR1W_SHIFT < STR1W_SHIFT
+		lsl	ip, ip, #STR1W_SHIFT - LDR1W_SHIFT
+#elif LDR1W_SHIFT > STR1W_SHIFT
+		lsr	ip, ip, #LDR1W_SHIFT - STR1W_SHIFT
+#endif
+		add	pc, pc, ip
+		nop
+		.rept	(1 << STR1W_SHIFT)
+		W(nop)
+		.endr
+		str1w	r0, r3, abort=20f
+		str1w	r0, r4, abort=20f
+		str1w	r0, r5, abort=20f
+		str1w	r0, r6, abort=20f
+		str1w	r0, r7, abort=20f
+		str1w	r0, r8, abort=20f
+		str1w	r0, lr, abort=20f
+
+	CALGN(	bcs	2b			)
+
+7:		ldmfd	sp!, {r5 - r8}
+
+8:		movs	r2, r2, lsl #31
+		ldr1b	r1, r3, ne, abort=21f
+		ldr1b	r1, r4, cs, abort=21f
+		ldr1b	r1, ip, cs, abort=21f
+		str1b	r0, r3, ne, abort=21f
+		str1b	r0, r4, cs, abort=21f
+		str1b	r0, ip, cs, abort=21f
+
+		exit	r4, pc
+
+9:		rsb	ip, ip, #4
+		cmp	ip, #2
+		ldr1b	r1, r3, gt, abort=21f
+		ldr1b	r1, r4, ge, abort=21f
+		ldr1b	r1, lr, abort=21f
+		str1b	r0, r3, gt, abort=21f
+		str1b	r0, r4, ge, abort=21f
+		subs	r2, r2, ip
+		str1b	r0, lr, abort=21f
+		blt	8b
+		ands	ip, r1, #3
+		beq	1b
+
+10:		bic	r1, r1, #3
+		cmp	ip, #2
+		ldr1w	r1, lr, abort=21f
+		beq	17f
+		bgt	18f
+
+
+		.macro	forward_copy_shift pull push
+
+		subs	r2, r2, #28
+		blt	14f
+
+	CALGN(	ands	ip, r0, #31		)
+	CALGN(	rsb	ip, ip, #32		)
+	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
+	CALGN(	subcc	r2, r2, ip		)
+	CALGN(	bcc	15f			)
+
+11:		stmfd	sp!, {r5 - r9}
+
+	PLD(	pld	[r1, #0]		)
+	PLD(	subs	r2, r2, #96		)
+	PLD(	pld	[r1, #28]		)
+	PLD(	blt	13f			)
+	PLD(	pld	[r1, #60]		)
+	PLD(	pld	[r1, #92]		)
+
+12:	PLD(	pld	[r1, #124]		)
+13:		ldr4w	r1, r4, r5, r6, r7, abort=19f
+		mov	r3, lr, pull #\pull
+		subs	r2, r2, #32
+		ldr4w	r1, r8, r9, ip, lr, abort=19f
+		orr	r3, r3, r4, push #\push
+		mov	r4, r4, pull #\pull
+		orr	r4, r4, r5, push #\push
+		mov	r5, r5, pull #\pull
+		orr	r5, r5, r6, push #\push
+		mov	r6, r6, pull #\pull
+		orr	r6, r6, r7, push #\push
+		mov	r7, r7, pull #\pull
+		orr	r7, r7, r8, push #\push
+		mov	r8, r8, pull #\pull
+		orr	r8, r8, r9, push #\push
+		mov	r9, r9, pull #\pull
+		orr	r9, r9, ip, push #\push
+		mov	ip, ip, pull #\pull
+		orr	ip, ip, lr, push #\push
+		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
+		bge	12b
+	PLD(	cmn	r2, #96			)
+	PLD(	bge	13b			)
+
+		ldmfd	sp!, {r5 - r9}
+
+14:		ands	ip, r2, #28
+		beq	16f
+
+15:		mov	r3, lr, pull #\pull
+		ldr1w	r1, lr, abort=21f
+		subs	ip, ip, #4
+		orr	r3, r3, lr, push #\push
+		str1w	r0, r3, abort=21f
+		bgt	15b
+	CALGN(	cmp	r2, #0			)
+	CALGN(	bge	11b			)
+
+16:		sub	r1, r1, #(\push / 8)
+		b	8b
+
+		.endm
+
+
+		forward_copy_shift	pull=8	push=24
+
+17:		forward_copy_shift	pull=16	push=16
+
+18:		forward_copy_shift	pull=24	push=8
+
+
+/*
+ * Abort preamble and completion macros.
+ * If a fixup handler is required then those macros must surround it.
+ * It is assumed that the fixup code will handle the private part of
+ * the exit macro.
+ */
+
+	.macro	copy_abort_preamble
+19:	ldmfd	sp!, {r5 - r9}
+	b	21f
+20:	ldmfd	sp!, {r5 - r8}
+21:
+	.endm
+
+	.macro	copy_abort_end
+	ldmfd	sp!, {r4, pc}
+	.endm
+
+
diff --git a/arch/arm/lib32/div0.c b/arch/arm/lib32/div0.c
new file mode 100644
index 0000000000..852cb72331
--- /dev/null
+++ b/arch/arm/lib32/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/lib32/findbit.S b/arch/arm/lib32/findbit.S
new file mode 100644
index 0000000000..ef4caff1ad
--- /dev/null
+++ b/arch/arm/lib32/findbit.S
@@ -0,0 +1,197 @@
+/*
+ * Originally from Linux kernel
+ *  arch/arm/lib/findbit.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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.
+ *
+ * 16th March 2001 - John Ripley <jripley@sonicblue.com>
+ *   Fixed so that "size" is an exclusive not an inclusive quantity.
+ *   All users of these functions expect exclusive sizes, and may
+ *   also call with zero size.
+ * Reworked by rmk.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+                .text
+
+/*
+ * Purpose  : Find a 'zero' bit
+ * Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
+ */
+ENTRY(_find_first_zero_bit_le)
+		teq	r1, #0
+		beq	3f
+		mov	r2, #0
+1:
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		eors	r3, r3, #0xff		@ invert bits
+		bne	.L_found		@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		mov	pc, lr
+ENDPROC(_find_first_zero_bit_le)
+
+/*
+ * Purpose  : Find next 'zero' bit
+ * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
+ */
+ENTRY(_find_next_zero_bit_le)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		eor	r3, r3, #0xff		@ now looking for a 1 bit
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.L_found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+ENDPROC(_find_next_zero_bit_le)
+
+/*
+ * Purpose  : Find a 'one' bit
+ * Prototype: int find_first_bit(const unsigned long *addr, unsigned int maxbit);
+ */
+ENTRY(_find_first_bit_le)
+		teq	r1, #0
+		beq	3f
+		mov	r2, #0
+1:
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		movs	r3, r3
+		bne	.L_found		@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		mov	pc, lr
+ENDPROC(_find_first_bit_le)
+
+/*
+ * Purpose  : Find next 'one' bit
+ * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
+ */
+ENTRY(_find_next_bit_le)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+ ARM(		ldrb	r3, [r0, r2, lsr #3]	)
+ THUMB(		lsr	r3, r2, #3		)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.L_found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+ENDPROC(_find_next_bit_le)
+
+#ifdef __ARMEB__
+
+ENTRY(_find_first_zero_bit_be)
+		teq	r1, #0
+		beq	3f
+		mov	r2, #0
+1:		eor	r3, r2, #0x18		@ big endian byte ordering
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		eors	r3, r3, #0xff		@ invert bits
+		bne	.L_found		@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		mov	pc, lr
+ENDPROC(_find_first_zero_bit_be)
+
+ENTRY(_find_next_zero_bit_be)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+		eor	r3, r2, #0x18		@ big endian byte ordering
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		eor	r3, r3, #0xff		@ now looking for a 1 bit
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.L_found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+ENDPROC(_find_next_zero_bit_be)
+
+ENTRY(_find_first_bit_be)
+		teq	r1, #0
+		beq	3f
+		mov	r2, #0
+1:		eor	r3, r2, #0x18		@ big endian byte ordering
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		movs	r3, r3
+		bne	.L_found		@ any now set - found zero bit
+		add	r2, r2, #8		@ next bit pointer
+2:		cmp	r2, r1			@ any more?
+		blo	1b
+3:		mov	r0, r1			@ no free bits
+		mov	pc, lr
+ENDPROC(_find_first_bit_be)
+
+ENTRY(_find_next_bit_be)
+		teq	r1, #0
+		beq	3b
+		ands	ip, r2, #7
+		beq	1b			@ If new byte, goto old routine
+		eor	r3, r2, #0x18		@ big endian byte ordering
+ ARM(		ldrb	r3, [r0, r3, lsr #3]	)
+ THUMB(		lsr	r3, #3			)
+ THUMB(		ldrb	r3, [r0, r3]		)
+		movs	r3, r3, lsr ip		@ shift off unused bits
+		bne	.L_found
+		orr	r2, r2, #7		@ if zero, then no bits here
+		add	r2, r2, #1		@ align bit pointer
+		b	2b			@ loop for next bit
+ENDPROC(_find_next_bit_be)
+
+#endif
+
+/*
+ * One or more bits in the LSB of r3 are assumed to be set.
+ */
+.L_found:
+#if __LINUX_ARM_ARCH__ >= 5
+		rsb	r0, r3, #0
+		and	r3, r3, r0
+		clz	r3, r3
+		rsb	r3, r3, #31
+		add	r0, r2, r3
+#else
+		tst	r3, #0x0f
+		addeq	r2, r2, #4
+		movne	r3, r3, lsl #4
+		tst	r3, #0x30
+		addeq	r2, r2, #2
+		movne	r3, r3, lsl #2
+		tst	r3, #0x40
+		addeq	r2, r2, #1
+		mov	r0, r2
+#endif
+		cmp	r1, r0			@ Clamp to maxbit
+		movlo	r0, r1
+		mov	pc, lr
+
diff --git a/arch/arm/lib32/io-readsb.S b/arch/arm/lib32/io-readsb.S
new file mode 100644
index 0000000000..963c455175
--- /dev/null
+++ b/arch/arm/lib32/io-readsb.S
@@ -0,0 +1,125 @@
+/*
+ *  linux/arch/arm/lib/io-readsb.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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>
+
+.section .text.readsb
+
+.Linsb_align:	rsb	ip, ip, #4
+		cmp	ip, r2
+		movgt	ip, r2
+		cmp	ip, #2
+		ldrb	r3, [r0]
+		strb	r3, [r1], #1
+		ldrgeb	r3, [r0]
+		strgeb	r3, [r1], #1
+		ldrgtb	r3, [r0]
+		strgtb	r3, [r1], #1
+		subs	r2, r2, ip
+		bne	.Linsb_aligned
+
+ENTRY(readsb)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	.Linsb_align
+
+.Linsb_aligned:	stmfd	sp!, {r4 - r6, lr}
+
+		subs	r2, r2, #16
+		bmi	.Linsb_no_16
+
+.Linsb_16_lp:	ldrb	r3, [r0]
+		ldrb	r4, [r0]
+		ldrb	r5, [r0]
+		mov	r3, r3,     put_byte_0
+		ldrb	r6, [r0]
+		orr	r3, r3, r4, put_byte_1
+		ldrb	r4, [r0]
+		orr	r3, r3, r5, put_byte_2
+		ldrb	r5, [r0]
+		orr	r3, r3, r6, put_byte_3
+		ldrb	r6, [r0]
+		mov	r4, r4,     put_byte_0
+		ldrb	ip, [r0]
+		orr	r4, r4, r5, put_byte_1
+		ldrb	r5, [r0]
+		orr	r4, r4, r6, put_byte_2
+		ldrb	r6, [r0]
+		orr	r4, r4, ip, put_byte_3
+		ldrb	ip, [r0]
+		mov	r5, r5,     put_byte_0
+		ldrb	lr, [r0]
+		orr	r5, r5, r6, put_byte_1
+		ldrb	r6, [r0]
+		orr	r5, r5, ip, put_byte_2
+		ldrb	ip, [r0]
+		orr	r5, r5, lr, put_byte_3
+		ldrb	lr, [r0]
+		mov	r6, r6,     put_byte_0
+		orr	r6, r6, ip, put_byte_1
+		ldrb	ip, [r0]
+		orr	r6, r6, lr, put_byte_2
+		orr	r6, r6, ip, put_byte_3
+		stmia	r1!, {r3 - r6}
+
+		subs	r2, r2, #16
+		bpl	.Linsb_16_lp
+
+		tst	r2, #15
+		ldmeqfd	sp!, {r4 - r6, pc}
+
+.Linsb_no_16:	tst	r2, #8
+		beq	.Linsb_no_8
+
+		ldrb	r3, [r0]
+		ldrb	r4, [r0]
+		ldrb	r5, [r0]
+		mov	r3, r3,     put_byte_0
+		ldrb	r6, [r0]
+		orr	r3, r3, r4, put_byte_1
+		ldrb	r4, [r0]
+		orr	r3, r3, r5, put_byte_2
+		ldrb	r5, [r0]
+		orr	r3, r3, r6, put_byte_3
+		ldrb	r6, [r0]
+		mov	r4, r4,     put_byte_0
+		ldrb	ip, [r0]
+		orr	r4, r4, r5, put_byte_1
+		orr	r4, r4, r6, put_byte_2
+		orr	r4, r4, ip, put_byte_3
+		stmia	r1!, {r3, r4}
+
+.Linsb_no_8:	tst	r2, #4
+		beq	.Linsb_no_4
+
+		ldrb	r3, [r0]
+		ldrb	r4, [r0]
+		ldrb	r5, [r0]
+		ldrb	r6, [r0]
+		mov	r3, r3,     put_byte_0
+		orr	r3, r3, r4, put_byte_1
+		orr	r3, r3, r5, put_byte_2
+		orr	r3, r3, r6, put_byte_3
+		str	r3, [r1], #4
+
+.Linsb_no_4:	ands	r2, r2, #3
+		ldmeqfd	sp!, {r4 - r6, pc}
+
+		cmp	r2, #2
+		ldrb	r3, [r0]
+		strb	r3, [r1], #1
+		ldrgeb	r3, [r0]
+		strgeb	r3, [r1], #1
+		ldrgtb	r3, [r0]
+		strgtb	r3, [r1]
+
+		ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(readsb)
diff --git a/arch/arm/lib32/io-readsl.S b/arch/arm/lib32/io-readsl.S
new file mode 100644
index 0000000000..47a29744e9
--- /dev/null
+++ b/arch/arm/lib32/io-readsl.S
@@ -0,0 +1,81 @@
+/*
+ *  linux/arch/arm/lib/io-readsl.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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>
+
+.section .text.readsl
+
+ENTRY(readsl)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	3f
+
+		subs	r2, r2, #4
+		bmi	2f
+		stmfd	sp!, {r4, lr}
+1:		ldr	r3, [r0, #0]
+		ldr	r4, [r0, #0]
+		ldr	ip, [r0, #0]
+		ldr	lr, [r0, #0]
+		subs	r2, r2, #4
+		stmia	r1!, {r3, r4, ip, lr}
+		bpl	1b
+		ldmfd	sp!, {r4, lr}
+2:		movs	r2, r2, lsl #31
+		ldrcs	r3, [r0, #0]
+		ldrcs	ip, [r0, #0]
+		stmcsia	r1!, {r3, ip}
+		ldrne	r3, [r0, #0]
+		strne	r3, [r1, #0]
+		mov	pc, lr
+
+3:		ldr	r3, [r0]
+		cmp	ip, #2
+		mov	ip, r3, get_byte_0
+		strb	ip, [r1], #1
+		bgt	6f
+		mov	ip, r3, get_byte_1
+		strb	ip, [r1], #1
+		beq	5f
+		mov	ip, r3, get_byte_2
+		strb	ip, [r1], #1
+
+4:		subs	r2, r2, #1
+		mov	ip, r3, pull #24
+		ldrne	r3, [r0]
+		orrne	ip, ip, r3, push #8
+		strne	ip, [r1], #4
+		bne	4b
+		b	8f
+
+5:		subs	r2, r2, #1
+		mov	ip, r3, pull #16
+		ldrne	r3, [r0]
+		orrne	ip, ip, r3, push #16
+		strne	ip, [r1], #4
+		bne	5b
+		b	7f
+
+6:		subs	r2, r2, #1
+		mov	ip, r3, pull #8
+		ldrne	r3, [r0]
+		orrne	ip, ip, r3, push #24
+		strne	ip, [r1], #4
+		bne	6b
+
+		mov	r3, ip, get_byte_2
+		strb	r3, [r1, #2]
+7:		mov	r3, ip, get_byte_1
+		strb	r3, [r1, #1]
+8:		mov	r3, ip, get_byte_0
+		strb	r3, [r1, #0]
+		mov	pc, lr
+ENDPROC(readsl)
diff --git a/arch/arm/lib32/io-readsw-armv4.S b/arch/arm/lib32/io-readsw-armv4.S
new file mode 100644
index 0000000000..f5b34a3479
--- /dev/null
+++ b/arch/arm/lib32/io-readsw-armv4.S
@@ -0,0 +1,133 @@
+/*
+ *  linux/arch/arm/lib/io-readsw-armv4.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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>
+
+		.macro	pack, rd, hw1, hw2
+#ifndef __ARMEB__
+		orr	\rd, \hw1, \hw2, lsl #16
+#else
+		orr	\rd, \hw2, \hw1, lsl #16
+#endif
+		.endm
+
+.section .text.readsw
+
+.Linsw_align:	movs	ip, r1, lsl #31
+		bne	.Linsw_noalign
+		ldrh	ip, [r0]
+		sub	r2, r2, #1
+		strh	ip, [r1], #2
+
+ENTRY(readsw)
+		teq	r2, #0
+		moveq	pc, lr
+		tst	r1, #3
+		bne	.Linsw_align
+
+		stmfd	sp!, {r4, r5, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_insw_8
+
+.Linsw_8_lp:	ldrh	r3, [r0]
+		ldrh	r4, [r0]
+		pack	r3, r3, r4
+
+		ldrh	r4, [r0]
+		ldrh	r5, [r0]
+		pack	r4, r4, r5
+
+		ldrh	r5, [r0]
+		ldrh	ip, [r0]
+		pack	r5, r5, ip
+
+		ldrh	ip, [r0]
+		ldrh	lr, [r0]
+		pack	ip, ip, lr
+
+		subs	r2, r2, #8
+		stmia	r1!, {r3 - r5, ip}
+		bpl	.Linsw_8_lp
+
+.Lno_insw_8:	tst	r2, #4
+		beq	.Lno_insw_4
+
+		ldrh	r3, [r0]
+		ldrh	r4, [r0]
+		pack	r3, r3, r4
+
+		ldrh	r4, [r0]
+		ldrh	ip, [r0]
+		pack	r4, r4, ip
+
+		stmia	r1!, {r3, r4}
+
+.Lno_insw_4:	movs	r2, r2, lsl #31
+		bcc	.Lno_insw_2
+
+		ldrh	r3, [r0]
+		ldrh	ip, [r0]
+		pack	r3, r3, ip
+		str	r3, [r1], #4
+
+.Lno_insw_2:	ldrneh	r3, [r0]
+		strneh	r3, [r1]
+
+		ldmfd	sp!, {r4, r5, pc}
+
+#ifdef __ARMEB__
+#define _BE_ONLY_(code...)	code
+#define _LE_ONLY_(code...)
+#define push_hbyte0		lsr #8
+#define pull_hbyte1		lsl #24
+#else
+#define _BE_ONLY_(code...)
+#define _LE_ONLY_(code...) code
+#define push_hbyte0		lsl #24
+#define pull_hbyte1		lsr #8
+#endif
+
+.Linsw_noalign:	stmfd	sp!, {r4, lr}
+		ldrccb	ip, [r1, #-1]!
+		bcc	1f
+
+		ldrh	ip, [r0]
+		sub	r2, r2, #1
+   _BE_ONLY_(	mov	ip, ip, ror #8		)
+		strb	ip, [r1], #1
+   _LE_ONLY_(	mov	ip, ip, lsr #8		)
+   _BE_ONLY_(	mov	ip, ip, lsr #24		)
+
+1:		subs	r2, r2, #2
+		bmi	3f
+   _BE_ONLY_(	mov	ip, ip, lsl #24		)
+
+2:		ldrh	r3, [r0]
+		ldrh	r4, [r0]
+		subs	r2, r2, #2
+		orr	ip, ip, r3, lsl #8
+		orr	ip, ip, r4, push_hbyte0
+		str	ip, [r1], #4
+		mov	ip, r4, pull_hbyte1
+		bpl	2b
+
+   _BE_ONLY_(	mov	ip, ip, lsr #24		)
+
+3:		tst	r2, #1
+		strb	ip, [r1], #1
+		ldrneh	ip, [r0]
+   _BE_ONLY_(	movne	ip, ip, ror #8		)
+		strneb	ip, [r1], #1
+   _LE_ONLY_(	movne	ip, ip, lsr #8		)
+   _BE_ONLY_(	movne	ip, ip, lsr #24		)
+		strneb	ip, [r1]
+		ldmfd	sp!, {r4, pc}
+ENDPROC(readsw)
diff --git a/arch/arm/lib32/io-writesb.S b/arch/arm/lib32/io-writesb.S
new file mode 100644
index 0000000000..1ab8e47cb4
--- /dev/null
+++ b/arch/arm/lib32/io-writesb.S
@@ -0,0 +1,96 @@
+/*
+ *  linux/arch/arm/lib/io-writesb.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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>
+
+		.macro	outword, rd
+#ifndef __ARMEB__
+		strb	\rd, [r0]
+		mov	\rd, \rd, lsr #8
+		strb	\rd, [r0]
+		mov	\rd, \rd, lsr #8
+		strb	\rd, [r0]
+		mov	\rd, \rd, lsr #8
+		strb	\rd, [r0]
+#else
+		mov	lr, \rd, lsr #24
+		strb	lr, [r0]
+		mov	lr, \rd, lsr #16
+		strb	lr, [r0]
+		mov	lr, \rd, lsr #8
+		strb	lr, [r0]
+		strb	\rd, [r0]
+#endif
+		.endm
+
+.section .text.writesb
+
+.Loutsb_align:	rsb	ip, ip, #4
+		cmp	ip, r2
+		movgt	ip, r2
+		cmp	ip, #2
+		ldrb	r3, [r1], #1
+		strb	r3, [r0]
+		ldrgeb	r3, [r1], #1
+		strgeb	r3, [r0]
+		ldrgtb	r3, [r1], #1
+		strgtb	r3, [r0]
+		subs	r2, r2, ip
+		bne	.Loutsb_aligned
+
+ENTRY(writesb)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	.Loutsb_align
+
+.Loutsb_aligned:
+		stmfd	sp!, {r4, r5, lr}
+
+		subs	r2, r2, #16
+		bmi	.Loutsb_no_16
+
+.Loutsb_16_lp:	ldmia	r1!, {r3, r4, r5, ip}
+		outword	r3
+		outword	r4
+		outword	r5
+		outword	ip
+		subs	r2, r2, #16
+		bpl	.Loutsb_16_lp
+
+		tst	r2, #15
+		ldmeqfd	sp!, {r4, r5, pc}
+
+.Loutsb_no_16:	tst	r2, #8
+		beq	.Loutsb_no_8
+
+		ldmia	r1!, {r3, r4}
+		outword	r3
+		outword	r4
+
+.Loutsb_no_8:	tst	r2, #4
+		beq	.Loutsb_no_4
+
+		ldr	r3, [r1], #4
+		outword	r3
+
+.Loutsb_no_4:	ands	r2, r2, #3
+		ldmeqfd	sp!, {r4, r5, pc}
+
+		cmp	r2, #2
+		ldrb	r3, [r1], #1
+		strb	r3, [r0]
+		ldrgeb	r3, [r1], #1
+		strgeb	r3, [r0]
+		ldrgtb	r3, [r1]
+		strgtb	r3, [r0]
+
+		ldmfd	sp!, {r4, r5, pc}
+ENDPROC(writesb)
diff --git a/arch/arm/lib32/io-writesl.S b/arch/arm/lib32/io-writesl.S
new file mode 100644
index 0000000000..8a3bcd6456
--- /dev/null
+++ b/arch/arm/lib32/io-writesl.S
@@ -0,0 +1,69 @@
+/*
+ *  linux/arch/arm/lib/io-writesl.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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>
+
+.section .text.writesl
+
+ENTRY(writesl)
+		teq	r2, #0		@ do we have to check for the zero len?
+		moveq	pc, lr
+		ands	ip, r1, #3
+		bne	3f
+
+		subs	r2, r2, #4
+		bmi	2f
+		stmfd	sp!, {r4, lr}
+1:		ldmia	r1!, {r3, r4, ip, lr}
+		subs	r2, r2, #4
+		str	r3, [r0, #0]
+		str	r4, [r0, #0]
+		str	ip, [r0, #0]
+		str	lr, [r0, #0]
+		bpl	1b
+		ldmfd	sp!, {r4, lr}
+2:		movs	r2, r2, lsl #31
+		ldmcsia	r1!, {r3, ip}
+		strcs	r3, [r0, #0]
+		ldrne	r3, [r1, #0]
+		strcs	ip, [r0, #0]
+		strne	r3, [r0, #0]
+		mov	pc, lr
+
+3:		bic	r1, r1, #3
+		ldr	r3, [r1], #4
+		cmp	ip, #2
+		blt	5f
+		bgt	6f
+
+4:		mov	ip, r3, pull #16
+		ldr	r3, [r1], #4
+		subs	r2, r2, #1
+		orr	ip, ip, r3, push #16
+		str	ip, [r0]
+		bne	4b
+		mov	pc, lr
+
+5:		mov	ip, r3, pull #8
+		ldr	r3, [r1], #4
+		subs	r2, r2, #1
+		orr	ip, ip, r3, push #24
+		str	ip, [r0]
+		bne	5b
+		mov	pc, lr
+
+6:		mov	ip, r3, pull #24
+		ldr	r3, [r1], #4
+		subs	r2, r2, #1
+		orr	ip, ip, r3, push #8
+		str	ip, [r0]
+		bne	6b
+		mov	pc, lr
+ENDPROC(writesl)
diff --git a/arch/arm/lib32/io-writesw-armv4.S b/arch/arm/lib32/io-writesw-armv4.S
new file mode 100644
index 0000000000..9e8308dd77
--- /dev/null
+++ b/arch/arm/lib32/io-writesw-armv4.S
@@ -0,0 +1,102 @@
+/*
+ *  linux/arch/arm/lib/io-writesw-armv4.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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>
+
+		.macro	outword, rd
+#ifndef __ARMEB__
+		strh	\rd, [r0]
+		mov	\rd, \rd, lsr #16
+		strh	\rd, [r0]
+#else
+		mov	lr, \rd, lsr #16
+		strh	lr, [r0]
+		strh	\rd, [r0]
+#endif
+		.endm
+
+.section .text.__raw_writesw
+
+.Loutsw_align:	movs	ip, r1, lsl #31
+		bne	.Loutsw_noalign
+
+		ldrh	r3, [r1], #2
+		sub	r2, r2, #1
+		strh	r3, [r0]
+
+ENTRY(__raw_writesw)
+		teq	r2, #0
+		moveq	pc, lr
+		ands	r3, r1, #3
+		bne	.Loutsw_align
+
+		stmfd	sp!, {r4, r5, lr}
+
+		subs	r2, r2, #8
+		bmi	.Lno_outsw_8
+
+.Loutsw_8_lp:	ldmia	r1!, {r3, r4, r5, ip}
+		subs	r2, r2, #8
+		outword	r3
+		outword	r4
+		outword	r5
+		outword	ip
+		bpl	.Loutsw_8_lp
+
+.Lno_outsw_8:	tst	r2, #4
+		beq	.Lno_outsw_4
+
+		ldmia	r1!, {r3, ip}
+		outword	r3
+		outword	ip
+
+.Lno_outsw_4:	movs	r2, r2, lsl #31
+		bcc	.Lno_outsw_2
+
+		ldr	r3, [r1], #4
+		outword	r3
+
+.Lno_outsw_2:	ldrneh	r3, [r1]
+		strneh	r3, [r0]
+
+		ldmfd	sp!, {r4, r5, pc}
+
+#ifdef __ARMEB__
+#define pull_hbyte0	lsl #8
+#define push_hbyte1	lsr #24
+#else
+#define pull_hbyte0	lsr #24
+#define push_hbyte1	lsl #8
+#endif
+
+.Loutsw_noalign:
+ ARM(		ldr	r3, [r1, -r3]!	)
+ THUMB(		rsb	r3, r3, #0	)
+ THUMB(		ldr	r3, [r1, r3]	)
+ THUMB(		sub	r1, r3		)
+		subcs	r2, r2, #1
+		bcs	2f
+		subs	r2, r2, #2
+		bmi	3f
+
+1:		mov	ip, r3, lsr #8
+		strh	ip, [r0]
+2:		mov	ip, r3, pull_hbyte0
+		ldr	r3, [r1, #4]!
+		subs	r2, r2, #2
+		orr	ip, ip, r3, push_hbyte1
+		strh	ip, [r0]
+		bpl	1b
+
+		tst	r2, #1
+3:		movne	ip, r3, lsr #8
+		strneh	ip, [r0]
+		mov	pc, lr
+ENDPROC(__raw_writesw)
diff --git a/arch/arm/lib32/io.c b/arch/arm/lib32/io.c
new file mode 100644
index 0000000000..abfd887aac
--- /dev/null
+++ b/arch/arm/lib32/io.c
@@ -0,0 +1,50 @@
+#include <module.h>
+#include <linux/types.h>
+#include <io.h>
+
+/*
+ * Copy data from IO memory space to "real" memory space.
+ * This needs to be optimized.
+ */
+void memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
+{
+	unsigned char *t = to;
+	while (count) {
+		count--;
+		*t = readb(from);
+		t++;
+		from++;
+	}
+}
+
+/*
+ * Copy data from "real" memory space to IO memory space.
+ * This needs to be optimized.
+ */
+void memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
+{
+	const unsigned char *f = from;
+	while (count) {
+		count--;
+		writeb(*f, to);
+		f++;
+		to++;
+	}
+}
+
+/*
+ * "memset" on IO memory space.
+ * This needs to be optimized.
+ */
+void memset_io(volatile void __iomem *dst, int c, size_t count)
+{
+	while (count) {
+		count--;
+		writeb(c, dst);
+		dst++;
+	}
+}
+
+EXPORT_SYMBOL(memcpy_fromio);
+EXPORT_SYMBOL(memcpy_toio);
+EXPORT_SYMBOL(memset_io);
diff --git a/arch/arm/lib32/lib1funcs.S b/arch/arm/lib32/lib1funcs.S
new file mode 100644
index 0000000000..bf1d0192d6
--- /dev/null
+++ b/arch/arm/lib32/lib1funcs.S
@@ -0,0 +1,351 @@
+/*
+ * linux/arch/arm/lib/lib1funcs.S: Optimized ARM division routines
+ *
+ * Author: Nicolas Pitre <nico@fluxnic.net>
+ *   - contributed to gcc-3.4 on Sep 30, 2003
+ *   - adapted for the Linux kernel on Oct 2, 2003
+ */
+
+/* Copyright 1995, 1996, 1998, 1999, 2000, 2003 Free Software Foundation, Inc.
+
+This file 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, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file 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 <linux/linkage.h>
+#include <asm/assembler.h>
+
+
+.macro ARM_DIV_BODY dividend, divisor, result, curbit
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\curbit, \divisor
+	clz	\result, \dividend
+	sub	\result, \curbit, \result
+	mov	\curbit, #1
+	mov	\divisor, \divisor, lsl \result
+	mov	\curbit, \curbit, lsl \result
+	mov	\result, #0
+
+#else
+
+	@ Initially shift the divisor left 3 bits if possible,
+	@ set curbit accordingly.  This allows for curbit to be located
+	@ at the left end of each 4 bit nibbles in the division loop
+	@ to save one loop in most cases.
+	tst	\divisor, #0xe0000000
+	moveq	\divisor, \divisor, lsl #3
+	moveq	\curbit, #8
+	movne	\curbit, #1
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	movlo	\curbit, \curbit, lsl #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	movlo	\curbit, \curbit, lsl #1
+	blo	1b
+
+	mov	\result, #0
+
+#endif
+
+	@ Division loop
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	orrhs	\result,   \result,   \curbit
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	orrhs	\result,   \result,   \curbit,  lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	orrhs	\result,   \result,   \curbit,  lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	orrhs	\result,   \result,   \curbit,  lsr #3
+	cmp	\dividend, #0			@ Early termination?
+	movnes	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
+	movne	\divisor,  \divisor, lsr #4
+	bne	1b
+
+.endm
+
+
+.macro ARM_DIV2_ORDER divisor, order
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	rsb	\order, \order, #31
+
+#else
+
+	cmp	\divisor, #(1 << 16)
+	movhs	\divisor, \divisor, lsr #16
+	movhs	\order, #16
+	movlo	\order, #0
+
+	cmp	\divisor, #(1 << 8)
+	movhs	\divisor, \divisor, lsr #8
+	addhs	\order, \order, #8
+
+	cmp	\divisor, #(1 << 4)
+	movhs	\divisor, \divisor, lsr #4
+	addhs	\order, \order, #4
+
+	cmp	\divisor, #(1 << 2)
+	addhi	\order, \order, #3
+	addls	\order, \order, \divisor, lsr #1
+
+#endif
+
+.endm
+
+
+.macro ARM_MOD_BODY dividend, divisor, order, spare
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	\order, \divisor
+	clz	\spare, \dividend
+	sub	\order, \order, \spare
+	mov	\divisor, \divisor, lsl \order
+
+#else
+
+	mov	\order, #0
+
+	@ Unless the divisor is very big, shift it up in multiples of
+	@ four bits, since this is the amount of unwinding in the main
+	@ division loop.  Continue shifting until the divisor is
+	@ larger than the dividend.
+1:	cmp	\divisor, #0x10000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #4
+	addlo	\order, \order, #4
+	blo	1b
+
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+1:	cmp	\divisor, #0x80000000
+	cmplo	\divisor, \dividend
+	movlo	\divisor, \divisor, lsl #1
+	addlo	\order, \order, #1
+	blo	1b
+
+#endif
+
+	@ Perform all needed substractions to keep only the reminder.
+	@ Do comparisons in batch of 4 first.
+	subs	\order, \order, #3		@ yes, 3 is intended here
+	blt	2f
+
+1:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	cmp	\dividend, \divisor,  lsr #1
+	subhs	\dividend, \dividend, \divisor, lsr #1
+	cmp	\dividend, \divisor,  lsr #2
+	subhs	\dividend, \dividend, \divisor, lsr #2
+	cmp	\dividend, \divisor,  lsr #3
+	subhs	\dividend, \dividend, \divisor, lsr #3
+	cmp	\dividend, #1
+	mov	\divisor, \divisor, lsr #4
+	subges	\order, \order, #4
+	bge	1b
+
+	tst	\order, #3
+	teqne	\dividend, #0
+	beq	5f
+
+	@ Either 1, 2 or 3 comparison/substractions are left.
+2:	cmn	\order, #2
+	blt	4f
+	beq	3f
+	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+3:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+	mov	\divisor,  \divisor,  lsr #1
+4:	cmp	\dividend, \divisor
+	subhs	\dividend, \dividend, \divisor
+5:
+.endm
+
+
+.section .text.__udivsi3
+ENTRY(__udivsi3)
+ENTRY(__aeabi_uidiv)
+
+	subs	r2, r1, #1
+	moveq	pc, lr
+	bcc	Ldiv0
+	cmp	r0, r1
+	bls	11f
+	tst	r1, r2
+	beq	12f
+
+	ARM_DIV_BODY r0, r1, r2, r3
+
+	mov	r0, r2
+	mov	pc, lr
+
+11:	moveq	r0, #1
+	movne	r0, #0
+	mov	pc, lr
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	mov	r0, r0, lsr r2
+	mov	pc, lr
+
+ENDPROC(__udivsi3)
+ENDPROC(__aeabi_uidiv)
+
+.section .text.__umodsi3
+ENTRY(__umodsi3)
+
+	subs	r2, r1, #1			@ compare divisor with 1
+	bcc	Ldiv0
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq   r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	movls	pc, lr
+
+	ARM_MOD_BODY r0, r1, r2, r3
+
+	mov	pc, lr
+
+ENDPROC(__umodsi3)
+
+.section .text.__divsi3
+ENTRY(__divsi3)
+ENTRY(__aeabi_idiv)
+
+	cmp	r1, #0
+	eor	ip, r0, r1			@ save the sign of the result.
+	beq	Ldiv0
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	subs	r2, r1, #1			@ division by 1 or -1 ?
+	beq	10f
+	movs	r3, r0
+	rsbmi	r3, r0, #0			@ positive dividend value
+	cmp	r3, r1
+	bls	11f
+	tst	r1, r2				@ divisor is power of 2 ?
+	beq	12f
+
+	ARM_DIV_BODY r3, r1, r0, r2
+
+	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+10:	teq	ip, r0				@ same sign ?
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+11:	movlo	r0, #0
+	moveq	r0, ip, asr #31
+	orreq	r0, r0, #1
+	mov	pc, lr
+
+12:	ARM_DIV2_ORDER r1, r2
+
+	cmp	ip, #0
+	mov	r0, r3, lsr r2
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+ENDPROC(__divsi3)
+ENDPROC(__aeabi_idiv)
+
+.section .text.__modsi3
+ENTRY(__modsi3)
+
+	cmp	r1, #0
+	beq	Ldiv0
+	rsbmi	r1, r1, #0			@ loops below use unsigned.
+	movs	ip, r0				@ preserve sign of dividend
+	rsbmi	r0, r0, #0			@ if negative make positive
+	subs	r2, r1, #1			@ compare divisor with 1
+	cmpne	r0, r1				@ compare dividend with divisor
+	moveq	r0, #0
+	tsthi	r1, r2				@ see if divisor is power of 2
+	andeq	r0, r0, r2
+	bls	10f
+
+	ARM_MOD_BODY r0, r1, r2, r3
+
+10:	cmp	ip, #0
+	rsbmi	r0, r0, #0
+	mov	pc, lr
+
+ENDPROC(__modsi3)
+
+#ifdef CONFIG_AEABI
+
+.section .text.__aeabi_uidivmod
+ENTRY(__aeabi_uidivmod)
+
+	stmfd	sp!, {r0, r1, ip, lr}
+	bl	__aeabi_uidiv
+	ldmfd	sp!, {r1, r2, ip, lr}
+	mul	r3, r0, r2
+	sub	r1, r1, r3
+	mov	pc, lr
+
+ENDPROC(__aeabi_uidivmod)
+
+.section .text.__aeabi_idivmod
+ENTRY(__aeabi_idivmod)
+
+	stmfd	sp!, {r0, r1, ip, lr}
+	bl	__aeabi_idiv
+	ldmfd	sp!, {r1, r2, ip, lr}
+	mul	r3, r0, r2
+	sub	r1, r1, r3
+	mov	pc, lr
+
+ENDPROC(__aeabi_idivmod)
+
+#endif
+
+.section .text.Ldiv0
+Ldiv0:
+
+	str	lr, [sp, #-8]!
+	bl	__div0
+	mov	r0, #0			@ About as wrong as it could be.
+	ldr	pc, [sp], #8
+
+
diff --git a/arch/arm/lib32/lshrdi3.S b/arch/arm/lib32/lshrdi3.S
new file mode 100644
index 0000000000..e77e96c7bc
--- /dev/null
+++ b/arch/arm/lib32/lshrdi3.S
@@ -0,0 +1,50 @@
+/* Copyright 1995, 1996, 1998, 1999, 2000, 2003, 2004, 2005
+   Free Software Foundation, Inc.
+
+This file 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, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file 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 <linux/linkage.h>
+
+#ifdef __ARMEB__
+#define al r1
+#define ah r0
+#else
+#define al r0
+#define ah r1
+#endif
+
+.section .text.__lshrdi3
+ENTRY(__lshrdi3)
+ENTRY(__aeabi_llsr)
+
+	subs	r3, r2, #32
+	rsb	ip, r2, #32
+	movmi	al, al, lsr r2
+	movpl	al, ah, lsr r3
+ ARM(	orrmi	al, al, ah, lsl ip	)
+ THUMB(	lslmi	r3, ah, ip		)
+ THUMB(	orrmi	al, al, r3		)
+	mov	ah, ah, lsr r2
+	mov	pc, lr
+
+ENDPROC(__lshrdi3)
+ENDPROC(__aeabi_llsr)
diff --git a/arch/arm/lib32/memcpy.S b/arch/arm/lib32/memcpy.S
new file mode 100644
index 0000000000..5123691ca9
--- /dev/null
+++ b/arch/arm/lib32/memcpy.S
@@ -0,0 +1,64 @@
+/*
+ *  linux/arch/arm/lib/memcpy.S
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	Sep 28, 2005
+ *  Copyright:	MontaVista Software, Inc.
+ *
+ *  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>
+
+#define LDR1W_SHIFT	0
+#define STR1W_SHIFT	0
+
+	.macro ldr1w ptr reg abort
+	W(ldr) \reg, [\ptr], #4
+	.endm
+
+	.macro ldr4w ptr reg1 reg2 reg3 reg4 abort
+	ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4}
+	.endm
+
+	.macro ldr8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
+	ldmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8}
+	.endm
+
+	.macro ldr1b ptr reg cond=al abort
+	ldr\cond\()b \reg, [\ptr], #1
+	.endm
+
+	.macro str1w ptr reg abort
+	W(str) \reg, [\ptr], #4
+	.endm
+
+	.macro str8w ptr reg1 reg2 reg3 reg4 reg5 reg6 reg7 reg8 abort
+	stmia \ptr!, {\reg1, \reg2, \reg3, \reg4, \reg5, \reg6, \reg7, \reg8}
+	.endm
+
+	.macro str1b ptr reg cond=al abort
+	str\cond\()b \reg, [\ptr], #1
+	.endm
+
+	.macro enter reg1 reg2
+	stmdb sp!, {r0, \reg1, \reg2}
+	.endm
+
+	.macro exit reg1 reg2
+	ldmfd sp!, {r0, \reg1, \reg2}
+	.endm
+
+	.text
+
+/* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
+
+ENTRY(memcpy)
+
+#include "copy_template.S"
+
+ENDPROC(memcpy)
+
diff --git a/arch/arm/lib32/memset.S b/arch/arm/lib32/memset.S
new file mode 100644
index 0000000000..c4d2672038
--- /dev/null
+++ b/arch/arm/lib32/memset.S
@@ -0,0 +1,124 @@
+/*
+ *  linux/arch/arm/lib/memset.S
+ *
+ *  Copyright (C) 1995-2000 Russell King
+ *
+ * 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.
+ *
+ *  ASM optimised string functions
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.align	5
+
+ENTRY(memset)
+	ands	r3, r0, #3		@ 1 unaligned?
+	mov	ip, r0			@ preserve r0 as return value
+	bne	6f			@ 1
+/*
+ * we know that the pointer in ip is aligned to a word boundary.
+ */
+1:	orr	r1, r1, r1, lsl #8
+	orr	r1, r1, r1, lsl #16
+	mov	r3, r1
+	cmp	r2, #16
+	blt	4f
+
+#if ! CALGN(1)+0
+
+/*
+ * We need an 2 extra registers for this loop - use r8 and the LR
+ */
+	stmfd	sp!, {r8, lr}
+	mov	r8, r1
+	mov	lr, r1
+
+2:	subs	r2, r2, #64
+	stmgeia	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
+	stmgeia	ip!, {r1, r3, r8, lr}
+	stmgeia	ip!, {r1, r3, r8, lr}
+	stmgeia	ip!, {r1, r3, r8, lr}
+	bgt	2b
+	ldmeqfd	sp!, {r8, pc}		@ Now <64 bytes to go.
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+	tst	r2, #32
+	stmneia	ip!, {r1, r3, r8, lr}
+	stmneia	ip!, {r1, r3, r8, lr}
+	tst	r2, #16
+	stmneia	ip!, {r1, r3, r8, lr}
+	ldmfd	sp!, {r8, lr}
+
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+	stmfd	sp!, {r4-r8, lr}
+	mov	r4, r1
+	mov	r5, r1
+	mov	r6, r1
+	mov	r7, r1
+	mov	r8, r1
+	mov	lr, r1
+
+	cmp	r2, #96
+	tstgt	ip, #31
+	ble	3f
+
+	and	r8, ip, #31
+	rsb	r8, r8, #32
+	sub	r2, r2, r8
+	movs	r8, r8, lsl #(32 - 4)
+	stmcsia	ip!, {r4, r5, r6, r7}
+	stmmiia	ip!, {r4, r5}
+	tst	r8, #(1 << 30)
+	mov	r8, r1
+	strne	r1, [ip], #4
+
+3:	subs	r2, r2, #64
+	stmgeia	ip!, {r1, r3-r8, lr}
+	stmgeia	ip!, {r1, r3-r8, lr}
+	bgt	3b
+	ldmeqfd	sp!, {r4-r8, pc}
+
+	tst	r2, #32
+	stmneia	ip!, {r1, r3-r8, lr}
+	tst	r2, #16
+	stmneia	ip!, {r4-r7}
+	ldmfd	sp!, {r4-r8, lr}
+
+#endif
+
+4:	tst	r2, #8
+	stmneia	ip!, {r1, r3}
+	tst	r2, #4
+	strne	r1, [ip], #4
+/*
+ * When we get here, we've got less than 4 bytes to zero.  We
+ * may have an unaligned pointer as well.
+ */
+5:	tst	r2, #2
+	strneb	r1, [ip], #1
+	strneb	r1, [ip], #1
+	tst	r2, #1
+	strneb	r1, [ip], #1
+	mov	pc, lr
+
+6:	subs	r2, r2, #4		@ 1 do we have enough
+	blt	5b			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strltb	r1, [ip], #1		@ 1
+	strleb	r1, [ip], #1		@ 1
+	strb	r1, [ip], #1		@ 1
+	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
+	b	1b
+ENDPROC(memset)
+
diff --git a/arch/arm/lib32/module.c b/arch/arm/lib32/module.c
new file mode 100644
index 0000000000..be7965d59c
--- /dev/null
+++ b/arch/arm/lib32/module.c
@@ -0,0 +1,98 @@
+/*
+ *  linux/arch/arm/kernel/module.c
+ *
+ *  Copyright (C) 2002 Russell King.
+ *  Modified for nommu by Hyok S. Choi
+ *
+ * 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.
+ *
+ * Module allocation method suggested by Andi Kleen.
+ */
+
+//#include <asm/pgtable.h>
+#include <common.h>
+#include <elf.h>
+#include <module.h>
+#include <errno.h>
+
+int
+apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
+	       unsigned int relindex, struct module *module)
+{
+	Elf32_Shdr *symsec = sechdrs + symindex;
+	Elf32_Shdr *relsec = sechdrs + relindex;
+	Elf32_Shdr *dstsec = sechdrs + relsec->sh_info;
+	Elf32_Rel *rel = (void *)relsec->sh_addr;
+	unsigned int i;
+
+	for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rel); i++, rel++) {
+		unsigned long loc;
+		Elf32_Sym *sym;
+		s32 offset;
+
+		offset = ELF32_R_SYM(rel->r_info);
+		if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) {
+			printf("%s: bad relocation, section %u reloc %u\n",
+				module->name, relindex, i);
+			return -ENOEXEC;
+		}
+
+		sym = ((Elf32_Sym *)symsec->sh_addr) + offset;
+
+		if (rel->r_offset < 0 || rel->r_offset > dstsec->sh_size - sizeof(u32)) {
+			printf("%s: out of bounds relocation, "
+				"section %u reloc %u offset %d size %d\n",
+				module->name, relindex, i, rel->r_offset,
+				dstsec->sh_size);
+			return -ENOEXEC;
+		}
+
+		loc = dstsec->sh_addr + rel->r_offset;
+
+		switch (ELF32_R_TYPE(rel->r_info)) {
+		case R_ARM_ABS32:
+			*(u32 *)loc += sym->st_value;
+			break;
+
+		case R_ARM_PC24:
+		case R_ARM_CALL:
+		case R_ARM_JUMP24:
+			offset = (*(u32 *)loc & 0x00ffffff) << 2;
+			if (offset & 0x02000000)
+				offset -= 0x04000000;
+
+			offset += sym->st_value - loc;
+			if (offset & 3 ||
+			    offset <= (s32)0xfe000000 ||
+			    offset >= (s32)0x02000000) {
+				printf("%s: relocation out of range, section "
+				       "%u reloc %u sym '%s'\n", module->name,
+				       relindex, i, strtab + sym->st_name);
+				return -ENOEXEC;
+			}
+
+			offset >>= 2;
+
+			*(u32 *)loc &= 0xff000000;
+			*(u32 *)loc |= offset & 0x00ffffff;
+			break;
+
+		default:
+			printf("%s: unknown relocation: %u\n",
+			       module->name, ELF32_R_TYPE(rel->r_info));
+			return -ENOEXEC;
+		}
+	}
+	return 0;
+}
+
+int
+apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
+		   unsigned int symindex, unsigned int relsec, struct module *module)
+{
+	printf("module %s: ADD RELOCATION unsupported\n",
+	       module->name);
+	return -ENOEXEC;
+}
diff --git a/arch/arm/lib32/runtime-offset.S b/arch/arm/lib32/runtime-offset.S
new file mode 100644
index 0000000000..f10c4c8469
--- /dev/null
+++ b/arch/arm/lib32/runtime-offset.S
@@ -0,0 +1,52 @@
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+.section ".text_bare_init","ax"
+
+/*
+ * Get the offset between the link address and the address
+ * we are currently running at.
+ */
+ENTRY(get_runtime_offset)
+1:	adr r0, 1b
+	ldr r1, linkadr
+	subs r0, r1, r0
+THUMB(	subs r0, r0, #1)
+	mov pc, lr
+
+linkadr:
+.word get_runtime_offset
+ENDPROC(get_runtime_offset)
+
+.globl __ld_var_base
+__ld_var_base:
+
+/*
+ * Functions to calculate selected linker supplied variables during runtime.
+ * This is needed for relocatable binaries when the linker variables are
+ * needed before finxing up the relocations.
+ */
+.macro ld_var_entry name
+	ENTRY(__ld_var_\name)
+		ldr r0, __\name
+		b 1f
+	__\name: .word \name - __ld_var_base
+	ENDPROC(__ld_var_\name)
+.endm
+
+ld_var_entry _text
+ld_var_entry __rel_dyn_start
+ld_var_entry __rel_dyn_end
+ld_var_entry __dynsym_start
+ld_var_entry __dynsym_end
+ld_var_entry _barebox_image_size
+ld_var_entry __bss_start
+ld_var_entry __bss_stop
+#ifdef __PBL__
+ld_var_entry __image_end
+#endif
+
+1:
+	ldr r1, =__ld_var_base
+	adds r0, r0, r1
+	mov pc, lr
diff --git a/arch/arm/lib32/semihosting-trap.S b/arch/arm/lib32/semihosting-trap.S
new file mode 100644
index 0000000000..9e40ebfe21
--- /dev/null
+++ b/arch/arm/lib32/semihosting-trap.S
@@ -0,0 +1,28 @@
+/*
+ * semihosting-trap.S -- Assembly code needed to make a semihosting call
+ *
+ * Copyright (c) 2015 Zodiac Inflight Innovations
+ * Author: Andrey Smirnov <andrew.smirnov@gmail.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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 <linux/linkage.h>
+#include <asm/unified.h>
+
+.section .text.semihosting_trap
+ENTRY(semihosting_trap)
+	@ In supervisor mode SVC would clobber LR
+	push	{lr}
+	ARM(	svc	#0x123456	)
+	THUMB(	svc	#0xAB		)
+	pop	{pc}
+ENDPROC(semihosting_trap)
diff --git a/arch/arm/lib32/semihosting.c b/arch/arm/lib32/semihosting.c
new file mode 100644
index 0000000000..a7351961dc
--- /dev/null
+++ b/arch/arm/lib32/semihosting.c
@@ -0,0 +1,227 @@
+/*
+ * semihosting.c -- ARM Semihoting API implementation
+ *
+ * Copyright (c) 2015 Zodiac Inflight Innovations
+ * Author: Andrey Smirnov <andrew.smirnov@gmail.com>
+ *
+ * based on a smiliar code from U-Boot
+ * Copyright (c) 2014 Broadcom Corporation
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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>
+#include <command.h>
+#include <fcntl.h>
+
+#ifndef O_BINARY
+#define O_BINARY	0
+#endif
+
+
+enum {
+	SEMIHOSTING_SYS_OPEN	= 0x01,
+	SEMIHOSTING_SYS_CLOSE	= 0x02,
+	SEMIHOSTING_SYS_WRITEC	= 0x03,
+	SEMIHOSTING_SYS_WRITE0	= 0x04,
+	SEMIHOSTING_SYS_WRITE	= 0x05,
+	SEMIHOSTING_SYS_READ	= 0x06,
+	SEMIHOSTING_SYS_READC	= 0x07,
+	/* SYS_ISERROR is not implemented  */
+	SEMIHOSTING_SYS_ISATTY	= 0x09,
+	SEMIHOSTING_SYS_SEEK	= 0x0a,
+	SEMIHOSTING_SYS_FLEN	= 0x0c,
+	SEMIHOSTING_SYS_REMOVE	= 0x0e,
+	SEMIHOSTING_SYS_RENAME	= 0x0f,
+	SEMIHOSTING_SYS_TIME	= 0x11,
+	SEMIHOSTING_SYS_ERRNO	= 0x13,
+	/* SYS_GET_CMDLINE is not implemented */
+	/* SYS_HEAPINFO is not implemented */
+	/* angel_SWIreason_ReportException is not implemented */
+	SEMIHOSTING_SYS_SYSTEM	= 0x12,
+};
+
+uint32_t semihosting_trap(uint32_t sysnum, void *addr);
+
+static uint32_t semihosting_flags_to_mode(int flags)
+{
+	static const int semihosting_open_modeflags[12] = {
+		O_RDONLY,
+		O_RDONLY | O_BINARY,
+		O_RDWR,
+		O_RDWR | O_BINARY,
+		O_WRONLY | O_CREAT | O_TRUNC,
+		O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+		O_RDWR | O_CREAT | O_TRUNC,
+		O_RDWR | O_CREAT | O_TRUNC | O_BINARY,
+		O_WRONLY | O_CREAT | O_APPEND,
+		O_WRONLY | O_CREAT | O_APPEND | O_BINARY,
+		O_RDWR | O_CREAT | O_APPEND,
+		O_RDWR | O_CREAT | O_APPEND | O_BINARY
+	};
+
+	int i;
+	for (i = 0; i < ARRAY_SIZE(semihosting_open_modeflags); i++) {
+		if (semihosting_open_modeflags[i] == flags)
+			return i;
+	}
+
+	return 0;
+}
+
+int semihosting_open(const char *fname, int flags)
+{
+	struct __packed {
+		uint32_t fname;
+		uint32_t mode;
+		uint32_t len;
+	} open = {
+		.fname = (uint32_t)fname,
+		.len = strlen(fname),
+		.mode = semihosting_flags_to_mode(flags),
+	};
+
+	return semihosting_trap(SEMIHOSTING_SYS_OPEN, &open);
+}
+EXPORT_SYMBOL(semihosting_open);
+
+int semihosting_close(int fd)
+{
+	return semihosting_trap(SEMIHOSTING_SYS_CLOSE, &fd);
+}
+EXPORT_SYMBOL(semihosting_close);
+
+int semihosting_writec(char c)
+{
+	return semihosting_trap(SEMIHOSTING_SYS_WRITEC, &c);
+}
+EXPORT_SYMBOL(semihosting_writec);
+
+int semihosting_write0(const char *str)
+{
+	return semihosting_trap(SEMIHOSTING_SYS_WRITE0, (void *)str);
+}
+EXPORT_SYMBOL(semihosting_write0);
+
+struct __packed semihosting_file_io {
+	uint32_t fd;
+	uint32_t memp;
+	uint32_t len;
+};
+
+ssize_t semihosting_write(int fd, const void *buf, size_t count)
+{
+	struct semihosting_file_io write = {
+		.fd = fd,
+		.memp = (uint32_t)buf,
+		.len = count,
+	};
+
+	return semihosting_trap(SEMIHOSTING_SYS_WRITE, &write);
+}
+EXPORT_SYMBOL(semihosting_write);
+
+ssize_t semihosting_read(int fd, void *buf, size_t count)
+{
+	struct semihosting_file_io read = {
+		.fd = fd,
+		.memp = (uint32_t)buf,
+		.len = count,
+	};
+
+	return semihosting_trap(SEMIHOSTING_SYS_READ, &read);
+}
+EXPORT_SYMBOL(semihosting_read);
+
+int semihosting_readc(void)
+{
+	return semihosting_trap(SEMIHOSTING_SYS_READC, NULL);
+}
+EXPORT_SYMBOL(semihosting_readc);
+
+int semihosting_isatty(int fd)
+{
+	return semihosting_trap(SEMIHOSTING_SYS_ISATTY, &fd);
+}
+EXPORT_SYMBOL(semihosting_isatty);
+
+int semihosting_seek(int fd, off_t pos)
+{
+	struct __packed {
+		uint32_t fd;
+		uint32_t pos;
+	} seek = {
+		.fd = fd,
+		.pos = pos,
+	};
+
+	return semihosting_trap(SEMIHOSTING_SYS_SEEK, &seek);
+}
+EXPORT_SYMBOL(semihosting_seek);
+
+int semihosting_flen(int fd)
+{
+	return semihosting_trap(SEMIHOSTING_SYS_FLEN, &fd);
+}
+EXPORT_SYMBOL(semihosting_flen);
+
+int semihosting_remove(const char *fname)
+{
+	struct __packed {
+		uint32_t fname;
+		uint32_t fname_length;
+	} remove = {
+		.fname = (uint32_t)fname,
+		.fname_length = strlen(fname),
+	};
+
+	return semihosting_trap(SEMIHOSTING_SYS_REMOVE, &remove);
+}
+EXPORT_SYMBOL(semihosting_remove);
+
+int semihosting_rename(const char *fname1, const char *fname2)
+{
+	struct __packed {
+		uint32_t fname1;
+		uint32_t fname1_length;
+		uint32_t fname2;
+		uint32_t fname2_length;
+	} rename = {
+		.fname1 = (uint32_t)fname1,
+		.fname1_length = strlen(fname1),
+		.fname2 = (uint32_t)fname2,
+		.fname2_length = strlen(fname2),
+	};
+
+	return semihosting_trap(SEMIHOSTING_SYS_RENAME, &rename);
+}
+EXPORT_SYMBOL(semihosting_rename);
+
+int semihosting_errno(void)
+{
+	return semihosting_trap(SEMIHOSTING_SYS_ERRNO, NULL);
+}
+EXPORT_SYMBOL(semihosting_errno);
+
+
+int semihosting_system(const char *command)
+{
+	struct __packed {
+		uint32_t cmd;
+		uint32_t cmd_len;
+	} system = {
+		.cmd = (uint32_t)command,
+		.cmd_len = strlen(command),
+	};
+
+	return semihosting_trap(SEMIHOSTING_SYS_SYSTEM, &system);
+}
+EXPORT_SYMBOL(semihosting_system);
diff --git a/arch/arm/lib32/unwind.c b/arch/arm/lib32/unwind.c
new file mode 100644
index 0000000000..c3dca5b61d
--- /dev/null
+++ b/arch/arm/lib32/unwind.c
@@ -0,0 +1,349 @@
+#include <common.h>
+#include <init.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+#include <asm/sections.h>
+
+/* Dummy functions to avoid linker complaints */
+void __aeabi_unwind_cpp_pr0(void)
+{
+};
+EXPORT_SYMBOL(__aeabi_unwind_cpp_pr0);
+
+void __aeabi_unwind_cpp_pr1(void)
+{
+};
+EXPORT_SYMBOL(__aeabi_unwind_cpp_pr1);
+
+void __aeabi_unwind_cpp_pr2(void)
+{
+};
+EXPORT_SYMBOL(__aeabi_unwind_cpp_pr2);
+
+struct unwind_ctrl_block {
+	unsigned long vrs[16];		/* virtual register set */
+	unsigned long *insn;		/* pointer to the current instructions word */
+	int entries;			/* number of entries left to interpret */
+	int byte;			/* current byte number in the instructions word */
+};
+
+enum regs {
+	FP = 11,
+	SP = 13,
+	LR = 14,
+	PC = 15
+};
+
+#define THREAD_SIZE               8192
+
+extern struct unwind_idx __start_unwind_idx[];
+extern struct unwind_idx __stop_unwind_idx[];
+
+/* Convert a prel31 symbol to an absolute address */
+#define prel31_to_addr(ptr)				\
+({							\
+	/* sign-extend to 32 bits */			\
+	long offset = (((long)*(ptr)) << 1) >> 1;	\
+	(unsigned long)(ptr) + offset;			\
+})
+
+static inline int is_kernel_text(unsigned long addr)
+{
+	if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext))
+		return 1;
+	return 0;
+}
+
+void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
+{
+#ifdef CONFIG_KALLSYMS
+	printk("[<%08lx>] (%pS) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
+#else
+	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
+#endif
+}
+
+/*
+ * Binary search in the unwind index. The entries entries are
+ * guaranteed to be sorted in ascending order by the linker.
+ */
+static struct unwind_idx *search_index(unsigned long addr,
+				       struct unwind_idx *first,
+				       struct unwind_idx *last)
+{
+	pr_debug("%s(%08lx, %p, %p)\n", __func__, addr, first, last);
+
+	if (addr < first->addr) {
+		pr_warning("unwind: Unknown symbol address %08lx\n", addr);
+		return NULL;
+	} else if (addr >= last->addr)
+		return last;
+
+	while (first < last - 1) {
+		struct unwind_idx *mid = first + ((last - first + 1) >> 1);
+
+		if (addr < mid->addr)
+			last = mid;
+		else
+			first = mid;
+	}
+
+	return first;
+}
+
+static struct unwind_idx *unwind_find_idx(unsigned long addr)
+{
+	struct unwind_idx *idx = NULL;
+
+	pr_debug("%s(%08lx)\n", __func__, addr);
+
+	if (is_kernel_text(addr))
+		/* main unwind table */
+		idx = search_index(addr, __start_unwind_idx,
+				   __stop_unwind_idx - 1);
+	else {
+		/* module unwinding not supported */
+	}
+
+	pr_debug("%s: idx = %p\n", __func__, idx);
+	return idx;
+}
+
+static unsigned long unwind_get_byte(struct unwind_ctrl_block *ctrl)
+{
+	unsigned long ret;
+
+	if (ctrl->entries <= 0) {
+		pr_warning("unwind: Corrupt unwind table\n");
+		return 0;
+	}
+
+	ret = (*ctrl->insn >> (ctrl->byte * 8)) & 0xff;
+
+	if (ctrl->byte == 0) {
+		ctrl->insn++;
+		ctrl->entries--;
+		ctrl->byte = 3;
+	} else
+		ctrl->byte--;
+
+	return ret;
+}
+
+/*
+ * Execute the current unwind instruction.
+ */
+static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
+{
+	unsigned long insn = unwind_get_byte(ctrl);
+
+	pr_debug("%s: insn = %08lx\n", __func__, insn);
+
+	if ((insn & 0xc0) == 0x00)
+		ctrl->vrs[SP] += ((insn & 0x3f) << 2) + 4;
+	else if ((insn & 0xc0) == 0x40)
+		ctrl->vrs[SP] -= ((insn & 0x3f) << 2) + 4;
+	else if ((insn & 0xf0) == 0x80) {
+		unsigned long mask;
+		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+		int load_sp, reg = 4;
+
+		insn = (insn << 8) | unwind_get_byte(ctrl);
+		mask = insn & 0x0fff;
+		if (mask == 0) {
+			pr_warning("unwind: 'Refuse to unwind' instruction %04lx\n",
+				   insn);
+			return -URC_FAILURE;
+		}
+
+		/* pop R4-R15 according to mask */
+		load_sp = mask & (1 << (13 - 4));
+		while (mask) {
+			if (mask & 1)
+				ctrl->vrs[reg] = *vsp++;
+			mask >>= 1;
+			reg++;
+		}
+		if (!load_sp)
+			ctrl->vrs[SP] = (unsigned long)vsp;
+	} else if ((insn & 0xf0) == 0x90 &&
+		   (insn & 0x0d) != 0x0d)
+		ctrl->vrs[SP] = ctrl->vrs[insn & 0x0f];
+	else if ((insn & 0xf0) == 0xa0) {
+		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+		int reg;
+
+		/* pop R4-R[4+bbb] */
+		for (reg = 4; reg <= 4 + (insn & 7); reg++)
+			ctrl->vrs[reg] = *vsp++;
+		if (insn & 0x80)
+			ctrl->vrs[14] = *vsp++;
+		ctrl->vrs[SP] = (unsigned long)vsp;
+	} else if (insn == 0xb0) {
+		if (ctrl->vrs[PC] == 0)
+			ctrl->vrs[PC] = ctrl->vrs[LR];
+		/* no further processing */
+		ctrl->entries = 0;
+	} else if (insn == 0xb1) {
+		unsigned long mask = unwind_get_byte(ctrl);
+		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+		int reg = 0;
+
+		if (mask == 0 || mask & 0xf0) {
+			pr_warning("unwind: Spare encoding %04lx\n",
+			       (insn << 8) | mask);
+			return -URC_FAILURE;
+		}
+
+		/* pop R0-R3 according to mask */
+		while (mask) {
+			if (mask & 1)
+				ctrl->vrs[reg] = *vsp++;
+			mask >>= 1;
+			reg++;
+		}
+		ctrl->vrs[SP] = (unsigned long)vsp;
+	} else if (insn == 0xb2) {
+		unsigned long uleb128 = unwind_get_byte(ctrl);
+
+		ctrl->vrs[SP] += 0x204 + (uleb128 << 2);
+	} else {
+		pr_warning("unwind: Unhandled instruction %02lx\n", insn);
+		return -URC_FAILURE;
+	}
+
+	pr_debug("%s: fp = %08lx sp = %08lx lr = %08lx pc = %08lx\n", __func__,
+		 ctrl->vrs[FP], ctrl->vrs[SP], ctrl->vrs[LR], ctrl->vrs[PC]);
+
+	return URC_OK;
+}
+
+/*
+ * Unwind a single frame starting with *sp for the symbol at *pc. It
+ * updates the *pc and *sp with the new values.
+ */
+int unwind_frame(struct stackframe *frame)
+{
+	unsigned long high, low;
+	struct unwind_idx *idx;
+	struct unwind_ctrl_block ctrl;
+
+	/* only go to a higher address on the stack */
+	low = frame->sp;
+	high = ALIGN(low, THREAD_SIZE);
+
+	pr_debug("%s(pc = %08lx lr = %08lx sp = %08lx)\n", __func__,
+		 frame->pc, frame->lr, frame->sp);
+
+	if (!is_kernel_text(frame->pc))
+		return -URC_FAILURE;
+
+	idx = unwind_find_idx(frame->pc);
+	if (!idx) {
+		pr_warning("unwind: Index not found %08lx\n", frame->pc);
+		return -URC_FAILURE;
+	}
+
+	ctrl.vrs[FP] = frame->fp;
+	ctrl.vrs[SP] = frame->sp;
+	ctrl.vrs[LR] = frame->lr;
+	ctrl.vrs[PC] = 0;
+
+	if (idx->insn == 1)
+		/* can't unwind */
+		return -URC_FAILURE;
+	else if ((idx->insn & 0x80000000) == 0)
+		/* prel31 to the unwind table */
+		ctrl.insn = (unsigned long *)prel31_to_addr(&idx->insn);
+	else if ((idx->insn & 0xff000000) == 0x80000000)
+		/* only personality routine 0 supported in the index */
+		ctrl.insn = &idx->insn;
+	else {
+		pr_warning("unwind: Unsupported personality routine %08lx in the index at %p\n",
+			   idx->insn, idx);
+		return -URC_FAILURE;
+	}
+
+	/* check the personality routine */
+	if ((*ctrl.insn & 0xff000000) == 0x80000000) {
+		ctrl.byte = 2;
+		ctrl.entries = 1;
+	} else if ((*ctrl.insn & 0xff000000) == 0x81000000) {
+		ctrl.byte = 1;
+		ctrl.entries = 1 + ((*ctrl.insn & 0x00ff0000) >> 16);
+	} else {
+		pr_warning("unwind: Unsupported personality routine %08lx at %p\n",
+			   *ctrl.insn, ctrl.insn);
+		return -URC_FAILURE;
+	}
+
+	while (ctrl.entries > 0) {
+		int urc = unwind_exec_insn(&ctrl);
+		if (urc < 0)
+			return urc;
+		if (ctrl.vrs[SP] < low || ctrl.vrs[SP] >= high)
+			return -URC_FAILURE;
+	}
+
+	if (ctrl.vrs[PC] == 0)
+		ctrl.vrs[PC] = ctrl.vrs[LR];
+
+	/* check for infinite loop */
+	if (frame->pc == ctrl.vrs[PC])
+		return -URC_FAILURE;
+
+	frame->fp = ctrl.vrs[FP];
+	frame->sp = ctrl.vrs[SP];
+	frame->lr = ctrl.vrs[LR];
+	frame->pc = ctrl.vrs[PC];
+
+	return URC_OK;
+}
+
+void unwind_backtrace(struct pt_regs *regs)
+{
+	struct stackframe frame;
+	register unsigned long current_sp asm ("sp");
+
+	pr_debug("%s\n", __func__);
+
+	if (regs) {
+		frame.fp = regs->ARM_fp;
+		frame.sp = regs->ARM_sp;
+		frame.lr = regs->ARM_lr;
+		/* PC might be corrupted, use LR in that case. */
+		frame.pc = is_kernel_text(regs->ARM_pc)
+			 ? regs->ARM_pc : regs->ARM_lr;
+	} else {
+		frame.sp = current_sp;
+		frame.lr = (unsigned long)__builtin_return_address(0);
+		frame.pc = (unsigned long)unwind_backtrace;
+	}
+
+	while (1) {
+		int urc;
+		unsigned long where = frame.pc;
+
+		urc = unwind_frame(&frame);
+		if (urc < 0)
+			break;
+		dump_backtrace_entry(where, frame.pc, frame.sp - 4);
+	}
+}
+
+void dump_stack(void)
+{
+	unwind_backtrace(NULL);
+}
+
+static int unwind_init(void)
+{
+	struct unwind_idx *idx;
+
+	/* Convert the symbol addresses to absolute values */
+	for (idx = __start_unwind_idx; idx < __stop_unwind_idx; idx++)
+		idx->addr = prel31_to_addr(&idx->addr);
+
+	return 0;
+}
+core_initcall(unwind_init);