WIP: Initial ARMv7 architecture implementation in coreboot

The first ARMv7 CPU we're going to support is the Exynos 5250
used in the Google Snow ChromeBook.

Change-Id: I4de8433bbc6202eb8fef2556a11186a3376d411b
Signed-off-by: David Hendricks <dhendrix@chromium.org>
Signed-off-by: Stefan Reinauer <reinauer@google.com>
Signed-off-by: Ronald G. Minnich <rminnich@gmail.com>
Reviewed-on: http://review.coreboot.org/2004
Tested-by: build bot (Jenkins)

22 files changed, 2741 insertions, 0 deletions

diff --git a/src/arch/armv7/lib/Makefile.inc b/src/arch/armv7/lib/Makefile.inc
new file mode 100644
index 0000000000..bdf6a64ffb
--- /dev/null
+++ b/src/arch/armv7/lib/Makefile.inc
@@ -0,0 +1,26 @@
+romstage-y += cache_v7.c
+romstage-y += cache-cp15.c
+romstage-y += div0.c
+romstage-y += div64.S
+romstage-y += hang_spl.c
+romstage-y += romstage_console.c
+romstage-y += syslib.c
+
+#ramstage-y += printk_init.c
+#romstage-y += walkcbfs.S
+
+ramstage-y += c_start.S
+
+#ramstage-y += div.c
+ramstage-y += div0.c
+ramstage-y += div64.S
+ramstage-y += hang_spl.c
+#ramstage-y += interrupts.c
+#ramstage-y += memcpy.S
+#ramstage-y += memset.S
+#ramstage-y += reset.c
+ramstage-y += syslib.c
+
+#FIXME(dhendrix): should this be a config option?
+romstage-y += eabi_compat.c
+ramstage-y += eabi_compat.c
diff --git a/src/arch/armv7/lib/Makefile.uboot b/src/arch/armv7/lib/Makefile.uboot
new file mode 100644
index 0000000000..d33d08b14d
--- /dev/null
+++ b/src/arch/armv7/lib/Makefile.uboot
@@ -0,0 +1,95 @@
+#
+# (C) Copyright 2002-2006
+# 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.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+# MA 02111-1307 USA
+#
+
+include $(TOPDIR)/config.mk
+
+LIB	= $(obj)lib$(ARCH).o
+LIBGCC	= $(obj)libgcc.o
+
+ifndef CONFIG_SPL_BUILD
+GLSOBJS	+= _ashldi3.o
+GLSOBJS	+= _ashrdi3.o
+GLSOBJS	+= _divsi3.o
+GLSOBJS	+= _lshrdi3.o
+GLSOBJS	+= _modsi3.o
+GLSOBJS	+= _udivsi3.o
+GLSOBJS	+= _umodsi3.o
+ifdef CONFIG_CHROMEOS
+GLSOBJS	+= _uldivmod.o
+endif
+
+GLCOBJS	+= div0.o
+
+ifeq ($(CONFIG_SYS_GENERIC_BOARD),)
+COBJS-y += board.o
+endif
+COBJS-y	+= bootm.o
+COBJS-y	+= cache.o
+COBJS-y	+= cache-cp15.o
+COBJS-$(CONFIG_SYS_L2_PL310) += cache-pl310.o
+SOBJS-$(CONFIG_USE_ARCH_MEMSET) += memset.o
+SOBJS-$(CONFIG_USE_ARCH_MEMCPY) += memcpy.o
+else	# CONFIG_SPL_BUILD
+ifeq ($(CONFIG_SYS_GENERIC_BOARD),)
+COBJS-y += hang_spl.o
+endif
+endif	# CONFIG_SPL_BUILD
+
+COBJS-y	+= interrupts.o
+COBJS-y	+= reset.o
+
+SRCS	:= $(GLSOBJS:.o=.S) $(GLCOBJS:.o=.c) \
+	   $(SOBJS-y:.o=.S) $(COBJS-y:.o=.c)
+OBJS	:= $(addprefix $(obj),$(SOBJS-y) $(COBJS-y))
+LGOBJS	:= $(addprefix $(obj),$(GLSOBJS)) \
+	   $(addprefix $(obj),$(GLCOBJS))
+
+# Always build libarm.o
+TARGETS	:= $(LIB)
+
+# Build private libgcc only when asked for
+ifdef USE_PRIVATE_LIBGCC
+TARGETS	+= $(LIBGCC)
+endif
+
+# For EABI conformant tool chains, provide eabi_compat()
+ifneq (,$(findstring -mabi=aapcs-linux,$(PLATFORM_CPPFLAGS)))
+TARGETS	+= $(obj)eabi_compat.o
+endif
+
+all:	$(TARGETS)
+
+$(LIB):	$(obj).depend $(OBJS)
+	$(call cmd_link_o_target, $(OBJS))
+
+$(LIBGCC): $(obj).depend $(LGOBJS)
+	$(call cmd_link_o_target, $(LGOBJS))
+
+#########################################################################
+
+# defines $(obj).depend target
+include $(SRCTREE)/rules.mk
+
+sinclude $(obj).depend
+
+#########################################################################
diff --git a/src/arch/armv7/lib/_divsi3.S b/src/arch/armv7/lib/_divsi3.S
new file mode 100644
index 0000000000..cfbadb2ab9
--- /dev/null
+++ b/src/arch/armv7/lib/_divsi3.S
@@ -0,0 +1,142 @@
+
+.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
+
+	.align	5
+.globl __divsi3
+.globl __aeabi_idiv
+__divsi3:
+__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
+
+Ldiv0:
+
+	str	lr, [sp, #-4]!
+	bl	__div0
+	mov	r0, #0			@ About as wrong as it could be.
+	ldr	pc, [sp], #4
diff --git a/src/arch/armv7/lib/_udivsi3.S b/src/arch/armv7/lib/_udivsi3.S
new file mode 100644
index 0000000000..1309802610
--- /dev/null
+++ b/src/arch/armv7/lib/_udivsi3.S
@@ -0,0 +1,93 @@
+/* # 1 "libgcc1.S" */
+@ libgcc1 routines for ARM cpu.
+@ Division routines, written by Richard Earnshaw, (rearnsha@armltd.co.uk)
+dividend	.req	r0
+divisor		.req	r1
+result		.req	r2
+curbit		.req	r3
+/* ip		.req	r12	*/
+/* sp		.req	r13	*/
+/* lr		.req	r14	*/
+/* pc		.req	r15	*/
+	.text
+	.globl	 __udivsi3
+	.type	__udivsi3 ,function
+	.globl	__aeabi_uidiv
+	.type	__aeabi_uidiv ,function
+	.align	0
+ __udivsi3:
+ __aeabi_uidiv:
+	cmp	divisor, #0
+	beq	Ldiv0
+	mov	curbit, #1
+	mov	result, #0
+	cmp	dividend, divisor
+	bcc	Lgot_result
+Loop1:
+	@ 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.
+	cmp	divisor, #0x10000000
+	cmpcc	divisor, dividend
+	movcc	divisor, divisor, lsl #4
+	movcc	curbit, curbit, lsl #4
+	bcc	Loop1
+Lbignum:
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+	cmp	divisor, #0x80000000
+	cmpcc	divisor, dividend
+	movcc	divisor, divisor, lsl #1
+	movcc	curbit, curbit, lsl #1
+	bcc	Lbignum
+Loop3:
+	@ Test for possible subtractions, and note which bits
+	@ are done in the result.  On the final pass, this may subtract
+	@ too much from the dividend, but the result will be ok, since the
+	@ "bit" will have been shifted out at the bottom.
+	cmp	dividend, divisor
+	subcs	dividend, dividend, divisor
+	orrcs	result, result, curbit
+	cmp	dividend, divisor, lsr #1
+	subcs	dividend, dividend, divisor, lsr #1
+	orrcs	result, result, curbit, lsr #1
+	cmp	dividend, divisor, lsr #2
+	subcs	dividend, dividend, divisor, lsr #2
+	orrcs	result, result, curbit, lsr #2
+	cmp	dividend, divisor, lsr #3
+	subcs	dividend, dividend, divisor, lsr #3
+	orrcs	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	Loop3
+Lgot_result:
+	mov	r0, result
+	mov	pc, lr
+Ldiv0:
+	str	lr, [sp, #-4]!
+	bl	 __div0       (PLT)
+	mov	r0, #0			@ about as wrong as it could be
+	ldmia	sp!, {pc}
+	.size  __udivsi3       , . -  __udivsi3
+
+.globl __aeabi_uidivmod
+__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
+
+.globl __aeabi_idivmod
+__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
diff --git a/src/arch/armv7/lib/_uldivmod.S b/src/arch/armv7/lib/_uldivmod.S
new file mode 100644
index 0000000000..65e4fa8441
--- /dev/null
+++ b/src/arch/armv7/lib/_uldivmod.S
@@ -0,0 +1,157 @@
+/*
+ * Copyright (c) 2011 The Chromium OS Authors. All rights reserved.
+ * Use of this source code is governed by a BSD-style license that can be
+ * found in the LICENSE file.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ */
+
+/*
+ * A, Q = r0 + (r1 << 32)
+ * B, R = r2 + (r3 << 32)
+ * A / B = Q ... R
+ */
+
+	.text
+	.global	__aeabi_uldivmod
+	.type	__aeabi_uldivmod, function
+	.align	0
+
+A_0	.req	r0
+A_1	.req	r1
+B_0	.req	r2
+B_1	.req	r3
+C_0	.req	r4
+C_1	.req	r5
+D_0	.req	r6
+D_1	.req	r7
+
+Q_0	.req	r0
+Q_1	.req	r1
+R_0	.req	r2
+R_1	.req	r3
+
+__aeabi_uldivmod:
+	stmfd	sp!, {r4, r5, r6, r7, lr}
+	@ Test if B == 0
+	orrs	ip, B_0, B_1		@ Z set -> B == 0
+	beq	L_div_by_0
+	@ Test if B is power of 2: (B & (B - 1)) == 0
+	subs	C_0, B_0, #1
+	sbc	C_1, B_1, #0
+	tst	C_0, B_0
+	tsteq	B_1, C_1
+	beq	L_pow2
+	@ Test if A_1 == B_1 == 0
+	orrs	ip, A_1, B_1
+	beq	L_div_32_32
+
+L_div_64_64:
+	mov	C_0, #1
+	mov	C_1, #0
+	@ D_0 = clz A
+	teq	A_1, #0
+	clz	D_0, A_1
+	clzeq	ip, A_0
+	addeq	D_0, D_0, ip
+	@ D_1 = clz B
+	teq	B_1, #0
+	clz	D_1, B_1
+	clzeq	ip, B_0
+	addeq	D_1, D_1, ip
+	@ if clz B - clz A > 0
+	subs	D_0, D_1, D_0
+	bls	L_done_shift
+	@ B <<= (clz B - clz A)
+	subs	D_1, D_0, #32
+	rsb	ip, D_0, #32
+	movmi	B_1, B_1, lsl D_0
+	orrmi	B_1, B_1, B_0, lsr ip
+	movpl	B_1, B_0, lsl D_1
+	mov	B_0, B_0, lsl D_0
+	@ C = 1 << (clz B - clz A)
+	movmi	C_1, C_1, lsl D_0
+	orrmi	C_1, C_1, C_0, lsr ip
+	movpl	C_1, C_0, lsl D_1
+	mov	C_0, C_0, lsl D_0
+L_done_shift:
+	mov	D_0, #0
+	mov	D_1, #0
+	@ C: current bit; D: result
+L_subtract:
+	@ if A >= B
+	cmp	A_1, B_1
+	cmpeq	A_0, B_0
+	bcc	L_update
+	@ A -= B
+	subs	A_0, A_0, B_0
+	sbc	A_1, A_1, B_1
+	@ D |= C
+	orr	D_0, D_0, C_0
+	orr	D_1, D_1, C_1
+L_update:
+	@ if A == 0: break
+	orrs	ip, A_1, A_0
+	beq	L_exit
+	@ C >>= 1
+	movs	C_1, C_1, lsr #1
+	movs	C_0, C_0, rrx
+	@ if C == 0: break
+	orrs	ip, C_1, C_0
+	beq	L_exit
+	@ B >>= 1
+	movs	B_1, B_1, lsr #1
+	mov	B_0, B_0, rrx
+	b	L_subtract
+L_exit:
+	@ Note: A, B & Q, R are aliases
+	mov	R_0, A_0
+	mov	R_1, A_1
+	mov	Q_0, D_0
+	mov	Q_1, D_1
+	ldmfd	sp!, {r4, r5, r6, r7, pc}
+
+L_div_32_32:
+	@ Note:	A_0 &	r0 are aliases
+	@	Q_1	r1
+	mov	r1, B_0
+	bl	__aeabi_uidivmod
+	mov	R_0, r1
+	mov	R_1, #0
+	mov	Q_1, #0
+	ldmfd	sp!, {r4, r5, r6, r7, pc}
+
+L_pow2:
+	@ Note: A, B and Q, R are aliases
+	@ R = A & (B - 1)
+	and	C_0, A_0, C_0
+	and	C_1, A_1, C_1
+	@ Q = A >> log2(B)
+	@ Note: B must not be 0 here!
+	clz	D_0, B_0
+	add	D_1, D_0, #1
+	rsbs	D_0, D_0, #31
+	bpl	L_1
+	clz	D_0, B_1
+	rsb	D_0, D_0, #31
+	mov	A_0, A_1, lsr D_0
+	add	D_0, D_0, #32
+L_1:
+	movpl	A_0, A_0, lsr D_0
+	orrpl	A_0, A_0, A_1, lsl D_1
+	mov	A_1, A_1, lsr D_0
+	@ Mov back C to R
+	mov	R_0, C_0
+	mov	R_1, C_1
+	ldmfd	sp!, {r4, r5, r6, r7, pc}
+
+L_div_by_0:
+	bl	__div0
+	@ As wrong as it could be
+	mov	Q_0, #0
+	mov	Q_1, #0
+	mov	R_0, #0
+	mov	R_1, #0
+	ldmfd	sp!, {r4, r5, r6, r7, pc}
diff --git a/src/arch/armv7/lib/bootm.c b/src/arch/armv7/lib/bootm.c
new file mode 100644
index 0000000000..afe1b70814
--- /dev/null
+++ b/src/arch/armv7/lib/bootm.c
@@ -0,0 +1,405 @@
+/*
+ * (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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307	 USA
+ *
+ */
+
+#include <common.h>
+#include <command.h>
+#include <image.h>
+#include <u-boot/zlib.h>
+#include <arch/byteorder.h>
+#include <fdt.h>
+#include <libfdt.h>
+#include <fdt_support.h>
+
+DECLARE_GLOBAL_DATA_PTR;
+
+#if defined (CONFIG_SETUP_MEMORY_TAGS) || \
+    defined (CONFIG_CMDLINE_TAG) || \
+    defined (CONFIG_INITRD_TAG) || \
+    defined (CONFIG_SERIAL_TAG) || \
+    defined (CONFIG_REVISION_TAG)
+static void setup_start_tag (bd_t *bd);
+
+# ifdef CONFIG_SETUP_MEMORY_TAGS
+static void setup_memory_tags (bd_t *bd);
+# endif
+static void setup_commandline_tag (bd_t *bd, char *commandline);
+
+# ifdef CONFIG_INITRD_TAG
+static void setup_initrd_tag (bd_t *bd, ulong initrd_start,
+			      ulong initrd_end);
+# endif
+static void setup_end_tag (bd_t *bd);
+
+# if defined (CONFIG_VFD) || defined (CONFIG_LCD)
+# if !defined(CONFIG_VIDEOFLB_ATAG_NOT_SUPPORTED)
+static void setup_videolfb_tag (gd_t *gd);
+# endif
+# endif
+
+static struct tag *params;
+#endif /* CONFIG_SETUP_MEMORY_TAGS || CONFIG_CMDLINE_TAG || CONFIG_INITRD_TAG */
+
+static ulong get_sp(void);
+#if defined(CONFIG_OF_LIBFDT) && !defined(CONFIG_OF_NO_KERNEL)
+static int bootm_linux_fdt(int machid, bootm_headers_t *images);
+#endif
+
+void arch_lmb_reserve(struct lmb *lmb)
+{
+	ulong sp;
+
+	/*
+	 * Booting a (Linux) kernel image
+	 *
+	 * Allocate space for command line and board info - the
+	 * address should be as high as possible within the reach of
+	 * the kernel (see CONFIG_SYS_BOOTMAPSZ settings), but in unused
+	 * memory, which means far enough below the current stack
+	 * pointer.
+	 */
+	sp = get_sp();
+	debug("## Current stack ends at 0x%08lx ", sp);
+
+	/* adjust sp by 1K to be safe */
+	sp -= 1024;
+	lmb_reserve(lmb, sp,
+		    gd->bd->bi_dram[0].start + gd->bd->bi_dram[0].size - sp);
+}
+
+static void announce_and_cleanup(void)
+{
+	printf("\nStarting kernel ...\n\n");
+	bootstage_mark_name(BOOTSTAGE_ID_BOOTM_HANDOFF, "start_kernel");
+
+#ifdef CONFIG_USB_DEVICE
+	{
+		extern void udc_disconnect(void);
+		udc_disconnect();
+	}
+#endif
+	cleanup_before_linux();
+}
+
+int do_bootm_linux(int flag, int argc, char *argv[], bootm_headers_t *images)
+{
+	bd_t	*bd = gd->bd;
+	char	*s;
+	int	machid = bd->bi_arch_number;
+	void	(*kernel_entry)(int zero, int arch, uint params);
+
+#ifdef CONFIG_CMDLINE_TAG
+	char *commandline = getenv ("bootargs");
+#endif
+
+	if ((flag != 0) && (flag != BOOTM_STATE_OS_GO))
+		return 1;
+
+	s = getenv ("machid");
+	if (s) {
+		machid = simple_strtoul (s, NULL, 16);
+		printf ("Using machid 0x%x from environment\n", machid);
+	}
+
+	bootstage_mark(BOOTSTAGE_ID_RUN_OS);
+
+#if defined(CONFIG_OF_LIBFDT) && !defined(CONFIG_OF_NO_KERNEL)
+	if (images->ft_len)
+		return bootm_linux_fdt(machid, images);
+#endif
+
+	kernel_entry = (void (*)(int, int, uint))images->ep;
+
+	debug ("## Transferring control to Linux (at address %08lx) ...\n",
+	       (ulong) kernel_entry);
+
+#if defined (CONFIG_SETUP_MEMORY_TAGS) || \
+    defined (CONFIG_CMDLINE_TAG) || \
+    defined (CONFIG_INITRD_TAG) || \
+    defined (CONFIG_SERIAL_TAG) || \
+    defined (CONFIG_REVISION_TAG)
+	setup_start_tag (bd);
+#ifdef CONFIG_SERIAL_TAG
+	setup_serial_tag (&params);
+#endif
+#ifdef CONFIG_REVISION_TAG
+	setup_revision_tag (&params);
+#endif
+#ifdef CONFIG_SETUP_MEMORY_TAGS
+	setup_memory_tags (bd);
+#endif
+#ifdef CONFIG_CMDLINE_TAG
+	setup_commandline_tag (bd, commandline);
+#endif
+#ifdef CONFIG_INITRD_TAG
+	if (images->rd_start && images->rd_end)
+		setup_initrd_tag (bd, images->rd_start, images->rd_end);
+#endif
+#if defined (CONFIG_VFD) || defined (CONFIG_LCD)
+#if !defined(CONFIG_VIDEOFLB_ATAG_NOT_SUPPORTED)
+	setup_videolfb_tag ((gd_t *) gd);
+#endif
+#endif
+	setup_end_tag (bd);
+#endif
+
+	announce_and_cleanup();
+
+	kernel_entry(0, machid, bd->bi_boot_params);
+	/* does not return */
+
+	return 1;
+}
+
+#if defined(CONFIG_OF_LIBFDT) && !defined(CONFIG_OF_NO_KERNEL)
+static int fixup_memory_node(void *blob)
+{
+	bd_t	*bd = gd->bd;
+	int bank;
+	u64 start[CONFIG_NR_DRAM_BANKS];
+	u64 size[CONFIG_NR_DRAM_BANKS];
+
+	for (bank = 0; bank < CONFIG_NR_DRAM_BANKS; bank++) {
+		start[bank] = bd->bi_dram[bank].start;
+		size[bank] = bd->bi_dram[bank].size;
+	}
+
+	return fdt_fixup_memory_banks(blob, start, size, CONFIG_NR_DRAM_BANKS);
+}
+
+static int bootm_linux_fdt(int machid, bootm_headers_t *images)
+{
+	ulong rd_len;
+	void (*kernel_entry)(int zero, int dt_machid, void *dtblob);
+	ulong of_size = images->ft_len;
+	char **of_flat_tree = &images->ft_addr;
+	ulong *initrd_start = &images->initrd_start;
+	ulong *initrd_end = &images->initrd_end;
+	struct lmb *lmb = &images->lmb;
+	int ret;
+
+	kernel_entry = (void (*)(int, int, void *))images->ep;
+
+	boot_fdt_add_mem_rsv_regions(lmb, *of_flat_tree);
+
+	rd_len = images->rd_end - images->rd_start;
+	ret = boot_ramdisk_high(lmb, images->rd_start, rd_len,
+				initrd_start, initrd_end);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_OF_BOARD_SETUP
+	/* Try to reserve 1024 bytes for board fixups */
+	if (!fdt_open_into(*of_flat_tree, *of_flat_tree, of_size + 1024))
+		of_size += 1024;
+	/* Call the board-specific fixup routine */
+	ft_board_setup(*of_flat_tree, gd->bd);
+#endif
+#ifdef CONFIG_OF_UPDATE_FDT_BEFORE_BOOT
+	/* this must be earlier than boot_relocate_fdt */
+	ret = fit_update_fdt_before_boot(*of_flat_tree, &of_size);
+	if (ret)
+		return ret;
+#endif
+
+	ret = boot_relocate_fdt(lmb, of_flat_tree, &of_size);
+	if (ret)
+		return ret;
+
+	debug("## Transferring control to Linux (at address %08lx) ...\n",
+	       (ulong) kernel_entry);
+
+	fdt_chosen(*of_flat_tree, 1);
+
+	fixup_memory_node(*of_flat_tree);
+
+	fdt_fixup_ethernet(*of_flat_tree);
+
+	fdt_initrd(*of_flat_tree, *initrd_start, *initrd_end, 1);
+
+	announce_and_cleanup();
+
+	kernel_entry(0, machid, *of_flat_tree);
+	/* does not return */
+
+	return 1;
+}
+#endif
+
+#if defined (CONFIG_SETUP_MEMORY_TAGS) || \
+    defined (CONFIG_CMDLINE_TAG) || \
+    defined (CONFIG_INITRD_TAG) || \
+    defined (CONFIG_SERIAL_TAG) || \
+    defined (CONFIG_REVISION_TAG)
+static void setup_start_tag (bd_t *bd)
+{
+	params = (struct tag *) bd->bi_boot_params;
+
+	params->hdr.tag = ATAG_CORE;
+	params->hdr.size = tag_size (tag_core);
+
+#if defined (ATAG_CORE_FLAGS) && \
+    defined (ATAG_PAGE_SIZE) && \
+    defined (ATAG_CORE_RDEV)
+	params->u.core.flags = ATAG_CORE_FLAGS;
+	params->u.core.pagesize = ATAG_PAGE_SIZE;
+	params->u.core.rootdev = ATAG_CORE_RDEV;
+#else
+	params->u.core.flags = 0;
+	params->u.core.pagesize = 0;
+	params->u.core.rootdev = 0;
+#endif
+
+	params = tag_next (params);
+}
+
+
+#ifdef CONFIG_SETUP_MEMORY_TAGS
+static void setup_memory_tags (bd_t *bd)
+{
+	int i;
+
+	for (i = 0; i < CONFIG_NR_DRAM_BANKS; i++) {
+		params->hdr.tag = ATAG_MEM;
+		params->hdr.size = tag_size (tag_mem32);
+
+		params->u.mem.start = bd->bi_dram[i].start;
+		params->u.mem.size = bd->bi_dram[i].size;
+
+		params = tag_next (params);
+	}
+}
+#endif /* CONFIG_SETUP_MEMORY_TAGS */
+
+
+static void setup_commandline_tag (bd_t *bd, char *commandline)
+{
+	char *p;
+
+	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;
+
+	params->hdr.tag = ATAG_CMDLINE;
+	params->hdr.size =
+		(sizeof (struct tag_header) + strlen (p) + 1 + 4) >> 2;
+
+	strcpy (params->u.cmdline.cmdline, p);
+
+	params = tag_next (params);
+}
+
+
+#ifdef CONFIG_INITRD_TAG
+static void setup_initrd_tag (bd_t *bd, ulong initrd_start, ulong initrd_end)
+{
+	/* 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 = initrd_start;
+	params->u.initrd.size = initrd_end - initrd_start;
+
+	params = tag_next (params);
+}
+#endif /* CONFIG_INITRD_TAG */
+
+#if defined (CONFIG_VFD) || defined (CONFIG_LCD)
+#if !defined(CONFIG_VIDEOFLB_ATAG_NOT_SUPPORTED)
+extern ulong calc_fbsize (void);
+static void setup_videolfb_tag (gd_t *gd)
+{
+	/* An ATAG_VIDEOLFB node tells the kernel where and how large
+	 * the framebuffer for video was allocated (among other things).
+	 * Note that a _physical_ address is passed !
+	 *
+	 * We only use it to pass the address and size, the other entries
+	 * in the tag_videolfb are not of interest.
+	 */
+	params->hdr.tag = ATAG_VIDEOLFB;
+	params->hdr.size = tag_size (tag_videolfb);
+
+	params->u.videolfb.lfb_base = (u32) gd->fb_base;
+	/* Fb size is calculated according to parameters for our panel
+	 */
+	params->u.videolfb.lfb_size = calc_fbsize();
+
+	params = tag_next (params);
+}
+#endif /* CONFIG_VIDEOFLB_ATAG_NOT_SUPPORTED */
+#endif /* CONFIG_VFD || CONFIG_LCD */
+
+#ifdef CONFIG_SERIAL_TAG
+void setup_serial_tag (struct tag **tmp)
+{
+	struct tag *params = *tmp;
+	struct tag_serialnr serialnr;
+	void get_board_serial(struct tag_serialnr *serialnr);
+
+	get_board_serial(&serialnr);
+	params->hdr.tag = ATAG_SERIAL;
+	params->hdr.size = tag_size (tag_serialnr);
+	params->u.serialnr.low = serialnr.low;
+	params->u.serialnr.high= serialnr.high;
+	params = tag_next (params);
+	*tmp = params;
+}
+#endif
+
+#ifdef CONFIG_REVISION_TAG
+void setup_revision_tag(struct tag **in_params)
+{
+	u32 rev = 0;
+	u32 get_board_rev(void);
+
+	rev = get_board_rev();
+	params->hdr.tag = ATAG_REVISION;
+	params->hdr.size = tag_size (tag_revision);
+	params->u.revision.rev = rev;
+	params = tag_next (params);
+}
+#endif  /* CONFIG_REVISION_TAG */
+
+static void setup_end_tag (bd_t *bd)
+{
+	params->hdr.tag = ATAG_NONE;
+	params->hdr.size = 0;
+}
+#endif /* CONFIG_SETUP_MEMORY_TAGS || CONFIG_CMDLINE_TAG || CONFIG_INITRD_TAG */
+
+static ulong get_sp(void)
+{
+	ulong ret;
+
+	asm("mov %0, sp" : "=r"(ret) : );
+	return ret;
+}
diff --git a/src/arch/armv7/lib/c_start.S b/src/arch/armv7/lib/c_start.S
new file mode 100644
index 0000000000..b6e746299d
--- /dev/null
+++ b/src/arch/armv7/lib/c_start.S
@@ -0,0 +1,9 @@
+.section ".text"
+.globl _start
+_start:
+	bl	_hardwaremain
+
+_hardwaremain: .word hardwaremain
+@ .word hardwaremain
+
+
diff --git a/src/arch/armv7/lib/cache-cp15.c b/src/arch/armv7/lib/cache-cp15.c
new file mode 100644
index 0000000000..1786725148
--- /dev/null
+++ b/src/arch/armv7/lib/cache-cp15.c
@@ -0,0 +1,304 @@
+/*
+ * (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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+/* FIXME(dhendrix): clean-up weak symbols if it looks unlikely we'll
+   want to override them with anything other than what's in cache_v7. */
+#include <common.h>
+#include <stdlib.h>
+#include <system.h>
+#include <global_data.h>
+
+#if !(defined(CONFIG_SYS_ICACHE_OFF) && defined(CONFIG_SYS_DCACHE_OFF))
+
+DECLARE_GLOBAL_DATA_PTR;
+
+#if 0
+void __arm_init_before_mmu(void)
+{
+}
+void arm_init_before_mmu(void)
+	__attribute__((weak, alias("__arm_init_before_mmu")));
+#endif
+
+static void cp_delay (void)
+{
+	volatile int i;
+
+	/* copro seems to need some delay between reading and writing */
+	for (i = 0; i < 100; i++)
+		nop();
+	asm volatile("" : : : "memory");
+}
+
+static void set_section_dcache(int section, enum dcache_option option)
+{
+	u32 value = section << MMU_SECTION_SHIFT | (3 << 10);
+//	u32 *page_table = (u32 *)gd->tlb_addr;
+	u32 *page_table;
+	unsigned int tlb_addr;
+	unsigned int tlb_size = 4096 * 4;
+
+	/*
+	 * FIXME(dhendrix): This calculation is from arch/arm/lib/board.c
+	 * in u-boot. We may need to subtract more due to logging.
+	 */
+	tlb_addr = (CONFIG_SYS_SDRAM_BASE + (CONFIG_DRAM_SIZE_MB << 20UL));
+	tlb_addr -= tlb_size;
+	/* round down to next 64KB limit */
+	tlb_addr &= ~(0x10000 - 1);
+	page_table = (u32 *)tlb_addr;
+
+	switch (option) {
+	case DCACHE_WRITETHROUGH:
+		value |= 0x1a;
+		break;
+
+	case DCACHE_WRITEBACK:
+		value |= 0x1e;
+		break;
+
+	case DCACHE_OFF:
+		value |= 0x12;
+		break;
+	}
+
+	page_table[section] = value;
+}
+
+#if 0
+void __mmu_page_table_flush(unsigned long start, unsigned long stop)
+{
+	debug("%s: Warning: not implemented\n", __func__);
+}
+#endif
+
+#if 0
+void mmu_page_table_flush(unsigned long start, unsigned long stop)
+	__attribute__((weak, alias("__mmu_page_table_flush")));
+#endif
+
+void mmu_set_region_dcache(unsigned long start, int size, enum dcache_option option)
+{
+	u32 *page_table = (u32 *)gd->tlb_addr;
+	u32 upto, end;
+
+	end = ALIGN(start + size, MMU_SECTION_SIZE) >> MMU_SECTION_SHIFT;
+	start = start >> MMU_SECTION_SHIFT;
+	debug("mmu_set_region_dcache start=%x, size=%x, option=%d\n",
+	      start, size, option);
+	for (upto = start; upto < end; upto++)
+		set_section_dcache(upto, option);
+	mmu_page_table_flush((u32)&page_table[start], (u32)&page_table[end]);
+}
+
+#if 0
+static inline void dram_bank_mmu_setup(int bank)
+{
+//	bd_t *bd = gd->bd;
+	int	i;
+
+	debug("%s: bank: %d\n", __func__, bank);
+	for (i = bd->bi_dram[bank].start >> 20;
+	     i < (bd->bi_dram[bank].start + bd->bi_dram[bank].size) >> 20;
+	     i++) {
+#if defined(CONFIG_SYS_ARM_CACHE_WRITETHROUGH)
+		set_section_dcache(i, DCACHE_WRITETHROUGH);
+#else
+		set_section_dcache(i, DCACHE_WRITEBACK);
+#endif
+	}
+}
+#endif
+
+/* FIXME(dhendrix): modified to take arguments from the caller (mainboard's
+   romstage.c) so it doesn't rely on global data struct */
+/**
+ * dram_bank_mmu_set - set up the data cache policy for a given dram bank
+ *
+ * @start:	virtual address start of bank
+ * @size:	size of bank (in bytes)
+ */
+inline void dram_bank_mmu_setup(unsigned long start, unsigned long size)
+{
+	int	i;
+
+	debug("%s: bank: %d\n", __func__, bank);
+	for (i = start >> 20; i < (start + size) >> 20; i++) {
+#if defined(CONFIG_ARM_DCACHE_POLICY_WRITEBACK)
+		set_section_dcache(i, DCACHE_WRITEBACK);
+#elif defined(CONFIG_ARM_DCACHE_POLICY_WRITETHROUGH)
+		set_section_dcache(i, DCACHE_WRITETHROUGH);
+#else
+#error "Must define dcache policy."
+#endif
+	}
+}
+
+/* to activate the MMU we need to set up virtual memory: use 1M areas */
+static inline void mmu_setup(void)
+{
+	int i;
+	u32 reg;
+
+	arm_init_before_mmu();
+	/* Set up an identity-mapping for all 4GB, rw for everyone */
+	for (i = 0; i < 4096; i++)
+		set_section_dcache(i, DCACHE_OFF);
+
+	/* FIXME(dhendrix): u-boot's global data struct was used here... */
+#if 0
+	for (i = 0; i < CONFIG_NR_DRAM_BANKS; i++) {
+		dram_bank_mmu_setup(i);
+	}
+#endif
+#if 0
+	/* comes from board's romstage.c, since we need to know which
+	   ranges to setup */
+	mainboard_setup_mmu();
+#endif
+	dram_bank_mmu_setup(CONFIG_SYS_SDRAM_BASE, CONFIG_DRAM_SIZE_MB << 20);
+
+	/* Copy the page table address to cp15 */
+	asm volatile("mcr p15, 0, %0, c2, c0, 0"
+		     : : "r" (gd->tlb_addr) : "memory");
+	/* Set the access control to all-supervisor */
+	asm volatile("mcr p15, 0, %0, c3, c0, 0"
+		     : : "r" (~0));
+	/* and enable the mmu */
+	reg = get_cr();	/* get control reg. */
+	cp_delay();
+	set_cr(reg | CR_M);
+}
+
+static int mmu_enabled(void)
+{
+	return get_cr() & CR_M;
+}
+
+/* cache_bit must be either CR_I or CR_C */
+static void cache_enable(uint32_t cache_bit)
+{
+	uint32_t reg;
+
+	/* The data cache is not active unless the mmu is enabled too */
+	if ((cache_bit == CR_C) && !mmu_enabled())
+		mmu_setup();
+	reg = get_cr();	/* get control reg. */
+	cp_delay();
+	set_cr(reg | cache_bit);
+}
+
+/*
+ * Big hack warning!
+ *
+ * Devs like to compile with -O0 to get a nice debugging illusion. But this
+ * function does not survive that since -O0 causes the compiler to read the
+ * PC back from the stack after the dcache flush. Might it be possible to fix
+ * this by flushing the write buffer?
+ */
+static void cache_disable(uint32_t cache_bit) __attribute__ ((optimize(2)));
+
+/* cache_bit must be either CR_I or CR_C */
+static void cache_disable(uint32_t cache_bit)
+{
+	uint32_t reg;
+
+	if (cache_bit == CR_C) {
+		/* if cache isn;t enabled no need to disable */
+		reg = get_cr();
+		if ((reg & CR_C) != CR_C)
+			return;
+		/* if disabling data cache, disable mmu too */
+		cache_bit |= CR_M;
+	}
+	reg = get_cr();
+	cp_delay();
+	if (cache_bit == (CR_C | CR_M))
+		flush_dcache_all();
+	set_cr(reg & ~cache_bit);
+}
+#endif
+
+#ifdef CONFIG_SYS_ICACHE_OFF
+void icache_enable (void)
+{
+	return;
+}
+
+void icache_disable (void)
+{
+	return;
+}
+
+int icache_status (void)
+{
+	return 0;					/* always off */
+}
+#else
+void icache_enable(void)
+{
+	cache_enable(CR_I);
+}
+
+void icache_disable(void)
+{
+	cache_disable(CR_I);
+}
+
+int icache_status(void)
+{
+	return (get_cr() & CR_I) != 0;
+}
+#endif
+
+#ifdef CONFIG_SYS_DCACHE_OFF
+void dcache_enable (void)
+{
+	return;
+}
+
+void dcache_disable (void)
+{
+	return;
+}
+
+int dcache_status (void)
+{
+	return 0;					/* always off */
+}
+#else
+void dcache_enable(void)
+{
+	cache_enable(CR_C);
+}
+
+void dcache_disable(void)
+{
+	cache_disable(CR_C);
+}
+
+int dcache_status(void)
+{
+	return (get_cr() & CR_C) != 0;
+}
+#endif
diff --git a/src/arch/armv7/lib/cache_v7.c b/src/arch/armv7/lib/cache_v7.c
new file mode 100644
index 0000000000..13bb59f025
--- /dev/null
+++ b/src/arch/armv7/lib/cache_v7.c
@@ -0,0 +1,427 @@
+/*
+ * (C) Copyright 2010
+ * Texas Instruments, <www.ti.com>
+ * Aneesh V <aneesh@ti.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+#include <armv7.h>
+#include <common.h>
+#include <system.h>
+#include <utils.h>
+#include <console/console.h>
+
+#define ARMV7_DCACHE_INVAL_ALL		1
+#define ARMV7_DCACHE_CLEAN_INVAL_ALL	2
+#define ARMV7_DCACHE_INVAL_RANGE	3
+#define ARMV7_DCACHE_CLEAN_INVAL_RANGE	4
+
+#ifndef CONFIG_SYS_DCACHE_OFF
+/*
+ * Write the level and type you want to Cache Size Selection Register(CSSELR)
+ * to get size details from Current Cache Size ID Register(CCSIDR)
+ */
+static void set_csselr(u32 level, u32 type)
+{	u32 csselr = level << 1 | type;
+
+	/* Write to Cache Size Selection Register(CSSELR) */
+	asm volatile ("mcr p15, 2, %0, c0, c0, 0" : : "r" (csselr));
+}
+
+static u32 get_ccsidr(void)
+{
+	u32 ccsidr;
+
+	/* Read current CP15 Cache Size ID Register */
+	asm volatile ("mrc p15, 1, %0, c0, c0, 0" : "=r" (ccsidr));
+	return ccsidr;
+}
+
+static u32 get_clidr(void)
+{
+	u32 clidr;
+
+	/* Read current CP15 Cache Level ID Register */
+	asm volatile ("mrc p15,1,%0,c0,c0,1" : "=r" (clidr));
+	return clidr;
+}
+
+static void v7_inval_dcache_level_setway(u32 level, u32 num_sets,
+					 u32 num_ways, u32 way_shift,
+					 u32 log2_line_len)
+{
+	int way, set, setway;
+
+	/*
+	 * For optimal assembly code:
+	 *	a. count down
+	 *	b. have bigger loop inside
+	 */
+	for (way = num_ways - 1; way >= 0 ; way--) {
+		for (set = num_sets - 1; set >= 0; set--) {
+			setway = (level << 1) | (set << log2_line_len) |
+				 (way << way_shift);
+			/* Invalidate data/unified cache line by set/way */
+			asm volatile ("	mcr p15, 0, %0, c7, c6, 2"
+					: : "r" (setway));
+		}
+	}
+	/* DSB to make sure the operation is complete */
+	CP15DSB;
+}
+
+static void v7_clean_inval_dcache_level_setway(u32 level, u32 num_sets,
+					       u32 num_ways, u32 way_shift,
+					       u32 log2_line_len)
+{
+	int way, set, setway;
+
+	/*
+	 * For optimal assembly code:
+	 *	a. count down
+	 *	b. have bigger loop inside
+	 */
+	for (way = num_ways - 1; way >= 0 ; way--) {
+		for (set = num_sets - 1; set >= 0; set--) {
+			setway = (level << 1) | (set << log2_line_len) |
+				 (way << way_shift);
+			/*
+			 * Clean & Invalidate data/unified
+			 * cache line by set/way
+			 */
+			asm volatile ("	mcr p15, 0, %0, c7, c14, 2"
+					: : "r" (setway));
+		}
+	}
+	/* DSB to make sure the operation is complete */
+	CP15DSB;
+}
+
+static void v7_maint_dcache_level_setway(u32 level, u32 operation)
+{
+	u32 ccsidr;
+	u32 num_sets, num_ways, log2_line_len, log2_num_ways;
+	u32 way_shift;
+
+	set_csselr(level, ARMV7_CSSELR_IND_DATA_UNIFIED);
+
+	ccsidr = get_ccsidr();
+
+	log2_line_len = ((ccsidr & CCSIDR_LINE_SIZE_MASK) >>
+				CCSIDR_LINE_SIZE_OFFSET) + 2;
+	/* Converting from words to bytes */
+	log2_line_len += 2;
+
+	num_ways  = ((ccsidr & CCSIDR_ASSOCIATIVITY_MASK) >>
+			CCSIDR_ASSOCIATIVITY_OFFSET) + 1;
+	num_sets  = ((ccsidr & CCSIDR_NUM_SETS_MASK) >>
+			CCSIDR_NUM_SETS_OFFSET) + 1;
+	/*
+	 * According to ARMv7 ARM number of sets and number of ways need
+	 * not be a power of 2
+	 */
+	log2_num_ways = log_2_n_round_up(num_ways);
+
+	way_shift = (32 - log2_num_ways);
+	if (operation == ARMV7_DCACHE_INVAL_ALL) {
+		v7_inval_dcache_level_setway(level, num_sets, num_ways,
+				      way_shift, log2_line_len);
+	} else if (operation == ARMV7_DCACHE_CLEAN_INVAL_ALL) {
+		v7_clean_inval_dcache_level_setway(level, num_sets, num_ways,
+						   way_shift, log2_line_len);
+	}
+}
+
+static void v7_maint_dcache_all(u32 operation)
+{
+	u32 level, cache_type, level_start_bit = 0;
+
+	u32 clidr = get_clidr();
+
+	for (level = 0; level < 7; level++) {
+		cache_type = (clidr >> level_start_bit) & 0x7;
+		if ((cache_type == ARMV7_CLIDR_CTYPE_DATA_ONLY) ||
+		    (cache_type == ARMV7_CLIDR_CTYPE_INSTRUCTION_DATA) ||
+		    (cache_type == ARMV7_CLIDR_CTYPE_UNIFIED))
+			v7_maint_dcache_level_setway(level, operation);
+		level_start_bit += 3;
+	}
+}
+
+static void v7_dcache_clean_inval_range(u32 start,
+					u32 stop, u32 line_len)
+{
+	u32 mva;
+
+	/* Align start to cache line boundary */
+	start &= ~(line_len - 1);
+	for (mva = start; mva < stop; mva = mva + line_len) {
+		/* DCCIMVAC - Clean & Invalidate data cache by MVA to PoC */
+		asm volatile ("mcr p15, 0, %0, c7, c14, 1" : : "r" (mva));
+	}
+}
+
+static void v7_dcache_inval_range(u32 start, u32 stop, u32 line_len)
+{
+	u32 mva;
+
+	/*
+	 * If start address is not aligned to cache-line do not
+	 * invalidate the first cache-line
+	 */
+	if (start & (line_len - 1)) {
+		printk(BIOS_ERR, "%s - start address is not aligned - 0x%08x\n",
+			__func__, start);
+		/* move to next cache line */
+		start = (start + line_len - 1) & ~(line_len - 1);
+	}
+
+	/*
+	 * If stop address is not aligned to cache-line do not
+	 * invalidate the last cache-line
+	 */
+	if (stop & (line_len - 1)) {
+		printk(BIOS_ERR, "%s - stop address is not aligned - 0x%08x\n",
+			__func__, stop);
+		/* align to the beginning of this cache line */
+		stop &= ~(line_len - 1);
+	}
+
+	for (mva = start; mva < stop; mva = mva + line_len) {
+		/* DCIMVAC - Invalidate data cache by MVA to PoC */
+		asm volatile ("mcr p15, 0, %0, c7, c6, 1" : : "r" (mva));
+	}
+}
+
+static void v7_dcache_maint_range(u32 start, u32 stop, u32 range_op)
+{
+	u32 line_len = dcache_get_line_size();
+
+	switch (range_op) {
+	case ARMV7_DCACHE_CLEAN_INVAL_RANGE:
+		v7_dcache_clean_inval_range(start, stop, line_len);
+		break;
+	case ARMV7_DCACHE_INVAL_RANGE:
+		v7_dcache_inval_range(start, stop, line_len);
+		break;
+	}
+
+	/* DSB to make sure the operation is complete */
+	CP15DSB;
+}
+
+/* Invalidate TLB */
+static void v7_inval_tlb(void)
+{
+	/* Invalidate entire unified TLB */
+	asm volatile ("mcr p15, 0, %0, c8, c7, 0" : : "r" (0));
+	/* Invalidate entire data TLB */
+	asm volatile ("mcr p15, 0, %0, c8, c6, 0" : : "r" (0));
+	/* Invalidate entire instruction TLB */
+	asm volatile ("mcr p15, 0, %0, c8, c5, 0" : : "r" (0));
+	/* Full system DSB - make sure that the invalidation is complete */
+	CP15DSB;
+	/* Full system ISB - make sure the instruction stream sees it */
+	CP15ISB;
+}
+
+ulong dcache_get_line_size(void)
+{
+	u32 line_len, ccsidr;
+
+	ccsidr = get_ccsidr();
+	line_len = ((ccsidr & CCSIDR_LINE_SIZE_MASK) >>
+			CCSIDR_LINE_SIZE_OFFSET) + 2;
+	/* Converting from words to bytes */
+	line_len += 2;
+	/* converting from log2(linelen) to linelen */
+	line_len = 1 << line_len;
+
+	return line_len;
+}
+
+void invalidate_dcache_all(void)
+{
+	v7_maint_dcache_all(ARMV7_DCACHE_INVAL_ALL);
+
+	v7_outer_cache_inval_all();
+}
+
+/*
+ * Performs a clean & invalidation of the entire data cache
+ * at all levels
+ */
+void flush_dcache_all(void)
+{
+	v7_maint_dcache_all(ARMV7_DCACHE_CLEAN_INVAL_ALL);
+
+	v7_outer_cache_flush_all();
+}
+
+/*
+ * Invalidates range in all levels of D-cache/unified cache used:
+ * Affects the range [start, stop - 1]
+ */
+void invalidate_dcache_range(unsigned long start, unsigned long stop)
+{
+
+	v7_dcache_maint_range(start, stop, ARMV7_DCACHE_INVAL_RANGE);
+
+	v7_outer_cache_inval_range(start, stop);
+}
+
+/*
+ * Flush range(clean & invalidate) from all levels of D-cache/unified
+ * cache used:
+ * Affects the range [start, stop - 1]
+ */
+void flush_dcache_range(unsigned long start, unsigned long stop)
+{
+	v7_dcache_maint_range(start, stop, ARMV7_DCACHE_CLEAN_INVAL_RANGE);
+
+	v7_outer_cache_flush_range(start, stop);
+}
+
+void arm_init_before_mmu(void)
+{
+	v7_outer_cache_enable();
+	invalidate_dcache_all();
+	v7_inval_tlb();
+}
+
+void mmu_page_table_flush(unsigned long start, unsigned long stop)
+{
+	flush_dcache_range(start, stop);
+	v7_inval_tlb();
+}
+
+/*
+ * Flush range from all levels of d-cache/unified-cache used:
+ * Affects the range [start, start + size - 1]
+ */
+void  flush_cache(unsigned long start, unsigned long size)
+{
+	flush_dcache_range(start, start + size);
+}
+#else /* #ifndef CONFIG_SYS_DCACHE_OFF */
+ulong dcache_get_line_size(void)
+{
+	return 0;
+}
+
+void invalidate_dcache_all(void)
+{
+}
+
+void flush_dcache_all(void)
+{
+}
+
+void invalidate_dcache_range(unsigned long start, unsigned long stop)
+{
+}
+
+void flush_dcache_range(unsigned long start, unsigned long stop)
+{
+}
+
+void arm_init_before_mmu(void)
+{
+}
+
+void  flush_cache(unsigned long start, unsigned long size)
+{
+}
+
+void mmu_page_table_flush(unsigned long start, unsigned long stop)
+{
+}
+
+#endif /* #ifndef CONFIG_SYS_DCACHE_OFF */
+
+#ifndef CONFIG_SYS_ICACHE_OFF
+/* Invalidate entire I-cache and branch predictor array */
+void invalidate_icache_all(void)
+{
+	/*
+	 * Invalidate all instruction caches to PoU.
+	 * Also flushes branch target cache.
+	 */
+	asm volatile ("mcr p15, 0, %0, c7, c5, 0" : : "r" (0));
+
+	/* Invalidate entire branch predictor array */
+	asm volatile ("mcr p15, 0, %0, c7, c5, 6" : : "r" (0));
+
+	/* Full system DSB - make sure that the invalidation is complete */
+	CP15DSB;
+
+	/* ISB - make sure the instruction stream sees it */
+	CP15ISB;
+}
+#else
+void invalidate_icache_all(void)
+{
+}
+#endif
+
+/*
+ * FIXME(dhendrix): had unexplainable compilation failure of weak symbols
+ * (in spite of having prototypes and whatnot)... ron's advice is "death
+ *  to weak symbols!"
+ */
+#if 0
+/*
+ * Stub implementations for outer cache operations
+ */
+void __v7_outer_cache_enable(void)
+{
+}
+void v7_outer_cache_enable(void)
+	__attribute__((weak, alias("__v7_outer_cache_enable")));
+
+void __v7_outer_cache_disable(void)
+{
+}
+void v7_outer_cache_disable(void)
+	__attribute__((weak, alias("__v7_outer_cache_disable")));
+
+void __v7_outer_cache_flush_all(void)
+{
+}
+void v7_outer_cache_flush_all(void)
+	__attribute__((weak, alias("__v7_outer_cache_flush_all")));
+
+void __v7_outer_cache_inval_all(void)
+{
+}
+void v7_outer_cache_inval_all(void)
+	__attribute__((weak, alias("__v7_outer_cache_inval_all")));
+
+void __v7_outer_cache_flush_range(u32 start, u32 end)
+{
+}
+void v7_outer_cache_flush_range(u32 start, u32 end)
+	__attribute__((weak, alias("__v7_outer_cache_flush_range")));
+
+void __v7_outer_cache_inval_range(u32 start, u32 end)
+{
+}
+void v7_outer_cache_inval_range(u32 start, u32 end)
+	__attribute__((weak, alias("__v7_outer_cache_inval_range")));
+#endif
diff --git a/src/arch/armv7/lib/div.c b/src/arch/armv7/lib/div.c
new file mode 100644
index 0000000000..03352dc7a5
--- /dev/null
+++ b/src/arch/armv7/lib/div.c
@@ -0,0 +1,5 @@
+void __div0(void); // called from asm so no need for a prototype in a header
+void __div0(void)
+{
+	// div by zero
+}
diff --git a/src/arch/armv7/lib/div0.c b/src/arch/armv7/lib/div0.c
new file mode 100644
index 0000000000..632c247b5c
--- /dev/null
+++ b/src/arch/armv7/lib/div0.c
@@ -0,0 +1,32 @@
+/*
+ * (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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+void __div0(void); // called from asm so no need for a prototype in a header
+
+/* Replacement (=dummy) for GNU/Linux division-by zero handler */
+void __div0 (void)
+{
+	extern void hang (void);
+
+	hang();
+}
diff --git a/src/arch/armv7/lib/div64.S b/src/arch/armv7/lib/div64.S
new file mode 100644
index 0000000000..44edf480ca
--- /dev/null
+++ b/src/arch/armv7/lib/div64.S
@@ -0,0 +1,208 @@
+/*
+ *  linux/arch/arm/lib/div64.S
+ *
+ *  Optimized computation of 64-bit dividend / 32-bit divisor
+ *
+ *  Author:	Nicolas Pitre
+ *  Created:	Oct 5, 2003
+ *  Copyright:	Monta Vista 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.
+ */
+
+// FIXME
+//#include <linux/linkage.h>
+#define __LINUX_ARM_ARCH__ 7
+
+#ifdef __ARMEB__
+#define xh r0
+#define xl r1
+#define yh r2
+#define yl r3
+#else
+#define xl r0
+#define xh r1
+#define yl r2
+#define yh r3
+#endif
+
+/*
+ * __do_div64: perform a division with 64-bit dividend and 32-bit divisor.
+ *
+ * Note: Calling convention is totally non standard for optimal code.
+ *       This is meant to be used by do_div() from include/asm/div64.h only.
+ *
+ * Input parameters:
+ * 	xh-xl	= dividend (clobbered)
+ * 	r4	= divisor (preserved)
+ *
+ * Output values:
+ * 	yh-yl	= result
+ * 	xh	= remainder
+ *
+ * Clobbered regs: xl, ip
+ */
+
+
+.globl __do_div64;
+.align 4,0x90
+__do_div64:
+
+	@ Test for easy paths first.
+	subs	ip, r4, #1
+	bls	9f			@ divisor is 0 or 1
+	tst	ip, r4
+	beq	8f			@ divisor is power of 2
+
+	@ See if we need to handle upper 32-bit result.
+	cmp	xh, r4
+	mov	yh, #0
+	blo	3f
+
+	@ Align divisor with upper part of dividend.
+	@ The aligned divisor is stored in yl preserving the original.
+	@ The bit position is stored in ip.
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	yl, r4
+	clz	ip, xh
+	sub	yl, yl, ip
+	mov	ip, #1
+	mov	ip, ip, lsl yl
+	mov	yl, r4, lsl yl
+
+#else
+
+	mov	yl, r4
+	mov	ip, #1
+1:	cmp	yl, #0x80000000
+	cmpcc	yl, xh
+	movcc	yl, yl, lsl #1
+	movcc	ip, ip, lsl #1
+	bcc	1b
+
+#endif
+
+	@ The division loop for needed upper bit positions.
+ 	@ Break out early if dividend reaches 0.
+2:	cmp	xh, yl
+	orrcs	yh, yh, ip
+	subcss	xh, xh, yl
+	movnes	ip, ip, lsr #1
+	mov	yl, yl, lsr #1
+	bne	2b
+
+	@ See if we need to handle lower 32-bit result.
+3:	cmp	xh, #0
+	mov	yl, #0
+	cmpeq	xl, r4
+	movlo	xh, xl
+	movlo	pc, lr
+
+	@ The division loop for lower bit positions.
+	@ Here we shift remainer bits leftwards rather than moving the
+	@ divisor for comparisons, considering the carry-out bit as well.
+	mov	ip, #0x80000000
+4:	movs	xl, xl, lsl #1
+	adcs	xh, xh, xh
+	beq	6f
+	cmpcc	xh, r4
+5:	orrcs	yl, yl, ip
+	subcs	xh, xh, r4
+	movs	ip, ip, lsr #1
+	bne	4b
+	mov	pc, lr
+
+	@ The top part of remainder became zero.  If carry is set
+	@ (the 33th bit) this is a false positive so resume the loop.
+	@ Otherwise, if lower part is also null then we are done.
+6:	bcs	5b
+	cmp	xl, #0
+	moveq	pc, lr
+
+	@ We still have remainer bits in the low part.  Bring them up.
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	xh, xl			@ we know xh is zero here so...
+	add	xh, xh, #1
+	mov	xl, xl, lsl xh
+	mov	ip, ip, lsr xh
+
+#else
+
+7:	movs	xl, xl, lsl #1
+	mov	ip, ip, lsr #1
+	bcc	7b
+
+#endif
+
+	@ Current remainder is now 1.  It is worthless to compare with
+	@ divisor at this point since divisor can not be smaller than 3 here.
+	@ If possible, branch for another shift in the division loop.
+	@ If no bit position left then we are done.
+	movs	ip, ip, lsr #1
+	mov	xh, #1
+	bne	4b
+	mov	pc, lr
+
+8:	@ Division by a power of 2: determine what that divisor order is
+	@ then simply shift values around
+
+#if __LINUX_ARM_ARCH__ >= 5
+
+	clz	ip, r4
+	rsb	ip, ip, #31
+
+#else
+
+	mov	yl, r4
+	cmp	r4, #(1 << 16)
+	mov	ip, #0
+	movhs	yl, yl, lsr #16
+	movhs	ip, #16
+
+	cmp	yl, #(1 << 8)
+	movhs	yl, yl, lsr #8
+	addhs	ip, ip, #8
+
+	cmp	yl, #(1 << 4)
+	movhs	yl, yl, lsr #4
+	addhs	ip, ip, #4
+
+	cmp	yl, #(1 << 2)
+	addhi	ip, ip, #3
+	addls	ip, ip, yl, lsr #1
+
+#endif
+
+	mov	yh, xh, lsr ip
+	mov	yl, xl, lsr ip
+	rsb	ip, ip, #32
+	orr	yl, yl, xh, lsl ip
+	mov	xh, xl, lsl ip
+	mov	xh, xh, lsr ip
+	mov	pc, lr
+
+	@ eq -> division by 1: obvious enough...
+9:	moveq	yl, xl
+	moveq	yh, xh
+	moveq	xh, #0
+	moveq	pc, lr
+
+	@ Division by 0:
+	str	lr, [sp, #-8]!
+	bl	__div0
+
+	@ as wrong as it could be...
+	mov	yl, #0
+	mov	yh, #0
+	mov	xh, #0
+	ldr	pc, [sp], #8
+
+@.type __do_div64, @function;
+@.size __do_div64, .-__do_div64,
+
diff --git a/src/arch/armv7/lib/eabi_compat.c b/src/arch/armv7/lib/eabi_compat.c
new file mode 100644
index 0000000000..5f59892432
--- /dev/null
+++ b/src/arch/armv7/lib/eabi_compat.c
@@ -0,0 +1,33 @@
+/*
+ * Utility functions needed for (some) EABI conformant tool chains.
+ *
+ * (C) Copyright 2009 Wolfgang Denk <wd@denx.de>
+ *
+ * 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.
+ */
+
+#include <common.h>
+
+/* FIXME(dhendrix): prototypes added for assembler */
+int raise (int signum);
+int raise (int signum)
+{
+#if !defined(CONFIG_SPL_BUILD) || defined(CONFIG_SPL_LIBCOMMON_SUPPORT)
+	printf("raise: Signal # %d caught\n", signum);
+#endif
+	return 0;
+}
+
+/* Dummy function to avoid linker complaints */
+void __aeabi_unwind_cpp_pr0(void);
+void __aeabi_unwind_cpp_pr0(void)
+{
+};
+
+void __aeabi_unwind_cpp_pr1(void);
+void __aeabi_unwind_cpp_pr1(void)
+{
+};
diff --git a/src/arch/armv7/lib/hang_spl.c b/src/arch/armv7/lib/hang_spl.c
new file mode 100644
index 0000000000..630a57af47
--- /dev/null
+++ b/src/arch/armv7/lib/hang_spl.c
@@ -0,0 +1,16 @@
+/*
+ * Copyright (c) 2012 The Chromium OS Authors. All rights reserved.
+ * Use of this source code is governed by a BSD-style license that can be
+ * found in the LICENSE file.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ */
+
+#include <hang.h> 
+
+void hang(void)
+{
+	for (;;);
+}
diff --git a/src/arch/armv7/lib/id.inc b/src/arch/armv7/lib/id.inc
new file mode 100644
index 0000000000..4da7024233
--- /dev/null
+++ b/src/arch/armv7/lib/id.inc
@@ -0,0 +1,18 @@
+	.section ".id", "a", %progbits
+
+	.globl __id_start
+__id_start:
+ver:
+	.asciz COREBOOT_VERSION
+vendor:
+	.asciz CONFIG_MAINBOARD_VENDOR
+part:
+	.asciz CONFIG_MAINBOARD_PART_NUMBER
+.long __id_end + CONFIG_ID_SECTION_OFFSET - ver  /* Reverse offset to the vendor id */
+.long __id_end + CONFIG_ID_SECTION_OFFSET - vendor  /* Reverse offset to the vendor id */
+.long __id_end + CONFIG_ID_SECTION_OFFSET - part    /* Reverse offset to the part number */
+.long CONFIG_ROM_SIZE                               /* Size of this romimage */
+	.globl __id_end
+
+__id_end:
+.previous
diff --git a/src/arch/armv7/lib/id.lds b/src/arch/armv7/lib/id.lds
new file mode 100644
index 0000000000..9e31ee615c
--- /dev/null
+++ b/src/arch/armv7/lib/id.lds
@@ -0,0 +1,6 @@
+SECTIONS {
+	. = (0x100000000 - CONFIG_ID_SECTION_OFFSET) - (__id_end - __id_start);
+	.id (.): {
+		*(.id)
+	}
+}
diff --git a/src/arch/armv7/lib/interrupts.c b/src/arch/armv7/lib/interrupts.c
new file mode 100644
index 0000000000..6ee3f267ef
--- /dev/null
+++ b/src/arch/armv7/lib/interrupts.c
@@ -0,0 +1,198 @@
+/*
+ * (C) Copyright 2003
+ * Texas Instruments <www.ti.com>
+ *
+ * (C) Copyright 2002
+ * Sysgo Real-Time Solutions, GmbH <www.elinos.com>
+ * Marius Groeger <mgroeger@sysgo.de>
+ *
+ * (C) Copyright 2002
+ * Sysgo Real-Time Solutions, GmbH <www.elinos.com>
+ * Alex Zuepke <azu@sysgo.de>
+ *
+ * (C) Copyright 2002-2004
+ * Gary Jennejohn, DENX Software Engineering, <garyj@denx.de>
+ *
+ * (C) Copyright 2004
+ * Philippe Robin, ARM Ltd. <philippe.robin@arm.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+#include <common.h>
+//#include <asm/proc-armv/ptrace.h>
+
+DECLARE_GLOBAL_DATA_PTR;
+
+#ifdef CONFIG_USE_IRQ
+int interrupt_init (void)
+{
+	/*
+	 * setup up stacks if necessary
+	 */
+	IRQ_STACK_START = gd->irq_sp - 4;
+	IRQ_STACK_START_IN = gd->irq_sp + 8;
+	FIQ_STACK_START = IRQ_STACK_START - CONFIG_STACKSIZE_IRQ;
+
+	return arch_interrupt_init();
+}
+
+/* enable IRQ interrupts */
+void enable_interrupts (void)
+{
+	unsigned long temp;
+	__asm__ __volatile__("mrs %0, cpsr\n"
+			     "bic %0, %0, #0x80\n"
+			     "msr cpsr_c, %0"
+			     : "=r" (temp)
+			     :
+			     : "memory");
+}
+
+
+/*
+ * disable IRQ/FIQ interrupts
+ * returns true if interrupts had been enabled before we disabled them
+ */
+int disable_interrupts (void)
+{
+	unsigned long old,temp;
+	__asm__ __volatile__("mrs %0, cpsr\n"
+			     "orr %1, %0, #0xc0\n"
+			     "msr cpsr_c, %1"
+			     : "=r" (old), "=r" (temp)
+			     :
+			     : "memory");
+	return (old & 0x80) == 0;
+}
+#else
+int interrupt_init (void)
+{
+	/*
+	 * setup up stacks if necessary
+	 */
+	IRQ_STACK_START_IN = gd->irq_sp + 8;
+
+	return 0;
+}
+
+void enable_interrupts (void)
+{
+	return;
+}
+int disable_interrupts (void)
+{
+	return 0;
+}
+#endif
+
+
+void bad_mode (void)
+{
+	panic ("Resetting CPU ...\n");
+	reset_cpu (0);
+}
+
+void show_regs (struct pt_regs *regs)
+{
+	unsigned long flags;
+	const char *processor_modes[] = {
+	"USER_26",	"FIQ_26",	"IRQ_26",	"SVC_26",
+	"UK4_26",	"UK5_26",	"UK6_26",	"UK7_26",
+	"UK8_26",	"UK9_26",	"UK10_26",	"UK11_26",
+	"UK12_26",	"UK13_26",	"UK14_26",	"UK15_26",
+	"USER_32",	"FIQ_32",	"IRQ_32",	"SVC_32",
+	"UK4_32",	"UK5_32",	"UK6_32",	"ABT_32",
+	"UK8_32",	"UK9_32",	"UK10_32",	"UND_32",
+	"UK12_32",	"UK13_32",	"UK14_32",	"SYS_32",
+	};
+
+	flags = condition_codes (regs);
+
+	printf ("pc : [<%08lx>]	   lr : [<%08lx>]\n"
+		"sp : %08lx  ip : %08lx	 fp : %08lx\n",
+		instruction_pointer (regs),
+		regs->ARM_lr, regs->ARM_sp, regs->ARM_ip, regs->ARM_fp);
+	printf ("r10: %08lx  r9 : %08lx	 r8 : %08lx\n",
+		regs->ARM_r10, regs->ARM_r9, regs->ARM_r8);
+	printf ("r7 : %08lx  r6 : %08lx	 r5 : %08lx  r4 : %08lx\n",
+		regs->ARM_r7, regs->ARM_r6, regs->ARM_r5, regs->ARM_r4);
+	printf ("r3 : %08lx  r2 : %08lx	 r1 : %08lx  r0 : %08lx\n",
+		regs->ARM_r3, regs->ARM_r2, regs->ARM_r1, regs->ARM_r0);
+	printf ("Flags: %c%c%c%c",
+		flags & CC_N_BIT ? 'N' : 'n',
+		flags & CC_Z_BIT ? 'Z' : 'z',
+		flags & CC_C_BIT ? 'C' : 'c', flags & CC_V_BIT ? 'V' : 'v');
+	printf ("  IRQs %s  FIQs %s  Mode %s%s\n",
+		interrupts_enabled (regs) ? "on" : "off",
+		fast_interrupts_enabled (regs) ? "on" : "off",
+		processor_modes[processor_mode (regs)],
+		thumb_mode (regs) ? " (T)" : "");
+}
+
+void do_undefined_instruction (struct pt_regs *pt_regs)
+{
+	printf ("undefined instruction\n");
+	show_regs (pt_regs);
+	bad_mode ();
+}
+
+void do_software_interrupt (struct pt_regs *pt_regs)
+{
+	printf ("software interrupt\n");
+	show_regs (pt_regs);
+	bad_mode ();
+}
+
+void do_prefetch_abort (struct pt_regs *pt_regs)
+{
+	printf ("prefetch abort\n");
+	show_regs (pt_regs);
+	bad_mode ();
+}
+
+void do_data_abort (struct pt_regs *pt_regs)
+{
+	printf ("data abort\n");
+	show_regs (pt_regs);
+	bad_mode ();
+}
+
+void do_not_used (struct pt_regs *pt_regs)
+{
+	printf ("not used\n");
+	show_regs (pt_regs);
+	bad_mode ();
+}
+
+void do_fiq (struct pt_regs *pt_regs)
+{
+	printf ("fast interrupt request\n");
+	show_regs (pt_regs);
+	bad_mode ();
+}
+
+#ifndef CONFIG_USE_IRQ
+void do_irq (struct pt_regs *pt_regs)
+{
+	printf ("interrupt request\n");
+	show_regs (pt_regs);
+	bad_mode ();
+}
+#endif
diff --git a/src/arch/armv7/lib/memcpy.S b/src/arch/armv7/lib/memcpy.S
new file mode 100644
index 0000000000..f655256b5d
--- /dev/null
+++ b/src/arch/armv7/lib/memcpy.S
@@ -0,0 +1,243 @@
+/*
+ *  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 <asm/assembler.h>
+
+#define W(instr)	instr
+
+#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); */
+
+.globl memcpy
+memcpy:
+
+		cmp	r0, r1
+		moveq	pc, lr
+
+		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
diff --git a/src/arch/armv7/lib/memset.S b/src/arch/armv7/lib/memset.S
new file mode 100644
index 0000000000..0cdf89535a
--- /dev/null
+++ b/src/arch/armv7/lib/memset.S
@@ -0,0 +1,126 @@
+/*
+ *  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 <asm/assembler.h>
+
+	.text
+	.align	5
+	.word	0
+
+1:	subs	r2, r2, #4		@ 1 do we have enough
+	blt	5f			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strltb	r1, [r0], #1		@ 1
+	strleb	r1, [r0], #1		@ 1
+	strb	r1, [r0], #1		@ 1
+	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
+/*
+ * The pointer is now aligned and the length is adjusted.  Try doing the
+ * memset again.
+ */
+
+.globl memset
+memset:
+	ands	r3, r0, #3		@ 1 unaligned?
+	bne	1b			@ 1
+/*
+ * we know that the pointer in r0 is aligned to a word boundary.
+ */
+	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 extra register for this loop - save the return address and
+ * use the LR
+ */
+	str	lr, [sp, #-4]!
+	mov	ip, r1
+	mov	lr, r1
+
+2:	subs	r2, r2, #64
+	stmgeia	r0!, {r1, r3, ip, lr}	@ 64 bytes at a time.
+	stmgeia	r0!, {r1, r3, ip, lr}
+	stmgeia	r0!, {r1, r3, ip, lr}
+	stmgeia	r0!, {r1, r3, ip, lr}
+	bgt	2b
+	ldmeqfd	sp!, {pc}		@ Now <64 bytes to go.
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+	tst	r2, #32
+	stmneia	r0!, {r1, r3, ip, lr}
+	stmneia	r0!, {r1, r3, ip, lr}
+	tst	r2, #16
+	stmneia	r0!, {r1, r3, ip, lr}
+	ldr	lr, [sp], #4
+
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+	stmfd	sp!, {r4-r7, lr}
+	mov	r4, r1
+	mov	r5, r1
+	mov	r6, r1
+	mov	r7, r1
+	mov	ip, r1
+	mov	lr, r1
+
+	cmp	r2, #96
+	tstgt	r0, #31
+	ble	3f
+
+	and	ip, r0, #31
+	rsb	ip, ip, #32
+	sub	r2, r2, ip
+	movs	ip, ip, lsl #(32 - 4)
+	stmcsia	r0!, {r4, r5, r6, r7}
+	stmmiia	r0!, {r4, r5}
+	tst	ip, #(1 << 30)
+	mov	ip, r1
+	strne	r1, [r0], #4
+
+3:	subs	r2, r2, #64
+	stmgeia	r0!, {r1, r3-r7, ip, lr}
+	stmgeia	r0!, {r1, r3-r7, ip, lr}
+	bgt	3b
+	ldmeqfd	sp!, {r4-r7, pc}
+
+	tst	r2, #32
+	stmneia	r0!, {r1, r3-r7, ip, lr}
+	tst	r2, #16
+	stmneia	r0!, {r4-r7}
+	ldmfd	sp!, {r4-r7, lr}
+
+#endif
+
+4:	tst	r2, #8
+	stmneia	r0!, {r1, r3}
+	tst	r2, #4
+	strne	r1, [r0], #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, [r0], #1
+	strneb	r1, [r0], #1
+	tst	r2, #1
+	strneb	r1, [r0], #1
+	mov	pc, lr
diff --git a/src/arch/armv7/lib/reset.c b/src/arch/armv7/lib/reset.c
new file mode 100644
index 0000000000..08e6acb261
--- /dev/null
+++ b/src/arch/armv7/lib/reset.c
@@ -0,0 +1,53 @@
+/*
+ * (C) Copyright 2002
+ * Sysgo Real-Time Solutions, GmbH <www.elinos.com>
+ * Marius Groeger <mgroeger@sysgo.de>
+ *
+ * (C) Copyright 2002
+ * Sysgo Real-Time Solutions, GmbH <www.elinos.com>
+ * Alex Zuepke <azu@sysgo.de>
+ *
+ * (C) Copyright 2002
+ * Gary Jennejohn, DENX Software Engineering, <garyj@denx.de>
+ *
+ * (C) Copyright 2004
+ * DAVE Srl
+ * http://www.dave-tech.it
+ * http://www.wawnet.biz
+ * mailto:info@wawnet.biz
+ *
+ * (C) Copyright 2004 Texas Insturments
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+#include <common.h>
+
+int do_reset(cmd_tbl_t *cmdtp, int flag, int argc, char * const argv[])
+{
+	puts ("resetting ...\n");
+
+	udelay (50000);				/* wait 50 ms */
+
+	disable_interrupts();
+	reset_cpu(0);
+
+	/*NOTREACHED*/
+	return 0;
+}
diff --git a/src/arch/armv7/lib/romstage_console.c b/src/arch/armv7/lib/romstage_console.c
new file mode 100644
index 0000000000..ead26f3521
--- /dev/null
+++ b/src/arch/armv7/lib/romstage_console.c
@@ -0,0 +1,75 @@
+/*
+ * This file is part of the coreboot 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; version 2 of
+ * the License.
+ *
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
+ * MA 02110-1301 USA
+ */
+
+#include <console/console.h>
+#include <console/vtxprintf.h>
+#if CONFIG_SERIAL_CONSOLE
+#include <uart.h>
+#endif
+#if CONFIG_USBDEBUG
+#include <usbdebug.h>
+#endif
+
+/* FIXME: need to make console driver more generic */
+void console_tx_byte(unsigned char byte)
+{
+	if (byte == '\n')
+		console_tx_byte('\r');
+
+#if CONFIG_SERIAL_CONSOLE
+	uart_tx_byte(byte);
+#endif
+#if CONFIG_USBDEBUG
+	usbdebug_tx_byte(0, byte);
+#endif
+#if CONFIG_CONSOLE_CBMEM
+	cbmemc_tx_byte(byte);
+#endif
+}
+
+/* FIXME(dhendrix): add this back in */
+#if 0
+static void console_tx_flush(void)
+{
+#if CONFIG_CONSOLE_SERIAL
+	uart_tx_flush(CONFIG_CONSOLE_SERIAL_UART_ADDRESS);
+#endif
+#if CONFIG_USBDEBUG
+	usbdebug_tx_flush(0);
+#endif
+}
+#endif
+
+int do_printk(int msg_level, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	if (msg_level > console_loglevel) {
+		return 0;
+	}
+
+	va_start(args, fmt);
+	i = vtxprintf(console_tx_byte, fmt, args);
+	va_end(args);
+
+//	console_tx_flush();
+
+	return i;
+}
diff --git a/src/arch/armv7/lib/syslib.c b/src/arch/armv7/lib/syslib.c
new file mode 100644
index 0000000000..6f38bf9679
--- /dev/null
+++ b/src/arch/armv7/lib/syslib.c
@@ -0,0 +1,70 @@
+/*
+ * (C) Copyright 2008
+ * Texas Instruments, <www.ti.com>
+ *
+ * Richard Woodruff <r-woodruff2@ti.com>
+ * Syed Mohammed Khasim <khasim@ti.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+//#include <common.h>
+#include <arch/io.h>
+#include <system.h>	/* FIXME: dumping ground for prototypes */
+
+/************************************************************
+ * sdelay() - simple spin loop.  Will be constant time as
+ *  its generally used in bypass conditions only.  This
+ *  is necessary until timers are accessible.
+ *
+ *  not inline to increase chances its in cache when called
+ *************************************************************/
+void sdelay(unsigned long loops)
+{
+	__asm__ volatile ("1:\n" "subs %0, %1, #1\n"
+			  "bne 1b":"=r" (loops):"0"(loops));
+}
+
+/*****************************************************************
+ * sr32 - clear & set a value in a bit range for a 32 bit address
+ *****************************************************************/
+void sr32(void *addr, u32 start_bit, u32 num_bits, u32 value)
+{
+	u32 tmp, msk = 0;
+	msk = 1 << num_bits;
+	--msk;
+	tmp = readl((u32)addr) & ~(msk << start_bit);
+	tmp |= value << start_bit;
+	writel(tmp, (u32)addr);
+}
+
+/*********************************************************************
+ * wait_on_value() - common routine to allow waiting for changes in
+ *   volatile regs.
+ *********************************************************************/
+u32 wait_on_value(u32 read_bit_mask, u32 match_value, void *read_addr,
+		  u32 bound)
+{
+	u32 i = 0, val;
+	do {
+		++i;
+		val = readl((u32)read_addr) & read_bit_mask;
+		if (val == match_value)
+			return 1;
+		if (i == bound)
+			return 0;
+	} while (1);
+}