summaryrefslogtreecommitdiffstats
path: root/arch/arm/boot/compressed
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/boot/compressed')
-rw-r--r--arch/arm/boot/compressed/Makefile191
-rw-r--r--arch/arm/boot/compressed/atags_to_fdt.c97
-rw-r--r--arch/arm/boot/compressed/big-endian.S13
-rw-r--r--arch/arm/boot/compressed/decompress.c50
-rw-r--r--arch/arm/boot/compressed/head-sa1100.S47
-rw-r--r--arch/arm/boot/compressed/head-shark.S139
-rw-r--r--arch/arm/boot/compressed/head-sharpsl.S150
-rw-r--r--arch/arm/boot/compressed/head-shmobile.S83
-rw-r--r--arch/arm/boot/compressed/head-vt8500.S46
-rw-r--r--arch/arm/boot/compressed/head-xscale.S41
-rw-r--r--arch/arm/boot/compressed/head.S1228
-rw-r--r--arch/arm/boot/compressed/libfdt_env.h15
-rw-r--r--arch/arm/boot/compressed/ll_char_wr.S134
-rw-r--r--arch/arm/boot/compressed/misc.c154
-rw-r--r--arch/arm/boot/compressed/mmcif-sh7372.c88
-rw-r--r--arch/arm/boot/compressed/ofw-shark.c260
-rw-r--r--arch/arm/boot/compressed/piggy.gzip.S6
-rw-r--r--arch/arm/boot/compressed/piggy.lzma.S6
-rw-r--r--arch/arm/boot/compressed/piggy.lzo.S6
-rw-r--r--arch/arm/boot/compressed/sdhi-sh7372.c95
-rw-r--r--arch/arm/boot/compressed/sdhi-shmobile.c449
-rw-r--r--arch/arm/boot/compressed/sdhi-shmobile.h11
-rw-r--r--arch/arm/boot/compressed/string.c127
-rw-r--r--arch/arm/boot/compressed/vmlinux.lds.in76
24 files changed, 3512 insertions, 0 deletions
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
new file mode 100644
index 00000000000..cf0a64ce4b8
--- /dev/null
+++ b/arch/arm/boot/compressed/Makefile
@@ -0,0 +1,191 @@
+#
+# linux/arch/arm/boot/compressed/Makefile
+#
+# create a compressed vmlinuz image from the original vmlinux
+#
+
+OBJS =
+
+# Ensure that MMCIF loader code appears early in the image
+# to minimise that number of bocks that have to be read in
+# order to load it.
+ifeq ($(CONFIG_ZBOOT_ROM_MMCIF),y)
+OBJS += mmcif-sh7372.o
+endif
+
+# Ensure that SDHI loader code appears early in the image
+# to minimise that number of bocks that have to be read in
+# order to load it.
+ifeq ($(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI),y)
+OBJS += sdhi-shmobile.o
+OBJS += sdhi-sh7372.o
+endif
+
+AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET)
+HEAD = head.o
+OBJS += misc.o decompress.o
+FONTC = $(srctree)/drivers/video/console/font_acorn_8x8.c
+
+# string library code (-Os is enforced to keep it much smaller)
+OBJS += string.o
+CFLAGS_string.o := -Os
+
+#
+# Architecture dependencies
+#
+ifeq ($(CONFIG_ARCH_ACORN),y)
+OBJS += ll_char_wr.o font.o
+endif
+
+ifeq ($(CONFIG_ARCH_SHARK),y)
+OBJS += head-shark.o ofw-shark.o
+endif
+
+ifeq ($(CONFIG_ARCH_P720T),y)
+# Borrow this code from SA1100
+OBJS += head-sa1100.o
+endif
+
+ifeq ($(CONFIG_ARCH_SA1100),y)
+OBJS += head-sa1100.o
+endif
+
+ifeq ($(CONFIG_ARCH_VT8500),y)
+OBJS += head-vt8500.o
+endif
+
+ifeq ($(CONFIG_CPU_XSCALE),y)
+OBJS += head-xscale.o
+endif
+
+ifeq ($(CONFIG_PXA_SHARPSL_DETECT_MACH_ID),y)
+OBJS += head-sharpsl.o
+endif
+
+ifeq ($(CONFIG_CPU_ENDIAN_BE32),y)
+ifeq ($(CONFIG_CPU_CP15),y)
+OBJS += big-endian.o
+else
+# The endian should be set by h/w design.
+endif
+endif
+
+ifeq ($(CONFIG_ARCH_SHMOBILE),y)
+OBJS += head-shmobile.o
+endif
+
+#
+# We now have a PIC decompressor implementation. Decompressors running
+# from RAM should not define ZTEXTADDR. Decompressors running directly
+# from ROM or Flash must define ZTEXTADDR (preferably via the config)
+# FIXME: Previous assignment to ztextaddr-y is lost here. See SHARK
+ifeq ($(CONFIG_ZBOOT_ROM),y)
+ZTEXTADDR := $(CONFIG_ZBOOT_ROM_TEXT)
+ZBSSADDR := $(CONFIG_ZBOOT_ROM_BSS)
+else
+ZTEXTADDR := 0
+ZBSSADDR := ALIGN(8)
+endif
+
+SEDFLAGS = s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/
+
+suffix_$(CONFIG_KERNEL_GZIP) = gzip
+suffix_$(CONFIG_KERNEL_LZO) = lzo
+suffix_$(CONFIG_KERNEL_LZMA) = lzma
+
+# Borrowed libfdt files for the ATAG compatibility mode
+
+libfdt := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c
+libfdt_hdrs := fdt.h libfdt.h libfdt_internal.h
+
+libfdt_objs := $(addsuffix .o, $(basename $(libfdt)))
+
+$(addprefix $(obj)/,$(libfdt) $(libfdt_hdrs)): $(obj)/%: $(srctree)/scripts/dtc/libfdt/%
+ $(call cmd,shipped)
+
+$(addprefix $(obj)/,$(libfdt_objs) atags_to_fdt.o): \
+ $(addprefix $(obj)/,$(libfdt_hdrs))
+
+ifeq ($(CONFIG_ARM_ATAG_DTB_COMPAT),y)
+OBJS += $(libfdt_objs) atags_to_fdt.o
+endif
+
+targets := vmlinux vmlinux.lds \
+ piggy.$(suffix_y) piggy.$(suffix_y).o \
+ lib1funcs.o lib1funcs.S font.o font.c head.o misc.o $(OBJS)
+
+# Make sure files are removed during clean
+extra-y += piggy.gzip piggy.lzo piggy.lzma lib1funcs.S $(libfdt) $(libfdt_hdrs)
+
+ifeq ($(CONFIG_FUNCTION_TRACER),y)
+ORIG_CFLAGS := $(KBUILD_CFLAGS)
+KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
+endif
+
+ccflags-y := -fpic -fno-builtin -I$(obj)
+asflags-y := -Wa,-march=all
+
+# Supply kernel BSS size to the decompressor via a linker symbol.
+KBSS_SZ = $(shell $(CROSS_COMPILE)size $(obj)/../../../../vmlinux | \
+ awk 'END{print $$3}')
+LDFLAGS_vmlinux = --defsym _kernel_bss_size=$(KBSS_SZ)
+# Supply ZRELADDR to the decompressor via a linker symbol.
+ifneq ($(CONFIG_AUTO_ZRELADDR),y)
+LDFLAGS_vmlinux += --defsym zreladdr=$(ZRELADDR)
+endif
+ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
+LDFLAGS_vmlinux += --be8
+endif
+# ?
+LDFLAGS_vmlinux += -p
+# Report unresolved symbol references
+LDFLAGS_vmlinux += --no-undefined
+# Delete all temporary local symbols
+LDFLAGS_vmlinux += -X
+# Next argument is a linker script
+LDFLAGS_vmlinux += -T
+
+# For __aeabi_uidivmod
+lib1funcs = $(obj)/lib1funcs.o
+
+$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S
+ $(call cmd,shipped)
+
+# We need to prevent any GOTOFF relocs being used with references
+# to symbols in the .bss section since we cannot relocate them
+# independently from the rest at run time. This can be achieved by
+# ensuring that no private .bss symbols exist, as global symbols
+# always have a GOT entry which is what we need.
+# The .data section is already discarded by the linker script so no need
+# to bother about it here.
+check_for_bad_syms = \
+bad_syms=$$($(CROSS_COMPILE)nm $@ | sed -n 's/^.\{8\} [bc] \(.*\)/\1/p') && \
+[ -z "$$bad_syms" ] || \
+ ( echo "following symbols must have non local/private scope:" >&2; \
+ echo "$$bad_syms" >&2; rm -f $@; false )
+
+check_for_multiple_zreladdr = \
+if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \
+ echo 'multiple zreladdrs: $(ZRELADDR)'; \
+ echo 'This needs CONFIG_AUTO_ZRELADDR to be set'; \
+ false; \
+fi
+
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
+ $(addprefix $(obj)/, $(OBJS)) $(lib1funcs) FORCE
+ @$(check_for_multiple_zreladdr)
+ $(call if_changed,ld)
+ @$(check_for_bad_syms)
+
+$(obj)/piggy.$(suffix_y): $(obj)/../Image FORCE
+ $(call if_changed,$(suffix_y))
+
+$(obj)/piggy.$(suffix_y).o: $(obj)/piggy.$(suffix_y) FORCE
+
+CFLAGS_font.o := -Dstatic=
+
+$(obj)/font.c: $(FONTC)
+ $(call cmd,shipped)
+
+$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
+ @sed "$(SEDFLAGS)" < $< > $@
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
new file mode 100644
index 00000000000..6ce11c48117
--- /dev/null
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -0,0 +1,97 @@
+#include <asm/setup.h>
+#include <libfdt.h>
+
+static int node_offset(void *fdt, const char *node_path)
+{
+ int offset = fdt_path_offset(fdt, node_path);
+ if (offset == -FDT_ERR_NOTFOUND)
+ offset = fdt_add_subnode(fdt, 0, node_path);
+ return offset;
+}
+
+static int setprop(void *fdt, const char *node_path, const char *property,
+ uint32_t *val_array, int size)
+{
+ int offset = node_offset(fdt, node_path);
+ if (offset < 0)
+ return offset;
+ return fdt_setprop(fdt, offset, property, val_array, size);
+}
+
+static int setprop_string(void *fdt, const char *node_path,
+ const char *property, const char *string)
+{
+ int offset = node_offset(fdt, node_path);
+ if (offset < 0)
+ return offset;
+ return fdt_setprop_string(fdt, offset, property, string);
+}
+
+static int setprop_cell(void *fdt, const char *node_path,
+ const char *property, uint32_t val)
+{
+ int offset = node_offset(fdt, node_path);
+ if (offset < 0)
+ return offset;
+ return fdt_setprop_cell(fdt, offset, property, val);
+}
+
+/*
+ * Convert and fold provided ATAGs into the provided FDT.
+ *
+ * REturn values:
+ * = 0 -> pretend success
+ * = 1 -> bad ATAG (may retry with another possible ATAG pointer)
+ * < 0 -> error from libfdt
+ */
+int atags_to_fdt(void *atag_list, void *fdt, int total_space)
+{
+ struct tag *atag = atag_list;
+ uint32_t mem_reg_property[2 * NR_BANKS];
+ int memcount = 0;
+ int ret;
+
+ /* make sure we've got an aligned pointer */
+ if ((u32)atag_list & 0x3)
+ return 1;
+
+ /* if we get a DTB here we're done already */
+ if (*(u32 *)atag_list == fdt32_to_cpu(FDT_MAGIC))
+ return 0;
+
+ /* validate the ATAG */
+ if (atag->hdr.tag != ATAG_CORE ||
+ (atag->hdr.size != tag_size(tag_core) &&
+ atag->hdr.size != 2))
+ return 1;
+
+ /* let's give it all the room it could need */
+ ret = fdt_open_into(fdt, fdt, total_space);
+ if (ret < 0)
+ return ret;
+
+ for_each_tag(atag, atag_list) {
+ if (atag->hdr.tag == ATAG_CMDLINE) {
+ setprop_string(fdt, "/chosen", "bootargs",
+ atag->u.cmdline.cmdline);
+ } else if (atag->hdr.tag == ATAG_MEM) {
+ if (memcount >= sizeof(mem_reg_property)/4)
+ continue;
+ mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
+ mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
+ } else if (atag->hdr.tag == ATAG_INITRD2) {
+ uint32_t initrd_start, initrd_size;
+ initrd_start = atag->u.initrd.start;
+ initrd_size = atag->u.initrd.size;
+ setprop_cell(fdt, "/chosen", "linux,initrd-start",
+ initrd_start);
+ setprop_cell(fdt, "/chosen", "linux,initrd-end",
+ initrd_start + initrd_size);
+ }
+ }
+
+ if (memcount)
+ setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount);
+
+ return fdt_pack(fdt);
+}
diff --git a/arch/arm/boot/compressed/big-endian.S b/arch/arm/boot/compressed/big-endian.S
new file mode 100644
index 00000000000..25ab26f1c6f
--- /dev/null
+++ b/arch/arm/boot/compressed/big-endian.S
@@ -0,0 +1,13 @@
+/*
+ * linux/arch/arm/boot/compressed/big-endian.S
+ *
+ * Switch CPU into big endian mode.
+ * Author: Nicolas Pitre
+ */
+
+ .section ".start", #alloc, #execinstr
+
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ orr r0, r0, #(1 << 7) @ enable big endian mode
+ mcr p15, 0, r0, c1, c0, 0 @ write control reg
+
diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c
new file mode 100644
index 00000000000..07be5a2f830
--- /dev/null
+++ b/arch/arm/boot/compressed/decompress.c
@@ -0,0 +1,50 @@
+#define _LINUX_STRING_H_
+
+#include <linux/compiler.h> /* for inline */
+#include <linux/types.h> /* for size_t */
+#include <linux/stddef.h> /* for NULL */
+#include <linux/linkage.h>
+#include <asm/string.h>
+
+extern unsigned long free_mem_ptr;
+extern unsigned long free_mem_end_ptr;
+extern void error(char *);
+
+#define STATIC static
+#define STATIC_RW_DATA /* non-static please */
+
+#define ARCH_HAS_DECOMP_WDOG
+
+/* Diagnostic functions */
+#ifdef DEBUG
+# define Assert(cond,msg) {if(!(cond)) error(msg);}
+# define Trace(x) fprintf x
+# define Tracev(x) {if (verbose) fprintf x ;}
+# define Tracevv(x) {if (verbose>1) fprintf x ;}
+# define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
+# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
+#else
+# define Assert(cond,msg)
+# define Trace(x)
+# define Tracev(x)
+# define Tracevv(x)
+# define Tracec(c,x)
+# define Tracecv(c,x)
+#endif
+
+#ifdef CONFIG_KERNEL_GZIP
+#include "../../../../lib/decompress_inflate.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZO
+#include "../../../../lib/decompress_unlzo.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZMA
+#include "../../../../lib/decompress_unlzma.c"
+#endif
+
+int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
+{
+ return decompress(input, len, NULL, NULL, output, NULL, error);
+}
diff --git a/arch/arm/boot/compressed/head-sa1100.S b/arch/arm/boot/compressed/head-sa1100.S
new file mode 100644
index 00000000000..6179d94dd5c
--- /dev/null
+++ b/arch/arm/boot/compressed/head-sa1100.S
@@ -0,0 +1,47 @@
+/*
+ * linux/arch/arm/boot/compressed/head-sa1100.S
+ *
+ * Copyright (C) 1999 Nicolas Pitre <nico@fluxnic.net>
+ *
+ * SA1100 specific tweaks. This is merged into head.S by the linker.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/mach-types.h>
+
+ .section ".start", "ax"
+
+__SA1100_start:
+
+ @ Preserve r8/r7 i.e. kernel entry values
+#ifdef CONFIG_SA1100_COLLIE
+ mov r7, #MACH_TYPE_COLLIE
+#endif
+#ifdef CONFIG_SA1100_SIMPAD
+ @ UNTIL we've something like an open bootldr
+ mov r7, #MACH_TYPE_SIMPAD @should be 87
+#endif
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ ands r0, r0, #0x0d
+ beq 99f
+
+ @ Data cache might be active.
+ @ Be sure to flush kernel binary out of the cache,
+ @ whatever state it is, before it is turned off.
+ @ This is done by fetching through currently executed
+ @ memory to be sure we hit the same cache.
+ bic r2, pc, #0x1f
+ add r3, r2, #0x4000 @ 16 kb is quite enough...
+1: ldr r0, [r2], #32
+ teq r2, r3
+ bne 1b
+ mcr p15, 0, r0, c7, c10, 4 @ drain WB
+ mcr p15, 0, r0, c7, c7, 0 @ flush I & D caches
+
+ @ disabling MMU and caches
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ bic r0, r0, #0x0d @ clear WB, DC, MMU
+ bic r0, r0, #0x1000 @ clear Icache
+ mcr p15, 0, r0, c1, c0, 0
+99:
diff --git a/arch/arm/boot/compressed/head-shark.S b/arch/arm/boot/compressed/head-shark.S
new file mode 100644
index 00000000000..089c560e07f
--- /dev/null
+++ b/arch/arm/boot/compressed/head-shark.S
@@ -0,0 +1,139 @@
+/* The head-file for the Shark
+ * by Alexander Schulz
+ *
+ * Does the following:
+ * - get the memory layout from firmware. This can only be done as long as the mmu
+ * is still on.
+ * - switch the mmu off, so we have physical addresses
+ * - copy the kernel to 0x08508000. This is done to have a fixed address where the
+ * C-parts (misc.c) are executed. This address must be known at compile-time,
+ * but the load-address of the kernel depends on how much memory is installed.
+ * - Jump to this location.
+ * - Set r8 with 0, r7 with the architecture ID for head.S
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+
+ .section ".start", "ax"
+
+ b __beginning
+
+__ofw_data: .long 0 @ the number of memory blocks
+ .space 128 @ (startaddr,size) ...
+ .space 128 @ bootargs
+ .align
+
+__beginning: mov r4, r0 @ save the entry to the firmware
+
+ mov r0, #0xC0 @ disable irq and fiq
+ mov r1, r0
+ mrs r3, cpsr
+ bic r2, r3, r0
+ eor r2, r2, r1
+ msr cpsr_c, r2
+
+ mov r0, r4 @ get the Memory layout from firmware
+ adr r1, __ofw_data
+ add r2, r1, #4
+ mov lr, pc
+ b ofw_init
+ mov r1, #0
+
+ adr r2, __mmu_off @ calculate physical address
+ sub r2, r2, #0xf0000000 @ openprom maps us at f000 virt, 0e50 phys
+ adr r0, __ofw_data
+ ldr r0, [r0, #4]
+ add r2, r2, r0
+ add r2, r2, #0x00500000
+
+ mrc p15, 0, r3, c1, c0
+ bic r3, r3, #0xC @ Write Buffer and DCache
+ bic r3, r3, #0x1000 @ ICache
+ mcr p15, 0, r3, c1, c0 @ disabled
+
+ mov r0, #0
+ mcr p15, 0, r0, c7, c7 @ flush I,D caches on v4
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer on v4
+ mcr p15, 0, r0, c8, c7 @ flush I,D TLBs on v4
+
+ bic r3, r3, #0x1 @ MMU
+ mcr p15, 0, r3, c1, c0 @ disabled
+
+ mov pc, r2
+
+__copy_target: .long 0x08507FFC
+__copy_end: .long 0x08607FFC
+
+ .word _start
+ .word __bss_start
+
+ .align
+__temp_stack: .space 128
+
+__mmu_off:
+ adr r0, __ofw_data @ read the 1. entry of the memory map
+ ldr r0, [r0, #4]
+ orr r0, r0, #0x00600000
+ sub r0, r0, #4
+
+ ldr r1, __copy_end
+ ldr r3, __copy_target
+
+/* r0 = 0x0e600000 (current end of kernelcode)
+ * r3 = 0x08508000 (where it should begin)
+ * r1 = 0x08608000 (end of copying area, 1MB)
+ * The kernel is compressed, so 1 MB should be enough.
+ * copy the kernel to the beginning of physical memory
+ * We start from the highest address, so we can copy
+ * from 0x08500000 to 0x08508000 if we have only 8MB
+ */
+
+/* As we get more 2.6-kernels it gets more and more
+ * uncomfortable to be bound to kernel images of 1MB only.
+ * So we add a loop here, to be able to copy some more.
+ * Alexander Schulz 2005-07-17
+ */
+
+ mov r4, #3 @ How many megabytes to copy
+
+
+__MoveCode: sub r4, r4, #1
+
+__Copy: ldr r2, [r0], #-4
+ str r2, [r1], #-4
+ teq r1, r3
+ bne __Copy
+
+ /* The firmware maps us in blocks of 1 MB, the next block is
+ _below_ the last one. So our decrementing source pointer
+ ist right here, but the destination pointer must be increased
+ by 2 MB */
+ add r1, r1, #0x00200000
+ add r3, r3, #0x00100000
+
+ teq r4, #0
+ bne __MoveCode
+
+
+ /* and jump to it */
+ adr r2, __go_on @ where we want to jump
+ adr r0, __ofw_data @ read the 1. entry of the memory map
+ ldr r0, [r0, #4]
+ sub r2, r2, r0 @ we are mapped add 0e50 now, sub that (-0e00)
+ sub r2, r2, #0x00500000 @ -0050
+ ldr r0, __copy_target @ and add 0850 8000 instead
+ add r0, r0, #4
+ add r2, r2, r0
+ mov pc, r2 @ and jump there
+
+__go_on:
+ adr sp, __temp_stack
+ add sp, sp, #128
+ adr r0, __ofw_data
+ mov lr, pc
+ b create_params
+
+ mov r8, #0
+ mov r7, #15
diff --git a/arch/arm/boot/compressed/head-sharpsl.S b/arch/arm/boot/compressed/head-sharpsl.S
new file mode 100644
index 00000000000..eb0084ea1ec
--- /dev/null
+++ b/arch/arm/boot/compressed/head-sharpsl.S
@@ -0,0 +1,150 @@
+/*
+ * linux/arch/arm/boot/compressed/head-sharpsl.S
+ *
+ * Copyright (C) 2004-2005 Richard Purdie <rpurdie@rpsys.net>
+ *
+ * Sharp's bootloader doesn't pass any kind of machine ID
+ * so we have to figure out the machine for ourselves...
+ *
+ * Support for Poodle, Corgi (SL-C700), Shepherd (SL-C750)
+ * Husky (SL-C760), Tosa (SL-C6000), Spitz (SL-C3000),
+ * Akita (SL-C1000) and Borzoi (SL-C3100).
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/mach-types.h>
+
+#ifndef CONFIG_PXA_SHARPSL
+#error What am I doing here...
+#endif
+
+ .section ".start", "ax"
+
+__SharpSL_start:
+
+/* Check for TC6393 - if found we have a Tosa */
+ ldr r7, .TOSAID
+ mov r1, #0x10000000 @ Base address of TC6393 chip
+ mov r6, #0x03
+ ldrh r3, [r1, #8] @ Load TC6393XB Revison: This is 0x0003
+ cmp r6, r3
+ beq .SHARPEND @ Success -> tosa
+
+/* Check for pxa270 - if found, branch */
+ mrc p15, 0, r4, c0, c0 @ Get Processor ID
+ and r4, r4, #0xffffff00
+ ldr r3, .PXA270ID
+ cmp r4, r3
+ beq .PXA270
+
+/* Check for w100 - if not found we have a Poodle */
+ ldr r1, .W100ADDR @ Base address of w100 chip + regs offset
+
+ mov r6, #0x31 @ Load Magic Init value
+ str r6, [r1, #0x280] @ to SCRATCH_UMSK
+ mov r5, #0x3000
+.W100LOOP:
+ subs r5, r5, #1
+ bne .W100LOOP
+ mov r6, #0x30 @ Load 2nd Magic Init value
+ str r6, [r1, #0x280] @ to SCRATCH_UMSK
+
+ ldr r6, [r1, #0] @ Load Chip ID
+ ldr r3, .W100ID
+ ldr r7, .POODLEID
+ cmp r6, r3
+ bne .SHARPEND @ We have no w100 - Poodle
+
+/* Check for pxa250 - if found we have a Corgi */
+ ldr r7, .CORGIID
+ ldr r3, .PXA255ID
+ cmp r4, r3
+ blo .SHARPEND @ We have a PXA250 - Corgi
+
+/* Check for 64MiB flash - if found we have a Shepherd */
+ bl get_flash_ids
+ ldr r7, .SHEPHERDID
+ cmp r3, #0x76 @ 64MiB flash
+ beq .SHARPEND @ We have Shepherd
+
+/* Must be a Husky */
+ ldr r7, .HUSKYID @ Must be Husky
+ b .SHARPEND
+
+.PXA270:
+/* Check for 16MiB flash - if found we have Spitz */
+ bl get_flash_ids
+ ldr r7, .SPITZID
+ cmp r3, #0x73 @ 16MiB flash
+ beq .SHARPEND @ We have Spitz
+
+/* Check for a second SCOOP chip - if found we have Borzoi */
+ ldr r1, .SCOOP2ADDR
+ ldr r7, .BORZOIID
+ mov r6, #0x0140
+ strh r6, [r1]
+ ldrh r6, [r1]
+ cmp r6, #0x0140
+ beq .SHARPEND @ We have Borzoi
+
+/* Must be Akita */
+ ldr r7, .AKITAID
+ b .SHARPEND @ We have Borzoi
+
+.PXA255ID:
+ .word 0x69052d00 @ PXA255 Processor ID
+.PXA270ID:
+ .word 0x69054100 @ PXA270 Processor ID
+.W100ID:
+ .word 0x57411002 @ w100 Chip ID
+.W100ADDR:
+ .word 0x08010000 @ w100 Chip ID Reg Address
+.SCOOP2ADDR:
+ .word 0x08800040
+.POODLEID:
+ .word MACH_TYPE_POODLE
+.CORGIID:
+ .word MACH_TYPE_CORGI
+.SHEPHERDID:
+ .word MACH_TYPE_SHEPHERD
+.HUSKYID:
+ .word MACH_TYPE_HUSKY
+.TOSAID:
+ .word MACH_TYPE_TOSA
+.SPITZID:
+ .word MACH_TYPE_SPITZ
+.AKITAID:
+ .word MACH_TYPE_AKITA
+.BORZOIID:
+ .word MACH_TYPE_BORZOI
+
+/*
+ * Return: r2 - NAND Manufacturer ID
+ * r3 - NAND Chip ID
+ * Corrupts: r1
+ */
+get_flash_ids:
+ mov r1, #0x0c000000 @ Base address of NAND chip
+ ldrb r3, [r1, #24] @ Load FLASHCTL
+ bic r3, r3, #0x11 @ SET NCE
+ orr r3, r3, #0x0a @ SET CLR + FLWP
+ strb r3, [r1, #24] @ Save to FLASHCTL
+ mov r2, #0x90 @ Command "readid"
+ strb r2, [r1, #20] @ Save to FLASHIO
+ bic r3, r3, #2 @ CLR CLE
+ orr r3, r3, #4 @ SET ALE
+ strb r3, [r1, #24] @ Save to FLASHCTL
+ mov r2, #0 @ Address 0x00
+ strb r2, [r1, #20] @ Save to FLASHIO
+ bic r3, r3, #4 @ CLR ALE
+ strb r3, [r1, #24] @ Save to FLASHCTL
+.fids1:
+ ldrb r3, [r1, #24] @ Load FLASHCTL
+ tst r3, #32 @ Is chip ready?
+ beq .fids1
+ ldrb r2, [r1, #20] @ NAND Manufacturer ID
+ ldrb r3, [r1, #20] @ NAND Chip ID
+ mov pc, lr
+
+.SHARPEND:
diff --git a/arch/arm/boot/compressed/head-shmobile.S b/arch/arm/boot/compressed/head-shmobile.S
new file mode 100644
index 00000000000..fe3719b516f
--- /dev/null
+++ b/arch/arm/boot/compressed/head-shmobile.S
@@ -0,0 +1,83 @@
+/*
+ * The head-file for SH-Mobile ARM platforms
+ *
+ * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ * Simon Horman <horms@verge.net.au>
+ *
+ * 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
+ */
+
+#ifdef CONFIG_ZBOOT_ROM
+
+ .section ".start", "ax"
+
+ /* load board-specific initialization code */
+#include <mach/zboot.h>
+
+#if defined(CONFIG_ZBOOT_ROM_MMCIF) || defined(CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI)
+ /* Load image from MMC/SD */
+ adr sp, __tmp_stack + 256
+ ldr r0, __image_start
+ ldr r1, __image_end
+ subs r1, r1, r0
+ ldr r0, __load_base
+ bl mmc_loader
+
+ /* Jump to loaded code */
+ ldr r0, __loaded
+ ldr r1, __image_start
+ sub r0, r0, r1
+ ldr r1, __load_base
+ add pc, r0, r1
+
+__image_start:
+ .long _start
+__image_end:
+ .long _got_end
+__load_base:
+ .long CONFIG_MEMORY_START + 0x02000000 @ Load at 32Mb into SDRAM
+__loaded:
+ .long __continue
+ .align
+__tmp_stack:
+ .space 256
+__continue:
+#endif /* CONFIG_ZBOOT_ROM_MMC || CONFIG_ZBOOT_ROM_SH_MOBILE_SDHI */
+
+ b 1f
+__atags:@ tag #1
+ .long 12 @ tag->hdr.size = tag_size(tag_core);
+ .long 0x54410001 @ tag->hdr.tag = ATAG_CORE;
+ .long 0 @ tag->u.core.flags = 0;
+ .long 0 @ tag->u.core.pagesize = 0;
+ .long 0 @ tag->u.core.rootdev = 0;
+ @ tag #2
+ .long 8 @ tag->hdr.size = tag_size(tag_mem32);
+ .long 0x54410002 @ tag->hdr.tag = ATAG_MEM;
+ .long CONFIG_MEMORY_SIZE @ tag->u.mem.size = CONFIG_MEMORY_SIZE;
+ .long CONFIG_MEMORY_START @ @ tag->u.mem.start = CONFIG_MEMORY_START;
+ @ tag #3
+ .long 0 @ tag->hdr.size = 0
+ .long 0 @ tag->hdr.tag = ATAG_NONE;
+1:
+
+ /* Set board ID necessary for boot */
+ ldr r7, 1f @ Set machine type register
+ adr r8, __atags @ Set atag register
+ b 2f
+
+1 : .long MACH_TYPE
+2 :
+
+#endif /* CONFIG_ZBOOT_ROM */
diff --git a/arch/arm/boot/compressed/head-vt8500.S b/arch/arm/boot/compressed/head-vt8500.S
new file mode 100644
index 00000000000..1dc1e21a3be
--- /dev/null
+++ b/arch/arm/boot/compressed/head-vt8500.S
@@ -0,0 +1,46 @@
+/*
+ * linux/arch/arm/boot/compressed/head-vt8500.S
+ *
+ * Copyright (C) 2010 Alexey Charkov <alchark@gmail.com>
+ *
+ * VIA VT8500 specific tweaks. This is merged into head.S by the linker.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/mach-types.h>
+
+ .section ".start", "ax"
+
+__VT8500_start:
+ @ Compare the SCC ID register against a list of known values
+ ldr r1, .SCCID
+ ldr r3, [r1]
+
+ @ VT8500 override
+ ldr r4, .VT8500SCC
+ cmp r3, r4
+ ldreq r7, .ID_BV07
+ beq .Lendvt8500
+
+ @ WM8505 override
+ ldr r4, .WM8505SCC
+ cmp r3, r4
+ ldreq r7, .ID_8505
+ beq .Lendvt8500
+
+ @ Otherwise, leave the bootloader's machine id untouched
+
+.SCCID:
+ .word 0xd8120000
+.VT8500SCC:
+ .word 0x34000102
+.WM8505SCC:
+ .word 0x34260103
+
+.ID_BV07:
+ .word MACH_TYPE_BV07
+.ID_8505:
+ .word MACH_TYPE_WM8505_7IN_NETBOOK
+
+.Lendvt8500:
diff --git a/arch/arm/boot/compressed/head-xscale.S b/arch/arm/boot/compressed/head-xscale.S
new file mode 100644
index 00000000000..aa5ee49c5c5
--- /dev/null
+++ b/arch/arm/boot/compressed/head-xscale.S
@@ -0,0 +1,41 @@
+/*
+ * linux/arch/arm/boot/compressed/head-xscale.S
+ *
+ * XScale specific tweaks. This is merged into head.S by the linker.
+ *
+ */
+
+#include <linux/linkage.h>
+
+ .section ".start", "ax"
+
+__XScale_start:
+
+ @ Preserve r8/r7 i.e. kernel entry values
+
+ @ Data cache might be active.
+ @ Be sure to flush kernel binary out of the cache,
+ @ whatever state it is, before it is turned off.
+ @ This is done by fetching through currently executed
+ @ memory to be sure we hit the same cache.
+ bic r2, pc, #0x1f
+ add r3, r2, #0x10000 @ 64 kb is quite enough...
+1: ldr r0, [r2], #32
+ teq r2, r3
+ bne 1b
+ mcr p15, 0, r0, c7, c10, 4 @ drain WB
+ mcr p15, 0, r0, c7, c7, 0 @ flush I & D caches
+
+ @ disabling MMU and caches
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ bic r0, r0, #0x05 @ clear DC, MMU
+ bic r0, r0, #0x1000 @ clear Icache
+ mcr p15, 0, r0, c1, c0, 0
+
+#ifdef CONFIG_ARCH_IXP2000
+ mov r1, #-1
+ mov r0, #0xd6000000
+ str r1, [r0, #0x14]
+ str r1, [r0, #0x18]
+#endif
+
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
new file mode 100644
index 00000000000..c5d60250d43
--- /dev/null
+++ b/arch/arm/boot/compressed/head.S
@@ -0,0 +1,1228 @@
+/*
+ * linux/arch/arm/boot/compressed/head.S
+ *
+ * Copyright (C) 1996-2002 Russell King
+ * Copyright (C) 2004 Hyok S. Choi (MPU support)
+ *
+ * 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>
+
+/*
+ * Debugging stuff
+ *
+ * Note that these macros must not contain any code which is not
+ * 100% relocatable. Any attempt to do so will result in a crash.
+ * Please select one of the following when turning on debugging.
+ */
+#ifdef DEBUG
+
+#if defined(CONFIG_DEBUG_ICEDCC)
+
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7)
+ .macro loadsp, rb, tmp
+ .endm
+ .macro writeb, ch, rb
+ mcr p14, 0, \ch, c0, c5, 0
+ .endm
+#elif defined(CONFIG_CPU_XSCALE)
+ .macro loadsp, rb, tmp
+ .endm
+ .macro writeb, ch, rb
+ mcr p14, 0, \ch, c8, c0, 0
+ .endm
+#else
+ .macro loadsp, rb, tmp
+ .endm
+ .macro writeb, ch, rb
+ mcr p14, 0, \ch, c1, c0, 0
+ .endm
+#endif
+
+#else
+
+#include <mach/debug-macro.S>
+
+ .macro writeb, ch, rb
+ senduart \ch, \rb
+ .endm
+
+#if defined(CONFIG_ARCH_SA1100)
+ .macro loadsp, rb, tmp
+ mov \rb, #0x80000000 @ physical base address
+#ifdef CONFIG_DEBUG_LL_SER3
+ add \rb, \rb, #0x00050000 @ Ser3
+#else
+ add \rb, \rb, #0x00010000 @ Ser1
+#endif
+ .endm
+#elif defined(CONFIG_ARCH_S3C2410)
+ .macro loadsp, rb, tmp
+ mov \rb, #0x50000000
+ add \rb, \rb, #0x4000 * CONFIG_S3C_LOWLEVEL_UART_PORT
+ .endm
+#else
+ .macro loadsp, rb, tmp
+ addruart \rb, \tmp
+ .endm
+#endif
+#endif
+#endif
+
+ .macro kputc,val
+ mov r0, \val
+ bl putc
+ .endm
+
+ .macro kphex,val,len
+ mov r0, \val
+ mov r1, #\len
+ bl phex
+ .endm
+
+ .macro debug_reloc_start
+#ifdef DEBUG
+ kputc #'\n'
+ kphex r6, 8 /* processor id */
+ kputc #':'
+ kphex r7, 8 /* architecture id */
+#ifdef CONFIG_CPU_CP15
+ kputc #':'
+ mrc p15, 0, r0, c1, c0
+ kphex r0, 8 /* control reg */
+#endif
+ kputc #'\n'
+ kphex r5, 8 /* decompressed kernel start */
+ kputc #'-'
+ kphex r9, 8 /* decompressed kernel end */
+ kputc #'>'
+ kphex r4, 8 /* kernel execution address */
+ kputc #'\n'
+#endif
+ .endm
+
+ .macro debug_reloc_end
+#ifdef DEBUG
+ kphex r5, 8 /* end of kernel */
+ kputc #'\n'
+ mov r0, r4
+ bl memdump /* dump 256 bytes at start of kernel */
+#endif
+ .endm
+
+ .section ".start", #alloc, #execinstr
+/*
+ * sort out different calling conventions
+ */
+ .align
+ .arm @ Always enter in ARM state
+start:
+ .type start,#function
+ .rept 7
+ mov r0, r0
+ .endr
+ ARM( mov r0, r0 )
+ ARM( b 1f )
+ THUMB( adr r12, BSYM(1f) )
+ THUMB( bx r12 )
+
+ .word 0x016f2818 @ Magic numbers to help the loader
+ .word start @ absolute load/run zImage address
+ .word _edata @ zImage end address
+ THUMB( .thumb )
+1: mov r7, r1 @ save architecture ID
+ mov r8, r2 @ save atags pointer
+
+#ifndef __ARM_ARCH_2__
+ /*
+ * Booting from Angel - need to enter SVC mode and disable
+ * FIQs/IRQs (numeric definitions from angel arm.h source).
+ * We only do this if we were in user mode on entry.
+ */
+ mrs r2, cpsr @ get current mode
+ tst r2, #3 @ not user?
+ bne not_angel
+ mov r0, #0x17 @ angel_SWIreason_EnterSVC
+ ARM( swi 0x123456 ) @ angel_SWI_ARM
+ THUMB( svc 0xab ) @ angel_SWI_THUMB
+not_angel:
+ mrs r2, cpsr @ turn off interrupts to
+ orr r2, r2, #0xc0 @ prevent angel from running
+ msr cpsr_c, r2
+#else
+ teqp pc, #0x0c000003 @ turn off interrupts
+#endif
+
+ /*
+ * Note that some cache flushing and other stuff may
+ * be needed here - is there an Angel SWI call for this?
+ */
+
+ /*
+ * some architecture specific code can be inserted
+ * by the linker here, but it should preserve r7, r8, and r9.
+ */
+
+ .text
+
+#ifdef CONFIG_AUTO_ZRELADDR
+ @ determine final kernel image address
+ mov r4, pc
+ and r4, r4, #0xf8000000
+ add r4, r4, #TEXT_OFFSET
+#else
+ ldr r4, =zreladdr
+#endif
+
+ bl cache_on
+
+restart: adr r0, LC0
+ ldmia r0, {r1, r2, r3, r6, r10, r11, r12}
+ ldr sp, [r0, #28]
+
+ /*
+ * We might be running at a different address. We need
+ * to fix up various pointers.
+ */
+ sub r0, r0, r1 @ calculate the delta offset
+ add r6, r6, r0 @ _edata
+ add r10, r10, r0 @ inflated kernel size location
+
+ /*
+ * The kernel build system appends the size of the
+ * decompressed kernel at the end of the compressed data
+ * in little-endian form.
+ */
+ ldrb r9, [r10, #0]
+ ldrb lr, [r10, #1]
+ orr r9, r9, lr, lsl #8
+ ldrb lr, [r10, #2]
+ ldrb r10, [r10, #3]
+ orr r9, r9, lr, lsl #16
+ orr r9, r9, r10, lsl #24
+
+#ifndef CONFIG_ZBOOT_ROM
+ /* malloc space is above the relocated stack (64k max) */
+ add sp, sp, r0
+ add r10, sp, #0x10000
+#else
+ /*
+ * With ZBOOT_ROM the bss/stack is non relocatable,
+ * but someone could still run this code from RAM,
+ * in which case our reference is _edata.
+ */
+ mov r10, r6
+#endif
+
+ mov r5, #0 @ init dtb size to 0
+#ifdef CONFIG_ARM_APPENDED_DTB
+/*
+ * r0 = delta
+ * r2 = BSS start
+ * r3 = BSS end
+ * r4 = final kernel address
+ * r5 = appended dtb size (still unknown)
+ * r6 = _edata
+ * r7 = architecture ID
+ * r8 = atags/device tree pointer
+ * r9 = size of decompressed image
+ * r10 = end of this image, including bss/stack/malloc space if non XIP
+ * r11 = GOT start
+ * r12 = GOT end
+ * sp = stack pointer
+ *
+ * if there are device trees (dtb) appended to zImage, advance r10 so that the
+ * dtb data will get relocated along with the kernel if necessary.
+ */
+
+ ldr lr, [r6, #0]
+#ifndef __ARMEB__
+ ldr r1, =0xedfe0dd0 @ sig is 0xd00dfeed big endian
+#else
+ ldr r1, =0xd00dfeed
+#endif
+ cmp lr, r1
+ bne dtb_check_done @ not found
+
+#ifdef CONFIG_ARM_ATAG_DTB_COMPAT
+ /*
+ * OK... Let's do some funky business here.
+ * If we do have a DTB appended to zImage, and we do have
+ * an ATAG list around, we want the later to be translated
+ * and folded into the former here. To be on the safe side,
+ * let's temporarily move the stack away into the malloc
+ * area. No GOT fixup has occurred yet, but none of the
+ * code we're about to call uses any global variable.
+ */
+ add sp, sp, #0x10000
+ stmfd sp!, {r0-r3, ip, lr}
+ mov r0, r8
+ mov r1, r6
+ sub r2, sp, r6
+ bl atags_to_fdt
+
+ /*
+ * If returned value is 1, there is no ATAG at the location
+ * pointed by r8. Try the typical 0x100 offset from start
+ * of RAM and hope for the best.
+ */
+ cmp r0, #1
+ sub r0, r4, #TEXT_OFFSET
+ add r0, r0, #0x100
+ mov r1, r6
+ sub r2, sp, r6
+ blne atags_to_fdt
+
+ ldmfd sp!, {r0-r3, ip, lr}
+ sub sp, sp, #0x10000
+#endif
+
+ mov r8, r6 @ use the appended device tree
+
+ /*
+ * Make sure that the DTB doesn't end up in the final
+ * kernel's .bss area. To do so, we adjust the decompressed
+ * kernel size to compensate if that .bss size is larger
+ * than the relocated code.
+ */
+ ldr r5, =_kernel_bss_size
+ adr r1, wont_overwrite
+ sub r1, r6, r1
+ subs r1, r5, r1
+ addhi r9, r9, r1
+
+ /* Get the dtb's size */
+ ldr r5, [r6, #4]
+#ifndef __ARMEB__
+ /* convert r5 (dtb size) to little endian */
+ eor r1, r5, r5, ror #16
+ bic r1, r1, #0x00ff0000
+ mov r5, r5, ror #8
+ eor r5, r5, r1, lsr #8
+#endif
+
+ /* preserve 64-bit alignment */
+ add r5, r5, #7
+ bic r5, r5, #7
+
+ /* relocate some pointers past the appended dtb */
+ add r6, r6, r5
+ add r10, r10, r5
+ add sp, sp, r5
+dtb_check_done:
+#endif
+
+/*
+ * Check to see if we will overwrite ourselves.
+ * r4 = final kernel address
+ * r9 = size of decompressed image
+ * r10 = end of this image, including bss/stack/malloc space if non XIP
+ * We basically want:
+ * r4 - 16k page directory >= r10 -> OK
+ * r4 + image length <= address of wont_overwrite -> OK
+ */
+ add r10, r10, #16384
+ cmp r4, r10
+ bhs wont_overwrite
+ add r10, r4, r9
+ adr r9, wont_overwrite
+ cmp r10, r9
+ bls wont_overwrite
+
+/*
+ * Relocate ourselves past the end of the decompressed kernel.
+ * r6 = _edata
+ * r10 = end of the decompressed kernel
+ * Because we always copy ahead, we need to do it from the end and go
+ * backward in case the source and destination overlap.
+ */
+ /*
+ * Bump to the next 256-byte boundary with the size of
+ * the relocation code added. This avoids overwriting
+ * ourself when the offset is small.
+ */
+ add r10, r10, #((reloc_code_end - restart + 256) & ~255)
+ bic r10, r10, #255
+
+ /* Get start of code we want to copy and align it down. */
+ adr r5, restart
+ bic r5, r5, #31
+
+ sub r9, r6, r5 @ size to copy
+ add r9, r9, #31 @ rounded up to a multiple
+ bic r9, r9, #31 @ ... of 32 bytes
+ add r6, r9, r5
+ add r9, r9, r10
+
+1: ldmdb r6!, {r0 - r3, r10 - r12, lr}
+ cmp r6, r5
+ stmdb r9!, {r0 - r3, r10 - r12, lr}
+ bhi 1b
+
+ /* Preserve offset to relocated code. */
+ sub r6, r9, r6
+
+#ifndef CONFIG_ZBOOT_ROM
+ /* cache_clean_flush may use the stack, so relocate it */
+ add sp, sp, r6
+#endif
+
+ bl cache_clean_flush
+
+ adr r0, BSYM(restart)
+ add r0, r0, r6
+ mov pc, r0
+
+wont_overwrite:
+/*
+ * If delta is zero, we are running at the address we were linked at.
+ * r0 = delta
+ * r2 = BSS start
+ * r3 = BSS end
+ * r4 = kernel execution address
+ * r5 = appended dtb size (0 if not present)
+ * r7 = architecture ID
+ * r8 = atags pointer
+ * r11 = GOT start
+ * r12 = GOT end
+ * sp = stack pointer
+ */
+ orrs r1, r0, r5
+ beq not_relocated
+
+ add r11, r11, r0
+ add r12, r12, r0
+
+#ifndef CONFIG_ZBOOT_ROM
+ /*
+ * If we're running fully PIC === CONFIG_ZBOOT_ROM = n,
+ * we need to fix up pointers into the BSS region.
+ * Note that the stack pointer has already been fixed up.
+ */
+ add r2, r2, r0
+ add r3, r3, r0
+
+ /*
+ * Relocate all entries in the GOT table.
+ * Bump bss entries to _edata + dtb size
+ */
+1: ldr r1, [r11, #0] @ relocate entries in the GOT
+ add r1, r1, r0 @ This fixes up C references
+ cmp r1, r2 @ if entry >= bss_start &&
+ cmphs r3, r1 @ bss_end > entry
+ addhi r1, r1, r5 @ entry += dtb size
+ str r1, [r11], #4 @ next entry
+ cmp r11, r12
+ blo 1b
+
+ /* bump our bss pointers too */
+ add r2, r2, r5
+ add r3, r3, r5
+
+#else
+
+ /*
+ * Relocate entries in the GOT table. We only relocate
+ * the entries that are outside the (relocated) BSS region.
+ */
+1: ldr r1, [r11, #0] @ relocate entries in the GOT
+ cmp r1, r2 @ entry < bss_start ||
+ cmphs r3, r1 @ _end < entry
+ addlo r1, r1, r0 @ table. This fixes up the
+ str r1, [r11], #4 @ C references.
+ cmp r11, r12
+ blo 1b
+#endif
+
+not_relocated: mov r0, #0
+1: str r0, [r2], #4 @ clear bss
+ str r0, [r2], #4
+ str r0, [r2], #4
+ str r0, [r2], #4
+ cmp r2, r3
+ blo 1b
+
+/*
+ * The C runtime environment should now be setup sufficiently.
+ * Set up some pointers, and start decompressing.
+ * r4 = kernel execution address
+ * r7 = architecture ID
+ * r8 = atags pointer
+ */
+ mov r0, r4
+ mov r1, sp @ malloc space above stack
+ add r2, sp, #0x10000 @ 64k max
+ mov r3, r7
+ bl decompress_kernel
+ bl cache_clean_flush
+ bl cache_off
+ mov r0, #0 @ must be zero
+ mov r1, r7 @ restore architecture number
+ mov r2, r8 @ restore atags pointer
+ ARM( mov pc, r4 ) @ call kernel
+ THUMB( bx r4 ) @ entry point is always ARM
+
+ .align 2
+ .type LC0, #object
+LC0: .word LC0 @ r1
+ .word __bss_start @ r2
+ .word _end @ r3
+ .word _edata @ r6
+ .word input_data_end - 4 @ r10 (inflated size location)
+ .word _got_start @ r11
+ .word _got_end @ ip
+ .word .L_user_stack_end @ sp
+ .size LC0, . - LC0
+
+#ifdef CONFIG_ARCH_RPC
+ .globl params
+params: ldr r0, =0x10000100 @ params_phys for RPC
+ mov pc, lr
+ .ltorg
+ .align
+#endif
+
+/*
+ * Turn on the cache. We need to setup some page tables so that we
+ * can have both the I and D caches on.
+ *
+ * We place the page tables 16k down from the kernel execution address,
+ * and we hope that nothing else is using it. If we're using it, we
+ * will go pop!
+ *
+ * On entry,
+ * r4 = kernel execution address
+ * r7 = architecture number
+ * r8 = atags pointer
+ * On exit,
+ * r0, r1, r2, r3, r9, r10, r12 corrupted
+ * This routine must preserve:
+ * r4, r7, r8
+ */
+ .align 5
+cache_on: mov r3, #8 @ cache_on function
+ b call_cache_fn
+
+/*
+ * Initialize the highest priority protection region, PR7
+ * to cover all 32bit address and cacheable and bufferable.
+ */
+__armv4_mpu_cache_on:
+ mov r0, #0x3f @ 4G, the whole
+ mcr p15, 0, r0, c6, c7, 0 @ PR7 Area Setting
+ mcr p15, 0, r0, c6, c7, 1
+
+ mov r0, #0x80 @ PR7
+ mcr p15, 0, r0, c2, c0, 0 @ D-cache on
+ mcr p15, 0, r0, c2, c0, 1 @ I-cache on
+ mcr p15, 0, r0, c3, c0, 0 @ write-buffer on
+
+ mov r0, #0xc000
+ mcr p15, 0, r0, c5, c0, 1 @ I-access permission
+ mcr p15, 0, r0, c5, c0, 0 @ D-access permission
+
+ mov r0, #0
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
+ mcr p15, 0, r0, c7, c5, 0 @ flush(inval) I-Cache
+ mcr p15, 0, r0, c7, c6, 0 @ flush(inval) D-Cache
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ @ ...I .... ..D. WC.M
+ orr r0, r0, #0x002d @ .... .... ..1. 11.1
+ orr r0, r0, #0x1000 @ ...1 .... .... ....
+
+ mcr p15, 0, r0, c1, c0, 0 @ write control reg
+
+ mov r0, #0
+ mcr p15, 0, r0, c7, c5, 0 @ flush(inval) I-Cache
+ mcr p15, 0, r0, c7, c6, 0 @ flush(inval) D-Cache
+ mov pc, lr
+
+__armv3_mpu_cache_on:
+ mov r0, #0x3f @ 4G, the whole
+ mcr p15, 0, r0, c6, c7, 0 @ PR7 Area Setting
+
+ mov r0, #0x80 @ PR7
+ mcr p15, 0, r0, c2, c0, 0 @ cache on
+ mcr p15, 0, r0, c3, c0, 0 @ write-buffer on
+
+ mov r0, #0xc000
+ mcr p15, 0, r0, c5, c0, 0 @ access permission
+
+ mov r0, #0
+ mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
+ /*
+ * ?? ARMv3 MMU does not allow reading the control register,
+ * does this really work on ARMv3 MPU?
+ */
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ @ .... .... .... WC.M
+ orr r0, r0, #0x000d @ .... .... .... 11.1
+ /* ?? this overwrites the value constructed above? */
+ mov r0, #0
+ mcr p15, 0, r0, c1, c0, 0 @ write control reg
+
+ /* ?? invalidate for the second time? */
+ mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
+ mov pc, lr
+
+__setup_mmu: sub r3, r4, #16384 @ Page directory size
+ bic r3, r3, #0xff @ Align the pointer
+ bic r3, r3, #0x3f00
+/*
+ * Initialise the page tables, turning on the cacheable and bufferable
+ * bits for the RAM area only.
+ */
+ mov r0, r3
+ mov r9, r0, lsr #18
+ mov r9, r9, lsl #18 @ start of RAM
+ add r10, r9, #0x10000000 @ a reasonable RAM size
+ mov r1, #0x12
+ orr r1, r1, #3 << 10
+ add r2, r3, #16384
+1: cmp r1, r9 @ if virt > start of RAM
+#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+ orrhs r1, r1, #0x08 @ set cacheable
+#else
+ orrhs r1, r1, #0x0c @ set cacheable, bufferable
+#endif
+ cmp r1, r10 @ if virt > end of RAM
+ bichs r1, r1, #0x0c @ clear cacheable, bufferable
+ str r1, [r0], #4 @ 1:1 mapping
+ add r1, r1, #1048576
+ teq r0, r2
+ bne 1b
+/*
+ * If ever we are running from Flash, then we surely want the cache
+ * to be enabled also for our execution instance... We map 2MB of it
+ * so there is no map overlap problem for up to 1 MB compressed kernel.
+ * If the execution is in RAM then we would only be duplicating the above.
+ */
+ mov r1, #0x1e
+ orr r1, r1, #3 << 10
+ mov r2, pc
+ mov r2, r2, lsr #20
+ orr r1, r1, r2, lsl #20
+ add r0, r3, r2, lsl #2
+ str r1, [r0], #4
+ add r1, r1, #1048576
+ str r1, [r0]
+ mov pc, lr
+ENDPROC(__setup_mmu)
+
+__arm926ejs_mmu_cache_on:
+#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+ mov r0, #4 @ put dcache in WT mode
+ mcr p15, 7, r0, c15, c0, 0
+#endif
+
+__armv4_mmu_cache_on:
+ mov r12, lr
+#ifdef CONFIG_MMU
+ bl __setup_mmu
+ mov r0, #0
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
+ mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement
+ orr r0, r0, #0x0030
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ orr r0, r0, #1 << 25 @ big-endian page tables
+#endif
+ bl __common_mmu_cache_on
+ mov r0, #0
+ mcr p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
+#endif
+ mov pc, r12
+
+__armv7_mmu_cache_on:
+ mov r12, lr
+#ifdef CONFIG_MMU
+ mrc p15, 0, r11, c0, c1, 4 @ read ID_MMFR0
+ tst r11, #0xf @ VMSA
+ blne __setup_mmu
+ mov r0, #0
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
+ tst r11, #0xf @ VMSA
+ mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs
+#endif
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ orr r0, r0, #0x5000 @ I-cache enable, RR cache replacement
+ orr r0, r0, #0x003c @ write buffer
+#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_ENDIAN_BE8
+ orr r0, r0, #1 << 25 @ big-endian page tables
+#endif
+ orrne r0, r0, #1 @ MMU enabled
+ movne r1, #-1
+ mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer
+ mcrne p15, 0, r1, c3, c0, 0 @ load domain access control
+#endif
+ mcr p15, 0, r0, c7, c5, 4 @ ISB
+ mcr p15, 0, r0, c1, c0, 0 @ load control register
+ mrc p15, 0, r0, c1, c0, 0 @ and read it back
+ mov r0, #0
+ mcr p15, 0, r0, c7, c5, 4 @ ISB
+ mov pc, r12
+
+__fa526_cache_on:
+ mov r12, lr
+ bl __setup_mmu
+ mov r0, #0
+ mcr p15, 0, r0, c7, c7, 0 @ Invalidate whole cache
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
+ mcr p15, 0, r0, c8, c7, 0 @ flush UTLB
+ mrc p15, 0, r0, c1, c0, 0 @ read control reg
+ orr r0, r0, #0x1000 @ I-cache enable
+ bl __common_mmu_cache_on
+ mov r0, #0
+ mcr p15, 0, r0, c8, c7, 0 @ flush UTLB
+ mov pc, r12
+
+__arm6_mmu_cache_on:
+ mov r12, lr
+ bl __setup_mmu
+ mov r0, #0
+ mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
+ mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3
+ mov r0, #0x30
+ bl __common_mmu_cache_on
+ mov r0, #0
+ mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3
+ mov pc, r12
+
+__common_mmu_cache_on:
+#ifndef CONFIG_THUMB2_KERNEL
+#ifndef DEBUG
+ orr r0, r0, #0x000d @ Write buffer, mmu
+#endif
+ mov r1, #-1
+ mcr p15, 0, r3, c2, c0, 0 @ load page table pointer
+ mcr p15, 0, r1, c3, c0, 0 @ load domain access control
+ b 1f
+ .align 5 @ cache line aligned
+1: mcr p15, 0, r0, c1, c0, 0 @ load control register
+ mrc p15, 0, r0, c1, c0, 0 @ and read it back to
+ sub pc, lr, r0, lsr #32 @ properly flush pipeline
+#endif
+
+#define PROC_ENTRY_SIZE (4*5)
+
+/*
+ * Here follow the relocatable cache support functions for the
+ * various processors. This is a generic hook for locating an
+ * entry and jumping to an instruction at the specified offset
+ * from the start of the block. Please note this is all position
+ * independent code.
+ *
+ * r1 = corrupted
+ * r2 = corrupted
+ * r3 = block offset
+ * r9 = corrupted
+ * r12 = corrupted
+ */
+
+call_cache_fn: adr r12, proc_types
+#ifdef CONFIG_CPU_CP15
+ mrc p15, 0, r9, c0, c0 @ get processor ID
+#else
+ ldr r9, =CONFIG_PROCESSOR_ID
+#endif
+1: ldr r1, [r12, #0] @ get value
+ ldr r2, [r12, #4] @ get mask
+ eor r1, r1, r9 @ (real ^ match)
+ tst r1, r2 @ & mask
+ ARM( addeq pc, r12, r3 ) @ call cache function
+ THUMB( addeq r12, r3 )
+ THUMB( moveq pc, r12 ) @ call cache function
+ add r12, r12, #PROC_ENTRY_SIZE
+ b 1b
+
+/*
+ * Table for cache operations. This is basically:
+ * - CPU ID match
+ * - CPU ID mask
+ * - 'cache on' method instruction
+ * - 'cache off' method instruction
+ * - 'cache flush' method instruction
+ *
+ * We match an entry using: ((real_id ^ match) & mask) == 0
+ *
+ * Writethrough caches generally only need 'on' and 'off'
+ * methods. Writeback caches _must_ have the flush method
+ * defined.
+ */
+ .align 2
+ .type proc_types,#object
+proc_types:
+ .word 0x41560600 @ ARM6/610
+ .word 0xffffffe0
+ W(b) __arm6_mmu_cache_off @ works, but slow
+ W(b) __arm6_mmu_cache_off
+ mov pc, lr
+ THUMB( nop )
+@ b __arm6_mmu_cache_on @ untested
+@ b __arm6_mmu_cache_off
+@ b __armv3_mmu_cache_flush
+
+ .word 0x00000000 @ old ARM ID
+ .word 0x0000f000
+ mov pc, lr
+ THUMB( nop )
+ mov pc, lr
+ THUMB( nop )
+ mov pc, lr
+ THUMB( nop )
+
+ .word 0x41007000 @ ARM7/710
+ .word 0xfff8fe00
+ W(b) __arm7_mmu_cache_off
+ W(b) __arm7_mmu_cache_off
+ mov pc, lr
+ THUMB( nop )
+
+ .word 0x41807200 @ ARM720T (writethrough)
+ .word 0xffffff00
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ mov pc, lr
+ THUMB( nop )
+
+ .word 0x41007400 @ ARM74x
+ .word 0xff00ff00
+ W(b) __armv3_mpu_cache_on
+ W(b) __armv3_mpu_cache_off
+ W(b) __armv3_mpu_cache_flush
+
+ .word 0x41009400 @ ARM94x
+ .word 0xff00ff00
+ W(b) __armv4_mpu_cache_on
+ W(b) __armv4_mpu_cache_off
+ W(b) __armv4_mpu_cache_flush
+
+ .word 0x41069260 @ ARM926EJ-S (v5TEJ)
+ .word 0xff0ffff0
+ W(b) __arm926ejs_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv5tej_mmu_cache_flush
+
+ .word 0x00007000 @ ARM7 IDs
+ .word 0x0000f000
+ mov pc, lr
+ THUMB( nop )
+ mov pc, lr
+ THUMB( nop )
+ mov pc, lr
+ THUMB( nop )
+
+ @ Everything from here on will be the new ID system.
+
+ .word 0x4401a100 @ sa110 / sa1100
+ .word 0xffffffe0
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv4_mmu_cache_flush
+
+ .word 0x6901b110 @ sa1110
+ .word 0xfffffff0
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv4_mmu_cache_flush
+
+ .word 0x56056900
+ .word 0xffffff00 @ PXA9xx
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv4_mmu_cache_flush
+
+ .word 0x56158000 @ PXA168
+ .word 0xfffff000
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv5tej_mmu_cache_flush
+
+ .word 0x56050000 @ Feroceon
+ .word 0xff0f0000
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv5tej_mmu_cache_flush
+
+#ifdef CONFIG_CPU_FEROCEON_OLD_ID
+ /* this conflicts with the standard ARMv5TE entry */
+ .long 0x41009260 @ Old Feroceon
+ .long 0xff00fff0
+ b __armv4_mmu_cache_on
+ b __armv4_mmu_cache_off
+ b __armv5tej_mmu_cache_flush
+#endif
+
+ .word 0x66015261 @ FA526
+ .word 0xff01fff1
+ W(b) __fa526_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __fa526_cache_flush
+
+ @ These match on the architecture ID
+
+ .word 0x00020000 @ ARMv4T
+ .word 0x000f0000
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv4_mmu_cache_flush
+
+ .word 0x00050000 @ ARMv5TE
+ .word 0x000f0000
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv4_mmu_cache_flush
+
+ .word 0x00060000 @ ARMv5TEJ
+ .word 0x000f0000
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv5tej_mmu_cache_flush
+
+ .word 0x0007b000 @ ARMv6
+ .word 0x000ff000
+ W(b) __armv4_mmu_cache_on
+ W(b) __armv4_mmu_cache_off
+ W(b) __armv6_mmu_cache_flush
+
+ .word 0x000f0000 @ new CPU Id
+ .word 0x000f0000
+ W(b) __armv7_mmu_cache_on
+ W(b) __armv7_mmu_cache_off
+ W(b) __armv7_mmu_cache_flush
+
+ .word 0 @ unrecognised type
+ .word 0
+ mov pc, lr
+ THUMB( nop )
+ mov pc, lr
+ THUMB( nop )
+ mov pc, lr
+ THUMB( nop )
+
+ .size proc_types, . - proc_types
+
+ /*
+ * If you get a "non-constant expression in ".if" statement"
+ * error from the assembler on this line, check that you have
+ * not accidentally written a "b" instruction where you should
+ * have written W(b).
+ */
+ .if (. - proc_types) % PROC_ENTRY_SIZE != 0
+ .error "The size of one or more proc_types entries is wrong."
+ .endif
+
+/*
+ * Turn off the Cache and MMU. ARMv3 does not support
+ * reading the control register, but ARMv4 does.
+ *
+ * On exit,
+ * r0, r1, r2, r3, r9, r12 corrupted
+ * This routine must preserve:
+ * r4, r7, r8
+ */
+ .align 5
+cache_off: mov r3, #12 @ cache_off function
+ b call_cache_fn
+
+__armv4_mpu_cache_off:
+ mrc p15, 0, r0, c1, c0
+ bic r0, r0, #0x000d
+ mcr p15, 0, r0, c1, c0 @ turn MPU and cache off
+ mov r0, #0
+ mcr p15, 0, r0, c7, c10, 4 @ drain write buffer
+ mcr p15, 0, r0, c7, c6, 0 @ flush D-Cache
+ mcr p15, 0, r0, c7, c5, 0 @ flush I-Cache
+ mov pc, lr
+
+__armv3_mpu_cache_off:
+ mrc p15, 0, r0, c1, c0
+ bic r0, r0, #0x000d
+ mcr p15, 0, r0, c1, c0, 0 @ turn MPU and cache off
+ mov r0, #0
+ mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
+ mov pc, lr
+
+__armv4_mmu_cache_off:
+#ifdef CONFIG_MMU
+ mrc p15, 0, r0, c1, c0
+ bic r0, r0, #0x000d
+ mcr p15, 0, r0, c1, c0 @ turn MMU and cache off
+ mov r0, #0
+ mcr p15, 0, r0, c7, c7 @ invalidate whole cache v4
+ mcr p15, 0, r0, c8, c7 @ invalidate whole TLB v4
+#endif
+ mov pc, lr
+
+__armv7_mmu_cache_off:
+ mrc p15, 0, r0, c1, c0
+#ifdef CONFIG_MMU
+ bic r0, r0, #0x000d
+#else
+ bic r0, r0, #0x000c
+#endif
+ mcr p15, 0, r0, c1, c0 @ turn MMU and cache off
+ mov r12, lr
+ bl __armv7_mmu_cache_flush
+ mov r0, #0
+#ifdef CONFIG_MMU
+ mcr p15, 0, r0, c8, c7, 0 @ invalidate whole TLB
+#endif
+ mcr p15, 0, r0, c7, c5, 6 @ invalidate BTC
+ mcr p15, 0, r0, c7, c10, 4 @ DSB
+ mcr p15, 0, r0, c7, c5, 4 @ ISB
+ mov pc, r12
+
+__arm6_mmu_cache_off:
+ mov r0, #0x00000030 @ ARM6 control reg.
+ b __armv3_mmu_cache_off
+
+__arm7_mmu_cache_off:
+ mov r0, #0x00000070 @ ARM7 control reg.
+ b __armv3_mmu_cache_off
+
+__armv3_mmu_cache_off:
+ mcr p15, 0, r0, c1, c0, 0 @ turn MMU and cache off
+ mov r0, #0
+ mcr p15, 0, r0, c7, c0, 0 @ invalidate whole cache v3
+ mcr p15, 0, r0, c5, c0, 0 @ invalidate whole TLB v3
+ mov pc, lr
+
+/*
+ * Clean and flush the cache to maintain consistency.
+ *
+ * On exit,
+ * r1, r2, r3, r9, r10, r11, r12 corrupted
+ * This routine must preserve:
+ * r4, r6, r7, r8
+ */
+ .align 5
+cache_clean_flush:
+ mov r3, #16
+ b call_cache_fn
+
+__armv4_mpu_cache_flush:
+ mov r2, #1
+ mov r3, #0
+ mcr p15, 0, ip, c7, c6, 0 @ invalidate D cache
+ mov r1, #7 << 5 @ 8 segments
+1: orr r3, r1, #63 << 26 @ 64 entries
+2: mcr p15, 0, r3, c7, c14, 2 @ clean & invalidate D index
+ subs r3, r3, #1 << 26
+ bcs 2b @ entries 63 to 0
+ subs r1, r1, #1 << 5
+ bcs 1b @ segments 7 to 0
+
+ teq r2, #0
+ mcrne p15, 0, ip, c7, c5, 0 @ invalidate I cache
+ mcr p15, 0, ip, c7, c10, 4 @ drain WB
+ mov pc, lr
+
+__fa526_cache_flush:
+ mov r1, #0
+ mcr p15, 0, r1, c7, c14, 0 @ clean and invalidate D cache
+ mcr p15, 0, r1, c7, c5, 0 @ flush I cache
+ mcr p15, 0, r1, c7, c10, 4 @ drain WB
+ mov pc, lr
+
+__armv6_mmu_cache_flush:
+ mov r1, #0
+ mcr p15, 0, r1, c7, c14, 0 @ clean+invalidate D
+ mcr p15, 0, r1, c7, c5, 0 @ invalidate I+BTB
+ mcr p15, 0, r1, c7, c15, 0 @ clean+invalidate unified
+ mcr p15, 0, r1, c7, c10, 4 @ drain WB
+ mov pc, lr
+
+__armv7_mmu_cache_flush:
+ mrc p15, 0, r10, c0, c1, 5 @ read ID_MMFR1
+ tst r10, #0xf << 16 @ hierarchical cache (ARMv7)
+ mov r10, #0
+ beq hierarchical
+ mcr p15, 0, r10, c7, c14, 0 @ clean+invalidate D
+ b iflush
+hierarchical:
+ mcr p15, 0, r10, c7, c10, 5 @ DMB
+ stmfd sp!, {r0-r7, r9-r11}
+ mrc p15, 1, r0, c0, c0, 1 @ read clidr
+ ands r3, r0, #0x7000000 @ extract loc from clidr
+ mov r3, r3, lsr #23 @ left align loc bit field
+ beq finished @ if loc is 0, then no need to clean
+ mov r10, #0 @ start clean at cache level 0
+loop1:
+ add r2, r10, r10, lsr #1 @ work out 3x current cache level
+ mov r1, r0, lsr r2 @ extract cache type bits from clidr
+ and r1, r1, #7 @ mask of the bits for current cache only
+ cmp r1, #2 @ see what cache we have at this level
+ blt skip @ skip if no cache, or just i-cache
+ mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr
+ mcr p15, 0, r10, c7, c5, 4 @ isb to sych the new cssr&csidr
+ mrc p15, 1, r1, c0, c0, 0 @ read the new csidr
+ and r2, r1, #7 @ extract the length of the cache lines
+ add r2, r2, #4 @ add 4 (line length offset)
+ ldr r4, =0x3ff
+ ands r4, r4, r1, lsr #3 @ find maximum number on the way size
+ clz r5, r4 @ find bit position of way size increment
+ ldr r7, =0x7fff
+ ands r7, r7, r1, lsr #13 @ extract max number of the index size
+loop2:
+ mov r9, r4 @ create working copy of max way size
+loop3:
+ ARM( orr r11, r10, r9, lsl r5 ) @ factor way and cache number into r11
+ ARM( orr r11, r11, r7, lsl r2 ) @ factor index number into r11
+ THUMB( lsl r6, r9, r5 )
+ THUMB( orr r11, r10, r6 ) @ factor way and cache number into r11
+ THUMB( lsl r6, r7, r2 )
+ THUMB( orr r11, r11, r6 ) @ factor index number into r11
+ mcr p15, 0, r11, c7, c14, 2 @ clean & invalidate by set/way
+ subs r9, r9, #1 @ decrement the way
+ bge loop3
+ subs r7, r7, #1 @ decrement the index
+ bge loop2
+skip:
+ add r10, r10, #2 @ increment cache number
+ cmp r3, r10
+ bgt loop1
+finished:
+ ldmfd sp!, {r0-r7, r9-r11}
+ mov r10, #0 @ swith back to cache level 0
+ mcr p15, 2, r10, c0, c0, 0 @ select current cache level in cssr
+iflush:
+ mcr p15, 0, r10, c7, c10, 4 @ DSB
+ mcr p15, 0, r10, c7, c5, 0 @ invalidate I+BTB
+ mcr p15, 0, r10, c7, c10, 4 @ DSB
+ mcr p15, 0, r10, c7, c5, 4 @ ISB
+ mov pc, lr
+
+__armv5tej_mmu_cache_flush:
+1: mrc p15, 0, r15, c7, c14, 3 @ test,clean,invalidate D cache
+ bne 1b
+ mcr p15, 0, r0, c7, c5, 0 @ flush I cache
+ mcr p15, 0, r0, c7, c10, 4 @ drain WB
+ mov pc, lr
+
+__armv4_mmu_cache_flush:
+ mov r2, #64*1024 @ default: 32K dcache size (*2)
+ mov r11, #32 @ default: 32 byte line size
+ mrc p15, 0, r3, c0, c0, 1 @ read cache type
+ teq r3, r9 @ cache ID register present?
+ beq no_cache_id
+ mov r1, r3, lsr #18
+ and r1, r1, #7
+ mov r2, #1024
+ mov r2, r2, lsl r1 @ base dcache size *2
+ tst r3, #1 << 14 @ test M bit
+ addne r2, r2, r2, lsr #1 @ +1/2 size if M == 1
+ mov r3, r3, lsr #12
+ and r3, r3, #3
+ mov r11, #8
+ mov r11, r11, lsl r3 @ cache line size in bytes
+no_cache_id:
+ mov r1, pc
+ bic r1, r1, #63 @ align to longest cache line
+ add r2, r1, r2
+1:
+ ARM( ldr r3, [r1], r11 ) @ s/w flush D cache
+ THUMB( ldr r3, [r1] ) @ s/w flush D cache
+ THUMB( add r1, r1, r11 )
+ teq r1, r2
+ bne 1b
+
+ mcr p15, 0, r1, c7, c5, 0 @ flush I cache
+ mcr p15, 0, r1, c7, c6, 0 @ flush D cache
+ mcr p15, 0, r1, c7, c10, 4 @ drain WB
+ mov pc, lr
+
+__armv3_mmu_cache_flush:
+__armv3_mpu_cache_flush:
+ mov r1, #0
+ mcr p15, 0, r1, c7, c0, 0 @ invalidate whole cache v3
+ mov pc, lr
+
+/*
+ * Various debugging routines for printing hex characters and
+ * memory, which again must be relocatable.
+ */
+#ifdef DEBUG
+ .align 2
+ .type phexbuf,#object
+phexbuf: .space 12
+ .size phexbuf, . - phexbuf
+
+@ phex corrupts {r0, r1, r2, r3}
+phex: adr r3, phexbuf
+ mov r2, #0
+ strb r2, [r3, r1]
+1: subs r1, r1, #1
+ movmi r0, r3
+ bmi puts
+ and r2, r0, #15
+ mov r0, r0, lsr #4
+ cmp r2, #10
+ addge r2, r2, #7
+ add r2, r2, #'0'
+ strb r2, [r3, r1]
+ b 1b
+
+@ puts corrupts {r0, r1, r2, r3}
+puts: loadsp r3, r1
+1: ldrb r2, [r0], #1
+ teq r2, #0
+ moveq pc, lr
+2: writeb r2, r3
+ mov r1, #0x00020000
+3: subs r1, r1, #1
+ bne 3b
+ teq r2, #'\n'
+ moveq r2, #'\r'
+ beq 2b
+ teq r0, #0
+ bne 1b
+ mov pc, lr
+@ putc corrupts {r0, r1, r2, r3}
+putc:
+ mov r2, r0
+ mov r0, #0
+ loadsp r3, r1
+ b 2b
+
+@ memdump corrupts {r0, r1, r2, r3, r10, r11, r12, lr}
+memdump: mov r12, r0
+ mov r10, lr
+ mov r11, #0
+2: mov r0, r11, lsl #2
+ add r0, r0, r12
+ mov r1, #8
+ bl phex
+ mov r0, #':'
+ bl putc
+1: mov r0, #' '
+ bl putc
+ ldr r0, [r12, r11, lsl #2]
+ mov r1, #8
+ bl phex
+ and r0, r11, #7
+ teq r0, #3
+ moveq r0, #' '
+ bleq putc
+ and r0, r11, #7
+ add r11, r11, #1
+ teq r0, #7
+ bne 1b
+ mov r0, #'\n'
+ bl putc
+ cmp r11, #64
+ blt 2b
+ mov pc, r10
+#endif
+
+ .ltorg
+reloc_code_end:
+
+ .align
+ .section ".stack", "aw", %nobits
+.L_user_stack: .space 4096
+.L_user_stack_end:
diff --git a/arch/arm/boot/compressed/libfdt_env.h b/arch/arm/boot/compressed/libfdt_env.h
new file mode 100644
index 00000000000..1f4e71876b0
--- /dev/null
+++ b/arch/arm/boot/compressed/libfdt_env.h
@@ -0,0 +1,15 @@
+#ifndef _ARM_LIBFDT_ENV_H
+#define _ARM_LIBFDT_ENV_H
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <asm/byteorder.h>
+
+#define fdt16_to_cpu(x) be16_to_cpu(x)
+#define cpu_to_fdt16(x) cpu_to_be16(x)
+#define fdt32_to_cpu(x) be32_to_cpu(x)
+#define cpu_to_fdt32(x) cpu_to_be32(x)
+#define fdt64_to_cpu(x) be64_to_cpu(x)
+#define cpu_to_fdt64(x) cpu_to_be64(x)
+
+#endif
diff --git a/arch/arm/boot/compressed/ll_char_wr.S b/arch/arm/boot/compressed/ll_char_wr.S
new file mode 100644
index 00000000000..8517c8606b4
--- /dev/null
+++ b/arch/arm/boot/compressed/ll_char_wr.S
@@ -0,0 +1,134 @@
+/*
+ * linux/arch/arm/lib/ll_char_wr.S
+ *
+ * Copyright (C) 1995, 1996 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.
+ *
+ * Speedups & 1bpp code (C) 1996 Philip Blundell & Russell King.
+ *
+ * 10-04-96 RMK Various cleanups & reduced register usage.
+ * 08-04-98 RMK Shifts re-ordered
+ */
+
+@ Regs: [] = corruptible
+@ {} = used
+@ () = do not use
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+ .text
+
+LC0: .word LC0
+ .word bytes_per_char_h
+ .word video_size_row
+ .word acorndata_8x8
+ .word con_charconvtable
+
+/*
+ * r0 = ptr
+ * r1 = char
+ * r2 = white
+ */
+ENTRY(ll_write_char)
+ stmfd sp!, {r4 - r7, lr}
+@
+@ Smashable regs: {r0 - r3}, [r4 - r7], (r8 - fp), [ip], (sp), [lr], (pc)
+@
+ /*
+ * calculate offset into character table
+ */
+ mov r1, r1, lsl #3
+ /*
+ * calculate offset required for each row.
+ */
+ adr ip, LC0
+ ldmia ip, {r3, r4, r5, r6, lr}
+ sub ip, ip, r3
+ add r6, r6, ip
+ add lr, lr, ip
+ ldr r4, [r4, ip]
+ ldr r5, [r5, ip]
+ /*
+ * Go to resolution-dependent routine...
+ */
+ cmp r4, #4
+ blt Lrow1bpp
+ add r0, r0, r5, lsl #3 @ Move to bottom of character
+ orr r1, r1, #7
+ ldrb r7, [r6, r1]
+ teq r4, #8
+ beq Lrow8bpplp
+@
+@ Smashable regs: {r0 - r3}, [r4], {r5 - r7}, (r8 - fp), [ip], (sp), {lr}, (pc)
+@
+Lrow4bpplp:
+ ldr r7, [lr, r7, lsl #2]
+ mul r7, r2, r7
+ sub r1, r1, #1 @ avoid using r7 directly after
+ str r7, [r0, -r5]!
+ ldrb r7, [r6, r1]
+ ldr r7, [lr, r7, lsl #2]
+ mul r7, r2, r7
+ tst r1, #7 @ avoid using r7 directly after
+ str r7, [r0, -r5]!
+ subne r1, r1, #1
+ ldrneb r7, [r6, r1]
+ bne Lrow4bpplp
+ ldmfd sp!, {r4 - r7, pc}
+
+@
+@ Smashable regs: {r0 - r3}, [r4], {r5 - r7}, (r8 - fp), [ip], (sp), {lr}, (pc)
+@
+Lrow8bpplp:
+ mov ip, r7, lsr #4
+ ldr ip, [lr, ip, lsl #2]
+ mul r4, r2, ip
+ and ip, r7, #15 @ avoid r4
+ ldr ip, [lr, ip, lsl #2] @ avoid r4
+ mul ip, r2, ip @ avoid r4
+ sub r1, r1, #1 @ avoid ip
+ sub r0, r0, r5 @ avoid ip
+ stmia r0, {r4, ip}
+ ldrb r7, [r6, r1]
+ mov ip, r7, lsr #4
+ ldr ip, [lr, ip, lsl #2]
+ mul r4, r2, ip
+ and ip, r7, #15 @ avoid r4
+ ldr ip, [lr, ip, lsl #2] @ avoid r4
+ mul ip, r2, ip @ avoid r4
+ tst r1, #7 @ avoid ip
+ sub r0, r0, r5 @ avoid ip
+ stmia r0, {r4, ip}
+ subne r1, r1, #1
+ ldrneb r7, [r6, r1]
+ bne Lrow8bpplp
+ ldmfd sp!, {r4 - r7, pc}
+
+@
+@ Smashable regs: {r0 - r3}, [r4], {r5, r6}, [r7], (r8 - fp), [ip], (sp), [lr], (pc)
+@
+Lrow1bpp:
+ add r6, r6, r1
+ ldmia r6, {r4, r7}
+ strb r4, [r0], r5
+ mov r4, r4, lsr #8
+ strb r4, [r0], r5
+ mov r4, r4, lsr #8
+ strb r4, [r0], r5
+ mov r4, r4, lsr #8
+ strb r4, [r0], r5
+ strb r7, [r0], r5
+ mov r7, r7, lsr #8
+ strb r7, [r0], r5
+ mov r7, r7, lsr #8
+ strb r7, [r0], r5
+ mov r7, r7, lsr #8
+ strb r7, [r0], r5
+ ldmfd sp!, {r4 - r7, pc}
+
+ .bss
+ENTRY(con_charconvtable)
+ .space 1024
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
new file mode 100644
index 00000000000..8e2a8fca5ed
--- /dev/null
+++ b/arch/arm/boot/compressed/misc.c
@@ -0,0 +1,154 @@
+/*
+ * misc.c
+ *
+ * This is a collection of several routines from gzip-1.0.3
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ *
+ * Modified for ARM Linux by Russell King
+ *
+ * Nicolas Pitre <nico@visuaide.com> 1999/04/14 :
+ * For this code to run directly from Flash, all constant variables must
+ * be marked with 'const' and all other variables initialized at run-time
+ * only. This way all non constant variables will end up in the bss segment,
+ * which should point to addresses in RAM and cleared to 0 on start.
+ * This allows for a much quicker boot time.
+ */
+
+unsigned int __machine_arch_type;
+
+#include <linux/compiler.h> /* for inline */
+#include <linux/types.h>
+#include <linux/linkage.h>
+
+static void putstr(const char *ptr);
+extern void error(char *x);
+
+#include <mach/uncompress.h>
+
+#ifdef CONFIG_DEBUG_ICEDCC
+
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) || defined(CONFIG_CPU_V7)
+
+static void icedcc_putc(int ch)
+{
+ int status, i = 0x4000000;
+
+ do {
+ if (--i < 0)
+ return;
+
+ asm volatile ("mrc p14, 0, %0, c0, c1, 0" : "=r" (status));
+ } while (status & (1 << 29));
+
+ asm("mcr p14, 0, %0, c0, c5, 0" : : "r" (ch));
+}
+
+
+#elif defined(CONFIG_CPU_XSCALE)
+
+static void icedcc_putc(int ch)
+{
+ int status, i = 0x4000000;
+
+ do {
+ if (--i < 0)
+ return;
+
+ asm volatile ("mrc p14, 0, %0, c14, c0, 0" : "=r" (status));
+ } while (status & (1 << 28));
+
+ asm("mcr p14, 0, %0, c8, c0, 0" : : "r" (ch));
+}
+
+#else
+
+static void icedcc_putc(int ch)
+{
+ int status, i = 0x4000000;
+
+ do {
+ if (--i < 0)
+ return;
+
+ asm volatile ("mrc p14, 0, %0, c0, c0, 0" : "=r" (status));
+ } while (status & 2);
+
+ asm("mcr p14, 0, %0, c1, c0, 0" : : "r" (ch));
+}
+
+#endif
+
+#define putc(ch) icedcc_putc(ch)
+#endif
+
+static void putstr(const char *ptr)
+{
+ char c;
+
+ while ((c = *ptr++) != '\0') {
+ if (c == '\n')
+ putc('\r');
+ putc(c);
+ }
+
+ flush();
+}
+
+/*
+ * gzip declarations
+ */
+extern char input_data[];
+extern char input_data_end[];
+
+unsigned char *output_data;
+
+unsigned long free_mem_ptr;
+unsigned long free_mem_end_ptr;
+
+#ifndef arch_error
+#define arch_error(x)
+#endif
+
+void error(char *x)
+{
+ arch_error(x);
+
+ putstr("\n\n");
+ putstr(x);
+ putstr("\n\n -- System halted");
+
+ while(1); /* Halt */
+}
+
+asmlinkage void __div0(void)
+{
+ error("Attempting division by 0!");
+}
+
+extern int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x));
+
+
+void
+decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p,
+ unsigned long free_mem_ptr_end_p,
+ int arch_id)
+{
+ int ret;
+
+ output_data = (unsigned char *)output_start;
+ free_mem_ptr = free_mem_ptr_p;
+ free_mem_end_ptr = free_mem_ptr_end_p;
+ __machine_arch_type = arch_id;
+
+ arch_decomp_setup();
+
+ putstr("Uncompressing Linux...");
+ ret = do_decompress(input_data, input_data_end - input_data,
+ output_data, error);
+ if (ret)
+ error("decompressor returned an error");
+ else
+ putstr(" done, booting the kernel.\n");
+}
diff --git a/arch/arm/boot/compressed/mmcif-sh7372.c b/arch/arm/boot/compressed/mmcif-sh7372.c
new file mode 100644
index 00000000000..672ae95db5c
--- /dev/null
+++ b/arch/arm/boot/compressed/mmcif-sh7372.c
@@ -0,0 +1,88 @@
+/*
+ * sh7372 MMCIF loader
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/mmc/sh_mmcif.h>
+#include <linux/mmc/boot.h>
+#include <mach/mmc.h>
+
+#define MMCIF_BASE (void __iomem *)0xe6bd0000
+
+#define PORT84CR (void __iomem *)0xe6050054
+#define PORT85CR (void __iomem *)0xe6050055
+#define PORT86CR (void __iomem *)0xe6050056
+#define PORT87CR (void __iomem *)0xe6050057
+#define PORT88CR (void __iomem *)0xe6050058
+#define PORT89CR (void __iomem *)0xe6050059
+#define PORT90CR (void __iomem *)0xe605005a
+#define PORT91CR (void __iomem *)0xe605005b
+#define PORT92CR (void __iomem *)0xe605005c
+#define PORT99CR (void __iomem *)0xe6050063
+
+#define SMSTPCR3 (void __iomem *)0xe615013c
+
+/* SH7372 specific MMCIF loader
+ *
+ * loads the zImage from an MMC card starting from block 1.
+ *
+ * The image must be start with a vrl4 header and
+ * the zImage must start at offset 512 of the image. That is,
+ * at block 2 (=byte 1024) on the media
+ *
+ * Use the following line to write the vrl4 formated zImage
+ * to an MMC card
+ * # dd if=vrl4.out of=/dev/sdx bs=512 seek=1
+ */
+asmlinkage void mmc_loader(unsigned char *buf, unsigned long len)
+{
+ mmc_init_progress();
+ mmc_update_progress(MMC_PROGRESS_ENTER);
+
+ /* Initialise MMC
+ * registers: PORT84CR-PORT92CR
+ * (MMCD0_0-MMCD0_7,MMCCMD0 Control)
+ * value: 0x04 - select function 4
+ */
+ __raw_writeb(0x04, PORT84CR);
+ __raw_writeb(0x04, PORT85CR);
+ __raw_writeb(0x04, PORT86CR);
+ __raw_writeb(0x04, PORT87CR);
+ __raw_writeb(0x04, PORT88CR);
+ __raw_writeb(0x04, PORT89CR);
+ __raw_writeb(0x04, PORT90CR);
+ __raw_writeb(0x04, PORT91CR);
+ __raw_writeb(0x04, PORT92CR);
+
+ /* Initialise MMC
+ * registers: PORT99CR (MMCCLK0 Control)
+ * value: 0x10 | 0x04 - enable output | select function 4
+ */
+ __raw_writeb(0x14, PORT99CR);
+
+ /* Enable clock to MMC hardware block */
+ __raw_writel(__raw_readl(SMSTPCR3) & ~(1 << 12), SMSTPCR3);
+
+ mmc_update_progress(MMC_PROGRESS_INIT);
+
+ /* setup MMCIF hardware */
+ sh_mmcif_boot_init(MMCIF_BASE);
+
+ mmc_update_progress(MMC_PROGRESS_LOAD);
+
+ /* load kernel via MMCIF interface */
+ sh_mmcif_boot_do_read(MMCIF_BASE, 2, /* Kernel is at block 2 */
+ (len + SH_MMCIF_BBS - 1) / SH_MMCIF_BBS, buf);
+
+
+ /* Disable clock to MMC hardware block */
+ __raw_writel(__raw_readl(SMSTPCR3) | (1 << 12), SMSTPCR3);
+
+ mmc_update_progress(MMC_PROGRESS_DONE);
+}
diff --git a/arch/arm/boot/compressed/ofw-shark.c b/arch/arm/boot/compressed/ofw-shark.c
new file mode 100644
index 00000000000..465c54b6b12
--- /dev/null
+++ b/arch/arm/boot/compressed/ofw-shark.c
@@ -0,0 +1,260 @@
+/*
+ * linux/arch/arm/boot/compressed/ofw-shark.c
+ *
+ * by Alexander Schulz
+ *
+ * This file is used to get some basic information
+ * about the memory layout of the shark we are running
+ * on. Memory is usually divided in blocks a 8 MB.
+ * And bootargs are copied from OpenFirmware.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <asm/setup.h>
+#include <asm/page.h>
+
+
+asmlinkage void
+create_params (unsigned long *buffer)
+{
+ /* Is there a better address? Also change in mach-shark/core.c */
+ struct tag *tag = (struct tag *) 0x08003000;
+ int j,i,m,k,nr_banks,size;
+ unsigned char *c;
+
+ k = 0;
+
+ /* Head of the taglist */
+ tag->hdr.tag = ATAG_CORE;
+ tag->hdr.size = tag_size(tag_core);
+ tag->u.core.flags = 1;
+ tag->u.core.pagesize = PAGE_SIZE;
+ tag->u.core.rootdev = 0;
+
+ /* Build up one tagged block for each memory region */
+ size=0;
+ nr_banks=(unsigned int) buffer[0];
+ for (j=0;j<nr_banks;j++){
+ /* search the lowest address and put it into the next entry */
+ /* not a fast sort algorithm, but there are at most 8 entries */
+ /* and this is used only once anyway */
+ m=0xffffffff;
+ for (i=0;i<(unsigned int) buffer[0];i++){
+ if (buffer[2*i+1]<m) {
+ m=buffer[2*i+1];
+ k=i;
+ }
+ }
+
+ tag = tag_next(tag);
+ tag->hdr.tag = ATAG_MEM;
+ tag->hdr.size = tag_size(tag_mem32);
+ tag->u.mem.size = buffer[2*k+2];
+ tag->u.mem.start = buffer[2*k+1];
+
+ size += buffer[2*k+2];
+
+ buffer[2*k+1]=0xffffffff; /* mark as copied */
+ }
+
+ /* The command line */
+ tag = tag_next(tag);
+ tag->hdr.tag = ATAG_CMDLINE;
+
+ c=(unsigned char *)(&buffer[34]);
+ j=0;
+ while (*c) tag->u.cmdline.cmdline[j++]=*c++;
+
+ tag->u.cmdline.cmdline[j]=0;
+ tag->hdr.size = (j + 7 + sizeof(struct tag_header)) >> 2;
+
+ /* Hardware revision */
+ tag = tag_next(tag);
+ tag->hdr.tag = ATAG_REVISION;
+ tag->hdr.size = tag_size(tag_revision);
+ tag->u.revision.rev = ((unsigned char) buffer[33])-'0';
+
+ /* End of the taglist */
+ tag = tag_next(tag);
+ tag->hdr.tag = 0;
+ tag->hdr.size = 0;
+}
+
+
+typedef int (*ofw_handle_t)(void *);
+
+/* Everything below is called with a wrong MMU setting.
+ * This means: no string constants, no initialization of
+ * arrays, no global variables! This is ugly but I didn't
+ * want to write this in assembler :-)
+ */
+
+int
+of_decode_int(const unsigned char *p)
+{
+ unsigned int i = *p++ << 8;
+ i = (i + *p++) << 8;
+ i = (i + *p++) << 8;
+ return (i + *p);
+}
+
+int
+OF_finddevice(ofw_handle_t openfirmware, char *name)
+{
+ unsigned int args[8];
+ char service[12];
+
+ service[0]='f';
+ service[1]='i';
+ service[2]='n';
+ service[3]='d';
+ service[4]='d';
+ service[5]='e';
+ service[6]='v';
+ service[7]='i';
+ service[8]='c';
+ service[9]='e';
+ service[10]='\0';
+
+ args[0]=(unsigned int)service;
+ args[1]=1;
+ args[2]=1;
+ args[3]=(unsigned int)name;
+
+ if (openfirmware(args) == -1)
+ return -1;
+ return args[4];
+}
+
+int
+OF_getproplen(ofw_handle_t openfirmware, int handle, char *prop)
+{
+ unsigned int args[8];
+ char service[12];
+
+ service[0]='g';
+ service[1]='e';
+ service[2]='t';
+ service[3]='p';
+ service[4]='r';
+ service[5]='o';
+ service[6]='p';
+ service[7]='l';
+ service[8]='e';
+ service[9]='n';
+ service[10]='\0';
+
+ args[0] = (unsigned int)service;
+ args[1] = 2;
+ args[2] = 1;
+ args[3] = (unsigned int)handle;
+ args[4] = (unsigned int)prop;
+
+ if (openfirmware(args) == -1)
+ return -1;
+ return args[5];
+}
+
+int
+OF_getprop(ofw_handle_t openfirmware, int handle, char *prop, void *buf, unsigned int buflen)
+{
+ unsigned int args[8];
+ char service[8];
+
+ service[0]='g';
+ service[1]='e';
+ service[2]='t';
+ service[3]='p';
+ service[4]='r';
+ service[5]='o';
+ service[6]='p';
+ service[7]='\0';
+
+ args[0] = (unsigned int)service;
+ args[1] = 4;
+ args[2] = 1;
+ args[3] = (unsigned int)handle;
+ args[4] = (unsigned int)prop;
+ args[5] = (unsigned int)buf;
+ args[6] = buflen;
+
+ if (openfirmware(args) == -1)
+ return -1;
+ return args[7];
+}
+
+asmlinkage void ofw_init(ofw_handle_t o, int *nomr, int *pointer)
+{
+ int phandle,i,mem_len,buffer[32];
+ char temp[15];
+
+ temp[0]='/';
+ temp[1]='m';
+ temp[2]='e';
+ temp[3]='m';
+ temp[4]='o';
+ temp[5]='r';
+ temp[6]='y';
+ temp[7]='\0';
+
+ phandle=OF_finddevice(o,temp);
+
+ temp[0]='r';
+ temp[1]='e';
+ temp[2]='g';
+ temp[3]='\0';
+
+ mem_len = OF_getproplen(o,phandle, temp);
+ OF_getprop(o,phandle, temp, buffer, mem_len);
+ *nomr=mem_len >> 3;
+
+ for (i=0; i<=mem_len/4; i++) pointer[i]=of_decode_int((const unsigned char *)&buffer[i]);
+
+ temp[0]='/';
+ temp[1]='c';
+ temp[2]='h';
+ temp[3]='o';
+ temp[4]='s';
+ temp[5]='e';
+ temp[6]='n';
+ temp[7]='\0';
+
+ phandle=OF_finddevice(o,temp);
+
+ temp[0]='b';
+ temp[1]='o';
+ temp[2]='o';
+ temp[3]='t';
+ temp[4]='a';
+ temp[5]='r';
+ temp[6]='g';
+ temp[7]='s';
+ temp[8]='\0';
+
+ mem_len = OF_getproplen(o,phandle, temp);
+ OF_getprop(o,phandle, temp, buffer, mem_len);
+ if (mem_len > 128) mem_len=128;
+ for (i=0; i<=mem_len/4; i++) pointer[i+33]=buffer[i];
+ pointer[i+33]=0;
+
+ temp[0]='/';
+ temp[1]='\0';
+ phandle=OF_finddevice(o,temp);
+ temp[0]='b';
+ temp[1]='a';
+ temp[2]='n';
+ temp[3]='n';
+ temp[4]='e';
+ temp[5]='r';
+ temp[6]='-';
+ temp[7]='n';
+ temp[8]='a';
+ temp[9]='m';
+ temp[10]='e';
+ temp[11]='\0';
+ mem_len = OF_getproplen(o,phandle, temp);
+ OF_getprop(o,phandle, temp, buffer, mem_len);
+ * ((unsigned char *) &pointer[32]) = ((unsigned char *) buffer)[mem_len-2];
+}
diff --git a/arch/arm/boot/compressed/piggy.gzip.S b/arch/arm/boot/compressed/piggy.gzip.S
new file mode 100644
index 00000000000..a68adf91a16
--- /dev/null
+++ b/arch/arm/boot/compressed/piggy.gzip.S
@@ -0,0 +1,6 @@
+ .section .piggydata,#alloc
+ .globl input_data
+input_data:
+ .incbin "arch/arm/boot/compressed/piggy.gzip"
+ .globl input_data_end
+input_data_end:
diff --git a/arch/arm/boot/compressed/piggy.lzma.S b/arch/arm/boot/compressed/piggy.lzma.S
new file mode 100644
index 00000000000..d7e69cffbc0
--- /dev/null
+++ b/arch/arm/boot/compressed/piggy.lzma.S
@@ -0,0 +1,6 @@
+ .section .piggydata,#alloc
+ .globl input_data
+input_data:
+ .incbin "arch/arm/boot/compressed/piggy.lzma"
+ .globl input_data_end
+input_data_end:
diff --git a/arch/arm/boot/compressed/piggy.lzo.S b/arch/arm/boot/compressed/piggy.lzo.S
new file mode 100644
index 00000000000..a425ad95959
--- /dev/null
+++ b/arch/arm/boot/compressed/piggy.lzo.S
@@ -0,0 +1,6 @@
+ .section .piggydata,#alloc
+ .globl input_data
+input_data:
+ .incbin "arch/arm/boot/compressed/piggy.lzo"
+ .globl input_data_end
+input_data_end:
diff --git a/arch/arm/boot/compressed/sdhi-sh7372.c b/arch/arm/boot/compressed/sdhi-sh7372.c
new file mode 100644
index 00000000000..d279294f238
--- /dev/null
+++ b/arch/arm/boot/compressed/sdhi-sh7372.c
@@ -0,0 +1,95 @@
+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <mach/mmc.h>
+#include <linux/mmc/boot.h>
+#include <linux/mmc/tmio.h>
+
+#include "sdhi-shmobile.h"
+
+#define PORT179CR 0xe60520b3
+#define PORT180CR 0xe60520b4
+#define PORT181CR 0xe60520b5
+#define PORT182CR 0xe60520b6
+#define PORT183CR 0xe60520b7
+#define PORT184CR 0xe60520b8
+
+#define SMSTPCR3 0xe615013c
+
+#define CR_INPUT_ENABLE 0x10
+#define CR_FUNCTION1 0x01
+
+#define SDHI1_BASE (void __iomem *)0xe6860000
+#define SDHI_BASE SDHI1_BASE
+
+/* SuperH Mobile SDHI loader
+ *
+ * loads the zImage from an SD card starting from block 0
+ * on physical partition 1
+ *
+ * The image must be start with a vrl4 header and
+ * the zImage must start at offset 512 of the image. That is,
+ * at block 1 (=byte 512) of physical partition 1
+ *
+ * Use the following line to write the vrl4 formated zImage
+ * to an SD card
+ * # dd if=vrl4.out of=/dev/sdx bs=512
+ */
+asmlinkage void mmc_loader(unsigned short *buf, unsigned long len)
+{
+ int high_capacity;
+
+ mmc_init_progress();
+
+ mmc_update_progress(MMC_PROGRESS_ENTER);
+ /* Initialise SDHI1 */
+ /* PORT184CR: GPIO_FN_SDHICMD1 Control */
+ __raw_writeb(CR_FUNCTION1, PORT184CR);
+ /* PORT179CR: GPIO_FN_SDHICLK1 Control */
+ __raw_writeb(CR_INPUT_ENABLE|CR_FUNCTION1, PORT179CR);
+ /* PORT181CR: GPIO_FN_SDHID1_3 Control */
+ __raw_writeb(CR_FUNCTION1, PORT183CR);
+ /* PORT182CR: GPIO_FN_SDHID1_2 Control */
+ __raw_writeb(CR_FUNCTION1, PORT182CR);
+ /* PORT183CR: GPIO_FN_SDHID1_1 Control */
+ __raw_writeb(CR_FUNCTION1, PORT181CR);
+ /* PORT180CR: GPIO_FN_SDHID1_0 Control */
+ __raw_writeb(CR_FUNCTION1, PORT180CR);
+
+ /* Enable clock to SDHI1 hardware block */
+ __raw_writel(__raw_readl(SMSTPCR3) & ~(1 << 13), SMSTPCR3);
+
+ /* setup SDHI hardware */
+ mmc_update_progress(MMC_PROGRESS_INIT);
+ high_capacity = sdhi_boot_init(SDHI_BASE);
+ if (high_capacity < 0)
+ goto err;
+
+ mmc_update_progress(MMC_PROGRESS_LOAD);
+ /* load kernel */
+ if (sdhi_boot_do_read(SDHI_BASE, high_capacity,
+ 0, /* Kernel is at block 1 */
+ (len + TMIO_BBS - 1) / TMIO_BBS, buf))
+ goto err;
+
+ /* Disable clock to SDHI1 hardware block */
+ __raw_writel(__raw_readl(SMSTPCR3) | (1 << 13), SMSTPCR3);
+
+ mmc_update_progress(MMC_PROGRESS_DONE);
+
+ return;
+err:
+ for(;;);
+}
diff --git a/arch/arm/boot/compressed/sdhi-shmobile.c b/arch/arm/boot/compressed/sdhi-shmobile.c
new file mode 100644
index 00000000000..bd3d4698095
--- /dev/null
+++ b/arch/arm/boot/compressed/sdhi-shmobile.c
@@ -0,0 +1,449 @@
+/*
+ * SuperH Mobile SDHI
+ *
+ * Copyright (C) 2010 Magnus Damm
+ * Copyright (C) 2010 Kuninori Morimoto
+ * Copyright (C) 2010 Simon Horman
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Parts inspired by u-boot
+ */
+
+#include <linux/io.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+#include <linux/mmc/tmio.h>
+#include <mach/sdhi.h>
+
+#define OCR_FASTBOOT (1<<29)
+#define OCR_HCS (1<<30)
+#define OCR_BUSY (1<<31)
+
+#define RESP_CMD12 0x00000030
+
+static inline u16 sd_ctrl_read16(void __iomem *base, int addr)
+{
+ return __raw_readw(base + addr);
+}
+
+static inline u32 sd_ctrl_read32(void __iomem *base, int addr)
+{
+ return __raw_readw(base + addr) |
+ __raw_readw(base + addr + 2) << 16;
+}
+
+static inline void sd_ctrl_write16(void __iomem *base, int addr, u16 val)
+{
+ __raw_writew(val, base + addr);
+}
+
+static inline void sd_ctrl_write32(void __iomem *base, int addr, u32 val)
+{
+ __raw_writew(val, base + addr);
+ __raw_writew(val >> 16, base + addr + 2);
+}
+
+#define ALL_ERROR (TMIO_STAT_CMD_IDX_ERR | TMIO_STAT_CRCFAIL | \
+ TMIO_STAT_STOPBIT_ERR | TMIO_STAT_DATATIMEOUT | \
+ TMIO_STAT_RXOVERFLOW | TMIO_STAT_TXUNDERRUN | \
+ TMIO_STAT_CMDTIMEOUT | TMIO_STAT_ILL_ACCESS | \
+ TMIO_STAT_ILL_FUNC)
+
+static int sdhi_intr(void __iomem *base)
+{
+ unsigned long state = sd_ctrl_read32(base, CTL_STATUS);
+
+ if (state & ALL_ERROR) {
+ sd_ctrl_write32(base, CTL_STATUS, ~ALL_ERROR);
+ sd_ctrl_write32(base, CTL_IRQ_MASK,
+ ALL_ERROR |
+ sd_ctrl_read32(base, CTL_IRQ_MASK));
+ return -EINVAL;
+ }
+ if (state & TMIO_STAT_CMDRESPEND) {
+ sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+ sd_ctrl_write32(base, CTL_IRQ_MASK,
+ TMIO_STAT_CMDRESPEND |
+ sd_ctrl_read32(base, CTL_IRQ_MASK));
+ return 0;
+ }
+ if (state & TMIO_STAT_RXRDY) {
+ sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_RXRDY);
+ sd_ctrl_write32(base, CTL_IRQ_MASK,
+ TMIO_STAT_RXRDY | TMIO_STAT_TXUNDERRUN |
+ sd_ctrl_read32(base, CTL_IRQ_MASK));
+ return 0;
+ }
+ if (state & TMIO_STAT_DATAEND) {
+ sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_DATAEND);
+ sd_ctrl_write32(base, CTL_IRQ_MASK,
+ TMIO_STAT_DATAEND |
+ sd_ctrl_read32(base, CTL_IRQ_MASK));
+ return 0;
+ }
+
+ return -EAGAIN;
+}
+
+static int sdhi_boot_wait_resp_end(void __iomem *base)
+{
+ int err = -EAGAIN, timeout = 10000000;
+
+ while (timeout--) {
+ err = sdhi_intr(base);
+ if (err != -EAGAIN)
+ break;
+ udelay(1);
+ }
+
+ return err;
+}
+
+/* SDHI_CLK_CTRL */
+#define CLK_MMC_ENABLE (1 << 8)
+#define CLK_MMC_INIT (1 << 6) /* clk / 256 */
+
+static void sdhi_boot_mmc_clk_stop(void __iomem *base)
+{
+ sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, 0x0000);
+ msleep(10);
+ sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, ~CLK_MMC_ENABLE &
+ sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+ msleep(10);
+}
+
+static void sdhi_boot_mmc_clk_start(void __iomem *base)
+{
+ sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL, CLK_MMC_ENABLE |
+ sd_ctrl_read16(base, CTL_SD_CARD_CLK_CTL));
+ msleep(10);
+ sd_ctrl_write16(base, CTL_CLK_AND_WAIT_CTL, CLK_MMC_ENABLE);
+ msleep(10);
+}
+
+static void sdhi_boot_reset(void __iomem *base)
+{
+ sd_ctrl_write16(base, CTL_RESET_SD, 0x0000);
+ msleep(10);
+ sd_ctrl_write16(base, CTL_RESET_SD, 0x0001);
+ msleep(10);
+}
+
+/* Set MMC clock / power.
+ * Note: This controller uses a simple divider scheme therefore it cannot
+ * run a MMC card at full speed (20MHz). The max clock is 24MHz on SD, but as
+ * MMC wont run that fast, it has to be clocked at 12MHz which is the next
+ * slowest setting.
+ */
+static int sdhi_boot_mmc_set_ios(void __iomem *base, struct mmc_ios *ios)
+{
+ if (sd_ctrl_read32(base, CTL_STATUS) & TMIO_STAT_CMD_BUSY)
+ return -EBUSY;
+
+ if (ios->clock)
+ sd_ctrl_write16(base, CTL_SD_CARD_CLK_CTL,
+ ios->clock | CLK_MMC_ENABLE);
+
+ /* Power sequence - OFF -> ON -> UP */
+ switch (ios->power_mode) {
+ case MMC_POWER_OFF: /* power down SD bus */
+ sdhi_boot_mmc_clk_stop(base);
+ break;
+ case MMC_POWER_ON: /* power up SD bus */
+ break;
+ case MMC_POWER_UP: /* start bus clock */
+ sdhi_boot_mmc_clk_start(base);
+ break;
+ }
+
+ switch (ios->bus_width) {
+ case MMC_BUS_WIDTH_1:
+ sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x80e0);
+ break;
+ case MMC_BUS_WIDTH_4:
+ sd_ctrl_write16(base, CTL_SD_MEM_CARD_OPT, 0x00e0);
+ break;
+ }
+
+ /* Let things settle. delay taken from winCE driver */
+ udelay(140);
+
+ return 0;
+}
+
+/* These are the bitmasks the tmio chip requires to implement the MMC response
+ * types. Note that R1 and R6 are the same in this scheme. */
+#define RESP_NONE 0x0300
+#define RESP_R1 0x0400
+#define RESP_R1B 0x0500
+#define RESP_R2 0x0600
+#define RESP_R3 0x0700
+#define DATA_PRESENT 0x0800
+#define TRANSFER_READ 0x1000
+
+static int sdhi_boot_request(void __iomem *base, struct mmc_command *cmd)
+{
+ int err, c = cmd->opcode;
+
+ switch (mmc_resp_type(cmd)) {
+ case MMC_RSP_NONE: c |= RESP_NONE; break;
+ case MMC_RSP_R1: c |= RESP_R1; break;
+ case MMC_RSP_R1B: c |= RESP_R1B; break;
+ case MMC_RSP_R2: c |= RESP_R2; break;
+ case MMC_RSP_R3: c |= RESP_R3; break;
+ default:
+ return -EINVAL;
+ }
+
+ /* No interrupts so this may not be cleared */
+ sd_ctrl_write32(base, CTL_STATUS, ~TMIO_STAT_CMDRESPEND);
+
+ sd_ctrl_write32(base, CTL_IRQ_MASK, TMIO_STAT_CMDRESPEND |
+ sd_ctrl_read32(base, CTL_IRQ_MASK));
+ sd_ctrl_write32(base, CTL_ARG_REG, cmd->arg);
+ sd_ctrl_write16(base, CTL_SD_CMD, c);
+
+
+ sd_ctrl_write32(base, CTL_IRQ_MASK,
+ ~(TMIO_STAT_CMDRESPEND | ALL_ERROR) &
+ sd_ctrl_read32(base, CTL_IRQ_MASK));
+
+ err = sdhi_boot_wait_resp_end(base);
+ if (err)
+ return err;
+
+ cmd->resp[0] = sd_ctrl_read32(base, CTL_RESPONSE);
+
+ return 0;
+}
+
+static int sdhi_boot_do_read_single(void __iomem *base, int high_capacity,
+ unsigned long block, unsigned short *buf)
+{
+ int err, i;
+
+ /* CMD17 - Read */
+ {
+ struct mmc_command cmd;
+
+ cmd.opcode = MMC_READ_SINGLE_BLOCK | \
+ TRANSFER_READ | DATA_PRESENT;
+ if (high_capacity)
+ cmd.arg = block;
+ else
+ cmd.arg = block * TMIO_BBS;
+ cmd.flags = MMC_RSP_R1;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+ }
+
+ sd_ctrl_write32(base, CTL_IRQ_MASK,
+ ~(TMIO_STAT_DATAEND | TMIO_STAT_RXRDY |
+ TMIO_STAT_TXUNDERRUN) &
+ sd_ctrl_read32(base, CTL_IRQ_MASK));
+ err = sdhi_boot_wait_resp_end(base);
+ if (err)
+ return err;
+
+ sd_ctrl_write16(base, CTL_SD_XFER_LEN, TMIO_BBS);
+ for (i = 0; i < TMIO_BBS / sizeof(*buf); i++)
+ *buf++ = sd_ctrl_read16(base, RESP_CMD12);
+
+ err = sdhi_boot_wait_resp_end(base);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+ unsigned long offset, unsigned short count,
+ unsigned short *buf)
+{
+ unsigned long i;
+ int err = 0;
+
+ for (i = 0; i < count; i++) {
+ err = sdhi_boot_do_read_single(base, high_capacity, offset + i,
+ buf + (i * TMIO_BBS /
+ sizeof(*buf)));
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+#define VOLTAGES (MMC_VDD_32_33 | MMC_VDD_33_34)
+
+int sdhi_boot_init(void __iomem *base)
+{
+ bool sd_v2 = false, sd_v1_0 = false;
+ unsigned short cid;
+ int err, high_capacity = 0;
+
+ sdhi_boot_mmc_clk_stop(base);
+ sdhi_boot_reset(base);
+
+ /* mmc0: clock 400000Hz busmode 1 powermode 2 cs 0 Vdd 21 width 0 timing 0 */
+ {
+ struct mmc_ios ios;
+ ios.power_mode = MMC_POWER_ON;
+ ios.bus_width = MMC_BUS_WIDTH_1;
+ ios.clock = CLK_MMC_INIT;
+ err = sdhi_boot_mmc_set_ios(base, &ios);
+ if (err)
+ return err;
+ }
+
+ /* CMD0 */
+ {
+ struct mmc_command cmd;
+ msleep(1);
+ cmd.opcode = MMC_GO_IDLE_STATE;
+ cmd.arg = 0;
+ cmd.flags = MMC_RSP_NONE;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+ msleep(2);
+ }
+
+ /* CMD8 - Test for SD version 2 */
+ {
+ struct mmc_command cmd;
+ cmd.opcode = SD_SEND_IF_COND;
+ cmd.arg = (VOLTAGES != 0) << 8 | 0xaa;
+ cmd.flags = MMC_RSP_R1;
+ err = sdhi_boot_request(base, &cmd); /* Ignore error */
+ if ((cmd.resp[0] & 0xff) == 0xaa)
+ sd_v2 = true;
+ }
+
+ /* CMD55 - Get OCR (SD) */
+ {
+ int timeout = 1000;
+ struct mmc_command cmd;
+
+ cmd.arg = 0;
+
+ do {
+ cmd.opcode = MMC_APP_CMD;
+ cmd.flags = MMC_RSP_R1;
+ cmd.arg = 0;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ break;
+
+ cmd.opcode = SD_APP_OP_COND;
+ cmd.flags = MMC_RSP_R3;
+ cmd.arg = (VOLTAGES & 0xff8000);
+ if (sd_v2)
+ cmd.arg |= OCR_HCS;
+ cmd.arg |= OCR_FASTBOOT;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ break;
+
+ msleep(1);
+ } while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+ if (!err && timeout) {
+ if (!sd_v2)
+ sd_v1_0 = true;
+ high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+ }
+ }
+
+ /* CMD1 - Get OCR (MMC) */
+ if (!sd_v2 && !sd_v1_0) {
+ int timeout = 1000;
+ struct mmc_command cmd;
+
+ do {
+ cmd.opcode = MMC_SEND_OP_COND;
+ cmd.arg = VOLTAGES | OCR_HCS;
+ cmd.flags = MMC_RSP_R3;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+
+ msleep(1);
+ } while((!(cmd.resp[0] & OCR_BUSY)) && --timeout);
+
+ if (!timeout)
+ return -EAGAIN;
+
+ high_capacity = (cmd.resp[0] & OCR_HCS) == OCR_HCS;
+ }
+
+ /* CMD2 - Get CID */
+ {
+ struct mmc_command cmd;
+ cmd.opcode = MMC_ALL_SEND_CID;
+ cmd.arg = 0;
+ cmd.flags = MMC_RSP_R2;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+ }
+
+ /* CMD3
+ * MMC: Set the relative address
+ * SD: Get the relative address
+ * Also puts the card into the standby state
+ */
+ {
+ struct mmc_command cmd;
+ cmd.opcode = MMC_SET_RELATIVE_ADDR;
+ cmd.arg = 0;
+ cmd.flags = MMC_RSP_R1;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+ cid = cmd.resp[0] >> 16;
+ }
+
+ /* CMD9 - Get CSD */
+ {
+ struct mmc_command cmd;
+ cmd.opcode = MMC_SEND_CSD;
+ cmd.arg = cid << 16;
+ cmd.flags = MMC_RSP_R2;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+ }
+
+ /* CMD7 - Select the card */
+ {
+ struct mmc_command cmd;
+ cmd.opcode = MMC_SELECT_CARD;
+ //cmd.arg = rca << 16;
+ cmd.arg = cid << 16;
+ //cmd.flags = MMC_RSP_R1B;
+ cmd.flags = MMC_RSP_R1;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+ }
+
+ /* CMD16 - Set the block size */
+ {
+ struct mmc_command cmd;
+ cmd.opcode = MMC_SET_BLOCKLEN;
+ cmd.arg = TMIO_BBS;
+ cmd.flags = MMC_RSP_R1;
+ err = sdhi_boot_request(base, &cmd);
+ if (err)
+ return err;
+ }
+
+ return high_capacity;
+}
diff --git a/arch/arm/boot/compressed/sdhi-shmobile.h b/arch/arm/boot/compressed/sdhi-shmobile.h
new file mode 100644
index 00000000000..92eaa09f985
--- /dev/null
+++ b/arch/arm/boot/compressed/sdhi-shmobile.h
@@ -0,0 +1,11 @@
+#ifndef SDHI_MOBILE_H
+#define SDHI_MOBILE_H
+
+#include <linux/compiler.h>
+
+int sdhi_boot_do_read(void __iomem *base, int high_capacity,
+ unsigned long offset, unsigned short count,
+ unsigned short *buf);
+int sdhi_boot_init(void __iomem *base);
+
+#endif
diff --git a/arch/arm/boot/compressed/string.c b/arch/arm/boot/compressed/string.c
new file mode 100644
index 00000000000..36e53ef9200
--- /dev/null
+++ b/arch/arm/boot/compressed/string.c
@@ -0,0 +1,127 @@
+/*
+ * arch/arm/boot/compressed/string.c
+ *
+ * Small subset of simple string routines
+ */
+
+#include <linux/string.h>
+
+void *memcpy(void *__dest, __const void *__src, size_t __n)
+{
+ int i = 0;
+ unsigned char *d = (unsigned char *)__dest, *s = (unsigned char *)__src;
+
+ for (i = __n >> 3; i > 0; i--) {
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ }
+
+ if (__n & 1 << 2) {
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ *d++ = *s++;
+ }
+
+ if (__n & 1 << 1) {
+ *d++ = *s++;
+ *d++ = *s++;
+ }
+
+ if (__n & 1)
+ *d++ = *s++;
+
+ return __dest;
+}
+
+void *memmove(void *__dest, __const void *__src, size_t count)
+{
+ unsigned char *d = __dest;
+ const unsigned char *s = __src;
+
+ if (__dest == __src)
+ return __dest;
+
+ if (__dest < __src)
+ return memcpy(__dest, __src, count);
+
+ while (count--)
+ d[count] = s[count];
+ return __dest;
+}
+
+size_t strlen(const char *s)
+{
+ const char *sc = s;
+
+ while (*sc != '\0')
+ sc++;
+ return sc - s;
+}
+
+int memcmp(const void *cs, const void *ct, size_t count)
+{
+ const unsigned char *su1 = cs, *su2 = ct, *end = su1 + count;
+ int res = 0;
+
+ while (su1 < end) {
+ res = *su1++ - *su2++;
+ if (res)
+ break;
+ }
+ return res;
+}
+
+int strcmp(const char *cs, const char *ct)
+{
+ unsigned char c1, c2;
+ int res = 0;
+
+ do {
+ c1 = *cs++;
+ c2 = *ct++;
+ res = c1 - c2;
+ if (res)
+ break;
+ } while (c1);
+ return res;
+}
+
+void *memchr(const void *s, int c, size_t count)
+{
+ const unsigned char *p = s;
+
+ while (count--)
+ if ((unsigned char)c == *p++)
+ return (void *)(p - 1);
+ return NULL;
+}
+
+char *strchr(const char *s, int c)
+{
+ while (*s != (char)c)
+ if (*s++ == '\0')
+ return NULL;
+ return (char *)s;
+}
+
+#undef memset
+
+void *memset(void *s, int c, size_t count)
+{
+ char *xs = s;
+ while (count--)
+ *xs++ = c;
+ return s;
+}
+
+void __memzero(void *s, size_t count)
+{
+ memset(s, 0, count);
+}
diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in
new file mode 100644
index 00000000000..4919f2ac8b8
--- /dev/null
+++ b/arch/arm/boot/compressed/vmlinux.lds.in
@@ -0,0 +1,76 @@
+/*
+ * linux/arch/arm/boot/compressed/vmlinux.lds.in
+ *
+ * Copyright (C) 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.
+ */
+OUTPUT_ARCH(arm)
+ENTRY(_start)
+SECTIONS
+{
+ /DISCARD/ : {
+ *(.ARM.exidx*)
+ *(.ARM.extab*)
+ /*
+ * Discard any r/w data - this produces a link error if we have any,
+ * which is required for PIC decompression. Local data generates
+ * GOTOFF relocations, which prevents it being relocated independently
+ * of the text/got segments.
+ */
+ *(.data)
+ }
+
+ . = TEXT_START;
+ _text = .;
+
+ .text : {
+ _start = .;
+ *(.start)
+ *(.text)
+ *(.text.*)
+ *(.fixup)
+ *(.gnu.warning)
+ *(.glue_7t)
+ *(.glue_7)
+ }
+ .rodata : {
+ *(.rodata)
+ *(.rodata.*)
+ }
+ .piggydata : {
+ *(.piggydata)
+ }
+
+ . = ALIGN(4);
+ _etext = .;
+
+ .got.plt : { *(.got.plt) }
+ _got_start = .;
+ .got : { *(.got) }
+ _got_end = .;
+
+ /* ensure the zImage file size is always a multiple of 64 bits */
+ /* (without a dummy byte, ld just ignores the empty section) */
+ .pad : { BYTE(0); . = ALIGN(8); }
+ _edata = .;
+
+ . = BSS_START;
+ __bss_start = .;
+ .bss : { *(.bss) }
+ _end = .;
+
+ . = ALIGN(8); /* the stack must be 64-bit aligned */
+ .stack : { *(.stack) }
+
+ .stab 0 : { *(.stab) }
+ .stabstr 0 : { *(.stabstr) }
+ .stab.excl 0 : { *(.stab.excl) }
+ .stab.exclstr 0 : { *(.stab.exclstr) }
+ .stab.index 0 : { *(.stab.index) }
+ .stab.indexstr 0 : { *(.stab.indexstr) }
+ .comment 0 : { *(.comment) }
+}
+