diff --git a/arch/ppc64/boot/Makefile b/arch/ppc64/boot/Makefile
index ac1f5a109a8a3ee57e5ce00f2b571065dbf931b7..8024fa77ca78b7c2a4eb7ef85e8796ea6fa14f17 100644
--- a/arch/ppc64/boot/Makefile
+++ b/arch/ppc64/boot/Makefile
@@ -24,35 +24,45 @@ CROSS32_COMPILE =
 #CROSS32_COMPILE = /usr/local/ppc/bin/powerpc-linux-
 
 BOOTCC		:= $(CROSS32_COMPILE)gcc
-BOOTCFLAGS	:= $(HOSTCFLAGS) -Iinclude
-BOOTLD		:= $(CROSS32_COMPILE)ld
+HOSTCC		:= gcc
+BOOTCFLAGS	:= $(HOSTCFLAGS) -Iinclude -fno-builtin 
 BOOTAS		:= $(CROSS32_COMPILE)as
-BOOTAFLAGS	:= -D__ASSEMBLY__ $(HOSTCFLAGS)
-
-CFLAGS		:= $(CPPFLAGS) -O -fno-builtin -DSTDC_HEADERS
-LD_ARGS		:= -Ttext 0x00400000 -e _start
-OBJCOPYFLAGS	:= -S -O binary
+BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional
+BOOTLD		:= $(CROSS32_COMPILE)ld
+BOOTLFLAGS	:= -Ttext 0x00400000 -e _start -T $(obj)/zImage.lds
+BOOTOBJCOPY	:= $(CROSS32_COMPILE)objcopy
+OBJCOPYFLAGS    := contents,alloc,load,readonly,data
 
-obj-boot := start.o main.o zlib.o imagesize.o no_initrd.o
-OBJS     := crt0.o start.o main.o zlib.o imagesize.o image.o
-obj-boot := $(addprefix $(obj)/,$(obj-boot))
-OBJS     := $(addprefix $(obj)/,$(OBJS))
-targets  += $(obj-boot) $(addprefix $(obj)/,image.c image.o)
+src-boot := crt0.S string.S prom.c main.c zlib.c imagesize.c
+src-boot := $(addprefix $(obj)/, $(src-boot))
+obj-boot := $(addsuffix .o, $(basename $(src-boot)))
 
 quiet_cmd_bootcc = BOOTCC  $@
       cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
-$(obj-boot): %.o: %.c FORCE
-	$(call if_changed_dep,bootcc)
 
 quiet_cmd_bootas = BOOTAS  $@
-      cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -traditional \
-						-c -o $@ $<
-$(obj)/crt0.o: %.o: %.S FORCE
+      cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
+
+$(patsubst %.c,%.o, $(filter %.c, $(src-boot))): %.o: %.c
+	$(call if_changed_dep,bootcc)
+$(patsubst %.S,%.o, $(filter %.S, $(src-boot))): %.o: %.S
 	$(call if_changed_dep,bootas)
 
-host-progs		:= piggyback addnote addSystemMap addRamDisk
-HOSTCFLAGS_piggyback.o	:= -DKERNELBASE=$(KERNELBASE)
-EXTRA_TARGETS 		+= zImage zImage.initrd vmlinux.bin vmlinux.gz \
+#-----------------------------------------------------------
+# ELF sections within the zImage bootloader/wrapper
+#-----------------------------------------------------------
+required := vmlinux .config System.map
+initrd   := initrd
+
+obj-sec = $(foreach section, $(1), $(patsubst %,$(obj)/kernel-%.o, $(section)))
+src-sec = $(foreach section, $(1), $(patsubst %,$(obj)/kernel-%.c, $(section)))
+gz-sec  = $(foreach section, $(1), $(patsubst %,$(obj)/kernel-%.gz, $(section)))
+
+host-progs		:= piggy addnote addSystemMap addRamDisk
+EXTRA_TARGETS 		+= zImage zImage.initrd imagesize.c \
+			   $(patsubst $(obj)/%,%, $(call obj-sec, $(required) $(initrd))) \
+			   $(patsubst $(obj)/%,%, $(call src-sec, $(required) $(initrd))) \
+			   $(patsubst $(obj)/%,%, $(call gz-sec, $(required) $(initrd))) \
 			   vmlinux.sm vmlinux.initrd vmlinux.sminitrd \
 			   sysmap.o initrd.o
 
@@ -69,42 +79,48 @@ $(obj)/vmlinux.initrd: vmlinux $(obj)/addRamDisk $(obj)/ramdisk.image.gz System.
 $(obj)/vmlinux.sminitrd: $(obj)/vmlinux.sm $(obj)/addRamDisk $(obj)/ramdisk.image.gz FORCE
 	$(call if_changed,ramdisk)
 
+$(obj)/sysmap.o: System.map $(obj)/piggyback
+	$(call if_changed,piggy)
+
+addsection = $(BOOTOBJCOPY) $(1) \
+		--add-section=.kernel:$(strip $(patsubst $(obj)/kernel-%.o,%, $(1)))=$(patsubst %.o,%.gz, $(1)) \
+		--set-section-flags=.kernel:$(strip $(patsubst $(obj)/kernel-%.o,%, $(1)))=$(OBJCOPYFLAGS)
+
+quiet_cmd_addnote = ADDNOTE $@ 
+      cmd_addnote = $(BOOTLD) $(BOOTLFLAGS) -o $@ $(obj-boot) && $(obj)/addnote $@
 
 quiet_cmd_piggy = PIGGY   $@
       cmd_piggy = $(obj)/piggyback $(@:.o=) < $< | $(BOOTAS) -o $@
 
-$(obj)/image.o: $(obj)/vmlinux.gz $(obj)/piggyback FORCE
-	$(call if_changed,piggy)
+$(call gz-sec, $(required)): $(obj)/kernel-%.gz: %
+	$(call if_changed,gzip)
 
-$(obj)/sysmap.o: System.map $(obj)/piggyback FORCE
-	$(call if_changed,piggy)
+$(obj)/kernel-initrd.gz: $(obj)/ramdisk.image.gz
+	cp -f $(obj)/ramdisk.image.gz $@
 
-$(obj)/initrd.o: $(obj)/ramdisk.image.gz $(obj)/piggyback FORCE
-	$(call if_changed,piggy)
+$(call src-sec, $(required) $(initrd)): $(obj)/kernel-%.c: $(obj)/kernel-%.gz
+	touch $@
 
-quiet_cmd_addnote = ADDNOTE $@ 
-      cmd_addnote = $(BOOTLD) $(LD_ARGS) -T $(obj)/zImage.lds -o $@ $(OBJS) $<\
-		    && $(obj)/addnote $@
+$(call obj-sec, $(required) $(initrd)): $(obj)/kernel-%.o: $(obj)/kernel-%.c
+	$(call if_changed_dep,bootcc)
+	$(call addsection, $@)
 
-$(obj)/zImage: $(obj)/no_initrd.o $(OBJS) $(obj)/addnote FORCE
+$(obj)/zImage: obj-boot += $(call obj-sec, $(required))
+$(obj)/zImage: $(call obj-sec, $(required)) $(obj-boot) $(obj)/addnote FORCE
 	$(call if_changed,addnote)
 
-$(obj)/zImage.initrd: $(obj)/initrd.o $(OBJS) $(obj)/addnote FORCE
+$(obj)/zImage.initrd: obj-boot += $(call obj-sec, $(required) $(initrd))
+$(obj)/zImage.initrd: $(call obj-sec, $(required) $(initrd)) $(obj-boot) $(obj)/addnote FORCE
 	$(call if_changed,addnote)
 
-$(obj)/vmlinux.bin: vmlinux FORCE
-	$(call if_changed,objcopy)
-
-$(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE
-	$(call if_changed,gzip)
-
 $(obj)/imagesize.c: vmlinux
 	@echo Generating $@
 	ls -l vmlinux | \
 	awk '{printf "/* generated -- do not edit! */\n" \
-		"int uncompressed_size = %d;\n", $$5}' > $(obj)/imagesize.c
+		"unsigned long vmlinux_filesize = %d;\n", $$5}' > $(obj)/imagesize.c
 	$(CROSS_COMPILE)nm -n vmlinux | tail -1 | \
-	awk '{printf "long vmlinux_end = 0x%s;\n", substr($$1,8)}' \
+	awk '{printf "unsigned long vmlinux_memsize = 0x%s;\n", substr($$1,8)}' \
 		>> $(obj)/imagesize.c
 
-clean-files :=  $(targets)
+
+clean-files := $(patsubst $(obj)/%,%, $(obj-boot))
diff --git a/arch/ppc64/boot/README b/arch/ppc64/boot/README
new file mode 100644
index 0000000000000000000000000000000000000000..3e11058760e4b7b08a893b4a48a87969ebed29e8
--- /dev/null
+++ b/arch/ppc64/boot/README
@@ -0,0 +1,11 @@
+
+To extract the kernel vmlinux, System.map, .config or initrd from the zImage binary:
+
+objcopy -j .kernel:vmlinux -O binary zImage vmlinux.gz
+objcopy -j .kernel:System.map -O binary zImage System.map.gz
+objcopy -j .kernel:.config -O binary zImage config.gz
+objcopy -j .kernel:initrd -O binary zImage.initrd initrd.gz
+
+
+	Peter
+
diff --git a/arch/ppc64/boot/addRamDisk.c b/arch/ppc64/boot/addRamDisk.c
index 1309861241e9cb82f0b9d7654274eba9177105b1..f940d0f99177d86d3ad1f0c859d7e10782774827 100644
--- a/arch/ppc64/boot/addRamDisk.c
+++ b/arch/ppc64/boot/addRamDisk.c
@@ -25,7 +25,7 @@ void put4k(FILE *file, char *buf )
 
 void death(const char *msg, FILE *fdesc, const char *fname) 
 {
-	printf(msg);
+	fprintf(stderr, msg);
 	fclose(fdesc);
 	unlink(fname);
 	exit(1);
@@ -66,47 +66,47 @@ int main(int argc, char **argv)
   
   
 	if (argc < 2) {
-		printf("Name of RAM disk file missing.\n");
+		fprintf(stderr, "Name of RAM disk file missing.\n");
 		exit(1);
 	}
 
 	if (argc < 3) {
-		printf("Name of System Map input file is missing.\n");
+		fprintf(stderr, "Name of System Map input file is missing.\n");
 		exit(1);
 	}
   
 	if (argc < 4) {
-		printf("Name of vmlinux file missing.\n");
+		fprintf(stderr, "Name of vmlinux file missing.\n");
 		exit(1);
 	}
 
 	if (argc < 5) {
-		printf("Name of vmlinux output file missing.\n");
+		fprintf(stderr, "Name of vmlinux output file missing.\n");
 		exit(1);
 	}
 
 
 	ramDisk = fopen(argv[1], "r");
 	if ( ! ramDisk ) {
-		printf("RAM disk file \"%s\" failed to open.\n", argv[1]);
+		fprintf(stderr, "RAM disk file \"%s\" failed to open.\n", argv[1]);
 		exit(1);
 	}
 
 	sysmap = fopen(argv[2], "r");
 	if ( ! sysmap ) {
-		printf("System Map file \"%s\" failed to open.\n", argv[2]);
+		fprintf(stderr, "System Map file \"%s\" failed to open.\n", argv[2]);
 		exit(1);
 	}
   
 	inputVmlinux = fopen(argv[3], "r");
 	if ( ! inputVmlinux ) {
-		printf("vmlinux file \"%s\" failed to open.\n", argv[3]);
+		fprintf(stderr, "vmlinux file \"%s\" failed to open.\n", argv[3]);
 		exit(1);
 	}
   
 	outputVmlinux = fopen(argv[4], "w+");
 	if ( ! outputVmlinux ) {
-		printf("output vmlinux file \"%s\" failed to open.\n", argv[4]);
+		fprintf(stderr, "output vmlinux file \"%s\" failed to open.\n", argv[4]);
 		exit(1);
 	}
   
@@ -118,7 +118,7 @@ int main(int argc, char **argv)
 	fseek(inputVmlinux, 0, SEEK_SET);
 	printf("kernel file size = %d\n", kernelLen);
 	if ( kernelLen == 0 ) {
-		printf("You must have a linux kernel specified as argv[3]\n");
+		fprintf(stderr, "You must have a linux kernel specified as argv[3]\n");
 		exit(1);
 	}
 
@@ -154,15 +154,14 @@ int main(int argc, char **argv)
   
 	/* Process the Sysmap file to determine where _end is */
 	sysmapPages = sysmapLen / 4096;
-	for (i=0; i<sysmapPages; ++i) {
-		get4k(sysmap, inbuf);
-	}
+	/* read the whole file line by line, expect that it doesnt fail */
+	while ( fgets(inbuf, 4096, sysmap) )  ;
 	/* search for _end in the last page of the system map */
 	ptr_end = strstr(inbuf, " _end");
 	if (!ptr_end) {
-		printf("Unable to find _end in the sysmap file \n");
-		printf("inbuf: \n");
-		printf("%s \n", inbuf);
+		fprintf(stderr, "Unable to find _end in the sysmap file \n");
+		fprintf(stderr, "inbuf: \n");
+		fprintf(stderr, "%s \n", inbuf);
 		exit(1);
 	}
 	printf("Found _end in the last page of the sysmap - backing up 10 characters it looks like %s", ptr_end-10);
diff --git a/arch/ppc64/boot/addSystemMap.c b/arch/ppc64/boot/addSystemMap.c
index 394028458ad74e11c74da89ca26837252035e199..03b9187d0c0095b7afaf2664fe6d541064b619cb 100644
--- a/arch/ppc64/boot/addSystemMap.c
+++ b/arch/ppc64/boot/addSystemMap.c
@@ -64,38 +64,38 @@ int main(int argc, char **argv)
 	long padPages = 0;
 	if ( argc < 2 )
 	{
-		printf("Name of System Map file missing.\n");
+		fprintf(stderr, "Name of System Map file missing.\n");
 		exit(1);
 	}
 
 	if ( argc < 3 )
 	{
-		printf("Name of vmlinux file missing.\n");
+		fprintf(stderr, "Name of vmlinux file missing.\n");
 		exit(1);
 	}
 
 	if ( argc < 4 )
 	{
-		printf("Name of vmlinux output file missing.\n");
+		fprintf(stderr, "Name of vmlinux output file missing.\n");
 		exit(1);
 	}
 
 	sysmap = fopen(argv[1], "r");
 	if ( ! sysmap )
 	{
-		printf("System Map file \"%s\" failed to open.\n", argv[1]);
+		fprintf(stderr, "System Map file \"%s\" failed to open.\n", argv[1]);
 		exit(1);
 	}
 	inputVmlinux = fopen(argv[2], "r");
 	if ( ! inputVmlinux )
 	{
-		printf("vmlinux file \"%s\" failed to open.\n", argv[2]);
+		fprintf(stderr, "vmlinux file \"%s\" failed to open.\n", argv[2]);
 		exit(1);
 	}
 	outputVmlinux = fopen(argv[3], "w");
 	if ( ! outputVmlinux )
 	{
-		printf("output vmlinux file \"%s\" failed to open.\n", argv[3]);
+		fprintf(stderr, "output vmlinux file \"%s\" failed to open.\n", argv[3]);
 		exit(1);
 	}
 
@@ -107,7 +107,7 @@ int main(int argc, char **argv)
 	printf("kernel file size = %ld\n", kernelLen);
 	if ( kernelLen == 0 )
 	{
-		printf("You must have a linux kernel specified as argv[2]\n");
+		fprintf(stderr, "You must have a linux kernel specified as argv[2]\n");
 		exit(1);
 	}
 
@@ -146,17 +146,15 @@ int main(int argc, char **argv)
   /* Process the Sysmap file to determine the true end of the kernel */
 	sysmapPages = sysmapLen / 4096;
 	printf("System map pages to copy = %ld\n", sysmapPages);
-	for (i=0; i<sysmapPages; ++i)
-	{
-		get4k(sysmap, inbuf);
-	}
+	/* read the whole file line by line, expect that it doesnt fail */
+	while ( fgets(inbuf, 4096, sysmap) )  ;
 	/* search for _end in the last page of the system map */
 	ptr_end = strstr(inbuf, " _end");
 	if (!ptr_end)
 	{
-		printf("Unable to find _end in the sysmap file \n");
-		printf("inbuf: \n");
-		printf("%s \n", inbuf);
+		fprintf(stderr, "Unable to find _end in the sysmap file \n");
+		fprintf(stderr, "inbuf: \n");
+		fprintf(stderr, "%s \n", inbuf);
 		exit(1);
 	}
 	printf("Found _end in the last page of the sysmap - backing up 10 characters it looks like %s", ptr_end-10);
diff --git a/arch/ppc64/boot/crt0.S b/arch/ppc64/boot/crt0.S
index 00a76ab75708e5f9b63c95fa69044cd34881f06d..04d3e74cd72f7d53fd9fbbfe7378a6b2f5e62e2f 100644
--- a/arch/ppc64/boot/crt0.S
+++ b/arch/ppc64/boot/crt0.S
@@ -8,258 +8,41 @@
  *
  * NOTE: this code runs in 32 bit mode and is packaged as ELF32.
  */
+
+#include <asm/ppc_asm.h>
+
 	.text
 	.globl	_start
 _start:
-	lis	9,_start@h
-	lis	8,_etext@ha
-	addi	8,8,_etext@l
-1:	dcbf	0,9
-	icbi	0,9
-	addi	9,9,0x20
-	cmplwi	0,9,8
+	lis	r9,_start@h
+	lis	r8,_etext@ha
+	addi	r8,r8,_etext@l
+1:	dcbf	r0,r9
+	icbi	r0,r9
+	addi	r9,r9,0x20
+	cmplwi	0,r9,8
 	blt	1b
 	sync
 	isync
 
 	## Clear out the BSS as per ANSI C requirements
 
-	lis 7,_end@ha
-	addi    7,7,_end@l		# r7 = &_end 
-	lis 8,__bss_start@ha		# 
-	addi    8,8,__bss_start@l	# r8 = &_bss_start
+	lis	r7,_end@ha
+	addi    r7,r7,_end@l		# r7 = &_end 
+	lis	r8,__bss_start@ha	# 
+	addi    r8,r8,__bss_start@l	# r8 = &_bss_start
 
 	## Determine how large an area, in number of words, to clear
 
-	subf	7,8,7			# r7 = &_end - &_bss_start + 1 
-	addi	7,7,3			# r7 += 3 
-	srwi.	7,7,2			# r7 = size in words.
-	beq	3f			# If the size is zero, do not bother
-	addi	8,8,-4			# r8 -= 4 
-	mtctr	7			# SPRN_CTR = number of words to clear
-	li	0,0			# r0 = 0
-2:	stwu	0,4(8)			# Clear out a word
-	bdnz	2b			# If we are not done yet, keep clearing
+	subf	r7,r8,r7		# r7 = &_end - &_bss_start + 1 
+	addi	r7,r7,3			# r7 += 3 
+	srwi.	r7,r7,2			# r7 = size in words.
+	beq	3f			# If the size is zero, don't bother
+	addi	r8,r8,-4		# r8 -= 4 
+	mtctr	r7			# SPRN_CTR = number of words to clear
+	li	r0,0			# r0 = 0
+2:	stwu	r0,4(r8)		# Clear out a word
+	bdnz	2b			# Keep clearing until done
 3:
-
-
 	b	start
 
-
-
-/*
- * Flush the dcache and invalidate the icache for a range of addresses.
- *
- * flush_cache(addr, len)
- */
-	.global	flush_cache
-flush_cache:
-	addi	4,4,0x1f	/* len = (len + 0x1f) / 0x20 */
-	rlwinm.	4,4,27,5,31
-	mtctr	4
-	beqlr
-1:	dcbf	0,3
-	icbi	0,3
-	addi	3,3,0x20
-	bdnz	1b
-	sync
-	isync
-	blr
-
-
-#define r0	0
-#define r3	3
-#define r4	4
-#define r5	5
-#define r6	6
-#define r7	7
-#define r8	8
-
-	.globl	strcpy
-strcpy:
-	addi	r5,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r0,1(r4)
-	cmpwi	0,r0,0
-	stbu	r0,1(r5)
-	bne	1b
-	blr
-
-	.globl	strncpy
-strncpy:
-	cmpwi	0,r5,0
-	beqlr
-	mtctr	r5
-	addi	r6,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r0,1(r4)
-	cmpwi	0,r0,0
-	stbu	r0,1(r6)
-	bdnzf	2,1b		/* dec ctr, branch if ctr != 0 && !cr0.eq */
-	blr
-
-	.globl	strcat
-strcat:
-	addi	r5,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r0,1(r5)
-	cmpwi	0,r0,0
-	bne	1b
-	addi	r5,r5,-1
-1:	lbzu	r0,1(r4)
-	cmpwi	0,r0,0
-	stbu	r0,1(r5)
-	bne	1b
-	blr
-
-	.globl	strcmp
-strcmp:
-	addi	r5,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r3,1(r5)
-	cmpwi	1,r3,0
-	lbzu	r0,1(r4)
-	subf.	r3,r0,r3
-	beqlr	1
-	beq	1b
-	blr
-
-	.globl	strlen
-strlen:
-	addi	r4,r3,-1
-1:	lbzu	r0,1(r4)
-	cmpwi	0,r0,0
-	bne	1b
-	subf	r3,r3,r4
-	blr
-
-	.globl	memset
-memset:
-	rlwimi	r4,r4,8,16,23
-	rlwimi	r4,r4,16,0,15
-	addi	r6,r3,-4
-	cmplwi	0,r5,4
-	blt	7f
-	stwu	r4,4(r6)
-	beqlr
-	andi.	r0,r6,3
-	add	r5,r0,r5
-	subf	r6,r0,r6
-	rlwinm	r0,r5,32-2,2,31
-	mtctr	r0
-	bdz	6f
-1:	stwu	r4,4(r6)
-	bdnz	1b
-6:	andi.	r5,r5,3
-7:	cmpwi	0,r5,0
-	beqlr
-	mtctr	r5
-	addi	r6,r6,3
-8:	stbu	r4,1(r6)
-	bdnz	8b
-	blr
-
-	.globl	bcopy
-bcopy:
-	mr	r6,r3
-	mr	r3,r4
-	mr	r4,r6
-	b	memcpy
-
-	.globl	memmove
-memmove:
-	cmplw	0,r3,r4
-	bgt	backwards_memcpy
-	/* fall through */
-
-	.globl	memcpy
-memcpy:
-	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */
-	addi	r6,r3,-4
-	addi	r4,r4,-4
-	beq	2f			/* if less than 8 bytes to do */
-	andi.	r0,r6,3			/* get dest word aligned */
-	mtctr	r7
-	bne	5f
-1:	lwz	r7,4(r4)
-	lwzu	r8,8(r4)
-	stw	r7,4(r6)
-	stwu	r8,8(r6)
-	bdnz	1b
-	andi.	r5,r5,7
-2:	cmplwi	0,r5,4
-	blt	3f
-	lwzu	r0,4(r4)
-	addi	r5,r5,-4
-	stwu	r0,4(r6)
-3:	cmpwi	0,r5,0
-	beqlr
-	mtctr	r5
-	addi	r4,r4,3
-	addi	r6,r6,3
-4:	lbzu	r0,1(r4)
-	stbu	r0,1(r6)
-	bdnz	4b
-	blr
-5:	subfic	r0,r0,4
-	mtctr	r0
-6:	lbz	r7,4(r4)
-	addi	r4,r4,1
-	stb	r7,4(r6)
-	addi	r6,r6,1
-	bdnz	6b
-	subf	r5,r0,r5
-	rlwinm.	r7,r5,32-3,3,31
-	beq	2b
-	mtctr	r7
-	b	1b
-
-	.globl	backwards_memcpy
-backwards_memcpy:
-	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */
-	add	r6,r3,r5
-	add	r4,r4,r5
-	beq	2f
-	andi.	r0,r6,3
-	mtctr	r7
-	bne	5f
-1:	lwz	r7,-4(r4)
-	lwzu	r8,-8(r4)
-	stw	r7,-4(r6)
-	stwu	r8,-8(r6)
-	bdnz	1b
-	andi.	r5,r5,7
-2:	cmplwi	0,r5,4
-	blt	3f
-	lwzu	r0,-4(r4)
-	subi	r5,r5,4
-	stwu	r0,-4(r6)
-3:	cmpwi	0,r5,0
-	beqlr
-	mtctr	r5
-4:	lbzu	r0,-1(r4)
-	stbu	r0,-1(r6)
-	bdnz	4b
-	blr
-5:	mtctr	r0
-6:	lbzu	r7,-1(r4)
-	stbu	r7,-1(r6)
-	bdnz	6b
-	subf	r5,r0,r5
-	rlwinm.	r7,r5,32-3,3,31
-	beq	2b
-	mtctr	r7
-	b	1b
-
-	.globl	memcmp
-memcmp:
-	cmpwi	0,r5,0
-	blelr
-	mtctr	r5
-	addi	r6,r3,-1
-	addi	r4,r4,-1
-1:	lbzu	r3,1(r6)
-	lbzu	r0,1(r4)
-	subf.	r3,r0,r3
-	bdnzt	2,1b
-	blr
diff --git a/arch/ppc64/boot/main.c b/arch/ppc64/boot/main.c
index 8d14d7172480b2a9be0907825695d447e79be5cd..11a6b84934788a162e9402af74b040e6801c789d 100644
--- a/arch/ppc64/boot/main.c
+++ b/arch/ppc64/boot/main.c
@@ -1,7 +1,7 @@
 /*
  * Copyright (C) Paul Mackerras 1997.
  *
- * Updates for PPC64 by Todd Inglett & Dave Engebretsen.
+ * Updates for PPC64 by Todd Inglett, Dave Engebretsen & Peter Bergner.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -9,31 +9,31 @@
  * 2 of the License, or (at your option) any later version.
  */
 #define __KERNEL__
+#include "ppc32-types.h"
 #include "zlib.h"
+#include <linux/elf.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/bootinfo.h>
 
-#undef DEBUG
-
 void memmove(void *dst, void *im, int len);
 
 extern void *finddevice(const char *);
 extern int getprop(void *, const char *, void *, int);
+extern void printk(char *fmt, ...);
 extern void printf(const char *fmt, ...);
 extern int sprintf(char *buf, const char *fmt, ...);
 void gunzip(void *, int, unsigned char *, int *);
 void *claim(unsigned int, unsigned int, unsigned int);
-void flush_cache(void *, int);
+void flush_cache(void *, unsigned long);
 void pause(void);
+extern void exit(void);
+
 static struct bi_record *make_bi_recs(unsigned long);
 
 #define RAM_START	0x00000000
 #define RAM_END		(64<<20)
 
-#define BOOT_START	((unsigned long)_start)
-#define BOOT_END	((unsigned long)_end)
-
 /* Value picked to match that used by yaboot */
 #define PROG_START	0x01400000
 
@@ -42,18 +42,26 @@ char *begin_avail, *end_avail;
 char *avail_high;
 unsigned int heap_use;
 unsigned int heap_max;
-unsigned long initrd_start = 0;
-unsigned long initrd_size = 0;
 
 extern char _end[];
-extern char image_data[];
-extern int image_len;
-extern char initrd_data[];
-extern int initrd_len;
-extern char sysmap_data[];
-extern int sysmap_len;
-extern int uncompressed_size;
-extern long vmlinux_end;
+extern char _vmlinux_start[];
+extern char _vmlinux_end[];
+extern char _sysmap_start[];
+extern char _sysmap_end[];
+extern char _initrd_start[];
+extern char _initrd_end[];
+extern unsigned long vmlinux_filesize;
+extern unsigned long vmlinux_memsize;
+
+struct addr_range {
+	unsigned long addr;
+	unsigned long size;
+	unsigned long memsize;
+};
+struct addr_range vmlinux = {0, 0, 0};
+struct addr_range vmlinuz = {0, 0, 0};
+struct addr_range sysmap  = {0, 0, 0};
+struct addr_range initrd  = {0, 0, 0};
 
 static char scratch[128<<10];	/* 128kB of scratch space for gunzip */
 
@@ -62,67 +70,126 @@ typedef void (*kernel_entry_t)( unsigned long,
                                 void *,
 				struct bi_record *);
 
+
+int (*prom)(void *);
+
+void *chosen_handle;
+void *stdin;
+void *stdout;
+void *stderr;
+
+
 void
-chrpboot(unsigned long a1, unsigned long a2, void *prom)
+start(unsigned long a1, unsigned long a2, void *promptr)
 {
-	unsigned len;
-	void *dst = (void *)-1;
-	unsigned long claim_addr;
-	unsigned char *im;
+	unsigned long i, claim_addr, claim_size;
 	extern char _start;
 	struct bi_record *bi_recs;
 	kernel_entry_t kernel_entry;
-    
-	printf("chrpboot starting: loaded at 0x%x\n\r", (unsigned)&_start);
+	Elf64_Ehdr *elf64;
+	Elf64_Phdr *elf64ph;
 
-	if (initrd_len) {
-		initrd_size = initrd_len;
-		initrd_start = (RAM_END - initrd_size) & ~0xFFF;
+	prom = (int (*)(void *)) promptr;
+	chosen_handle = finddevice("/chosen");
+	if (chosen_handle == (void *) -1)
+		exit();
+	if (getprop(chosen_handle, "stdout", &stdout, sizeof(stdout)) != 4)
+		exit();
+	stderr = stdout;
+	if (getprop(chosen_handle, "stdin", &stdin, sizeof(stdin)) != 4)
+		exit();
+
+	printf("zImage starting: loaded at 0x%x\n\r", (unsigned)&_start);
+
+#if 0
+	sysmap.size = (unsigned long)(_sysmap_end - _sysmap_start);
+	sysmap.memsize = sysmap.size;
+	if ( sysmap.size > 0 ) {
+		sysmap.addr = (RAM_END - sysmap.size) & ~0xFFF;
+		claim(sysmap.addr, RAM_END - sysmap.addr, 0);
+		printf("initial ramdisk moving 0x%lx <- 0x%lx (%lx bytes)\n\r",
+		       sysmap.addr, (unsigned long)_sysmap_start, sysmap.size);
+		memcpy((void *)sysmap.addr, (void *)_sysmap_start, sysmap.size);
+	}
+#endif
+
+	initrd.size = (unsigned long)(_initrd_end - _initrd_start);
+	initrd.memsize = initrd.size;
+	if ( initrd.size > 0 ) {
+		initrd.addr = (RAM_END - initrd.size) & ~0xFFF;
 		a1 = a2 = 0;
-		claim(initrd_start, RAM_END - initrd_start, 0);
+		claim(initrd.addr, RAM_END - initrd.addr, 0);
 		printf("initial ramdisk moving 0x%lx <- 0x%lx (%lx bytes)\n\r",
-		       initrd_start, (unsigned long)initrd_data, initrd_size);
-		memcpy((void *)initrd_start, (void *)initrd_data, initrd_size);
+		       initrd.addr, (unsigned long)_initrd_start, initrd.size);
+		memcpy((void *)initrd.addr, (void *)_initrd_start, initrd.size);
 	}
 
-	im = image_data;
-	len = image_len;
-	uncompressed_size = PAGE_ALIGN(uncompressed_size);
+	vmlinuz.addr = (unsigned long)_vmlinux_start;
+	vmlinuz.size = (unsigned long)(_vmlinux_end - _vmlinux_start);
+	vmlinux.addr = (unsigned long)(void *)-1;
+	vmlinux.size = PAGE_ALIGN(vmlinux_filesize);
+	vmlinux.memsize = vmlinux_memsize;
 
+	claim_size = vmlinux.memsize /* PPPBBB: + fudge for bi_recs */;
 	for(claim_addr = PROG_START; 
 	    claim_addr <= PROG_START * 8; 
 	    claim_addr += 0x100000) {
-#ifdef DEBUG
 		printf("    trying: 0x%08lx\n\r", claim_addr);
-#endif
-		dst = claim(claim_addr, uncompressed_size, 0);
-		if (dst != (void *)-1) break;
+		vmlinux.addr = (unsigned long)claim(claim_addr, claim_size, 0);
+		if ((void *)vmlinux.addr != (void *)-1) break;
 	}
-	if (dst == (void *)-1) {
+	if ((void *)vmlinux.addr == (void *)-1) {
 		printf("claim error, can't allocate kernel memory\n\r");
-		return;
+		exit();
 	}
 
-	if (im[0] == 0x1f && im[1] == 0x8b) {
+	/* PPPBBB: should kernel always be gziped? */
+	if (*(unsigned short *)vmlinuz.addr == 0x1f8b) {
 		avail_ram = scratch;
 		begin_avail = avail_high = avail_ram;
 		end_avail = scratch + sizeof(scratch);
-		printf("gunzipping (0x%x <- 0x%x:0x%0x)...",
-		       (unsigned)dst, (unsigned)im, (unsigned)im+len);
-		gunzip(dst, uncompressed_size, im, &len);
-		printf("done %u bytes\n\r", len);
+		printf("gunzipping (0x%lx <- 0x%lx:0x%0lx)...",
+		       vmlinux.addr, vmlinuz.addr, vmlinuz.addr+vmlinuz.size);
+		gunzip((void *)vmlinux.addr, vmlinux.size,
+			(unsigned char *)vmlinuz.addr, (int *)&vmlinuz.size);
+		printf("done %lu bytes\n\r", vmlinuz.size);
 		printf("%u bytes of heap consumed, max in use %u\n\r",
 		       (unsigned)(avail_high - begin_avail), heap_max);
 	} else {
-		memmove(dst, im, len);
+		memmove((void *)vmlinux.addr,(void *)vmlinuz.addr,vmlinuz.size);
+	}
+
+	/* Skip over the ELF header */
+	elf64 = (Elf64_Ehdr *)vmlinux.addr;
+	if ( elf64->e_ident[EI_MAG0]  != ELFMAG0	||
+	     elf64->e_ident[EI_MAG1]  != ELFMAG1	||
+	     elf64->e_ident[EI_MAG2]  != ELFMAG2	||
+	     elf64->e_ident[EI_MAG3]  != ELFMAG3	||
+	     elf64->e_ident[EI_CLASS] != ELFCLASS64	||
+	     elf64->e_ident[EI_DATA]  != ELFDATA2MSB	||
+	     elf64->e_type            != ET_EXEC	||
+	     elf64->e_machine         != EM_PPC64 )
+	{
+		printf("Error: not a valid PPC64 ELF file!\n\r");
+		exit();
+	}
+
+	elf64ph = (Elf64_Phdr *)((unsigned long)elf64 +
+				(unsigned long)elf64->e_phoff);
+	for(i=0; i < (unsigned int)elf64->e_phnum ;i++,elf64ph++) {
+		if (elf64ph->p_type == PT_LOAD && elf64ph->p_offset != 0)
+			break;
 	}
+	printf("... skipping 0x%lx bytes of ELF header\n\r",
+			(unsigned long)elf64ph->p_offset);
+	vmlinux.addr += (unsigned long)elf64ph->p_offset;
+	vmlinux.size -= (unsigned long)elf64ph->p_offset;
 
-	flush_cache(dst, len);
+	flush_cache((void *)vmlinux.addr, vmlinux.memsize);
 
-	bi_recs = make_bi_recs((unsigned long)dst + vmlinux_end);
+	bi_recs = make_bi_recs(vmlinux.addr + vmlinux.memsize);
 
-	kernel_entry = (kernel_entry_t)dst;
-#ifdef DEBUG
+	kernel_entry = (kernel_entry_t)vmlinux.addr;
 	printf( "kernel:\n\r"
 		"        entry addr = 0x%lx\n\r"
 		"        a1         = 0x%lx,\n\r"
@@ -131,13 +198,12 @@ chrpboot(unsigned long a1, unsigned long a2, void *prom)
 		"        bi_recs    = 0x%lx,\n\r",
 		(unsigned long)kernel_entry, a1, a2,
 		(unsigned long)prom, (unsigned long)bi_recs);
-#endif
 
 	kernel_entry( a1, a2, prom, bi_recs );
 
-	printf("returned?\n\r");
+	printf("Error: Linux kernel returned to zImage bootloader!\n\r");
 
-	pause();
+	exit();
 }
 
 static struct bi_record *
@@ -162,21 +228,19 @@ make_bi_recs(unsigned long addr)
 	rec->data[0] = PLATFORM_PSERIES;
 	rec->data[1] = 1;
 
-	if ( initrd_size > 0 ) {
+	if ( initrd.size > 0 ) {
 		rec = bi_rec_alloc(rec, 2);
 		rec->tag = BI_INITRD;
-		rec->data[0] = initrd_start;
-		rec->data[1] = initrd_size;
+		rec->data[0] = initrd.addr;
+		rec->data[1] = initrd.size;
 	}
 
-#if 0
-	if ( sysmap_len > 0 ) {
+	if ( sysmap.size > 0 ) {
 		rec = bi_rec_alloc(rec, 2);
 		rec->tag = BI_SYSMAP;
-		rec->data[0] = (unsigned long)sysmap_data;
-		rec->data[1] = sysmap_len;
+		rec->data[0] = (unsigned long)sysmap.addr;
+		rec->data[1] = (unsigned long)sysmap.size;
 	}
-#endif
 
 	rec = bi_rec_alloc(rec, 1);
 	rec->tag = BI_LAST;
diff --git a/arch/ppc64/boot/ppc32-types.h b/arch/ppc64/boot/ppc32-types.h
new file mode 100644
index 0000000000000000000000000000000000000000..16d5be49b2841b77002371c495dbf165db7103b3
--- /dev/null
+++ b/arch/ppc64/boot/ppc32-types.h
@@ -0,0 +1,30 @@
+#ifndef _PPC64_TYPES_H
+#define _PPC64_TYPES_H
+
+typedef __signed__ char __s8;
+typedef unsigned char __u8;
+
+typedef __signed__ short __s16;
+typedef unsigned short __u16;
+
+typedef __signed__ int __s32;
+typedef unsigned int __u32;
+
+typedef __signed__ long long __s64;
+typedef unsigned long long __u64;
+
+typedef signed char s8;
+typedef unsigned char u8;
+
+typedef signed short s16;
+typedef unsigned short u16;
+
+typedef signed int s32;
+typedef unsigned int u32;
+
+typedef signed long long s64;
+typedef unsigned long long u64;
+
+#define BITS_PER_LONG 32
+
+#endif /* _PPC64_TYPES_H */
diff --git a/arch/ppc64/boot/prom.c b/arch/ppc64/boot/prom.c
new file mode 100644
index 0000000000000000000000000000000000000000..2c620f105896426980bc472a49d6e8c27e384df4
--- /dev/null
+++ b/arch/ppc64/boot/prom.c
@@ -0,0 +1,636 @@
+/*
+ * Copyright (C) Paul Mackerras 1997.
+ *
+ * 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 <stdarg.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+
+#include <asm/div64.h>
+
+int (*prom)(void *);
+
+void *chosen_handle;
+void *stdin;
+void *stdout;
+void *stderr;
+
+void exit(void);
+void *finddevice(const char *name);
+int getprop(void *phandle, const char *name, void *buf, int buflen);
+void chrpboot(int a1, int a2, void *prom);	/* in main.c */
+
+void printk(char *fmt, ...);
+
+int
+write(void *handle, void *ptr, int nb)
+{
+	struct prom_args {
+		char *service;
+		int nargs;
+		int nret;
+		void *ihandle;
+		void *addr;
+		int len;
+		int actual;
+	} args;
+
+	args.service = "write";
+	args.nargs = 3;
+	args.nret = 1;
+	args.ihandle = handle;
+	args.addr = ptr;
+	args.len = nb;
+	args.actual = -1;
+	(*prom)(&args);
+	return args.actual;
+}
+
+int
+read(void *handle, void *ptr, int nb)
+{
+	struct prom_args {
+		char *service;
+		int nargs;
+		int nret;
+		void *ihandle;
+		void *addr;
+		int len;
+		int actual;
+	} args;
+
+	args.service = "read";
+	args.nargs = 3;
+	args.nret = 1;
+	args.ihandle = handle;
+	args.addr = ptr;
+	args.len = nb;
+	args.actual = -1;
+	(*prom)(&args);
+	return args.actual;
+}
+
+void
+exit()
+{
+	struct prom_args {
+		char *service;
+	} args;
+
+	for (;;) {
+		args.service = "exit";
+		(*prom)(&args);
+	}
+}
+
+void
+pause(void)
+{
+	struct prom_args {
+		char *service;
+	} args;
+
+	args.service = "enter";
+	(*prom)(&args);
+}
+
+void *
+finddevice(const char *name)
+{
+	struct prom_args {
+		char *service;
+		int nargs;
+		int nret;
+		const char *devspec;
+		void *phandle;
+	} args;
+
+	args.service = "finddevice";
+	args.nargs = 1;
+	args.nret = 1;
+	args.devspec = name;
+	args.phandle = (void *) -1;
+	(*prom)(&args);
+	return args.phandle;
+}
+
+void *
+claim(unsigned long virt, unsigned long size, unsigned long align)
+{
+	struct prom_args {
+		char *service;
+		int nargs;
+		int nret;
+		unsigned int virt;
+		unsigned int size;
+		unsigned int align;
+		void *ret;
+	} args;
+
+	args.service = "claim";
+	args.nargs = 3;
+	args.nret = 1;
+	args.virt = virt;
+	args.size = size;
+	args.align = align;
+	(*prom)(&args);
+	return args.ret;
+}
+
+int
+getprop(void *phandle, const char *name, void *buf, int buflen)
+{
+	struct prom_args {
+		char *service;
+		int nargs;
+		int nret;
+		void *phandle;
+		const char *name;
+		void *buf;
+		int buflen;
+		int size;
+	} args;
+
+	args.service = "getprop";
+	args.nargs = 4;
+	args.nret = 1;
+	args.phandle = phandle;
+	args.name = name;
+	args.buf = buf;
+	args.buflen = buflen;
+	args.size = -1;
+	(*prom)(&args);
+	return args.size;
+}
+
+int
+putc(int c, void *f)
+{
+	char ch = c;
+
+	if (c == '\n')
+		putc('\r', f);
+	return write(f, &ch, 1) == 1? c: -1;
+}
+
+int
+putchar(int c)
+{
+	return putc(c, stdout);
+}
+
+int
+fputs(char *str, void *f)
+{
+	int n = strlen(str);
+
+	return write(f, str, n) == n? 0: -1;
+}
+
+int
+readchar(void)
+{
+	char ch;
+
+	for (;;) {
+		switch (read(stdin, &ch, 1)) {
+		case 1:
+			return ch;
+		case -1:
+			printk("read(stdin) returned -1\r\n");
+			return -1;
+		}
+	}
+}
+
+static char line[256];
+static char *lineptr;
+static int lineleft;
+
+int
+getchar(void)
+{
+	int c;
+
+	if (lineleft == 0) {
+		lineptr = line;
+		for (;;) {
+			c = readchar();
+			if (c == -1 || c == 4)
+				break;
+			if (c == '\r' || c == '\n') {
+				*lineptr++ = '\n';
+				putchar('\n');
+				break;
+			}
+			switch (c) {
+			case 0177:
+			case '\b':
+				if (lineptr > line) {
+					putchar('\b');
+					putchar(' ');
+					putchar('\b');
+					--lineptr;
+				}
+				break;
+			case 'U' & 0x1F:
+				while (lineptr > line) {
+					putchar('\b');
+					putchar(' ');
+					putchar('\b');
+					--lineptr;
+				}
+				break;
+			default:
+				if (lineptr >= &line[sizeof(line) - 1])
+					putchar('\a');
+				else {
+					putchar(c);
+					*lineptr++ = c;
+				}
+			}
+		}
+		lineleft = lineptr - line;
+		lineptr = line;
+	}
+	if (lineleft == 0)
+		return -1;
+	--lineleft;
+	return *lineptr++;
+}
+
+
+
+/* String functions lifted from lib/vsprintf.c and lib/ctype.c */
+unsigned char _ctype[] = {
+_C,_C,_C,_C,_C,_C,_C,_C,			/* 0-7 */
+_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C,		/* 8-15 */
+_C,_C,_C,_C,_C,_C,_C,_C,			/* 16-23 */
+_C,_C,_C,_C,_C,_C,_C,_C,			/* 24-31 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,			/* 32-39 */
+_P,_P,_P,_P,_P,_P,_P,_P,			/* 40-47 */
+_D,_D,_D,_D,_D,_D,_D,_D,			/* 48-55 */
+_D,_D,_P,_P,_P,_P,_P,_P,			/* 56-63 */
+_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U,	/* 64-71 */
+_U,_U,_U,_U,_U,_U,_U,_U,			/* 72-79 */
+_U,_U,_U,_U,_U,_U,_U,_U,			/* 80-87 */
+_U,_U,_U,_P,_P,_P,_P,_P,			/* 88-95 */
+_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L,	/* 96-103 */
+_L,_L,_L,_L,_L,_L,_L,_L,			/* 104-111 */
+_L,_L,_L,_L,_L,_L,_L,_L,			/* 112-119 */
+_L,_L,_L,_P,_P,_P,_P,_C,			/* 120-127 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 128-143 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 144-159 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,   /* 160-175 */
+_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,       /* 176-191 */
+_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,       /* 192-207 */
+_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L,       /* 208-223 */
+_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,       /* 224-239 */
+_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L};      /* 240-255 */
+
+size_t strnlen(const char * s, size_t count)
+{
+	const char *sc;
+
+	for (sc = s; count-- && *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
+
+unsigned long simple_strtoul(const char *cp,char **endp,unsigned int base)
+{
+	unsigned long result = 0,value;
+
+	if (!base) {
+		base = 10;
+		if (*cp == '0') {
+			base = 8;
+			cp++;
+			if ((*cp == 'x') && isxdigit(cp[1])) {
+				cp++;
+				base = 16;
+			}
+		}
+	}
+	while (isxdigit(*cp) &&
+	       (value = isdigit(*cp) ? *cp-'0' : toupper(*cp)-'A'+10) < base) {
+		result = result*base + value;
+		cp++;
+	}
+	if (endp)
+		*endp = (char *)cp;
+	return result;
+}
+
+long simple_strtol(const char *cp,char **endp,unsigned int base)
+{
+	if(*cp=='-')
+		return -simple_strtoul(cp+1,endp,base);
+	return simple_strtoul(cp,endp,base);
+}
+
+static int skip_atoi(const char **s)
+{
+	int i=0;
+
+	while (isdigit(**s))
+		i = i*10 + *((*s)++) - '0';
+	return i;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SPECIAL	32		/* 0x */
+#define LARGE	64		/* use 'ABCDEF' instead of 'abcdef' */
+
+static char * number(char * str, long long num, int base, int size, int precision, int type)
+{
+	char c,sign,tmp[66];
+	const char *digits="0123456789abcdefghijklmnopqrstuvwxyz";
+	int i;
+
+	if (type & LARGE)
+		digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+	if (type & LEFT)
+		type &= ~ZEROPAD;
+	if (base < 2 || base > 36)
+		return 0;
+	c = (type & ZEROPAD) ? '0' : ' ';
+	sign = 0;
+	if (type & SIGN) {
+		if (num < 0) {
+			sign = '-';
+			num = -num;
+			size--;
+		} else if (type & PLUS) {
+			sign = '+';
+			size--;
+		} else if (type & SPACE) {
+			sign = ' ';
+			size--;
+		}
+	}
+	if (type & SPECIAL) {
+		if (base == 16)
+			size -= 2;
+		else if (base == 8)
+			size--;
+	}
+	i = 0;
+	if (num == 0)
+		tmp[i++]='0';
+	else while (num != 0)
+		tmp[i++] = digits[do_div(num,base)];
+	if (i > precision)
+		precision = i;
+	size -= precision;
+	if (!(type&(ZEROPAD+LEFT)))
+		while(size-->0)
+			*str++ = ' ';
+	if (sign)
+		*str++ = sign;
+	if (type & SPECIAL) {
+		if (base==8)
+			*str++ = '0';
+		else if (base==16) {
+			*str++ = '0';
+			*str++ = digits[33];
+		}
+	}
+	if (!(type & LEFT))
+		while (size-- > 0)
+			*str++ = c;
+	while (i < precision--)
+		*str++ = '0';
+	while (i-- > 0)
+		*str++ = tmp[i];
+	while (size-- > 0)
+		*str++ = ' ';
+	return str;
+}
+
+/* Forward decl. needed for IP address printing stuff... */
+int sprintf(char * buf, const char *fmt, ...);
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+	int len;
+	unsigned long long num;
+	int i, base;
+	char * str;
+	const char *s;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/* min. # of digits for integers; max
+				   number of chars for from string */
+	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
+	                        /* 'z' support added 23/7/1999 S.H.    */
+				/* 'z' changed to 'Z' --davidm 1/25/99 */
+
+	
+	for (str=buf ; *fmt ; ++fmt) {
+		if (*fmt != '%') {
+			*str++ = *fmt;
+			continue;
+		}
+			
+		/* process flags */
+		flags = 0;
+		repeat:
+			++fmt;		/* this also skips first '%' */
+			switch (*fmt) {
+				case '-': flags |= LEFT; goto repeat;
+				case '+': flags |= PLUS; goto repeat;
+				case ' ': flags |= SPACE; goto repeat;
+				case '#': flags |= SPECIAL; goto repeat;
+				case '0': flags |= ZEROPAD; goto repeat;
+				}
+		
+		/* get field width */
+		field_width = -1;
+		if (isdigit(*fmt))
+			field_width = skip_atoi(&fmt);
+		else if (*fmt == '*') {
+			++fmt;
+			/* it's the next argument */
+			field_width = va_arg(args, int);
+			if (field_width < 0) {
+				field_width = -field_width;
+				flags |= LEFT;
+			}
+		}
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;	
+			if (isdigit(*fmt))
+				precision = skip_atoi(&fmt);
+			else if (*fmt == '*') {
+				++fmt;
+				/* it's the next argument */
+				precision = va_arg(args, int);
+			}
+			if (precision < 0)
+				precision = 0;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' || *fmt =='Z') {
+			qualifier = *fmt;
+			++fmt;
+		}
+
+		/* default base */
+		base = 10;
+
+		switch (*fmt) {
+		case 'c':
+			if (!(flags & LEFT))
+				while (--field_width > 0)
+					*str++ = ' ';
+			*str++ = (unsigned char) va_arg(args, int);
+			while (--field_width > 0)
+				*str++ = ' ';
+			continue;
+
+		case 's':
+			s = va_arg(args, char *);
+			if (!s)
+				s = "<NULL>";
+
+			len = strnlen(s, precision);
+
+			if (!(flags & LEFT))
+				while (len < field_width--)
+					*str++ = ' ';
+			for (i = 0; i < len; ++i)
+				*str++ = *s++;
+			while (len < field_width--)
+				*str++ = ' ';
+			continue;
+
+		case 'p':
+			if (field_width == -1) {
+				field_width = 2*sizeof(void *);
+				flags |= ZEROPAD;
+			}
+			str = number(str,
+				(unsigned long) va_arg(args, void *), 16,
+				field_width, precision, flags);
+			continue;
+
+
+		case 'n':
+			if (qualifier == 'l') {
+				long * ip = va_arg(args, long *);
+				*ip = (str - buf);
+			} else if (qualifier == 'Z') {
+				size_t * ip = va_arg(args, size_t *);
+				*ip = (str - buf);
+			} else {
+				int * ip = va_arg(args, int *);
+				*ip = (str - buf);
+			}
+			continue;
+
+		case '%':
+			*str++ = '%';
+			continue;
+
+		/* integer number formats - set up the flags and "break" */
+		case 'o':
+			base = 8;
+			break;
+
+		case 'X':
+			flags |= LARGE;
+		case 'x':
+			base = 16;
+			break;
+
+		case 'd':
+		case 'i':
+			flags |= SIGN;
+		case 'u':
+			break;
+
+		default:
+			*str++ = '%';
+			if (*fmt)
+				*str++ = *fmt;
+			else
+				--fmt;
+			continue;
+		}
+		if (qualifier == 'L')
+			num = va_arg(args, long long);
+		else if (qualifier == 'l') {
+			num = va_arg(args, unsigned long);
+			if (flags & SIGN)
+				num = (signed long) num;
+		} else if (qualifier == 'Z') {
+			num = va_arg(args, size_t);
+		} else if (qualifier == 'h') {
+			num = (unsigned short) va_arg(args, int);
+			if (flags & SIGN)
+				num = (signed short) num;
+		} else {
+			num = va_arg(args, unsigned int);
+			if (flags & SIGN)
+				num = (signed int) num;
+		}
+		str = number(str, num, base, field_width, precision, flags);
+	}
+	*str = '\0';
+	return str-buf;
+}
+
+int sprintf(char * buf, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i=vsprintf(buf,fmt,args);
+	va_end(args);
+	return i;
+}
+
+static char sprint_buf[1024];
+
+void
+printk(char *fmt, ...)
+{
+	va_list args;
+	int n;
+
+	va_start(args, fmt);
+	n = vsprintf(sprint_buf, fmt, args);
+	va_end(args);
+	write(stdout, sprint_buf, n);
+}
+
+int
+printf(char *fmt, ...)
+{
+	va_list args;
+	int n;
+
+	va_start(args, fmt);
+	n = vsprintf(sprint_buf, fmt, args);
+	va_end(args);
+	write(stdout, sprint_buf, n);
+	return n;
+}
diff --git a/arch/ppc64/boot/string.S b/arch/ppc64/boot/string.S
new file mode 100644
index 0000000000000000000000000000000000000000..105368607e85e43b0cfdc3365b9c17bd0150c070
--- /dev/null
+++ b/arch/ppc64/boot/string.S
@@ -0,0 +1,223 @@
+/*
+ * Copyright (C) Paul Mackerras 1997.
+ *
+ * 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.
+ *
+ * NOTE: this code runs in 32 bit mode and is packaged as ELF32.
+ */
+
+#include <asm/ppc_asm.h>
+
+	.text
+	.globl	strcpy
+strcpy:
+	addi	r5,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	stbu	r0,1(r5)
+	bne	1b
+	blr
+
+	.globl	strncpy
+strncpy:
+	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r6,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	stbu	r0,1(r6)
+	bdnzf	2,1b		/* dec ctr, branch if ctr != 0 && !cr0.eq */
+	blr
+
+	.globl	strcat
+strcat:
+	addi	r5,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r0,1(r5)
+	cmpwi	0,r0,0
+	bne	1b
+	addi	r5,r5,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	stbu	r0,1(r5)
+	bne	1b
+	blr
+
+	.globl	strcmp
+strcmp:
+	addi	r5,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r3,1(r5)
+	cmpwi	1,r3,0
+	lbzu	r0,1(r4)
+	subf.	r3,r0,r3
+	beqlr	1
+	beq	1b
+	blr
+
+	.globl	strlen
+strlen:
+	addi	r4,r3,-1
+1:	lbzu	r0,1(r4)
+	cmpwi	0,r0,0
+	bne	1b
+	subf	r3,r3,r4
+	blr
+
+	.globl	memset
+memset:
+	rlwimi	r4,r4,8,16,23
+	rlwimi	r4,r4,16,0,15
+	addi	r6,r3,-4
+	cmplwi	0,r5,4
+	blt	7f
+	stwu	r4,4(r6)
+	beqlr
+	andi.	r0,r6,3
+	add	r5,r0,r5
+	subf	r6,r0,r6
+	rlwinm	r0,r5,32-2,2,31
+	mtctr	r0
+	bdz	6f
+1:	stwu	r4,4(r6)
+	bdnz	1b
+6:	andi.	r5,r5,3
+7:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r6,r6,3
+8:	stbu	r4,1(r6)
+	bdnz	8b
+	blr
+
+	.globl	bcopy
+bcopy:
+	mr	r6,r3
+	mr	r3,r4
+	mr	r4,r6
+	b	memcpy
+
+	.globl	memmove
+memmove:
+	cmplw	0,r3,r4
+	bgt	backwards_memcpy
+	/* fall through */
+
+	.globl	memcpy
+memcpy:
+	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */
+	addi	r6,r3,-4
+	addi	r4,r4,-4
+	beq	2f			/* if less than 8 bytes to do */
+	andi.	r0,r6,3			/* get dest word aligned */
+	mtctr	r7
+	bne	5f
+1:	lwz	r7,4(r4)
+	lwzu	r8,8(r4)
+	stw	r7,4(r6)
+	stwu	r8,8(r6)
+	bdnz	1b
+	andi.	r5,r5,7
+2:	cmplwi	0,r5,4
+	blt	3f
+	lwzu	r0,4(r4)
+	addi	r5,r5,-4
+	stwu	r0,4(r6)
+3:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+	addi	r4,r4,3
+	addi	r6,r6,3
+4:	lbzu	r0,1(r4)
+	stbu	r0,1(r6)
+	bdnz	4b
+	blr
+5:	subfic	r0,r0,4
+	mtctr	r0
+6:	lbz	r7,4(r4)
+	addi	r4,r4,1
+	stb	r7,4(r6)
+	addi	r6,r6,1
+	bdnz	6b
+	subf	r5,r0,r5
+	rlwinm.	r7,r5,32-3,3,31
+	beq	2b
+	mtctr	r7
+	b	1b
+
+	.globl	backwards_memcpy
+backwards_memcpy:
+	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */
+	add	r6,r3,r5
+	add	r4,r4,r5
+	beq	2f
+	andi.	r0,r6,3
+	mtctr	r7
+	bne	5f
+1:	lwz	r7,-4(r4)
+	lwzu	r8,-8(r4)
+	stw	r7,-4(r6)
+	stwu	r8,-8(r6)
+	bdnz	1b
+	andi.	r5,r5,7
+2:	cmplwi	0,r5,4
+	blt	3f
+	lwzu	r0,-4(r4)
+	subi	r5,r5,4
+	stwu	r0,-4(r6)
+3:	cmpwi	0,r5,0
+	beqlr
+	mtctr	r5
+4:	lbzu	r0,-1(r4)
+	stbu	r0,-1(r6)
+	bdnz	4b
+	blr
+5:	mtctr	r0
+6:	lbzu	r7,-1(r4)
+	stbu	r7,-1(r6)
+	bdnz	6b
+	subf	r5,r0,r5
+	rlwinm.	r7,r5,32-3,3,31
+	beq	2b
+	mtctr	r7
+	b	1b
+
+	.globl	memcmp
+memcmp:
+	cmpwi	0,r5,0
+	blelr
+	mtctr	r5
+	addi	r6,r3,-1
+	addi	r4,r4,-1
+1:	lbzu	r3,1(r6)
+	lbzu	r0,1(r4)
+	subf.	r3,r0,r3
+	bdnzt	2,1b
+	blr
+
+
+/*
+ * Flush the dcache and invalidate the icache for a range of addresses.
+ *
+ * flush_cache(addr, len)
+ */
+	.global	flush_cache
+flush_cache:
+	addi	4,4,0x1f	/* len = (len + 0x1f) / 0x20 */
+	rlwinm.	4,4,27,5,31
+	mtctr	4
+	beqlr
+1:	dcbf	0,3
+	icbi	0,3
+	addi	3,3,0x20
+	bdnz	1b
+	sync
+	isync
+	blr
+
diff --git a/arch/ppc64/boot/zImage.lds b/arch/ppc64/boot/zImage.lds
index f0a4179ab7a4e9b7c5d7b4b1e015b91544a23794..7070cd2f77de7d8b6a7b27a311f286c2d298f084 100644
--- a/arch/ppc64/boot/zImage.lds
+++ b/arch/ppc64/boot/zImage.lds
@@ -58,6 +58,27 @@ SECTIONS
     *(.dynamic)
     CONSTRUCTORS
   }
+
+  . = ALIGN(4096);
+  _vmlinux_start =  .;
+  .kernel:vmlinux : { *(.kernel:vmlinux) }
+  _vmlinux_end =  .;
+
+  . = ALIGN(4096);
+  _dotconfig_start =  .;
+  .kernel:.config : { *(.kernel:.config) }
+  _dotconfig_end =  .;
+
+  . = ALIGN(4096);
+  _sysmap_start =  .;
+  .kernel:System.map : { *(.kernel:System.map) }
+  _sysmap_end =  .;
+
+  . = ALIGN(4096);
+  _initrd_start =  .;
+  .kernel:initrd : { *(.kernel:initrd) }
+  _initrd_end =  .;
+
   . = ALIGN(4096);
   _edata  =  .;
   PROVIDE (edata = .);