diff --git a/arch/powerpc/cpu/mpc8xx/start.S b/arch/powerpc/cpu/mpc8xx/start.S
new file mode 100644
index 0000000..b00696f
--- /dev/null
+++ b/arch/powerpc/cpu/mpc8xx/start.S
@@ -0,0 +1,636 @@
+/*
+ *  Copyright (C) 1998	Dan Malek <dmalek@jlc.net>
+ *  Copyright (C) 1999	Magnus Damm <kieraypc01.p.y.kie.era.ericsson.se>
+ *  Copyright (C) 2000,2001,2002 Wolfgang Denk <wd@denx.de>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+/*  U-Boot - Startup Code for PowerPC based Embedded Boards
+ *
+ *
+ *  The processor starts at 0x00000100 and the code is executed
+ *  from flash. The code is organized to be at an other address
+ *  in memory, but as long we don't jump around before relocating,
+ *  board_init lies at a quite high address and when the cpu has
+ *  jumped there, everything is ok.
+ *  This works because the cpu gives the FLASH (CS0) the whole
+ *  address space at startup, and board_init lies as a echo of
+ *  the flash somewhere up there in the memory map.
+ *
+ *  board_init will change CS0 to be positioned at the correct
+ *  address and (s)dram will be positioned at address 0
+ */
+#include <asm-offsets.h>
+#include <config.h>
+#include <mpc8xx.h>
+#include <version.h>
+
+#include <ppc_asm.tmpl>
+#include <ppc_defs.h>
+
+#include <asm/cache.h>
+#include <asm/mmu.h>
+#include <asm/u-boot.h>
+
+/* We don't want the  MMU yet.
+*/
+#undef	MSR_KERNEL
+#define MSR_KERNEL ( MSR_ME | MSR_RI )	/* Machine Check and Recoverable Interr. */
+
+/*
+ * Set up GOT: Global Offset Table
+ *
+ * Use r12 to access the GOT
+ */
+	START_GOT
+	GOT_ENTRY(_GOT2_TABLE_)
+	GOT_ENTRY(_FIXUP_TABLE_)
+
+	GOT_ENTRY(_start)
+	GOT_ENTRY(_start_of_vectors)
+	GOT_ENTRY(_end_of_vectors)
+	GOT_ENTRY(transfer_to_handler)
+
+	GOT_ENTRY(__init_end)
+	GOT_ENTRY(__bss_end)
+	GOT_ENTRY(__bss_start)
+	END_GOT
+
+/*
+ * r3 - 1st arg to board_init(): IMMP pointer
+ * r4 - 2nd arg to board_init(): boot flag
+ */
+	.text
+	.long	0x27051956		/* U-Boot Magic Number			*/
+	.globl	version_string
+version_string:
+	.ascii U_BOOT_VERSION_STRING, "\0"
+
+	. = EXC_OFF_SYS_RESET
+	.globl	_start
+_start:
+	lis	r3, CONFIG_SYS_IMMR@h		/* position IMMR */
+	mtspr	638, r3
+
+	/* Initialize machine status; enable machine check interrupt		*/
+	/*----------------------------------------------------------------------*/
+	li	r3, MSR_KERNEL		/* Set ME, RI flags */
+	mtmsr	r3
+	mtspr	SRR1, r3		/* Make SRR1 match MSR */
+
+	mfspr	r3, ICR			/* clear Interrupt Cause Register */
+
+	/* Initialize debug port registers					*/
+	/*----------------------------------------------------------------------*/
+	xor	r0, r0, r0		/* Clear R0 */
+	mtspr	LCTRL1, r0		/* Initialize debug port regs */
+	mtspr	LCTRL2, r0
+	mtspr	COUNTA, r0
+	mtspr	COUNTB, r0
+
+	/* Reset the caches							*/
+	/*----------------------------------------------------------------------*/
+
+	mfspr	r3, IC_CST		/* Clear error bits */
+	mfspr	r3, DC_CST
+
+	lis	r3, IDC_UNALL@h		/* Unlock all */
+	mtspr	IC_CST, r3
+	mtspr	DC_CST, r3
+
+	lis	r3, IDC_INVALL@h	/* Invalidate all */
+	mtspr	IC_CST, r3
+	mtspr	DC_CST, r3
+
+	lis	r3, IDC_DISABLE@h	/* Disable data cache */
+	mtspr	DC_CST, r3
+
+	lis	r3, IDC_ENABLE@h	/* Enable instruction cache */
+	mtspr	IC_CST, r3
+
+	/* invalidate all tlb's							*/
+	/*----------------------------------------------------------------------*/
+
+	tlbia
+	isync
+
+	/*
+	 * Calculate absolute address in FLASH and jump there
+	 *----------------------------------------------------------------------*/
+
+	lis	r3, CONFIG_SYS_MONITOR_BASE@h
+	ori	r3, r3, CONFIG_SYS_MONITOR_BASE@l
+	addi	r3, r3, in_flash - _start + EXC_OFF_SYS_RESET
+	mtlr	r3
+	blr
+
+in_flash:
+
+	/* initialize some SPRs that are hard to access from C			*/
+	/*----------------------------------------------------------------------*/
+
+	lis	r3, CONFIG_SYS_IMMR@h		/* pass IMMR as arg1 to C routine */
+	ori	r1, r3, CONFIG_SYS_INIT_SP_OFFSET /* set up the stack in internal DPRAM */
+	/* Note: R0 is still 0 here */
+	stwu	r0, -4(r1)		/* clear final stack frame so that	*/
+	stwu	r0, -4(r1)		/* stack backtraces terminate cleanly	*/
+
+	/*
+	 * Disable serialized ifetch and show cycles
+	 * (i.e. set processor to normal mode).
+	 * This is also a silicon bug workaround, see errata
+	 */
+
+	li	r2, 0x0007
+	mtspr	ICTRL, r2
+
+	/* Set up debug mode entry */
+
+	lis	r2, CONFIG_SYS_DER@h
+	ori	r2, r2, CONFIG_SYS_DER@l
+	mtspr	DER, r2
+
+	/* let the C-code set up the rest					*/
+	/*									*/
+	/* Be careful to keep code relocatable !				*/
+	/*----------------------------------------------------------------------*/
+
+	GET_GOT			/* initialize GOT access			*/
+
+	/* r3: IMMR */
+	bl	cpu_init_f	/* run low-level CPU init code     (from Flash)	*/
+
+	bl	board_init_f	/* run 1st part of board init code (from Flash) */
+
+	/* NOTREACHED - board_init_f() does not return */
+
+
+	.globl	_start_of_vectors
+_start_of_vectors:
+
+/* Machine check */
+	STD_EXCEPTION(0x200, MachineCheck, MachineCheckException)
+
+/* Data Storage exception.  "Never" generated on the 860. */
+	STD_EXCEPTION(0x300, DataStorage, UnknownException)
+
+/* Instruction Storage exception.  "Never" generated on the 860. */
+	STD_EXCEPTION(0x400, InstStorage, UnknownException)
+
+/* External Interrupt exception. */
+	STD_EXCEPTION(0x500, ExtInterrupt, external_interrupt)
+
+/* Alignment exception. */
+	. = 0x600
+Alignment:
+	EXCEPTION_PROLOG(SRR0, SRR1)
+	mfspr	r4,DAR
+	stw	r4,_DAR(r21)
+	mfspr	r5,DSISR
+	stw	r5,_DSISR(r21)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_TEMPLATE(Alignment, AlignmentException, MSR_KERNEL, COPY_EE)
+
+/* Program check exception */
+	. = 0x700
+ProgramCheck:
+	EXCEPTION_PROLOG(SRR0, SRR1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_TEMPLATE(ProgramCheck, ProgramCheckException,
+		MSR_KERNEL, COPY_EE)
+
+	/* No FPU on MPC8xx.  This exception is not supposed to happen.
+	*/
+	STD_EXCEPTION(0x800, FPUnavailable, UnknownException)
+
+	/* I guess we could implement decrementer, and may have
+	 * to someday for timekeeping.
+	 */
+	STD_EXCEPTION(0x900, Decrementer, timer_interrupt)
+	STD_EXCEPTION(0xa00, Trap_0a, UnknownException)
+	STD_EXCEPTION(0xb00, Trap_0b, UnknownException)
+	STD_EXCEPTION(0xc00, SystemCall, UnknownException)
+	STD_EXCEPTION(0xd00, SingleStep, UnknownException)
+
+	STD_EXCEPTION(0xe00, Trap_0e, UnknownException)
+	STD_EXCEPTION(0xf00, Trap_0f, UnknownException)
+
+	/* On the MPC8xx, this is a software emulation interrupt.  It occurs
+	 * for all unimplemented and illegal instructions.
+	 */
+	STD_EXCEPTION(0x1000, SoftEmu, SoftEmuException)
+
+	STD_EXCEPTION(0x1100, InstructionTLBMiss, UnknownException)
+	STD_EXCEPTION(0x1200, DataTLBMiss, UnknownException)
+	STD_EXCEPTION(0x1300, InstructionTLBError, UnknownException)
+	STD_EXCEPTION(0x1400, DataTLBError, UnknownException)
+
+	STD_EXCEPTION(0x1500, Reserved5, UnknownException)
+	STD_EXCEPTION(0x1600, Reserved6, UnknownException)
+	STD_EXCEPTION(0x1700, Reserved7, UnknownException)
+	STD_EXCEPTION(0x1800, Reserved8, UnknownException)
+	STD_EXCEPTION(0x1900, Reserved9, UnknownException)
+	STD_EXCEPTION(0x1a00, ReservedA, UnknownException)
+	STD_EXCEPTION(0x1b00, ReservedB, UnknownException)
+
+	STD_EXCEPTION(0x1c00, DataBreakpoint, UnknownException)
+	STD_EXCEPTION(0x1d00, InstructionBreakpoint, DebugException)
+	STD_EXCEPTION(0x1e00, PeripheralBreakpoint, UnknownException)
+	STD_EXCEPTION(0x1f00, DevPortBreakpoint, UnknownException)
+
+
+	.globl	_end_of_vectors
+_end_of_vectors:
+
+
+	. = 0x2000
+
+/*
+ * This code finishes saving the registers to the exception frame
+ * and jumps to the appropriate handler for the exception.
+ * Register r21 is pointer into trap frame, r1 has new stack pointer.
+ */
+	.globl	transfer_to_handler
+transfer_to_handler:
+	stw	r22,_NIP(r21)
+	lis	r22,MSR_POW@h
+	andc	r23,r23,r22
+	stw	r23,_MSR(r21)
+	SAVE_GPR(7, r21)
+	SAVE_4GPRS(8, r21)
+	SAVE_8GPRS(12, r21)
+	SAVE_8GPRS(24, r21)
+	mflr	r23
+	andi.	r24,r23,0x3f00		/* get vector offset */
+	stw	r24,TRAP(r21)
+	li	r22,0
+	stw	r22,RESULT(r21)
+	mtspr	SPRG2,r22		/* r1 is now kernel sp */
+	lwz	r24,0(r23)		/* virtual address of handler */
+	lwz	r23,4(r23)		/* where to go when done */
+	mtspr	SRR0,r24
+	mtspr	SRR1,r20
+	mtlr	r23
+	SYNC
+	rfi				/* jump to handler, enable MMU */
+
+int_return:
+	mfmsr	r28			/* Disable interrupts */
+	li	r4,0
+	ori	r4,r4,MSR_EE
+	andc	r28,r28,r4
+	SYNC				/* Some chip revs need this... */
+	mtmsr	r28
+	SYNC
+	lwz	r2,_CTR(r1)
+	lwz	r0,_LINK(r1)
+	mtctr	r2
+	mtlr	r0
+	lwz	r2,_XER(r1)
+	lwz	r0,_CCR(r1)
+	mtspr	XER,r2
+	mtcrf	0xFF,r0
+	REST_10GPRS(3, r1)
+	REST_10GPRS(13, r1)
+	REST_8GPRS(23, r1)
+	REST_GPR(31, r1)
+	lwz	r2,_NIP(r1)		/* Restore environment */
+	lwz	r0,_MSR(r1)
+	mtspr	SRR0,r2
+	mtspr	SRR1,r0
+	lwz	r0,GPR0(r1)
+	lwz	r2,GPR2(r1)
+	lwz	r1,GPR1(r1)
+	SYNC
+	rfi
+
+/* Cache functions.
+*/
+	.globl	icache_enable
+icache_enable:
+	SYNC
+	lis	r3, IDC_INVALL@h
+	mtspr	IC_CST, r3
+	lis	r3, IDC_ENABLE@h
+	mtspr	IC_CST, r3
+	blr
+
+	.globl	icache_disable
+icache_disable:
+	SYNC
+	lis	r3, IDC_DISABLE@h
+	mtspr	IC_CST, r3
+	blr
+
+	.globl	icache_status
+icache_status:
+	mfspr	r3, IC_CST
+	srwi	r3, r3, 31	/* >>31 => select bit 0 */
+	blr
+
+	.globl	dcache_enable
+dcache_enable:
+	lis	r3, 0x0400		/* Set cache mode with MMU off */
+	mtspr	MD_CTR, r3
+
+	lis	r3, IDC_INVALL@h
+	mtspr	DC_CST, r3
+	lis	r3, IDC_ENABLE@h
+	mtspr	DC_CST, r3
+	blr
+
+	.globl	dcache_disable
+dcache_disable:
+	SYNC
+	lis	r3, IDC_DISABLE@h
+	mtspr	DC_CST, r3
+	lis	r3, IDC_INVALL@h
+	mtspr	DC_CST, r3
+	blr
+
+	.globl	dcache_status
+dcache_status:
+	mfspr	r3, DC_CST
+	srwi	r3, r3, 31	/* >>31 => select bit 0 */
+	blr
+
+	.globl	dc_read
+dc_read:
+	mtspr	DC_ADR, r3
+	mfspr	r3, DC_DAT
+	blr
+
+/*
+ * unsigned int get_immr (unsigned int mask)
+ *
+ * return (mask ? (IMMR & mask) : IMMR);
+ */
+	.globl	get_immr
+get_immr:
+	mr	r4,r3		/* save mask */
+	mfspr	r3, IMMR	/* IMMR */
+	cmpwi	0,r4,0		/* mask != 0 ? */
+	beq	4f
+	and	r3,r3,r4	/* IMMR & mask */
+4:
+	blr
+
+	.globl get_pvr
+get_pvr:
+	mfspr	r3, PVR
+	blr
+
+
+	.globl wr_ic_cst
+wr_ic_cst:
+	mtspr	IC_CST, r3
+	blr
+
+	.globl rd_ic_cst
+rd_ic_cst:
+	mfspr	r3, IC_CST
+	blr
+
+	.globl wr_ic_adr
+wr_ic_adr:
+	mtspr	IC_ADR, r3
+	blr
+
+
+	.globl wr_dc_cst
+wr_dc_cst:
+	mtspr	DC_CST, r3
+	blr
+
+	.globl rd_dc_cst
+rd_dc_cst:
+	mfspr	r3, DC_CST
+	blr
+
+	.globl wr_dc_adr
+wr_dc_adr:
+	mtspr	DC_ADR, r3
+	blr
+
+/*------------------------------------------------------------------------------*/
+
+/*
+ * void relocate_code (addr_sp, gd, addr_moni)
+ *
+ * This "function" does not return, instead it continues in RAM
+ * after relocating the monitor code.
+ *
+ * r3 = dest
+ * r4 = src
+ * r5 = length in bytes
+ * r6 = cachelinesize
+ */
+	.globl	relocate_code
+relocate_code:
+	mr	r1,  r3		/* Set new stack pointer		*/
+	mr	r9,  r4		/* Save copy of Global Data pointer	*/
+	mr	r10, r5		/* Save copy of Destination Address	*/
+
+	GET_GOT
+	mr	r3,  r5				/* Destination Address	*/
+	lis	r4, CONFIG_SYS_MONITOR_BASE@h		/* Source      Address	*/
+	ori	r4, r4, CONFIG_SYS_MONITOR_BASE@l
+	lwz	r5, GOT(__init_end)
+	sub	r5, r5, r4
+	li	r6, CONFIG_SYS_CACHELINE_SIZE		/* Cache Line Size	*/
+
+	/*
+	 * Fix GOT pointer:
+	 *
+	 * New GOT-PTR = (old GOT-PTR - CONFIG_SYS_MONITOR_BASE) + Destination Address
+	 *
+	 * Offset:
+	 */
+	sub	r15, r10, r4
+
+	/* First our own GOT */
+	add	r12, r12, r15
+	/* then the one used by the C code */
+	add	r30, r30, r15
+
+	/*
+	 * Now relocate code
+	 */
+
+	cmplw	cr1,r3,r4
+	addi	r0,r5,3
+	srwi.	r0,r0,2
+	beq	cr1,4f		/* In place copy is not necessary	*/
+	beq	7f		/* Protect against 0 count		*/
+	mtctr	r0
+	bge	cr1,2f
+
+	la	r8,-4(r4)
+	la	r7,-4(r3)
+1:	lwzu	r0,4(r8)
+	stwu	r0,4(r7)
+	bdnz	1b
+	b	4f
+
+2:	slwi	r0,r0,2
+	add	r8,r4,r0
+	add	r7,r3,r0
+3:	lwzu	r0,-4(r8)
+	stwu	r0,-4(r7)
+	bdnz	3b
+
+/*
+ * Now flush the cache: note that we must start from a cache aligned
+ * address. Otherwise we might miss one cache line.
+ */
+4:	cmpwi	r6,0
+	add	r5,r3,r5
+	beq	7f		/* Always flush prefetch queue in any case */
+	subi	r0,r6,1
+	andc	r3,r3,r0
+	mr	r4,r3
+5:	dcbst	0,r4
+	add	r4,r4,r6
+	cmplw	r4,r5
+	blt	5b
+	sync			/* Wait for all dcbst to complete on bus */
+	mr	r4,r3
+6:	icbi	0,r4
+	add	r4,r4,r6
+	cmplw	r4,r5
+	blt	6b
+7:	sync			/* Wait for all icbi to complete on bus	*/
+	isync
+
+/*
+ * We are done. Do not return, instead branch to second part of board
+ * initialization, now running from RAM.
+ */
+
+	addi	r0, r10, in_ram - _start + EXC_OFF_SYS_RESET
+	mtlr	r0
+	blr
+
+in_ram:
+
+	/*
+	 * Relocation Function, r12 point to got2+0x8000
+	 *
+	 * Adjust got2 pointers, no need to check for 0, this code
+	 * already puts a few entries in the table.
+	 */
+	li	r0,__got2_entries@sectoff@l
+	la	r3,GOT(_GOT2_TABLE_)
+	lwz	r11,GOT(_GOT2_TABLE_)
+	mtctr	r0
+	sub	r11,r3,r11
+	addi	r3,r3,-4
+1:	lwzu	r0,4(r3)
+	cmpwi	r0,0
+	beq-	2f
+	add	r0,r0,r11
+	stw	r0,0(r3)
+2:	bdnz	1b
+
+	/*
+	 * Now adjust the fixups and the pointers to the fixups
+	 * in case we need to move ourselves again.
+	 */
+	li	r0,__fixup_entries@sectoff@l
+	lwz	r3,GOT(_FIXUP_TABLE_)
+	cmpwi	r0,0
+	mtctr	r0
+	addi	r3,r3,-4
+	beq	4f
+3:	lwzu	r4,4(r3)
+	lwzux	r0,r4,r11
+	cmpwi	r0,0
+	add	r0,r0,r11
+	stw	r4,0(r3)
+	beq-	5f
+	stw	r0,0(r4)
+5:	bdnz	3b
+4:
+clear_bss:
+	/*
+	 * Now clear BSS segment
+	 */
+	lwz	r3,GOT(__bss_start)
+	lwz	r4,GOT(__bss_end)
+
+	cmplw	0, r3, r4
+	beq	6f
+
+	li	r0, 0
+5:
+	stw	r0, 0(r3)
+	addi	r3, r3, 4
+	cmplw	0, r3, r4
+	bne	5b
+6:
+
+	mr	r3, r9		/* Global Data pointer		*/
+	mr	r4, r10		/* Destination Address		*/
+	bl	board_init_r
+
+	/*
+	 * Copy exception vector code to low memory
+	 *
+	 * r3: dest_addr
+	 * r7: source address, r8: end address, r9: target address
+	 */
+	.globl	trap_init
+trap_init:
+	mflr	r4			/* save link register		*/
+	GET_GOT
+	lwz	r7, GOT(_start)
+	lwz	r8, GOT(_end_of_vectors)
+
+	li	r9, 0x100		/* reset vector always at 0x100 */
+
+	cmplw	0, r7, r8
+	bgelr				/* return if r7>=r8 - just in case */
+1:
+	lwz	r0, 0(r7)
+	stw	r0, 0(r9)
+	addi	r7, r7, 4
+	addi	r9, r9, 4
+	cmplw	0, r7, r8
+	bne	1b
+
+	/*
+	 * relocate `hdlr' and `int_return' entries
+	 */
+	li	r7, .L_MachineCheck - _start + EXC_OFF_SYS_RESET
+	li	r8, Alignment - _start + EXC_OFF_SYS_RESET
+2:
+	bl	trap_reloc
+	addi	r7, r7, 0x100		/* next exception vector	*/
+	cmplw	0, r7, r8
+	blt	2b
+
+	li	r7, .L_Alignment - _start + EXC_OFF_SYS_RESET
+	bl	trap_reloc
+
+	li	r7, .L_ProgramCheck - _start + EXC_OFF_SYS_RESET
+	bl	trap_reloc
+
+	li	r7, .L_FPUnavailable - _start + EXC_OFF_SYS_RESET
+	li	r8, SystemCall - _start + EXC_OFF_SYS_RESET
+3:
+	bl	trap_reloc
+	addi	r7, r7, 0x100		/* next exception vector	*/
+	cmplw	0, r7, r8
+	blt	3b
+
+	li	r7, .L_SingleStep - _start + EXC_OFF_SYS_RESET
+	li	r8, _end_of_vectors - _start + EXC_OFF_SYS_RESET
+4:
+	bl	trap_reloc
+	addi	r7, r7, 0x100		/* next exception vector	*/
+	cmplw	0, r7, r8
+	blt	4b
+
+	mtlr	r4			/* restore link register	*/
+	blr