@@/*bl code for debugging*/

		add	r0, r0, #127
		bic	r0, r0, #127		@ align the kernel length
/*
 * r0     = decompressed kernel length
 * r1-r3  = unused
 * r4     = kernel execution address
 * r5     = decompressed kernel start
 * r6     = processor ID
 * r7     = architecture ID
 * r8     = atags pointer
 * r9-r14 = corrupted
 */
		add	r1, r5, r0		@ end of decompressed kernel
		adr	r2, reloc_start
		ldr	r3, LC1
		add	r3, r2, r3
1:		ldmia	r2!, {r9 - r14}		@ copy relocation code
		stmia	r1!, {r9 - r14}
		ldmia	r2!, {r9 - r14}
		stmia	r1!, {r9 - r14}
		cmp	r2, r3
		blo	1b

		bl	cache_clean_flush
		add	pc, r5, r0		@ call relocation code

/*
 * We're not in danger of overwriting ourselves.  Do this the simple way.
 *
 * r4     = kernel execution address
 * r7     = architecture ID
 */

@@/*bl code for debugging purposes
*	mov	r13, #0x0
*	mov	r14, #0x41000000
*	orr	r14, r14, #0x00300000
*	orr	r14, r14, #0x00000004
*	strb	r13, [r14]
*end bl code*/