zte's code,first commit

Change-Id: I9a04da59e459a9bc0d67f101f700d9d7dc8d681b
diff --git a/ap/os/linux/linux-3.4.x/arch/arm/kernel/head.S b/ap/os/linux/linux-3.4.x/arch/arm/kernel/head.S
new file mode 100644
index 0000000..7170ec8
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/arch/arm/kernel/head.S
@@ -0,0 +1,632 @@
+/*
+ *  linux/arch/arm/kernel/head.S
+ *
+ *  Copyright (C) 1994-2002 Russell King
+ *  Copyright (c) 2003 ARM Limited
+ *  All Rights Reserved
+ *
+ * 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.
+ *
+ *  Kernel startup code for all 32-bit CPUs
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+#include <asm/assembler.h>
+#include <asm/cp15.h>
+#include <asm/domain.h>
+#include <asm/ptrace.h>
+#include <asm/asm-offsets.h>
+#include <asm/memory.h>
+#include <asm/thread_info.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_DEBUG_LL
+#include <mach/debug-macro.S>
+#endif
+
+/*
+ * swapper_pg_dir is the virtual address of the initial page table.
+ * We place the page tables 16K below KERNEL_RAM_VADDR.  Therefore, we must
+ * make sure that KERNEL_RAM_VADDR is correctly set.  Currently, we expect
+ * the least significant 16 bits to be 0x8000, but we could probably
+ * relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x4000.
+ */
+#define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
+#if (KERNEL_RAM_VADDR & 0xffff) != 0x8000
+#error KERNEL_RAM_VADDR must start at 0xXXXX8000
+#endif
+
+#ifdef CONFIG_ARM_LPAE
+	/* LPAE requires an additional page for the PGD */
+#define PG_DIR_SIZE	0x5000
+#define PMD_ORDER	3
+#else
+#define PG_DIR_SIZE	0x4000
+#define PMD_ORDER	2
+#endif
+
+	.globl	swapper_pg_dir
+	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
+
+	.macro	pgtbl, rd, phys
+	add	\rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE
+	.endm
+
+#ifdef CONFIG_XIP_KERNEL
+#define KERNEL_START	XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR)
+#define KERNEL_END	_edata_loc
+#else
+#define KERNEL_START	KERNEL_RAM_VADDR
+#define KERNEL_END	_end
+#endif
+
+/*
+ * Kernel startup entry point.
+ * ---------------------------
+ *
+ * This is normally called from the decompressor code.  The requirements
+ * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0,
+ * r1 = machine nr, r2 = atags or dtb pointer.
+ *
+ * This code is mostly position independent, so if you link the kernel at
+ * 0xc0008000, you call this at __pa(0xc0008000).
+ *
+ * See linux/arch/arm/tools/mach-types for the complete list of machine
+ * numbers for r1.
+ *
+ * We're trying to keep crap to a minimum; DO NOT add any machine specific
+ * crap here - that's what the boot loader (or in extreme, well justified
+ * circumstances, zImage) is for.
+ */
+	.arm
+
+	__HEAD
+ENTRY(stext)
+#ifdef CONFIG_BOOT_WITHOUT_UBOOT
+	ldr r2, =CONFIG_BOOT_WITHOUT_UBOOT_ADDR
+	ldr r0, [r2]
+	ldr r1, [r2, #4]
+	ldr r2, [r2, #8]
+#endif
+
+ THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
+
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
+						@ and irqs disabled
+	mrc	p15, 0, r9, c0, c0		@ get processor id
+	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
+	movs	r10, r5				@ invalid processor (r5=0)?
+ THUMB( it	eq )		@ force fixup-able long branch encoding
+	beq	__error_p			@ yes, error 'p'
+
+#ifdef CONFIG_ARM_LPAE
+	mrc	p15, 0, r3, c0, c1, 4		@ read ID_MMFR0
+	and	r3, r3, #0xf			@ extract VMSA support
+	cmp	r3, #5				@ long-descriptor translation table format?
+ THUMB( it	lo )				@ force fixup-able long branch encoding
+	blo	__error_p			@ only classic page table format
+#endif
+
+#ifndef CONFIG_XIP_KERNEL
+	adr	r3, 2f
+	ldmia	r3, {r4, r8}
+	sub	r4, r3, r4			@ (PHYS_OFFSET - PAGE_OFFSET)
+	add	r8, r8, r4			@ PHYS_OFFSET
+#else
+	ldr	r8, =PHYS_OFFSET		@ always constant in this case
+#endif
+
+	/*
+	 * r1 = machine no, r2 = atags or dtb,
+	 * r8 = phys_offset, r9 = cpuid, r10 = procinfo
+	 */
+	bl	__vet_atags
+#ifdef CONFIG_SMP_ON_UP
+	bl	__fixup_smp
+#endif
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+	bl	__fixup_pv_table
+#endif
+	bl	__create_page_tables
+
+	/*
+	 * The following calls CPU specific code in a position independent
+	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
+	 * xxx_proc_info structure selected by __lookup_processor_type
+	 * above.  On return, the CPU will be ready for the MMU to be
+	 * turned on, and r0 will hold the CPU control register value.
+	 */
+	ldr	r13, =__mmap_switched		@ address to jump to after
+						@ mmu has been enabled
+	adr	lr, BSYM(1f)			@ return (PIC) address
+	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
+ ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
+ THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
+ THUMB(	mov	pc, r12				)
+1:	b	__enable_mmu
+ENDPROC(stext)
+	.ltorg
+#ifndef CONFIG_XIP_KERNEL
+2:	.long	.
+	.long	PAGE_OFFSET
+#endif
+
+/*
+ * Setup the initial page tables.  We only setup the barest
+ * amount which are required to get the kernel running, which
+ * generally means mapping in the kernel code.
+ *
+ * r8 = phys_offset, r9 = cpuid, r10 = procinfo
+ *
+ * Returns:
+ *  r0, r3, r5-r7 corrupted
+ *  r4 = physical page table address
+ */
+__create_page_tables:
+	pgtbl	r4, r8				@ page table address
+
+	/*
+	 * Clear the swapper page table
+	 */
+	mov	r0, r4
+	mov	r3, #0
+	add	r6, r0, #PG_DIR_SIZE
+1:	str	r3, [r0], #4
+	str	r3, [r0], #4
+	str	r3, [r0], #4
+	str	r3, [r0], #4
+	teq	r0, r6
+	bne	1b
+
+#ifdef CONFIG_ARM_LPAE
+	/*
+	 * Build the PGD table (first level) to point to the PMD table. A PGD
+	 * entry is 64-bit wide.
+	 */
+	mov	r0, r4
+	add	r3, r4, #0x1000			@ first PMD table address
+	orr	r3, r3, #3			@ PGD block type
+	mov	r6, #4				@ PTRS_PER_PGD
+	mov	r7, #1 << (55 - 32)		@ L_PGD_SWAPPER
+1:	str	r3, [r0], #4			@ set bottom PGD entry bits
+	str	r7, [r0], #4			@ set top PGD entry bits
+	add	r3, r3, #0x1000			@ next PMD table
+	subs	r6, r6, #1
+	bne	1b
+
+	add	r4, r4, #0x1000			@ point to the PMD tables
+#endif
+
+	ldr	r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags
+
+	/*
+	 * Create identity mapping to cater for __enable_mmu.
+	 * This identity mapping will be removed by paging_init().
+	 */
+	adr	r0, __turn_mmu_on_loc
+	ldmia	r0, {r3, r5, r6}
+	sub	r0, r0, r3			@ virt->phys offset
+	add	r5, r5, r0			@ phys __turn_mmu_on
+	add	r6, r6, r0			@ phys __turn_mmu_on_end
+	mov	r5, r5, lsr #SECTION_SHIFT
+	mov	r6, r6, lsr #SECTION_SHIFT
+
+1:	orr	r3, r7, r5, lsl #SECTION_SHIFT	@ flags + kernel base
+	str	r3, [r4, r5, lsl #PMD_ORDER]	@ identity mapping
+	cmp	r5, r6
+	addlo	r5, r5, #1			@ next section
+	blo	1b
+
+	/*
+	 * Now setup the pagetables for our kernel direct
+	 * mapped region.
+	 */
+	mov	r3, pc
+	mov	r3, r3, lsr #SECTION_SHIFT
+	orr	r3, r7, r3, lsl #SECTION_SHIFT
+	add	r0, r4,  #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0, #((KERNEL_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]!
+	ldr	r6, =(KERNEL_END - 1)
+	add	r0, r0, #1 << PMD_ORDER
+	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
+1:	cmp	r0, r6
+	add	r3, r3, #1 << SECTION_SHIFT
+	strls	r3, [r0], #1 << PMD_ORDER
+	bls	1b
+
+#ifdef CONFIG_XIP_KERNEL
+	/*
+	 * Map some ram to cover our .data and .bss areas.
+	 */
+	add	r3, r8, #TEXT_OFFSET
+	orr	r3, r3, r7
+	add	r0, r4,  #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]!
+	ldr	r6, =(_end - 1)
+	add	r0, r0, #4
+	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
+1:	cmp	r0, r6
+	add	r3, r3, #1 << 20
+	strls	r3, [r0], #4
+	bls	1b
+#endif
+
+	/*
+	 * Then map boot params address in r2 or the first 1MB (2MB with LPAE)
+	 * of ram if boot params address is not specified.
+	 * We map 2 sections in case the ATAGs/DTB crosses a section boundary.
+	 */
+	mov	r0, r2, lsr #SECTION_SHIFT
+	movs	r0, r0, lsl #SECTION_SHIFT
+	moveq	r0, r8
+	sub	r3, r0, r8
+	ldr r6, =PAGE_OFFSET
+	add	r3, r3, r6
+	add	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
+	orr	r6, r7, r0
+	str	r6, [r3], #1 << PMD_ORDER
+	add	r6, r6, #1 << SECTION_SHIFT
+	str	r6, [r3]
+
+#ifdef CONFIG_DEBUG_LL
+#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING)
+	/*
+	 * Map in IO space for serial debugging.
+	 * This allows debug messages to be output
+	 * via a serial console before paging_init.
+	 */
+	addruart r7, r3, r0
+
+	mov	r3, r3, lsr #SECTION_SHIFT
+	mov	r3, r3, lsl #PMD_ORDER
+
+	add	r0, r4, r3
+	rsb	r3, r3, #0x4000			@ PTRS_PER_PGD*sizeof(long)
+	cmp	r3, #0x0800			@ limit to 512MB
+	movhi	r3, #0x0800
+	add	r6, r0, r3
+	mov	r3, r7, lsr #SECTION_SHIFT
+	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
+	orr	r3, r7, r3, lsl #SECTION_SHIFT
+#ifdef CONFIG_ARM_LPAE
+	mov	r7, #1 << (54 - 32)		@ XN
+#else
+	orr	r3, r3, #PMD_SECT_XN
+#endif
+1:	str	r3, [r0], #4
+#ifdef CONFIG_ARM_LPAE
+	str	r7, [r0], #4
+#endif
+	add	r3, r3, #1 << SECTION_SHIFT
+	cmp	r0, r6
+	blo	1b
+
+#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */
+	/* we don't need any serial debugging mappings */
+	ldr	r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags
+#endif
+
+#if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS)
+	/*
+	 * If we're using the NetWinder or CATS, we also need to map
+	 * in the 16550-type serial port for the debug messages
+	 */
+	add	r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ORDER)
+	orr	r3, r7, #0x7c000000
+	str	r3, [r0]
+#endif
+#ifdef CONFIG_ARCH_RPC
+	/*
+	 * Map in screen at 0x02000000 & SCREEN2_BASE
+	 * Similar reasons here - for debug.  This is
+	 * only for Acorn RiscPC architectures.
+	 */
+	add	r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ORDER)
+	orr	r3, r7, #0x02000000
+	str	r3, [r0]
+	add	r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0]
+#endif
+#endif
+#ifdef CONFIG_ARM_LPAE
+	sub	r4, r4, #0x1000		@ point to the PGD table
+#endif
+	mov	pc, lr
+ENDPROC(__create_page_tables)
+	.ltorg
+	.align
+__turn_mmu_on_loc:
+	.long	.
+	.long	__turn_mmu_on
+	.long	__turn_mmu_on_end
+
+#if defined(CONFIG_SMP)
+	__CPUINIT
+ENTRY(secondary_startup)
+	/*
+	 * Common entry point for secondary CPUs.
+	 *
+	 * Ensure that we're in SVC mode, and IRQs are disabled.  Lookup
+	 * the processor type - there is no need to check the machine type
+	 * as it has already been validated by the primary processor.
+	 */
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
+	mrc	p15, 0, r9, c0, c0		@ get processor id
+	bl	__lookup_processor_type
+	movs	r10, r5				@ invalid processor?
+	moveq	r0, #'p'			@ yes, error 'p'
+ THUMB( it	eq )		@ force fixup-able long branch encoding
+	beq	__error_p
+
+	/*
+	 * Use the page tables supplied from  __cpu_up.
+	 */
+	adr	r4, __secondary_data
+	ldmia	r4, {r5, r7, r12}		@ address to jump to after
+	sub	lr, r4, r5			@ mmu has been enabled
+	ldr	r4, [r7, lr]			@ get secondary_data.pgdir
+	add	r7, r7, #4
+	ldr	r8, [r7, lr]			@ get secondary_data.swapper_pg_dir
+	adr	lr, BSYM(__enable_mmu)		@ return address
+	mov	r13, r12			@ __secondary_switched address
+ ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
+						  @ (return control reg)
+ THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
+ THUMB(	mov	pc, r12				)
+ENDPROC(secondary_startup)
+
+	/*
+	 * r6  = &secondary_data
+	 */
+ENTRY(__secondary_switched)
+	ldr	sp, [r7, #4]			@ get secondary_data.stack
+	mov	fp, #0
+	b	secondary_start_kernel
+ENDPROC(__secondary_switched)
+
+	.align
+
+	.type	__secondary_data, %object
+__secondary_data:
+	.long	.
+	.long	secondary_data
+	.long	__secondary_switched
+#endif /* defined(CONFIG_SMP) */
+
+
+
+/*
+ * Setup common bits before finally enabling the MMU.  Essentially
+ * this is just loading the page table pointer and domain access
+ * registers.
+ *
+ *  r0  = cp#15 control register
+ *  r1  = machine ID
+ *  r2  = atags or dtb pointer
+ *  r4  = page table pointer
+ *  r9  = processor ID
+ *  r13 = *virtual* address to jump to upon completion
+ */
+__enable_mmu:
+#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
+	orr	r0, r0, #CR_A
+#else
+	bic	r0, r0, #CR_A
+#endif
+#ifdef CONFIG_CPU_DCACHE_DISABLE
+	bic	r0, r0, #CR_C
+#endif
+#ifdef CONFIG_CPU_BPREDICT_DISABLE
+	bic	r0, r0, #CR_Z
+#endif
+#ifdef CONFIG_CPU_ICACHE_DISABLE
+	bic	r0, r0, #CR_I
+#endif
+#ifdef CONFIG_ARM_LPAE
+	mov	r5, #0
+	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
+#else
+	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
+		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
+		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
+	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
+#endif
+	b	__turn_mmu_on
+ENDPROC(__enable_mmu)
+
+/*
+ * Enable the MMU.  This completely changes the structure of the visible
+ * memory space.  You will not be able to trace execution through this.
+ * If you have an enquiry about this, *please* check the linux-arm-kernel
+ * mailing list archives BEFORE sending another post to the list.
+ *
+ *  r0  = cp#15 control register
+ *  r1  = machine ID
+ *  r2  = atags or dtb pointer
+ *  r9  = processor ID
+ *  r13 = *virtual* address to jump to upon completion
+ *
+ * other registers depend on the function called upon completion
+ */
+	.align	5
+	.pushsection	.idmap.text, "ax"
+ENTRY(__turn_mmu_on)
+	mov	r0, r0
+	instr_sync
+	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
+	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
+	instr_sync
+	mov	r3, r3
+	mov	r3, r13
+	mov	pc, r3
+__turn_mmu_on_end:
+ENDPROC(__turn_mmu_on)
+	.popsection
+
+
+#ifdef CONFIG_SMP_ON_UP
+	__INIT
+__fixup_smp:
+	and	r3, r9, #0x000f0000	@ architecture version
+	teq	r3, #0x000f0000		@ CPU ID supported?
+	bne	__fixup_smp_on_up	@ no, assume UP
+
+	bic	r3, r9, #0x00ff0000
+	bic	r3, r3, #0x0000000f	@ mask 0xff00fff0
+	mov	r4, #0x41000000
+	orr	r4, r4, #0x0000b000
+	orr	r4, r4, #0x00000020	@ val 0x4100b020
+	teq	r3, r4			@ ARM 11MPCore?
+	moveq	pc, lr			@ yes, assume SMP
+
+	mrc	p15, 0, r0, c0, c0, 5	@ read MPIDR
+	and	r0, r0, #0xc0000000	@ multiprocessing extensions and
+	teq	r0, #0x80000000		@ not part of a uniprocessor system?
+	moveq	pc, lr			@ yes, assume SMP
+
+__fixup_smp_on_up:
+	adr	r0, 1f
+	ldmia	r0, {r3 - r5}
+	sub	r3, r0, r3
+	add	r4, r4, r3
+	add	r5, r5, r3
+	b	__do_fixup_smp_on_up
+ENDPROC(__fixup_smp)
+
+	.align
+1:	.word	.
+	.word	__smpalt_begin
+	.word	__smpalt_end
+
+	.pushsection .data
+	.globl	smp_on_up
+smp_on_up:
+	ALT_SMP(.long	1)
+	ALT_UP(.long	0)
+	.popsection
+#endif
+
+	.text
+__do_fixup_smp_on_up:
+	cmp	r4, r5
+	movhs	pc, lr
+	ldmia	r4!, {r0, r6}
+ ARM(	str	r6, [r0, r3]	)
+ THUMB(	add	r0, r0, r3	)
+#ifdef __ARMEB__
+ THUMB(	mov	r6, r6, ror #16	)	@ Convert word order for big-endian.
+#endif
+ THUMB(	strh	r6, [r0], #2	)	@ For Thumb-2, store as two halfwords
+ THUMB(	mov	r6, r6, lsr #16	)	@ to be robust against misaligned r3.
+ THUMB(	strh	r6, [r0]	)
+	b	__do_fixup_smp_on_up
+ENDPROC(__do_fixup_smp_on_up)
+
+ENTRY(fixup_smp)
+	stmfd	sp!, {r4 - r6, lr}
+	mov	r4, r0
+	add	r5, r0, r1
+	mov	r3, #0
+	bl	__do_fixup_smp_on_up
+	ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(fixup_smp)
+
+#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+
+/* __fixup_pv_table - patch the stub instructions with the delta between
+ * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be 16MiB aligned and
+ * can be expressed by an immediate shifter operand. The stub instruction
+ * has a form of '(add|sub) rd, rn, #imm'.
+ */
+	__HEAD
+__fixup_pv_table:
+	adr	r0, 1f
+	ldmia	r0, {r3-r5, r7}
+	sub	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
+	add	r4, r4, r3	@ adjust table start address
+	add	r5, r5, r3	@ adjust table end address
+	add	r7, r7, r3	@ adjust __pv_phys_offset address
+	str	r8, [r7]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	mov	r6, r3, lsr #24	@ constant for add/sub instructions
+	teq	r3, r6, lsl #24 @ must be 16MiB aligned
+THUMB(	it	ne		@ cross section branch )
+	bne	__error
+	str	r6, [r7, #4]	@ save to __pv_offset
+	b	__fixup_a_pv_table
+ENDPROC(__fixup_pv_table)
+
+	.align
+1:	.long	.
+	.long	__pv_table_begin
+	.long	__pv_table_end
+2:	.long	__pv_phys_offset
+
+	.text
+__fixup_a_pv_table:
+#ifdef CONFIG_THUMB2_KERNEL
+	lsls	r6, #24
+	beq	2f
+	clz	r7, r6
+	lsr	r6, #24
+	lsl	r6, r7
+	bic	r6, #0x0080
+	lsrs	r7, #1
+	orrcs	r6, #0x0080
+	orr	r6, r6, r7, lsl #12
+	orr	r6, #0x4000
+	b	2f
+1:	add     r7, r3
+	ldrh	ip, [r7, #2]
+	and	ip, 0x8f00
+	orr	ip, r6	@ mask in offset bits 31-24
+	strh	ip, [r7, #2]
+2:	cmp	r4, r5
+	ldrcc	r7, [r4], #4	@ use branch for delay slot
+	bcc	1b
+	bx	lr
+#else
+	b	2f
+1:	ldr	ip, [r7, r3]
+	bic	ip, ip, #0x000000ff
+	orr	ip, ip, r6	@ mask in offset bits 31-24
+	str	ip, [r7, r3]
+2:	cmp	r4, r5
+	ldrcc	r7, [r4], #4	@ use branch for delay slot
+	bcc	1b
+	mov	pc, lr
+#endif
+ENDPROC(__fixup_a_pv_table)
+
+ENTRY(fixup_pv_table)
+	stmfd	sp!, {r4 - r7, lr}
+	ldr	r2, 2f			@ get address of __pv_phys_offset
+	mov	r3, #0			@ no offset
+	mov	r4, r0			@ r0 = table start
+	add	r5, r0, r1		@ r1 = table size
+	ldr	r6, [r2, #4]		@ get __pv_offset
+	bl	__fixup_a_pv_table
+	ldmfd	sp!, {r4 - r7, pc}
+ENDPROC(fixup_pv_table)
+
+	.align
+2:	.long	__pv_phys_offset
+
+	.data
+	.globl	__pv_phys_offset
+	.type	__pv_phys_offset, %object
+__pv_phys_offset:
+	.long	0
+	.size	__pv_phys_offset, . - __pv_phys_offset
+__pv_offset:
+	.long	0
+#endif
+
+#include "head-common.S"