xref: /openbmc/linux/arch/powerpc/kernel/head_64.S (revision 63ce271b5e377deaddace4bac6dafb6e79d2bee4)

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 *  PowerPC version
 *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
 *
 *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
 *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
 *  Adapted for Power Macintosh by Paul Mackerras.
 *  Low-level exception handlers and MMU support
 *  rewritten by Paul Mackerras.
 *    Copyright (C) 1996 Paul Mackerras.
 *
 *  Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and
 *    Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com
 *
 *  This file contains the entry point for the 64-bit kernel along
 *  with some early initialization code common to all 64-bit powerpc
 *  variants.
 */

#include <linux/threads.h>
#include <linux/init.h>
#include <asm/reg.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/ppc_asm.h>
#include <asm/head-64.h>
#include <asm/asm-offsets.h>
#include <asm/bug.h>
#include <asm/cputable.h>
#include <asm/setup.h>
#include <asm/hvcall.h>
#include <asm/thread_info.h>
#include <asm/firmware.h>
#include <asm/page_64.h>
#include <asm/irqflags.h>
#include <asm/kvm_book3s_asm.h>
#include <asm/ptrace.h>
#include <asm/hw_irq.h>
#include <asm/cputhreads.h>
#include <asm/ppc-opcode.h>
#include <asm/export.h>
#include <asm/feature-fixups.h>

/* The physical memory is laid out such that the secondary processor
 * spin code sits at 0x0000...0x00ff. On server, the vectors follow
 * using the layout described in exceptions-64s.S
 */

/*
 * Entering into this code we make the following assumptions:
 *
 *  For pSeries or server processors:
 *   1. The MMU is off & open firmware is running in real mode.
 *   2. The primary CPU enters at __start.
 *   3. If the RTAS supports "query-cpu-stopped-state", then secondary
 *      CPUs will enter as directed by "start-cpu" RTAS call, which is
 *      generic_secondary_smp_init, with PIR in r3.
 *   4. Else the secondary CPUs will enter at secondary_hold (0x60) as
 *      directed by the "start-cpu" RTS call, with PIR in r3.
 * -or- For OPAL entry:
 *   1. The MMU is off, processor in HV mode.
 *   2. The primary CPU enters at 0 with device-tree in r3, OPAL base
 *      in r8, and entry in r9 for debugging purposes.
 *   3. Secondary CPUs enter as directed by OPAL_START_CPU call, which
 *      is at generic_secondary_smp_init, with PIR in r3.
 *
 *  For Book3E processors:
 *   1. The MMU is on running in AS0 in a state defined in ePAPR
 *   2. The kernel is entered at __start
 */

OPEN_FIXED_SECTION(first_256B, 0x0, 0x100)
USE_FIXED_SECTION(first_256B)
	/*
	 * Offsets are relative from the start of fixed section, and
	 * first_256B starts at 0. Offsets are a bit easier to use here
	 * than the fixed section entry macros.
	 */
	. = 0x0
_GLOBAL(__start)
	/* NOP this out unconditionally */
BEGIN_FTR_SECTION
	FIXUP_ENDIAN
	b	__start_initialization_multiplatform
END_FTR_SECTION(0, 1)

	/* Catch branch to 0 in real mode */
	trap

	/* Secondary processors spin on this value until it becomes non-zero.
	 * When non-zero, it contains the real address of the function the cpu
	 * should jump to.
	 */
	.balign 8
	.globl  __secondary_hold_spinloop
__secondary_hold_spinloop:
	.8byte	0x0

	/* Secondary processors write this value with their cpu # */
	/* after they enter the spin loop immediately below.	  */
	.globl	__secondary_hold_acknowledge
__secondary_hold_acknowledge:
	.8byte	0x0

#ifdef CONFIG_RELOCATABLE
	/* This flag is set to 1 by a loader if the kernel should run
	 * at the loaded address instead of the linked address.  This
	 * is used by kexec-tools to keep the the kdump kernel in the
	 * crash_kernel region.  The loader is responsible for
	 * observing the alignment requirement.
	 */

#ifdef CONFIG_RELOCATABLE_TEST
#define RUN_AT_LOAD_DEFAULT 1		/* Test relocation, do not copy to 0 */
#else
#define RUN_AT_LOAD_DEFAULT 0x72756e30  /* "run0" -- relocate to 0 by default */
#endif

	/* Do not move this variable as kexec-tools knows about it. */
	. = 0x5c
	.globl	__run_at_load
__run_at_load:
DEFINE_FIXED_SYMBOL(__run_at_load)
	.long	RUN_AT_LOAD_DEFAULT
#endif

	. = 0x60
/*
 * The following code is used to hold secondary processors
 * in a spin loop after they have entered the kernel, but
 * before the bulk of the kernel has been relocated.  This code
 * is relocated to physical address 0x60 before prom_init is run.
 * All of it must fit below the first exception vector at 0x100.
 * Use .globl here not _GLOBAL because we want __secondary_hold
 * to be the actual text address, not a descriptor.
 */
	.globl	__secondary_hold
__secondary_hold:
	FIXUP_ENDIAN
#ifndef CONFIG_PPC_BOOK3E
	mfmsr	r24
	ori	r24,r24,MSR_RI
	mtmsrd	r24			/* RI on */
#endif
	/* Grab our physical cpu number */
	mr	r24,r3
	/* stash r4 for book3e */
	mr	r25,r4

	/* Tell the master cpu we're here */
	/* Relocation is off & we are located at an address less */
	/* than 0x100, so only need to grab low order offset.    */
	std	r24,(ABS_ADDR(__secondary_hold_acknowledge))(0)
	sync

	li	r26,0
#ifdef CONFIG_PPC_BOOK3E
	tovirt(r26,r26)
#endif
	/* All secondary cpus wait here until told to start. */
100:	ld	r12,(ABS_ADDR(__secondary_hold_spinloop))(r26)
	cmpdi	0,r12,0
	beq	100b

#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
#ifdef CONFIG_PPC_BOOK3E
	tovirt(r12,r12)
#endif
	mtctr	r12
	mr	r3,r24
	/*
	 * it may be the case that other platforms have r4 right to
	 * begin with, this gives us some safety in case it is not
	 */
#ifdef CONFIG_PPC_BOOK3E
	mr	r4,r25
#else
	li	r4,0
#endif
	/* Make sure that patched code is visible */
	isync
	bctr
#else
0:	trap
	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
#endif
CLOSE_FIXED_SECTION(first_256B)

/* This value is used to mark exception frames on the stack. */
	.section ".toc","aw"
exception_marker:
	.tc	ID_72656773_68657265[TC],0x7265677368657265
	.previous

/*
 * On server, we include the exception vectors code here as it
 * relies on absolute addressing which is only possible within
 * this compilation unit
 */
#ifdef CONFIG_PPC_BOOK3S
#include "exceptions-64s.S"
#else
OPEN_TEXT_SECTION(0x100)
#endif

USE_TEXT_SECTION()

#ifdef CONFIG_PPC_BOOK3E
/*
 * The booting_thread_hwid holds the thread id we want to boot in cpu
 * hotplug case. It is set by cpu hotplug code, and is invalid by default.
 * The thread id is the same as the initial value of SPRN_PIR[THREAD_ID]
 * bit field.
 */
	.globl	booting_thread_hwid
booting_thread_hwid:
	.long  INVALID_THREAD_HWID
	.align 3
/*
 * start a thread in the same core
 * input parameters:
 * r3 = the thread physical id
 * r4 = the entry point where thread starts
 */
_GLOBAL(book3e_start_thread)
	LOAD_REG_IMMEDIATE(r5, MSR_KERNEL)
	cmpwi	r3, 0
	beq	10f
	cmpwi	r3, 1
	beq	11f
	/* If the thread id is invalid, just exit. */
	b	13f
10:
	MTTMR(TMRN_IMSR0, 5)
	MTTMR(TMRN_INIA0, 4)
	b	12f
11:
	MTTMR(TMRN_IMSR1, 5)
	MTTMR(TMRN_INIA1, 4)
12:
	isync
	li	r6, 1
	sld	r6, r6, r3
	mtspr	SPRN_TENS, r6
13:
	blr

/*
 * stop a thread in the same core
 * input parameter:
 * r3 = the thread physical id
 */
_GLOBAL(book3e_stop_thread)
	cmpwi	r3, 0
	beq	10f
	cmpwi	r3, 1
	beq	10f
	/* If the thread id is invalid, just exit. */
	b	13f
10:
	li	r4, 1
	sld	r4, r4, r3
	mtspr	SPRN_TENC, r4
13:
	blr

_GLOBAL(fsl_secondary_thread_init)
	mfspr	r4,SPRN_BUCSR

	/* Enable branch prediction */
	lis     r3,BUCSR_INIT@h
	ori     r3,r3,BUCSR_INIT@l
	mtspr   SPRN_BUCSR,r3
	isync

	/*
	 * Fix PIR to match the linear numbering in the device tree.
	 *
	 * On e6500, the reset value of PIR uses the low three bits for
	 * the thread within a core, and the upper bits for the core
	 * number.  There are two threads per core, so shift everything
	 * but the low bit right by two bits so that the cpu numbering is
	 * continuous.
	 *
	 * If the old value of BUCSR is non-zero, this thread has run
	 * before.  Thus, we assume we are coming from kexec or a similar
	 * scenario, and PIR is already set to the correct value.  This
	 * is a bit of a hack, but there are limited opportunities for
	 * getting information into the thread and the alternatives
	 * seemed like they'd be overkill.  We can't tell just by looking
	 * at the old PIR value which state it's in, since the same value
	 * could be valid for one thread out of reset and for a different
	 * thread in Linux.
	 */

	mfspr	r3, SPRN_PIR
	cmpwi	r4,0
	bne	1f
	rlwimi	r3, r3, 30, 2, 30
	mtspr	SPRN_PIR, r3
1:
#endif

_GLOBAL(generic_secondary_thread_init)
	mr	r24,r3

	/* turn on 64-bit mode */
	bl	enable_64b_mode

	/* get a valid TOC pointer, wherever we're mapped at */
	bl	relative_toc
	tovirt(r2,r2)

#ifdef CONFIG_PPC_BOOK3E
	/* Book3E initialization */
	mr	r3,r24
	bl	book3e_secondary_thread_init
#endif
	b	generic_secondary_common_init

/*
 * On pSeries and most other platforms, secondary processors spin
 * in the following code.
 * At entry, r3 = this processor's number (physical cpu id)
 *
 * On Book3E, r4 = 1 to indicate that the initial TLB entry for
 * this core already exists (setup via some other mechanism such
 * as SCOM before entry).
 */
_GLOBAL(generic_secondary_smp_init)
	FIXUP_ENDIAN
	mr	r24,r3
	mr	r25,r4

	/* turn on 64-bit mode */
	bl	enable_64b_mode

	/* get a valid TOC pointer, wherever we're mapped at */
	bl	relative_toc
	tovirt(r2,r2)

#ifdef CONFIG_PPC_BOOK3E
	/* Book3E initialization */
	mr	r3,r24
	mr	r4,r25
	bl	book3e_secondary_core_init

/*
 * After common core init has finished, check if the current thread is the
 * one we wanted to boot. If not, start the specified thread and stop the
 * current thread.
 */
	LOAD_REG_ADDR(r4, booting_thread_hwid)
	lwz     r3, 0(r4)
	li	r5, INVALID_THREAD_HWID
	cmpw	r3, r5
	beq	20f

	/*
	 * The value of booting_thread_hwid has been stored in r3,
	 * so make it invalid.
	 */
	stw	r5, 0(r4)

	/*
	 * Get the current thread id and check if it is the one we wanted.
	 * If not, start the one specified in booting_thread_hwid and stop
	 * the current thread.
	 */
	mfspr	r8, SPRN_TIR
	cmpw	r3, r8
	beq	20f

	/* start the specified thread */
	LOAD_REG_ADDR(r5, fsl_secondary_thread_init)
	ld	r4, 0(r5)
	bl	book3e_start_thread

	/* stop the current thread */
	mr	r3, r8
	bl	book3e_stop_thread
10:
	b	10b
20:
#endif

generic_secondary_common_init:
	/* Set up a paca value for this processor. Since we have the
	 * physical cpu id in r24, we need to search the pacas to find
	 * which logical id maps to our physical one.
	 */
#ifndef CONFIG_SMP
	b	kexec_wait		/* wait for next kernel if !SMP	 */
#else
	LOAD_REG_ADDR(r8, paca_ptrs)	/* Load paca_ptrs pointe	 */
	ld	r8,0(r8)		/* Get base vaddr of array	 */
	LOAD_REG_ADDR(r7, nr_cpu_ids)	/* Load nr_cpu_ids address       */
	lwz	r7,0(r7)		/* also the max paca allocated 	 */
	li	r5,0			/* logical cpu id                */
1:
	sldi	r9,r5,3			/* get paca_ptrs[] index from cpu id */
	ldx	r13,r9,r8		/* r13 = paca_ptrs[cpu id]       */
	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
	cmpw	r6,r24			/* Compare to our id             */
	beq	2f
	addi	r5,r5,1
	cmpw	r5,r7			/* Check if more pacas exist     */
	blt	1b

	mr	r3,r24			/* not found, copy phys to r3	 */
	b	kexec_wait		/* next kernel might do better	 */

2:	SET_PACA(r13)
#ifdef CONFIG_PPC_BOOK3E
	addi	r12,r13,PACA_EXTLB	/* and TLB exc frame in another  */
	mtspr	SPRN_SPRG_TLB_EXFRAME,r12
#endif

	/* From now on, r24 is expected to be logical cpuid */
	mr	r24,r5

	/* See if we need to call a cpu state restore handler */
	LOAD_REG_ADDR(r23, cur_cpu_spec)
	ld	r23,0(r23)
	ld	r12,CPU_SPEC_RESTORE(r23)
	cmpdi	0,r12,0
	beq	3f
#ifdef PPC64_ELF_ABI_v1
	ld	r12,0(r12)
#endif
	mtctr	r12
	bctrl

3:	LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */
	lwarx	r4,0,r3
	subi	r4,r4,1
	stwcx.	r4,0,r3
	bne	3b
	isync

4:	HMT_LOW
	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor should */
					/* start.			 */
	cmpwi	0,r23,0
	beq	4b			/* Loop until told to go	 */

	sync				/* order paca.run and cur_cpu_spec */
	isync				/* In case code patching happened */

	/* Create a temp kernel stack for use before relocation is on.	*/
	ld	r1,PACAEMERGSP(r13)
	subi	r1,r1,STACK_FRAME_OVERHEAD

	b	__secondary_start
#endif /* SMP */

/*
 * Turn the MMU off.
 * Assumes we're mapped EA == RA if the MMU is on.
 */
#ifdef CONFIG_PPC_BOOK3S
__mmu_off:
	mfmsr	r3
	andi.	r0,r3,MSR_IR|MSR_DR
	beqlr
	mflr	r4
	andc	r3,r3,r0
	mtspr	SPRN_SRR0,r4
	mtspr	SPRN_SRR1,r3
	sync
	rfid
	b	.	/* prevent speculative execution */
#endif


/*
 * Here is our main kernel entry point. We support currently 2 kind of entries
 * depending on the value of r5.
 *
 *   r5 != NULL -> OF entry, we go to prom_init, "legacy" parameter content
 *                 in r3...r7
 *
 *   r5 == NULL -> kexec style entry. r3 is a physical pointer to the
 *                 DT block, r4 is a physical pointer to the kernel itself
 *
 */
__start_initialization_multiplatform:
	/* Make sure we are running in 64 bits mode */
	bl	enable_64b_mode

	/* Get TOC pointer (current runtime address) */
	bl	relative_toc

	/* find out where we are now */
	bcl	20,31,$+4
0:	mflr	r26			/* r26 = runtime addr here */
	addis	r26,r26,(_stext - 0b)@ha
	addi	r26,r26,(_stext - 0b)@l	/* current runtime base addr */

	/*
	 * Are we booted from a PROM Of-type client-interface ?
	 */
	cmpldi	cr0,r5,0
	beq	1f
	b	__boot_from_prom		/* yes -> prom */
1:
	/* Save parameters */
	mr	r31,r3
	mr	r30,r4
#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
	/* Save OPAL entry */
	mr	r28,r8
	mr	r29,r9
#endif

#ifdef CONFIG_PPC_BOOK3E
	bl	start_initialization_book3e
	b	__after_prom_start
#else
	/* Setup some critical 970 SPRs before switching MMU off */
	mfspr	r0,SPRN_PVR
	srwi	r0,r0,16
	cmpwi	r0,0x39		/* 970 */
	beq	1f
	cmpwi	r0,0x3c		/* 970FX */
	beq	1f
	cmpwi	r0,0x44		/* 970MP */
	beq	1f
	cmpwi	r0,0x45		/* 970GX */
	bne	2f
1:	bl	__cpu_preinit_ppc970
2:

	/* Switch off MMU if not already off */
	bl	__mmu_off
	b	__after_prom_start
#endif /* CONFIG_PPC_BOOK3E */

__boot_from_prom:
#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
	/* Save parameters */
	mr	r31,r3
	mr	r30,r4
	mr	r29,r5
	mr	r28,r6
	mr	r27,r7

	/*
	 * Align the stack to 16-byte boundary
	 * Depending on the size and layout of the ELF sections in the initial
	 * boot binary, the stack pointer may be unaligned on PowerMac
	 */
	rldicr	r1,r1,0,59

#ifdef CONFIG_RELOCATABLE
	/* Relocate code for where we are now */
	mr	r3,r26
	bl	relocate
#endif

	/* Restore parameters */
	mr	r3,r31
	mr	r4,r30
	mr	r5,r29
	mr	r6,r28
	mr	r7,r27

	/* Do all of the interaction with OF client interface */
	mr	r8,r26
	bl	prom_init
#endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */

	/* We never return. We also hit that trap if trying to boot
	 * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
	trap

__after_prom_start:
#ifdef CONFIG_RELOCATABLE
	/* process relocations for the final address of the kernel */
	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
	sldi	r25,r25,32
#if defined(CONFIG_PPC_BOOK3E)
	tovirt(r26,r26)		/* on booke, we already run at PAGE_OFFSET */
#endif
	lwz	r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
#if defined(CONFIG_PPC_BOOK3E)
	tophys(r26,r26)
#endif
	cmplwi	cr0,r7,1	/* flagged to stay where we are ? */
	bne	1f
	add	r25,r25,r26
1:	mr	r3,r25
	bl	relocate
#if defined(CONFIG_PPC_BOOK3E)
	/* IVPR needs to be set after relocation. */
	bl	init_core_book3e
#endif
#endif

/*
 * We need to run with _stext at physical address PHYSICAL_START.
 * This will leave some code in the first 256B of
 * real memory, which are reserved for software use.
 *
 * Note: This process overwrites the OF exception vectors.
 */
	li	r3,0			/* target addr */
#ifdef CONFIG_PPC_BOOK3E
	tovirt(r3,r3)		/* on booke, we already run at PAGE_OFFSET */
#endif
	mr.	r4,r26			/* In some cases the loader may  */
#if defined(CONFIG_PPC_BOOK3E)
	tovirt(r4,r4)
#endif
	beq	9f			/* have already put us at zero */
	li	r6,0x100		/* Start offset, the first 0x100 */
					/* bytes were copied earlier.	 */

#ifdef CONFIG_RELOCATABLE
/*
 * Check if the kernel has to be running as relocatable kernel based on the
 * variable __run_at_load, if it is set the kernel is treated as relocatable
 * kernel, otherwise it will be moved to PHYSICAL_START
 */
#if defined(CONFIG_PPC_BOOK3E)
	tovirt(r26,r26)		/* on booke, we already run at PAGE_OFFSET */
#endif
	lwz	r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
	cmplwi	cr0,r7,1
	bne	3f

#ifdef CONFIG_PPC_BOOK3E
	LOAD_REG_ADDR(r5, __end_interrupts)
	LOAD_REG_ADDR(r11, _stext)
	sub	r5,r5,r11
#else
	/* just copy interrupts */
	LOAD_REG_IMMEDIATE_SYM(r5, r11, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
#endif
	b	5f
3:
#endif
	/* # bytes of memory to copy */
	lis	r5,(ABS_ADDR(copy_to_here))@ha
	addi	r5,r5,(ABS_ADDR(copy_to_here))@l

	bl	copy_and_flush		/* copy the first n bytes	 */
					/* this includes the code being	 */
					/* executed here.		 */
	/* Jump to the copy of this code that we just made */
	addis	r8,r3,(ABS_ADDR(4f))@ha
	addi	r12,r8,(ABS_ADDR(4f))@l
	mtctr	r12
	bctr

.balign 8
p_end: .8byte _end - copy_to_here

4:
	/*
	 * Now copy the rest of the kernel up to _end, add
	 * _end - copy_to_here to the copy limit and run again.
	 */
	addis   r8,r26,(ABS_ADDR(p_end))@ha
	ld      r8,(ABS_ADDR(p_end))@l(r8)
	add	r5,r5,r8
5:	bl	copy_and_flush		/* copy the rest */

9:	b	start_here_multiplatform

/*
 * Copy routine used to copy the kernel to start at physical address 0
 * and flush and invalidate the caches as needed.
 * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset
 * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5.
 *
 * Note: this routine *only* clobbers r0, r6 and lr
 */
_GLOBAL(copy_and_flush)
	addi	r5,r5,-8
	addi	r6,r6,-8
4:	li	r0,8			/* Use the smallest common	*/
					/* denominator cache line	*/
					/* size.  This results in	*/
					/* extra cache line flushes	*/
					/* but operation is correct.	*/
					/* Can't get cache line size	*/
					/* from NACA as it is being	*/
					/* moved too.			*/

	mtctr	r0			/* put # words/line in ctr	*/
3:	addi	r6,r6,8			/* copy a cache line		*/
	ldx	r0,r6,r4
	stdx	r0,r6,r3
	bdnz	3b
	dcbst	r6,r3			/* write it to memory		*/
	sync
	icbi	r6,r3			/* flush the icache line	*/
	cmpld	0,r6,r5
	blt	4b
	sync
	addi	r5,r5,8
	addi	r6,r6,8
	isync
	blr

.align 8
copy_to_here:

#ifdef CONFIG_SMP
#ifdef CONFIG_PPC_PMAC
/*
 * On PowerMac, secondary processors starts from the reset vector, which
 * is temporarily turned into a call to one of the functions below.
 */
	.section ".text";
	.align 2 ;

	.globl	__secondary_start_pmac_0
__secondary_start_pmac_0:
	/* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */
	li	r24,0
	b	1f
	li	r24,1
	b	1f
	li	r24,2
	b	1f
	li	r24,3
1:

_GLOBAL(pmac_secondary_start)
	/* turn on 64-bit mode */
	bl	enable_64b_mode

	li	r0,0
	mfspr	r3,SPRN_HID4
	rldimi	r3,r0,40,23	/* clear bit 23 (rm_ci) */
	sync
	mtspr	SPRN_HID4,r3
	isync
	sync
	slbia

	/* get TOC pointer (real address) */
	bl	relative_toc
	tovirt(r2,r2)

	/* Copy some CPU settings from CPU 0 */
	bl	__restore_cpu_ppc970

	/* pSeries do that early though I don't think we really need it */
	mfmsr	r3
	ori	r3,r3,MSR_RI
	mtmsrd	r3			/* RI on */

	/* Set up a paca value for this processor. */
	LOAD_REG_ADDR(r4,paca_ptrs)	/* Load paca pointer		*/
	ld	r4,0(r4)		/* Get base vaddr of paca_ptrs array */
	sldi	r5,r24,3		/* get paca_ptrs[] index from cpu id */
	ldx	r13,r5,r4		/* r13 = paca_ptrs[cpu id]       */
	SET_PACA(r13)			/* Save vaddr of paca in an SPRG*/

	/* Mark interrupts soft and hard disabled (they might be enabled
	 * in the PACA when doing hotplug)
	 */
	li	r0,IRQS_DISABLED
	stb	r0,PACAIRQSOFTMASK(r13)
	li	r0,PACA_IRQ_HARD_DIS
	stb	r0,PACAIRQHAPPENED(r13)

	/* Create a temp kernel stack for use before relocation is on.	*/
	ld	r1,PACAEMERGSP(r13)
	subi	r1,r1,STACK_FRAME_OVERHEAD

	b	__secondary_start

#endif /* CONFIG_PPC_PMAC */

/*
 * This function is called after the master CPU has released the
 * secondary processors.  The execution environment is relocation off.
 * The paca for this processor has the following fields initialized at
 * this point:
 *   1. Processor number
 *   2. Segment table pointer (virtual address)
 * On entry the following are set:
 *   r1	       = stack pointer (real addr of temp stack)
 *   r24       = cpu# (in Linux terms)
 *   r13       = paca virtual address
 *   SPRG_PACA = paca virtual address
 */
	.section ".text";
	.align 2 ;

	.globl	__secondary_start
__secondary_start:
	/* Set thread priority to MEDIUM */
	HMT_MEDIUM

	/*
	 * Do early setup for this CPU, in particular initialising the MMU so we
	 * can turn it on below. This is a call to C, which is OK, we're still
	 * running on the emergency stack.
	 */
	bl	early_setup_secondary

	/*
	 * The primary has initialized our kernel stack for us in the paca, grab
	 * it and put it in r1. We must *not* use it until we turn on the MMU
	 * below, because it may not be inside the RMO.
	 */
	ld	r1, PACAKSAVE(r13)

	/* Clear backchain so we get nice backtraces */
	li	r7,0
	mtlr	r7

	/* Mark interrupts soft and hard disabled (they might be enabled
	 * in the PACA when doing hotplug)
	 */
	li	r7,IRQS_DISABLED
	stb	r7,PACAIRQSOFTMASK(r13)
	li	r0,PACA_IRQ_HARD_DIS
	stb	r0,PACAIRQHAPPENED(r13)

	/* enable MMU and jump to start_secondary */
	LOAD_REG_ADDR(r3, start_secondary_prolog)
	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)

	mtspr	SPRN_SRR0,r3
	mtspr	SPRN_SRR1,r4
	RFI
	b	.	/* prevent speculative execution */

/*
 * Running with relocation on at this point.  All we want to do is
 * zero the stack back-chain pointer and get the TOC virtual address
 * before going into C code.
 */
start_secondary_prolog:
	ld	r2,PACATOC(r13)
	li	r3,0
	std	r3,0(r1)		/* Zero the stack frame pointer	*/
	bl	start_secondary
	b	.
/*
 * Reset stack pointer and call start_secondary
 * to continue with online operation when woken up
 * from cede in cpu offline.
 */
_GLOBAL(start_secondary_resume)
	ld	r1,PACAKSAVE(r13)	/* Reload kernel stack pointer */
	li	r3,0
	std	r3,0(r1)		/* Zero the stack frame pointer	*/
	bl	start_secondary
	b	.
#endif

/*
 * This subroutine clobbers r11 and r12
 */
enable_64b_mode:
	mfmsr	r11			/* grab the current MSR */
#ifdef CONFIG_PPC_BOOK3E
	oris	r11,r11,0x8000		/* CM bit set, we'll set ICM later */
	mtmsr	r11
#else /* CONFIG_PPC_BOOK3E */
	li	r12,(MSR_64BIT | MSR_ISF)@highest
	sldi	r12,r12,48
	or	r11,r11,r12
	mtmsrd	r11
	isync
#endif
	blr

/*
 * This puts the TOC pointer into r2, offset by 0x8000 (as expected
 * by the toolchain).  It computes the correct value for wherever we
 * are running at the moment, using position-independent code.
 *
 * Note: The compiler constructs pointers using offsets from the
 * TOC in -mcmodel=medium mode. After we relocate to 0 but before
 * the MMU is on we need our TOC to be a virtual address otherwise
 * these pointers will be real addresses which may get stored and
 * accessed later with the MMU on. We use tovirt() at the call
 * sites to handle this.
 */
_GLOBAL(relative_toc)
	mflr	r0
	bcl	20,31,$+4
0:	mflr	r11
	ld	r2,(p_toc - 0b)(r11)
	add	r2,r2,r11
	mtlr	r0
	blr

.balign 8
p_toc:	.8byte	__toc_start + 0x8000 - 0b

/*
 * This is where the main kernel code starts.
 */
__REF
start_here_multiplatform:
	/* set up the TOC */
	bl      relative_toc
	tovirt(r2,r2)

	/* Clear out the BSS. It may have been done in prom_init,
	 * already but that's irrelevant since prom_init will soon
	 * be detached from the kernel completely. Besides, we need
	 * to clear it now for kexec-style entry.
	 */
	LOAD_REG_ADDR(r11,__bss_stop)
	LOAD_REG_ADDR(r8,__bss_start)
	sub	r11,r11,r8		/* bss size			*/
	addi	r11,r11,7		/* round up to an even double word */
	srdi.	r11,r11,3		/* shift right by 3		*/
	beq	4f
	addi	r8,r8,-8
	li	r0,0
	mtctr	r11			/* zero this many doublewords	*/
3:	stdu	r0,8(r8)
	bdnz	3b
4:

#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
	/* Setup OPAL entry */
	LOAD_REG_ADDR(r11, opal)
	std	r28,0(r11);
	std	r29,8(r11);
#endif

#ifndef CONFIG_PPC_BOOK3E
	mfmsr	r6
	ori	r6,r6,MSR_RI
	mtmsrd	r6			/* RI on */
#endif

#ifdef CONFIG_RELOCATABLE
	/* Save the physical address we're running at in kernstart_addr */
	LOAD_REG_ADDR(r4, kernstart_addr)
	clrldi	r0,r25,2
	std	r0,0(r4)
#endif

	/* The following gets the stack set up with the regs */
	/* pointing to the real addr of the kernel stack.  This is   */
	/* all done to support the C function call below which sets  */
	/* up the htab.  This is done because we have relocated the  */
	/* kernel but are still running in real mode. */

	LOAD_REG_ADDR(r3,init_thread_union)

	/* set up a stack pointer */
	LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
	add	r1,r3,r1
	li	r0,0
	stdu	r0,-STACK_FRAME_OVERHEAD(r1)

	/*
	 * Do very early kernel initializations, including initial hash table
	 * and SLB setup before we turn on relocation.
	 */

	/* Restore parameters passed from prom_init/kexec */
	mr	r3,r31
	LOAD_REG_ADDR(r12, DOTSYM(early_setup))
	mtctr	r12
	bctrl		/* also sets r13 and SPRG_PACA */

	LOAD_REG_ADDR(r3, start_here_common)
	ld	r4,PACAKMSR(r13)
	mtspr	SPRN_SRR0,r3
	mtspr	SPRN_SRR1,r4
	RFI
	b	.	/* prevent speculative execution */

	.previous
	/* This is where all platforms converge execution */

start_here_common:
	/* relocation is on at this point */
	std	r1,PACAKSAVE(r13)

	/* Load the TOC (virtual address) */
	ld	r2,PACATOC(r13)

	/* Mark interrupts soft and hard disabled (they might be enabled
	 * in the PACA when doing hotplug)
	 */
	li	r0,IRQS_DISABLED
	stb	r0,PACAIRQSOFTMASK(r13)
	li	r0,PACA_IRQ_HARD_DIS
	stb	r0,PACAIRQHAPPENED(r13)

	/* Generic kernel entry */
	bl	start_kernel

	/* Not reached */
	trap
	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0

/*
 * We put a few things here that have to be page-aligned.
 * This stuff goes at the beginning of the bss, which is page-aligned.
 */
	.section ".bss"
/*
 * pgd dir should be aligned to PGD_TABLE_SIZE which is 64K.
 * We will need to find a better way to fix this
 */
	.align	16

	.globl	swapper_pg_dir
swapper_pg_dir:
	.space	PGD_TABLE_SIZE

	.globl	empty_zero_page
empty_zero_page:
	.space	PAGE_SIZE
EXPORT_SYMBOL(empty_zero_page)