powerpc: Merge enough to start building in arch/powerpc.

This creates the directory structure under arch/powerpc and a bunch
of Kconfig files.  It does a first-cut merge of arch/powerpc/mm,
arch/powerpc/lib and arch/powerpc/platforms/powermac.  This is enough
to build a 32-bit powermac kernel with ARCH=powerpc.

For now we are getting some unmerged files from arch/ppc/kernel and
arch/ppc/syslib, or arch/ppc64/kernel.  This makes some minor changes
to files in those directories and files outside arch/powerpc.

The boot directory is still not merged.  That's going to be interesting.

Signed-off-by: Paul Mackerras <paulus@samba.org>
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
new file mode 100644
index 0000000..22a5ee0
--- /dev/null
+++ b/arch/powerpc/kernel/head_64.S
@@ -0,0 +1,2011 @@
+/*
+ *  arch/ppc64/kernel/head.S
+ *
+ *  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 low-level support and setup for the
+ *  PowerPC-64 platform, including trap and interrupt dispatch.
+ *
+ *  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 <linux/config.h>
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/systemcfg.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/bug.h>
+#include <asm/cputable.h>
+#include <asm/setup.h>
+#include <asm/hvcall.h>
+#include <asm/iSeries/LparMap.h>
+
+#ifdef CONFIG_PPC_ISERIES
+#define DO_SOFT_DISABLE
+#endif
+
+/*
+ * We layout physical memory as follows:
+ * 0x0000 - 0x00ff : Secondary processor spin code
+ * 0x0100 - 0x2fff : pSeries Interrupt prologs
+ * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs
+ * 0x6000 - 0x6fff : Initial (CPU0) segment table
+ * 0x7000 - 0x7fff : FWNMI data area
+ * 0x8000 -        : Early init and support code
+ */
+
+/*
+ *   SPRG Usage
+ *
+ *   Register	Definition
+ *
+ *   SPRG0	reserved for hypervisor
+ *   SPRG1	temp - used to save gpr
+ *   SPRG2	temp - used to save gpr
+ *   SPRG3	virt addr of paca
+ */
+
+/*
+ * Entering into this code we make the following assumptions:
+ *  For pSeries:
+ *   1. The MMU is off & open firmware is running in real mode.
+ *   2. The kernel is entered at __start
+ *
+ *  For iSeries:
+ *   1. The MMU is on (as it always is for iSeries)
+ *   2. The kernel is entered at system_reset_iSeries
+ */
+
+	.text
+	.globl  _stext
+_stext:
+#ifdef CONFIG_PPC_MULTIPLATFORM
+_GLOBAL(__start)
+	/* NOP this out unconditionally */
+BEGIN_FTR_SECTION
+	b .__start_initialization_multiplatform
+END_FTR_SECTION(0, 1)
+#endif /* CONFIG_PPC_MULTIPLATFORM */
+
+	/* Catch branch to 0 in real mode */
+	trap
+
+#ifdef CONFIG_PPC_ISERIES
+	/*
+	 * At offset 0x20, there is a pointer to iSeries LPAR data.
+	 * This is required by the hypervisor
+	 */
+	. = 0x20
+	.llong hvReleaseData-KERNELBASE
+
+	/*
+	 * At offset 0x28 and 0x30 are offsets to the mschunks_map
+	 * array (used by the iSeries LPAR debugger to do translation
+	 * between physical addresses and absolute addresses) and
+	 * to the pidhash table (also used by the debugger)
+	 */
+	.llong mschunks_map-KERNELBASE
+	.llong 0	/* pidhash-KERNELBASE SFRXXX */
+
+	/* Offset 0x38 - Pointer to start of embedded System.map */
+	.globl	embedded_sysmap_start
+embedded_sysmap_start:
+	.llong	0
+	/* Offset 0x40 - Pointer to end of embedded System.map */
+	.globl	embedded_sysmap_end
+embedded_sysmap_end:
+	.llong	0
+
+#endif /* CONFIG_PPC_ISERIES */
+
+	/* Secondary processors spin on this value until it goes to 1. */
+	.globl  __secondary_hold_spinloop
+__secondary_hold_spinloop:
+	.llong	0x0
+
+	/* Secondary processors write this value with their cpu # */
+	/* after they enter the spin loop immediately below.	  */
+	.globl	__secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+	.llong	0x0
+
+	. = 0x60
+/*
+ * The following code is used on pSeries to hold secondary processors
+ * in a spin loop after they have been freed from OpenFirmware, 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.
+ */
+_GLOBAL(__secondary_hold)
+	mfmsr	r24
+	ori	r24,r24,MSR_RI
+	mtmsrd	r24			/* RI on */
+
+	/* Grab our linux cpu number */
+	mr	r24,r3
+
+	/* 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,__secondary_hold_acknowledge@l(0)
+	sync
+
+	/* All secondary cpus wait here until told to start. */
+100:	ld	r4,__secondary_hold_spinloop@l(0)
+	cmpdi	0,r4,1
+	bne	100b
+
+#ifdef CONFIG_HMT
+	b	.hmt_init
+#else
+#ifdef CONFIG_SMP
+	mr	r3,r24
+	b	.pSeries_secondary_smp_init
+#else
+	BUG_OPCODE
+#endif
+#endif
+
+/* This value is used to mark exception frames on the stack. */
+	.section ".toc","aw"
+exception_marker:
+	.tc	ID_72656773_68657265[TC],0x7265677368657265
+	.text
+
+/*
+ * The following macros define the code that appears as
+ * the prologue to each of the exception handlers.  They
+ * are split into two parts to allow a single kernel binary
+ * to be used for pSeries and iSeries.
+ * LOL.  One day... - paulus
+ */
+
+/*
+ * We make as much of the exception code common between native
+ * exception handlers (including pSeries LPAR) and iSeries LPAR
+ * implementations as possible.
+ */
+
+/*
+ * This is the start of the interrupt handlers for pSeries
+ * This code runs with relocation off.
+ */
+#define EX_R9		0
+#define EX_R10		8
+#define EX_R11		16
+#define EX_R12		24
+#define EX_R13		32
+#define EX_SRR0		40
+#define EX_R3		40	/* SLB miss saves R3, but not SRR0 */
+#define EX_DAR		48
+#define EX_LR		48	/* SLB miss saves LR, but not DAR */
+#define EX_DSISR	56
+#define EX_CCR		60
+
+#define EXCEPTION_PROLOG_PSERIES(area, label)				\
+	mfspr	r13,SPRG3;		/* get paca address into r13 */	\
+	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
+	std	r10,area+EX_R10(r13);					\
+	std	r11,area+EX_R11(r13);					\
+	std	r12,area+EX_R12(r13);					\
+	mfspr	r9,SPRG1;						\
+	std	r9,area+EX_R13(r13);					\
+	mfcr	r9;							\
+	clrrdi	r12,r13,32;		/* get high part of &label */	\
+	mfmsr	r10;							\
+	mfspr	r11,SRR0;		/* save SRR0 */			\
+	ori	r12,r12,(label)@l;	/* virt addr of handler */	\
+	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI;				\
+	mtspr	SRR0,r12;						\
+	mfspr	r12,SRR1;		/* and SRR1 */			\
+	mtspr	SRR1,r10;						\
+	rfid;								\
+	b	.	/* prevent speculative execution */
+
+/*
+ * This is the start of the interrupt handlers for iSeries
+ * This code runs with relocation on.
+ */
+#define EXCEPTION_PROLOG_ISERIES_1(area)				\
+	mfspr	r13,SPRG3;		/* get paca address into r13 */	\
+	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
+	std	r10,area+EX_R10(r13);					\
+	std	r11,area+EX_R11(r13);					\
+	std	r12,area+EX_R12(r13);					\
+	mfspr	r9,SPRG1;						\
+	std	r9,area+EX_R13(r13);					\
+	mfcr	r9
+
+#define EXCEPTION_PROLOG_ISERIES_2					\
+	mfmsr	r10;							\
+	ld	r11,PACALPPACA+LPPACASRR0(r13);				\
+	ld	r12,PACALPPACA+LPPACASRR1(r13);				\
+	ori	r10,r10,MSR_RI;						\
+	mtmsrd	r10,1
+
+/*
+ * The common exception prolog is used for all except a few exceptions
+ * such as a segment miss on a kernel address.  We have to be prepared
+ * to take another exception from the point where we first touch the
+ * kernel stack onwards.
+ *
+ * On entry r13 points to the paca, r9-r13 are saved in the paca,
+ * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
+ * SRR1, and relocation is on.
+ */
+#define EXCEPTION_PROLOG_COMMON(n, area)				   \
+	andi.	r10,r12,MSR_PR;		/* See if coming from user	*/ \
+	mr	r10,r1;			/* Save r1			*/ \
+	subi	r1,r1,INT_FRAME_SIZE;	/* alloc frame on kernel stack	*/ \
+	beq-	1f;							   \
+	ld	r1,PACAKSAVE(r13);	/* kernel stack to use		*/ \
+1:	cmpdi	cr1,r1,0;		/* check if r1 is in userspace	*/ \
+	bge-	cr1,bad_stack;		/* abort if it is		*/ \
+	std	r9,_CCR(r1);		/* save CR in stackframe	*/ \
+	std	r11,_NIP(r1);		/* save SRR0 in stackframe	*/ \
+	std	r12,_MSR(r1);		/* save SRR1 in stackframe	*/ \
+	std	r10,0(r1);		/* make stack chain pointer	*/ \
+	std	r0,GPR0(r1);		/* save r0 in stackframe	*/ \
+	std	r10,GPR1(r1);		/* save r1 in stackframe	*/ \
+	std	r2,GPR2(r1);		/* save r2 in stackframe	*/ \
+	SAVE_4GPRS(3, r1);		/* save r3 - r6 in stackframe	*/ \
+	SAVE_2GPRS(7, r1);		/* save r7, r8 in stackframe	*/ \
+	ld	r9,area+EX_R9(r13);	/* move r9, r10 to stackframe	*/ \
+	ld	r10,area+EX_R10(r13);					   \
+	std	r9,GPR9(r1);						   \
+	std	r10,GPR10(r1);						   \
+	ld	r9,area+EX_R11(r13);	/* move r11 - r13 to stackframe	*/ \
+	ld	r10,area+EX_R12(r13);					   \
+	ld	r11,area+EX_R13(r13);					   \
+	std	r9,GPR11(r1);						   \
+	std	r10,GPR12(r1);						   \
+	std	r11,GPR13(r1);						   \
+	ld	r2,PACATOC(r13);	/* get kernel TOC into r2	*/ \
+	mflr	r9;			/* save LR in stackframe	*/ \
+	std	r9,_LINK(r1);						   \
+	mfctr	r10;			/* save CTR in stackframe	*/ \
+	std	r10,_CTR(r1);						   \
+	mfspr	r11,XER;		/* save XER in stackframe	*/ \
+	std	r11,_XER(r1);						   \
+	li	r9,(n)+1;						   \
+	std	r9,_TRAP(r1);		/* set trap number		*/ \
+	li	r10,0;							   \
+	ld	r11,exception_marker@toc(r2);				   \
+	std	r10,RESULT(r1);		/* clear regs->result		*/ \
+	std	r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame	*/
+
+/*
+ * Exception vectors.
+ */
+#define STD_EXCEPTION_PSERIES(n, label)			\
+	. = n;						\
+	.globl label##_pSeries;				\
+label##_pSeries:					\
+	HMT_MEDIUM;					\
+	mtspr	SPRG1,r13;		/* save r13 */	\
+	RUNLATCH_ON(r13);				\
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
+
+#define STD_EXCEPTION_ISERIES(n, label, area)		\
+	.globl label##_iSeries;				\
+label##_iSeries:					\
+	HMT_MEDIUM;					\
+	mtspr	SPRG1,r13;		/* save r13 */	\
+	RUNLATCH_ON(r13);				\
+	EXCEPTION_PROLOG_ISERIES_1(area);		\
+	EXCEPTION_PROLOG_ISERIES_2;			\
+	b	label##_common
+
+#define MASKABLE_EXCEPTION_ISERIES(n, label)				\
+	.globl label##_iSeries;						\
+label##_iSeries:							\
+	HMT_MEDIUM;							\
+	mtspr	SPRG1,r13;		/* save r13 */			\
+	RUNLATCH_ON(r13);						\
+	EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN);				\
+	lbz	r10,PACAPROCENABLED(r13);				\
+	cmpwi	0,r10,0;						\
+	beq-	label##_iSeries_masked;					\
+	EXCEPTION_PROLOG_ISERIES_2;					\
+	b	label##_common;						\
+
+#ifdef DO_SOFT_DISABLE
+#define DISABLE_INTS				\
+	lbz	r10,PACAPROCENABLED(r13);	\
+	li	r11,0;				\
+	std	r10,SOFTE(r1);			\
+	mfmsr	r10;				\
+	stb	r11,PACAPROCENABLED(r13);	\
+	ori	r10,r10,MSR_EE;			\
+	mtmsrd	r10,1
+
+#define ENABLE_INTS				\
+	lbz	r10,PACAPROCENABLED(r13);	\
+	mfmsr	r11;				\
+	std	r10,SOFTE(r1);			\
+	ori	r11,r11,MSR_EE;			\
+	mtmsrd	r11,1
+
+#else	/* hard enable/disable interrupts */
+#define DISABLE_INTS
+
+#define ENABLE_INTS				\
+	ld	r12,_MSR(r1);			\
+	mfmsr	r11;				\
+	rlwimi	r11,r12,0,MSR_EE;		\
+	mtmsrd	r11,1
+
+#endif
+
+#define STD_EXCEPTION_COMMON(trap, label, hdlr)		\
+	.align	7;					\
+	.globl label##_common;				\
+label##_common:						\
+	EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);	\
+	DISABLE_INTS;					\
+	bl	.save_nvgprs;				\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;		\
+	bl	hdlr;					\
+	b	.ret_from_except
+
+#define STD_EXCEPTION_COMMON_LITE(trap, label, hdlr)	\
+	.align	7;					\
+	.globl label##_common;				\
+label##_common:						\
+	EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);	\
+	DISABLE_INTS;					\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;		\
+	bl	hdlr;					\
+	b	.ret_from_except_lite
+
+/*
+ * Start of pSeries system interrupt routines
+ */
+	. = 0x100
+	.globl __start_interrupts
+__start_interrupts:
+
+	STD_EXCEPTION_PSERIES(0x100, system_reset)
+
+	. = 0x200
+_machine_check_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRG1,r13		/* save r13 */
+	RUNLATCH_ON(r13)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+
+	. = 0x300
+	.globl data_access_pSeries
+data_access_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRG1,r13
+BEGIN_FTR_SECTION
+	mtspr	SPRG2,r12
+	mfspr	r13,DAR
+	mfspr	r12,DSISR
+	srdi	r13,r13,60
+	rlwimi	r13,r12,16,0x20
+	mfcr	r12
+	cmpwi	r13,0x2c
+	beq	.do_stab_bolted_pSeries
+	mtcrf	0x80,r12
+	mfspr	r12,SPRG2
+END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common)
+
+	. = 0x380
+	.globl data_access_slb_pSeries
+data_access_slb_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRG1,r13
+	RUNLATCH_ON(r13)
+	mfspr	r13,SPRG3		/* get paca address into r13 */
+	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r9,SPRG1
+	std	r9,PACA_EXSLB+EX_R13(r13)
+	mfcr	r9
+	mfspr	r12,SRR1		/* and SRR1 */
+	mfspr	r3,DAR
+	b	.do_slb_miss		/* Rel. branch works in real mode */
+
+	STD_EXCEPTION_PSERIES(0x400, instruction_access)
+
+	. = 0x480
+	.globl instruction_access_slb_pSeries
+instruction_access_slb_pSeries:
+	HMT_MEDIUM
+	mtspr	SPRG1,r13
+	RUNLATCH_ON(r13)
+	mfspr	r13,SPRG3		/* get paca address into r13 */
+	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r9,SPRG1
+	std	r9,PACA_EXSLB+EX_R13(r13)
+	mfcr	r9
+	mfspr	r12,SRR1		/* and SRR1 */
+	mfspr	r3,SRR0			/* SRR0 is faulting address */
+	b	.do_slb_miss		/* Rel. branch works in real mode */
+
+	STD_EXCEPTION_PSERIES(0x500, hardware_interrupt)
+	STD_EXCEPTION_PSERIES(0x600, alignment)
+	STD_EXCEPTION_PSERIES(0x700, program_check)
+	STD_EXCEPTION_PSERIES(0x800, fp_unavailable)
+	STD_EXCEPTION_PSERIES(0x900, decrementer)
+	STD_EXCEPTION_PSERIES(0xa00, trap_0a)
+	STD_EXCEPTION_PSERIES(0xb00, trap_0b)
+
+	. = 0xc00
+	.globl	system_call_pSeries
+system_call_pSeries:
+	HMT_MEDIUM
+	RUNLATCH_ON(r9)
+	mr	r9,r13
+	mfmsr	r10
+	mfspr	r13,SPRG3
+	mfspr	r11,SRR0
+	clrrdi	r12,r13,32
+	oris	r12,r12,system_call_common@h
+	ori	r12,r12,system_call_common@l
+	mtspr	SRR0,r12
+	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI
+	mfspr	r12,SRR1
+	mtspr	SRR1,r10
+	rfid
+	b	.	/* prevent speculative execution */
+
+	STD_EXCEPTION_PSERIES(0xd00, single_step)
+	STD_EXCEPTION_PSERIES(0xe00, trap_0e)
+
+	/* We need to deal with the Altivec unavailable exception
+	 * here which is at 0xf20, thus in the middle of the
+	 * prolog code of the PerformanceMonitor one. A little
+	 * trickery is thus necessary
+	 */
+	. = 0xf00
+	b	performance_monitor_pSeries
+
+	STD_EXCEPTION_PSERIES(0xf20, altivec_unavailable)
+
+	STD_EXCEPTION_PSERIES(0x1300, instruction_breakpoint)
+	STD_EXCEPTION_PSERIES(0x1700, altivec_assist)
+
+	. = 0x3000
+
+/*** pSeries interrupt support ***/
+
+	/* moved from 0xf00 */
+	STD_EXCEPTION_PSERIES(., performance_monitor)
+
+	.align	7
+_GLOBAL(do_stab_bolted_pSeries)
+	mtcrf	0x80,r12
+	mfspr	r12,SPRG2
+	EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted)
+
+/*
+ * Vectors for the FWNMI option.  Share common code.
+ */
+      .globl system_reset_fwnmi
+system_reset_fwnmi:
+      HMT_MEDIUM
+      mtspr   SPRG1,r13               /* save r13 */
+      RUNLATCH_ON(r13)
+      EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common)
+
+      .globl machine_check_fwnmi
+machine_check_fwnmi:
+      HMT_MEDIUM
+      mtspr   SPRG1,r13               /* save r13 */
+      RUNLATCH_ON(r13)
+      EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
+
+#ifdef CONFIG_PPC_ISERIES
+/***  ISeries-LPAR interrupt handlers ***/
+
+	STD_EXCEPTION_ISERIES(0x200, machine_check, PACA_EXMC)
+
+	.globl data_access_iSeries
+data_access_iSeries:
+	mtspr	SPRG1,r13
+BEGIN_FTR_SECTION
+	mtspr	SPRG2,r12
+	mfspr	r13,DAR
+	mfspr	r12,DSISR
+	srdi	r13,r13,60
+	rlwimi	r13,r12,16,0x20
+	mfcr	r12
+	cmpwi	r13,0x2c
+	beq	.do_stab_bolted_iSeries
+	mtcrf	0x80,r12
+	mfspr	r12,SPRG2
+END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+	EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN)
+	EXCEPTION_PROLOG_ISERIES_2
+	b	data_access_common
+
+.do_stab_bolted_iSeries:
+	mtcrf	0x80,r12
+	mfspr	r12,SPRG2
+	EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB)
+	EXCEPTION_PROLOG_ISERIES_2
+	b	.do_stab_bolted
+
+	.globl	data_access_slb_iSeries
+data_access_slb_iSeries:
+	mtspr	SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB)
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	ld	r12,PACALPPACA+LPPACASRR1(r13)
+	mfspr	r3,DAR
+	b	.do_slb_miss
+
+	STD_EXCEPTION_ISERIES(0x400, instruction_access, PACA_EXGEN)
+
+	.globl	instruction_access_slb_iSeries
+instruction_access_slb_iSeries:
+	mtspr	SPRG1,r13		/* save r13 */
+	EXCEPTION_PROLOG_ISERIES_1(PACA_EXSLB)
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	ld	r12,PACALPPACA+LPPACASRR1(r13)
+	ld	r3,PACALPPACA+LPPACASRR0(r13)
+	b	.do_slb_miss
+
+	MASKABLE_EXCEPTION_ISERIES(0x500, hardware_interrupt)
+	STD_EXCEPTION_ISERIES(0x600, alignment, PACA_EXGEN)
+	STD_EXCEPTION_ISERIES(0x700, program_check, PACA_EXGEN)
+	STD_EXCEPTION_ISERIES(0x800, fp_unavailable, PACA_EXGEN)
+	MASKABLE_EXCEPTION_ISERIES(0x900, decrementer)
+	STD_EXCEPTION_ISERIES(0xa00, trap_0a, PACA_EXGEN)
+	STD_EXCEPTION_ISERIES(0xb00, trap_0b, PACA_EXGEN)
+
+	.globl	system_call_iSeries
+system_call_iSeries:
+	mr	r9,r13
+	mfspr	r13,SPRG3
+	EXCEPTION_PROLOG_ISERIES_2
+	b	system_call_common
+
+	STD_EXCEPTION_ISERIES( 0xd00, single_step, PACA_EXGEN)
+	STD_EXCEPTION_ISERIES( 0xe00, trap_0e, PACA_EXGEN)
+	STD_EXCEPTION_ISERIES( 0xf00, performance_monitor, PACA_EXGEN)
+
+	.globl system_reset_iSeries
+system_reset_iSeries:
+	mfspr	r13,SPRG3		/* Get paca address */
+	mfmsr	r24
+	ori	r24,r24,MSR_RI
+	mtmsrd	r24			/* RI on */
+	lhz	r24,PACAPACAINDEX(r13)	/* Get processor # */
+	cmpwi	0,r24,0			/* Are we processor 0? */
+	beq	.__start_initialization_iSeries	/* Start up the first processor */
+	mfspr	r4,SPRN_CTRLF
+	li	r5,CTRL_RUNLATCH	/* Turn off the run light */
+	andc	r4,r4,r5
+	mtspr	SPRN_CTRLT,r4
+
+1:
+	HMT_LOW
+#ifdef CONFIG_SMP
+	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor
+					 * should start */
+	sync
+	LOADADDR(r3,current_set)
+	sldi	r28,r24,3		/* get current_set[cpu#] */
+	ldx	r3,r3,r28
+	addi	r1,r3,THREAD_SIZE
+	subi	r1,r1,STACK_FRAME_OVERHEAD
+
+	cmpwi	0,r23,0
+	beq	iSeries_secondary_smp_loop	/* Loop until told to go */
+	bne	.__secondary_start		/* Loop until told to go */
+iSeries_secondary_smp_loop:
+	/* Let the Hypervisor know we are alive */
+	/* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */
+	lis	r3,0x8002
+	rldicr	r3,r3,32,15		/* r0 = (r3 << 32) & 0xffff000000000000 */
+#else /* CONFIG_SMP */
+	/* Yield the processor.  This is required for non-SMP kernels
+		which are running on multi-threaded machines. */
+	lis	r3,0x8000
+	rldicr	r3,r3,32,15		/* r3 = (r3 << 32) & 0xffff000000000000 */
+	addi	r3,r3,18		/* r3 = 0x8000000000000012 which is "yield" */
+	li	r4,0			/* "yield timed" */
+	li	r5,-1			/* "yield forever" */
+#endif /* CONFIG_SMP */
+	li	r0,-1			/* r0=-1 indicates a Hypervisor call */
+	sc				/* Invoke the hypervisor via a system call */
+	mfspr	r13,SPRG3		/* Put r13 back ???? */
+	b	1b			/* If SMP not configured, secondaries
+					 * loop forever */
+
+	.globl decrementer_iSeries_masked
+decrementer_iSeries_masked:
+	li	r11,1
+	stb	r11,PACALPPACA+LPPACADECRINT(r13)
+	lwz	r12,PACADEFAULTDECR(r13)
+	mtspr	SPRN_DEC,r12
+	/* fall through */
+
+	.globl hardware_interrupt_iSeries_masked
+hardware_interrupt_iSeries_masked:
+	mtcrf	0x80,r9		/* Restore regs */
+	ld	r11,PACALPPACA+LPPACASRR0(r13)
+	ld	r12,PACALPPACA+LPPACASRR1(r13)
+	mtspr	SRR0,r11
+	mtspr	SRR1,r12
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	ld	r11,PACA_EXGEN+EX_R11(r13)
+	ld	r12,PACA_EXGEN+EX_R12(r13)
+	ld	r13,PACA_EXGEN+EX_R13(r13)
+	rfid
+	b	.	/* prevent speculative execution */
+#endif /* CONFIG_PPC_ISERIES */
+
+/*** Common interrupt handlers ***/
+
+	STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception)
+
+	/*
+	 * Machine check is different because we use a different
+	 * save area: PACA_EXMC instead of PACA_EXGEN.
+	 */
+	.align	7
+	.globl machine_check_common
+machine_check_common:
+	EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
+	DISABLE_INTS
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.machine_check_exception
+	b	.ret_from_except
+
+	STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt)
+	STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
+	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xf00, performance_monitor, .performance_monitor_exception)
+	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
+#ifdef CONFIG_ALTIVEC
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
+#else
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception)
+#endif
+
+/*
+ * Here we have detected that the kernel stack pointer is bad.
+ * R9 contains the saved CR, r13 points to the paca,
+ * r10 contains the (bad) kernel stack pointer,
+ * r11 and r12 contain the saved SRR0 and SRR1.
+ * We switch to using an emergency stack, save the registers there,
+ * and call kernel_bad_stack(), which panics.
+ */
+bad_stack:
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,64+INT_FRAME_SIZE
+	std	r9,_CCR(r1)
+	std	r10,GPR1(r1)
+	std	r11,_NIP(r1)
+	std	r12,_MSR(r1)
+	mfspr	r11,DAR
+	mfspr	r12,DSISR
+	std	r11,_DAR(r1)
+	std	r12,_DSISR(r1)
+	mflr	r10
+	mfctr	r11
+	mfxer	r12
+	std	r10,_LINK(r1)
+	std	r11,_CTR(r1)
+	std	r12,_XER(r1)
+	SAVE_GPR(0,r1)
+	SAVE_GPR(2,r1)
+	SAVE_4GPRS(3,r1)
+	SAVE_2GPRS(7,r1)
+	SAVE_10GPRS(12,r1)
+	SAVE_10GPRS(22,r1)
+	addi	r11,r1,INT_FRAME_SIZE
+	std	r11,0(r1)
+	li	r12,0
+	std	r12,0(r11)
+	ld	r2,PACATOC(r13)
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.kernel_bad_stack
+	b	1b
+
+/*
+ * Return from an exception with minimal checks.
+ * The caller is assumed to have done EXCEPTION_PROLOG_COMMON.
+ * If interrupts have been enabled, or anything has been
+ * done that might have changed the scheduling status of
+ * any task or sent any task a signal, you should use
+ * ret_from_except or ret_from_except_lite instead of this.
+ */
+fast_exception_return:
+	ld	r12,_MSR(r1)
+	ld	r11,_NIP(r1)
+	andi.	r3,r12,MSR_RI		/* check if RI is set */
+	beq-	unrecov_fer
+	ld	r3,_CCR(r1)
+	ld	r4,_LINK(r1)
+	ld	r5,_CTR(r1)
+	ld	r6,_XER(r1)
+	mtcr	r3
+	mtlr	r4
+	mtctr	r5
+	mtxer	r6
+	REST_GPR(0, r1)
+	REST_8GPRS(2, r1)
+
+	mfmsr	r10
+	clrrdi	r10,r10,2		/* clear RI (LE is 0 already) */
+	mtmsrd	r10,1
+
+	mtspr	SRR1,r12
+	mtspr	SRR0,r11
+	REST_4GPRS(10, r1)
+	ld	r1,GPR1(r1)
+	rfid
+	b	.	/* prevent speculative execution */
+
+unrecov_fer:
+	bl	.save_nvgprs
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.unrecoverable_exception
+	b	1b
+
+/*
+ * Here r13 points to the paca, r9 contains the saved CR,
+ * SRR0 and SRR1 are saved in r11 and r12,
+ * r9 - r13 are saved in paca->exgen.
+ */
+	.align	7
+	.globl data_access_common
+data_access_common:
+	RUNLATCH_ON(r10)		/* It wont fit in the 0x300 handler */
+	mfspr	r10,DAR
+	std	r10,PACA_EXGEN+EX_DAR(r13)
+	mfspr	r10,DSISR
+	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN)
+	ld	r3,PACA_EXGEN+EX_DAR(r13)
+	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	li	r5,0x300
+	b	.do_hash_page	 	/* Try to handle as hpte fault */
+
+	.align	7
+	.globl instruction_access_common
+instruction_access_common:
+	EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN)
+	ld	r3,_NIP(r1)
+	andis.	r4,r12,0x5820
+	li	r5,0x400
+	b	.do_hash_page		/* Try to handle as hpte fault */
+
+	.align	7
+	.globl hardware_interrupt_common
+	.globl hardware_interrupt_entry
+hardware_interrupt_common:
+	EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
+hardware_interrupt_entry:
+	DISABLE_INTS
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.do_IRQ
+	b	.ret_from_except_lite
+
+	.align	7
+	.globl alignment_common
+alignment_common:
+	mfspr	r10,DAR
+	std	r10,PACA_EXGEN+EX_DAR(r13)
+	mfspr	r10,DSISR
+	stw	r10,PACA_EXGEN+EX_DSISR(r13)
+	EXCEPTION_PROLOG_COMMON(0x600, PACA_EXGEN)
+	ld	r3,PACA_EXGEN+EX_DAR(r13)
+	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
+	std	r3,_DAR(r1)
+	std	r4,_DSISR(r1)
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.alignment_exception
+	b	.ret_from_except
+
+	.align	7
+	.globl program_check_common
+program_check_common:
+	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.program_check_exception
+	b	.ret_from_except
+
+	.align	7
+	.globl fp_unavailable_common
+fp_unavailable_common:
+	EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
+	bne	.load_up_fpu		/* if from user, just load it up */
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.kernel_fp_unavailable_exception
+	BUG_OPCODE
+
+/*
+ * load_up_fpu(unused, unused, tsk)
+ * Disable FP for the task which had the FPU previously,
+ * and save its floating-point registers in its thread_struct.
+ * Enables the FPU for use in the kernel on return.
+ * On SMP we know the fpu is free, since we give it up every
+ * switch (ie, no lazy save of the FP registers).
+ * On entry: r13 == 'current' && last_task_used_math != 'current'
+ */
+_STATIC(load_up_fpu)
+	mfmsr	r5			/* grab the current MSR */
+	ori	r5,r5,MSR_FP
+	mtmsrd	r5			/* enable use of fpu now */
+	isync
+/*
+ * For SMP, we don't do lazy FPU switching because it just gets too
+ * horrendously complex, especially when a task switches from one CPU
+ * to another.  Instead we call giveup_fpu in switch_to.
+ *
+ */
+#ifndef CONFIG_SMP
+	ld	r3,last_task_used_math@got(r2)
+	ld	r4,0(r3)
+	cmpdi	0,r4,0
+	beq	1f
+	/* Save FP state to last_task_used_math's THREAD struct */
+	addi	r4,r4,THREAD
+	SAVE_32FPRS(0, r4)
+	mffs	fr0
+	stfd	fr0,THREAD_FPSCR(r4)
+	/* Disable FP for last_task_used_math */
+	ld	r5,PT_REGS(r4)
+	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	li	r6,MSR_FP|MSR_FE0|MSR_FE1
+	andc	r4,r4,r6
+	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+	/* enable use of FP after return */
+	ld	r4,PACACURRENT(r13)
+	addi	r5,r4,THREAD		/* Get THREAD */
+	ld	r4,THREAD_FPEXC_MODE(r5)
+	ori	r12,r12,MSR_FP
+	or	r12,r12,r4
+	std	r12,_MSR(r1)
+	lfd	fr0,THREAD_FPSCR(r5)
+	mtfsf	0xff,fr0
+	REST_32FPRS(0, r5)
+#ifndef CONFIG_SMP
+	/* Update last_task_used_math to 'current' */
+	subi	r4,r5,THREAD		/* Back to 'current' */
+	std	r4,0(r3)
+#endif /* CONFIG_SMP */
+	/* restore registers and return */
+	b	fast_exception_return
+
+	.align	7
+	.globl altivec_unavailable_common
+altivec_unavailable_common:
+	EXCEPTION_PROLOG_COMMON(0xf20, PACA_EXGEN)
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+	bne	.load_up_altivec	/* if from user, just load it up */
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.altivec_unavailable_exception
+	b	.ret_from_except
+
+#ifdef CONFIG_ALTIVEC
+/*
+ * load_up_altivec(unused, unused, tsk)
+ * Disable VMX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Enables the VMX for use in the kernel on return.
+ * On SMP we know the VMX is free, since we give it up every
+ * switch (ie, no lazy save of the vector registers).
+ * On entry: r13 == 'current' && last_task_used_altivec != 'current'
+ */
+_STATIC(load_up_altivec)
+	mfmsr	r5			/* grab the current MSR */
+	oris	r5,r5,MSR_VEC@h
+	mtmsrd	r5			/* enable use of VMX now */
+	isync
+
+/*
+ * For SMP, we don't do lazy VMX switching because it just gets too
+ * horrendously complex, especially when a task switches from one CPU
+ * to another.  Instead we call giveup_altvec in switch_to.
+ * VRSAVE isn't dealt with here, that is done in the normal context
+ * switch code. Note that we could rely on vrsave value to eventually
+ * avoid saving all of the VREGs here...
+ */
+#ifndef CONFIG_SMP
+	ld	r3,last_task_used_altivec@got(r2)
+	ld	r4,0(r3)
+	cmpdi	0,r4,0
+	beq	1f
+	/* Save VMX state to last_task_used_altivec's THREAD struct */
+	addi	r4,r4,THREAD
+	SAVE_32VRS(0,r5,r4)
+	mfvscr	vr0
+	li	r10,THREAD_VSCR
+	stvx	vr0,r10,r4
+	/* Disable VMX for last_task_used_altivec */
+	ld	r5,PT_REGS(r4)
+	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	lis	r6,MSR_VEC@h
+	andc	r4,r4,r6
+	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+	/* Hack: if we get an altivec unavailable trap with VRSAVE
+	 * set to all zeros, we assume this is a broken application
+	 * that fails to set it properly, and thus we switch it to
+	 * all 1's
+	 */
+	mfspr	r4,SPRN_VRSAVE
+	cmpdi	0,r4,0
+	bne+	1f
+	li	r4,-1
+	mtspr	SPRN_VRSAVE,r4
+1:
+	/* enable use of VMX after return */
+	ld	r4,PACACURRENT(r13)
+	addi	r5,r4,THREAD		/* Get THREAD */
+	oris	r12,r12,MSR_VEC@h
+	std	r12,_MSR(r1)
+	li	r4,1
+	li	r10,THREAD_VSCR
+	stw	r4,THREAD_USED_VR(r5)
+	lvx	vr0,r10,r5
+	mtvscr	vr0
+	REST_32VRS(0,r4,r5)
+#ifndef CONFIG_SMP
+	/* Update last_task_used_math to 'current' */
+	subi	r4,r5,THREAD		/* Back to 'current' */
+	std	r4,0(r3)
+#endif /* CONFIG_SMP */
+	/* restore registers and return */
+	b	fast_exception_return
+#endif /* CONFIG_ALTIVEC */
+
+/*
+ * Hash table stuff
+ */
+	.align	7
+_GLOBAL(do_hash_page)
+	std	r3,_DAR(r1)
+	std	r4,_DSISR(r1)
+
+	andis.	r0,r4,0xa450		/* weird error? */
+	bne-	.handle_page_fault	/* if not, try to insert a HPTE */
+BEGIN_FTR_SECTION
+	andis.	r0,r4,0x0020		/* Is it a segment table fault? */
+	bne-	.do_ste_alloc		/* If so handle it */
+END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
+
+	/*
+	 * We need to set the _PAGE_USER bit if MSR_PR is set or if we are
+	 * accessing a userspace segment (even from the kernel). We assume
+	 * kernel addresses always have the high bit set.
+	 */
+	rlwinm	r4,r4,32-25+9,31-9,31-9	/* DSISR_STORE -> _PAGE_RW */
+	rotldi	r0,r3,15		/* Move high bit into MSR_PR posn */
+	orc	r0,r12,r0		/* MSR_PR | ~high_bit */
+	rlwimi	r4,r0,32-13,30,30	/* becomes _PAGE_USER access bit */
+	ori	r4,r4,1			/* add _PAGE_PRESENT */
+	rlwimi	r4,r5,22+2,31-2,31-2	/* Set _PAGE_EXEC if trap is 0x400 */
+
+	/*
+	 * On iSeries, we soft-disable interrupts here, then
+	 * hard-enable interrupts so that the hash_page code can spin on
+	 * the hash_table_lock without problems on a shared processor.
+	 */
+	DISABLE_INTS
+
+	/*
+	 * r3 contains the faulting address
+	 * r4 contains the required access permissions
+	 * r5 contains the trap number
+	 *
+	 * at return r3 = 0 for success
+	 */
+	bl	.hash_page		/* build HPTE if possible */
+	cmpdi	r3,0			/* see if hash_page succeeded */
+
+#ifdef DO_SOFT_DISABLE
+	/*
+	 * If we had interrupts soft-enabled at the point where the
+	 * DSI/ISI occurred, and an interrupt came in during hash_page,
+	 * handle it now.
+	 * We jump to ret_from_except_lite rather than fast_exception_return
+	 * because ret_from_except_lite will check for and handle pending
+	 * interrupts if necessary.
+	 */
+	beq	.ret_from_except_lite
+	/* For a hash failure, we don't bother re-enabling interrupts */
+	ble-	12f
+
+	/*
+	 * hash_page couldn't handle it, set soft interrupt enable back
+	 * to what it was before the trap.  Note that .local_irq_restore
+	 * handles any interrupts pending at this point.
+	 */
+	ld	r3,SOFTE(r1)
+	bl	.local_irq_restore
+	b	11f
+#else
+	beq	fast_exception_return   /* Return from exception on success */
+	ble-	12f			/* Failure return from hash_page */
+
+	/* fall through */
+#endif
+
+/* Here we have a page fault that hash_page can't handle. */
+_GLOBAL(handle_page_fault)
+	ENABLE_INTS
+11:	ld	r4,_DAR(r1)
+	ld	r5,_DSISR(r1)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.do_page_fault
+	cmpdi	r3,0
+	beq+	.ret_from_except_lite
+	bl	.save_nvgprs
+	mr	r5,r3
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	lwz	r4,_DAR(r1)
+	bl	.bad_page_fault
+	b	.ret_from_except
+
+/* We have a page fault that hash_page could handle but HV refused
+ * the PTE insertion
+ */
+12:	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	lwz	r4,_DAR(r1)
+	bl	.low_hash_fault
+	b	.ret_from_except
+
+	/* here we have a segment miss */
+_GLOBAL(do_ste_alloc)
+	bl	.ste_allocate		/* try to insert stab entry */
+	cmpdi	r3,0
+	beq+	fast_exception_return
+	b	.handle_page_fault
+
+/*
+ * r13 points to the PACA, r9 contains the saved CR,
+ * r11 and r12 contain the saved SRR0 and SRR1.
+ * r9 - r13 are saved in paca->exslb.
+ * We assume we aren't going to take any exceptions during this procedure.
+ * We assume (DAR >> 60) == 0xc.
+ */
+	.align	7
+_GLOBAL(do_stab_bolted)
+	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
+	std	r11,PACA_EXSLB+EX_SRR0(r13)	/* save SRR0 in exc. frame */
+
+	/* Hash to the primary group */
+	ld	r10,PACASTABVIRT(r13)
+	mfspr	r11,DAR
+	srdi	r11,r11,28
+	rldimi	r10,r11,7,52	/* r10 = first ste of the group */
+
+	/* Calculate VSID */
+	/* This is a kernel address, so protovsid = ESID */
+	ASM_VSID_SCRAMBLE(r11, r9)
+	rldic	r9,r11,12,16	/* r9 = vsid << 12 */
+
+	/* Search the primary group for a free entry */
+1:	ld	r11,0(r10)	/* Test valid bit of the current ste	*/
+	andi.	r11,r11,0x80
+	beq	2f
+	addi	r10,r10,16
+	andi.	r11,r10,0x70
+	bne	1b
+
+	/* Stick for only searching the primary group for now.		*/
+	/* At least for now, we use a very simple random castout scheme */
+	/* Use the TB as a random number ;  OR in 1 to avoid entry 0	*/
+	mftb	r11
+	rldic	r11,r11,4,57	/* r11 = (r11 << 4) & 0x70 */
+	ori	r11,r11,0x10
+
+	/* r10 currently points to an ste one past the group of interest */
+	/* make it point to the randomly selected entry			*/
+	subi	r10,r10,128
+	or 	r10,r10,r11	/* r10 is the entry to invalidate	*/
+
+	isync			/* mark the entry invalid		*/
+	ld	r11,0(r10)
+	rldicl	r11,r11,56,1	/* clear the valid bit */
+	rotldi	r11,r11,8
+	std	r11,0(r10)
+	sync
+
+	clrrdi	r11,r11,28	/* Get the esid part of the ste		*/
+	slbie	r11
+
+2:	std	r9,8(r10)	/* Store the vsid part of the ste	*/
+	eieio
+
+	mfspr	r11,DAR		/* Get the new esid			*/
+	clrrdi	r11,r11,28	/* Permits a full 32b of ESID		*/
+	ori	r11,r11,0x90	/* Turn on valid and kp			*/
+	std	r11,0(r10)	/* Put new entry back into the stab	*/
+
+	sync
+
+	/* All done -- return from exception. */
+	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
+	ld	r11,PACA_EXSLB+EX_SRR0(r13)	/* get saved SRR0 */
+
+	andi.	r10,r12,MSR_RI
+	beq-	unrecov_slb
+
+	mtcrf	0x80,r9			/* restore CR */
+
+	mfmsr	r10
+	clrrdi	r10,r10,2
+	mtmsrd	r10,1
+
+	mtspr	SRR0,r11
+	mtspr	SRR1,r12
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	rfid
+	b	.	/* prevent speculative execution */
+
+/*
+ * r13 points to the PACA, r9 contains the saved CR,
+ * r11 and r12 contain the saved SRR0 and SRR1.
+ * r3 has the faulting address
+ * r9 - r13 are saved in paca->exslb.
+ * r3 is saved in paca->slb_r3
+ * We assume we aren't going to take any exceptions during this procedure.
+ */
+_GLOBAL(do_slb_miss)
+	mflr	r10
+
+	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
+	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
+
+	bl	.slb_allocate			/* handle it */
+
+	/* All done -- return from exception. */
+
+	ld	r10,PACA_EXSLB+EX_LR(r13)
+	ld	r3,PACA_EXSLB+EX_R3(r13)
+	lwz	r9,PACA_EXSLB+EX_CCR(r13)	/* get saved CR */
+#ifdef CONFIG_PPC_ISERIES
+	ld	r11,PACALPPACA+LPPACASRR0(r13)	/* get SRR0 value */
+#endif /* CONFIG_PPC_ISERIES */
+
+	mtlr	r10
+
+	andi.	r10,r12,MSR_RI	/* check for unrecoverable exception */
+	beq-	unrecov_slb
+
+.machine	push
+.machine	"power4"
+	mtcrf	0x80,r9
+	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
+.machine	pop
+
+#ifdef CONFIG_PPC_ISERIES
+	mtspr	SRR0,r11
+	mtspr	SRR1,r12
+#endif /* CONFIG_PPC_ISERIES */
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	rfid
+	b	.	/* prevent speculative execution */
+
+unrecov_slb:
+	EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
+	DISABLE_INTS
+	bl	.save_nvgprs
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	.unrecoverable_exception
+	b	1b
+
+/*
+ * Space for CPU0's segment table.
+ *
+ * On iSeries, the hypervisor must fill in at least one entry before
+ * we get control (with relocate on).  The address is give to the hv
+ * as a page number (see xLparMap in LparData.c), so this must be at a
+ * fixed address (the linker can't compute (u64)&initial_stab >>
+ * PAGE_SHIFT).
+ */
+	. = STAB0_PHYS_ADDR	/* 0x6000 */
+	.globl initial_stab
+initial_stab:
+	.space	4096
+
+/*
+ * Data area reserved for FWNMI option.
+ * This address (0x7000) is fixed by the RPA.
+ */
+	.= 0x7000
+	.globl fwnmi_data_area
+fwnmi_data_area:
+
+	/* iSeries does not use the FWNMI stuff, so it is safe to put
+	 * this here, even if we later allow kernels that will boot on
+	 * both pSeries and iSeries */
+#ifdef CONFIG_PPC_ISERIES
+        . = LPARMAP_PHYS
+#include "lparmap.s"
+/*
+ * This ".text" is here for old compilers that generate a trailing
+ * .note section when compiling .c files to .s
+ */
+	.text
+#endif /* CONFIG_PPC_ISERIES */
+
+        . = 0x8000
+
+/*
+ * On pSeries, secondary processors spin in the following code.
+ * At entry, r3 = this processor's number (physical cpu id)
+ */
+_GLOBAL(pSeries_secondary_smp_init)
+	mr	r24,r3
+	
+	/* turn on 64-bit mode */
+	bl	.enable_64b_mode
+	isync
+
+	/* Copy some CPU settings from CPU 0 */
+	bl	.__restore_cpu_setup
+
+	/* 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.
+	 */
+	LOADADDR(r13, paca) 		/* Get base vaddr of paca array	 */
+	li	r5,0			/* logical cpu id                */
+1:	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
+	cmpw	r6,r24			/* Compare to our id             */
+	beq	2f
+	addi	r13,r13,PACA_SIZE	/* Loop to next PACA on miss     */
+	addi	r5,r5,1
+	cmpwi	r5,NR_CPUS
+	blt	1b
+
+	mr	r3,r24			/* not found, copy phys to r3	 */
+	b	.kexec_wait		/* next kernel might do better	 */
+
+2:	mtspr	SPRG3,r13		/* Save vaddr of paca in SPRG3	 */
+	/* From now on, r24 is expected to be logical cpuid */
+	mr	r24,r5
+3:	HMT_LOW
+	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor should */
+					/* start.			 */
+	sync
+
+	/* Create a temp kernel stack for use before relocation is on.	*/
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,STACK_FRAME_OVERHEAD
+
+	cmpwi	0,r23,0
+#ifdef CONFIG_SMP
+	bne	.__secondary_start
+#endif
+	b 	3b			/* Loop until told to go	 */
+
+#ifdef CONFIG_PPC_ISERIES
+_STATIC(__start_initialization_iSeries)
+	/* Clear out the BSS */
+	LOADADDR(r11,__bss_stop)
+	LOADADDR(r8,__bss_start)
+	sub	r11,r11,r8		/* bss size			*/
+	addi	r11,r11,7		/* round up to an even double word */
+	rldicl. r11,r11,61,3		/* 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:
+	LOADADDR(r1,init_thread_union)
+	addi	r1,r1,THREAD_SIZE
+	li	r0,0
+	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
+
+	LOADADDR(r3,cpu_specs)
+	LOADADDR(r4,cur_cpu_spec)
+	li	r5,0
+	bl	.identify_cpu
+
+	LOADADDR(r2,__toc_start)
+	addi	r2,r2,0x4000
+	addi	r2,r2,0x4000
+
+	bl	.iSeries_early_setup
+
+	/* relocation is on at this point */
+
+	b	.start_here_common
+#endif /* CONFIG_PPC_ISERIES */
+
+#ifdef CONFIG_PPC_MULTIPLATFORM
+
+_STATIC(__mmu_off)
+	mfmsr	r3
+	andi.	r0,r3,MSR_IR|MSR_DR
+	beqlr
+	andc	r3,r3,r0
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r3
+	sync
+	rfid
+	b	.	/* prevent speculative execution */
+
+
+/*
+ * 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
+ *
+ */
+_GLOBAL(__start_initialization_multiplatform)
+	/*
+	 * Are we booted from a PROM Of-type client-interface ?
+	 */
+	cmpldi	cr0,r5,0
+	bne	.__boot_from_prom		/* yes -> prom */
+
+	/* Save parameters */
+	mr	r31,r3
+	mr	r30,r4
+
+	/* Make sure we are running in 64 bits mode */
+	bl	.enable_64b_mode
+
+	/* Setup some critical 970 SPRs before switching MMU off */
+	bl	.__970_cpu_preinit
+
+	/* cpu # */
+	li	r24,0
+
+	/* Switch off MMU if not already */
+	LOADADDR(r4, .__after_prom_start - KERNELBASE)
+	add	r4,r4,r30
+	bl	.__mmu_off
+	b	.__after_prom_start
+
+_STATIC(__boot_from_prom)
+	/* Save parameters */
+	mr	r31,r3
+	mr	r30,r4
+	mr	r29,r5
+	mr	r28,r6
+	mr	r27,r7
+
+	/* Make sure we are running in 64 bits mode */
+	bl	.enable_64b_mode
+
+	/* put a relocation offset into r3 */
+	bl	.reloc_offset
+
+	LOADADDR(r2,__toc_start)
+	addi	r2,r2,0x4000
+	addi	r2,r2,0x4000
+
+	/* Relocate the TOC from a virt addr to a real addr */
+	sub	r2,r2,r3
+
+	/* 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 */
+	bl	.prom_init
+	/* We never return */
+	trap
+
+/*
+ * At this point, r3 contains the physical address we are running at,
+ * returned by prom_init()
+ */
+_STATIC(__after_prom_start)
+
+/*
+ * We need to run with __start at physical address 0.
+ * This will leave some code in the first 256B of
+ * real memory, which are reserved for software use.
+ * The remainder of the first page is loaded with the fixed
+ * interrupt vectors.  The next two pages are filled with
+ * unknown exception placeholders.
+ *
+ * Note: This process overwrites the OF exception vectors.
+ *	r26 == relocation offset
+ *	r27 == KERNELBASE
+ */
+	bl	.reloc_offset
+	mr	r26,r3
+	SET_REG_TO_CONST(r27,KERNELBASE)
+
+	li	r3,0			/* target addr */
+
+	// XXX FIXME: Use phys returned by OF (r30)
+	sub	r4,r27,r26 		/* source addr			 */
+					/* current address of _start	 */
+					/*   i.e. where we are running	 */
+					/*	the source addr		 */
+
+	LOADADDR(r5,copy_to_here)	/* # bytes of memory to copy	 */
+	sub	r5,r5,r27
+
+	li	r6,0x100		/* Start offset, the first 0x100 */
+					/* bytes were copied earlier.	 */
+
+	bl	.copy_and_flush		/* copy the first n bytes	 */
+					/* this includes the code being	 */
+					/* executed here.		 */
+
+	LOADADDR(r0, 4f)		/* Jump to the copy of this code */
+	mtctr	r0			/* that we just made/relocated	 */
+	bctr
+
+4:	LOADADDR(r5,klimit)
+	sub	r5,r5,r26
+	ld	r5,0(r5)		/* get the value of klimit */
+	sub	r5,r5,r27
+	bl	.copy_and_flush		/* copy the rest */
+	b	.start_here_multiplatform
+
+#endif /* CONFIG_PPC_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	r0,16			/* Use the least 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
+	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	pmac_secondary_start_1	
+pmac_secondary_start_1:	
+	li	r24, 1
+	b	.pmac_secondary_start
+	
+	.globl pmac_secondary_start_2
+pmac_secondary_start_2:	
+	li	r24, 2
+	b	.pmac_secondary_start
+	
+	.globl pmac_secondary_start_3
+pmac_secondary_start_3:
+	li	r24, 3
+	b	.pmac_secondary_start
+	
+_GLOBAL(pmac_secondary_start)
+	/* turn on 64-bit mode */
+	bl	.enable_64b_mode
+	isync
+
+	/* Copy some CPU settings from CPU 0 */
+	bl	.__restore_cpu_setup
+
+	/* 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. */
+	LOADADDR(r4, paca) 		 /* Get base vaddr of paca array	*/
+	mulli	r13,r24,PACA_SIZE	 /* Calculate vaddr of right paca */
+	add	r13,r13,r4		/* for this processor.		*/
+	mtspr	SPRG3,r13		 /* Save vaddr of paca in SPRG3	*/
+
+	/* 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.  vaddr for iSeries, raddr (temp stack) for pSeries
+ *   r24   = cpu# (in Linux terms)
+ *   r13   = paca virtual address
+ *   SPRG3 = paca virtual address
+ */
+_GLOBAL(__secondary_start)
+
+	HMT_MEDIUM			/* Set thread priority to MEDIUM */
+
+	ld	r2,PACATOC(r13)
+	li	r6,0
+	stb	r6,PACAPROCENABLED(r13)
+
+#ifndef CONFIG_PPC_ISERIES
+	/* Initialize the page table pointer register. */
+	LOADADDR(r6,_SDR1)
+	ld	r6,0(r6)		/* get the value of _SDR1	 */
+	mtspr	SDR1,r6			/* set the htab location	 */
+#endif
+	/* Initialize the first segment table (or SLB) entry		 */
+	ld	r3,PACASTABVIRT(r13)	/* get addr of segment table	 */
+	bl	.stab_initialize
+
+	/* Initialize the kernel stack.  Just a repeat for iSeries.	 */
+	LOADADDR(r3,current_set)
+	sldi	r28,r24,3		/* get current_set[cpu#]	 */
+	ldx	r1,r3,r28
+	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+	std	r1,PACAKSAVE(r13)
+
+	ld	r3,PACASTABREAL(r13)	/* get raddr of segment table	 */
+	ori	r4,r3,1			/* turn on valid bit		 */
+
+#ifdef CONFIG_PPC_ISERIES
+	li	r0,-1			/* hypervisor call */
+	li	r3,1
+	sldi	r3,r3,63		/* 0x8000000000000000 */
+	ori	r3,r3,4			/* 0x8000000000000004 */
+	sc				/* HvCall_setASR */
+#else
+	/* set the ASR */
+	ld	r3,systemcfg@got(r2)	/* r3 = ptr to systemcfg	 */
+	ld	r3,0(r3)
+	lwz	r3,PLATFORM(r3)		/* r3 = platform flags		 */
+	andi.	r3,r3,PLATFORM_LPAR	/* Test if bit 0 is set (LPAR bit) */
+	beq	98f			/* branch if result is 0  */
+	mfspr	r3,PVR
+	srwi	r3,r3,16
+	cmpwi	r3,0x37			/* SStar  */
+	beq	97f
+	cmpwi	r3,0x36			/* IStar  */
+	beq	97f
+	cmpwi	r3,0x34			/* Pulsar */
+	bne	98f
+97:	li	r3,H_SET_ASR		/* hcall = H_SET_ASR */
+	HVSC				/* Invoking hcall */
+	b	99f
+98:					/* !(rpa hypervisor) || !(star)  */
+	mtasr	r4			/* set the stab location	 */
+99:
+#endif
+	li	r7,0
+	mtlr	r7
+
+	/* enable MMU and jump to start_secondary */
+	LOADADDR(r3,.start_secondary_prolog)
+	SET_REG_TO_CONST(r4, MSR_KERNEL)
+#ifdef DO_SOFT_DISABLE
+	ori	r4,r4,MSR_EE
+#endif
+	mtspr	SRR0,r3
+	mtspr	SRR1,r4
+	rfid
+	b	.	/* prevent speculative execution */
+
+/* 
+ * Running with relocation on at this point.  All we want to do is
+ * zero the stack back-chain pointer before going into C code.
+ */
+_GLOBAL(start_secondary_prolog)
+	li	r3,0
+	std	r3,0(r1)		/* Zero the stack frame pointer	*/
+	bl	.start_secondary
+#endif
+
+/*
+ * This subroutine clobbers r11 and r12
+ */
+_GLOBAL(enable_64b_mode)
+	mfmsr	r11			/* grab the current MSR */
+	li	r12,1
+	rldicr	r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
+	or	r11,r11,r12
+	li	r12,1
+	rldicr	r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
+	or	r11,r11,r12
+	mtmsrd	r11
+	isync
+	blr
+
+#ifdef CONFIG_PPC_MULTIPLATFORM
+/*
+ * This is where the main kernel code starts.
+ */
+_STATIC(start_here_multiplatform)
+	/* get a new offset, now that the kernel has moved. */
+	bl	.reloc_offset
+	mr	r26,r3
+
+	/* 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.
+	 */
+	LOADADDR(r11,__bss_stop)
+	LOADADDR(r8,__bss_start)
+	sub	r11,r11,r8		/* bss size			*/
+	addi	r11,r11,7		/* round up to an even double word */
+	rldicl. r11,r11,61,3		/* 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:
+
+	mfmsr	r6
+	ori	r6,r6,MSR_RI
+	mtmsrd	r6			/* RI on */
+
+#ifdef CONFIG_HMT
+	/* Start up the second thread on cpu 0 */
+	mfspr	r3,PVR
+	srwi	r3,r3,16
+	cmpwi	r3,0x34			/* Pulsar  */
+	beq	90f
+	cmpwi	r3,0x36			/* Icestar */
+	beq	90f
+	cmpwi	r3,0x37			/* SStar   */
+	beq	90f
+	b	91f			/* HMT not supported */
+90:	li	r3,0
+	bl	.hmt_start_secondary
+91:
+#endif
+
+	/* The following gets the stack and TOC 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. */
+
+	LOADADDR(r3,init_thread_union)
+	sub	r3,r3,r26
+
+	/* set up a stack pointer (physical address) */
+	addi	r1,r3,THREAD_SIZE
+	li	r0,0
+	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
+
+	/* set up the TOC (physical address) */
+	LOADADDR(r2,__toc_start)
+	addi	r2,r2,0x4000
+	addi	r2,r2,0x4000
+	sub	r2,r2,r26
+
+	LOADADDR(r3,cpu_specs)
+	sub	r3,r3,r26
+	LOADADDR(r4,cur_cpu_spec)
+	sub	r4,r4,r26
+	mr	r5,r26
+	bl	.identify_cpu
+
+	/* Save some low level config HIDs of CPU0 to be copied to
+	 * other CPUs later on, or used for suspend/resume
+	 */
+	bl	.__save_cpu_setup
+	sync
+
+	/* Setup a valid physical PACA pointer in SPRG3 for early_setup
+	 * note that boot_cpuid can always be 0 nowadays since there is
+	 * nowhere it can be initialized differently before we reach this
+	 * code
+	 */
+	LOADADDR(r27, boot_cpuid)
+	sub	r27,r27,r26
+	lwz	r27,0(r27)
+
+	LOADADDR(r24, paca) 		/* Get base vaddr of paca array	 */
+	mulli	r13,r27,PACA_SIZE	/* Calculate vaddr of right paca */
+	add	r13,r13,r24		/* for this processor.		 */
+	sub	r13,r13,r26		/* convert to physical addr	 */
+	mtspr	SPRG3,r13		/* PPPBBB: Temp... -Peter */
+	
+	/* Do very early kernel initializations, including initial hash table,
+	 * stab and slb setup before we turn on relocation.	*/
+
+	/* Restore parameters passed from prom_init/kexec */
+	mr	r3,r31
+ 	bl	.early_setup
+
+	/* set the ASR */
+	ld	r3,PACASTABREAL(r13)
+	ori	r4,r3,1			/* turn on valid bit		 */
+	ld	r3,systemcfg@got(r2)	/* r3 = ptr to systemcfg */
+	ld	r3,0(r3)
+	lwz	r3,PLATFORM(r3)		/* r3 = platform flags */
+	andi.	r3,r3,PLATFORM_LPAR	/* Test if bit 0 is set (LPAR bit) */
+	beq	98f			/* branch if result is 0  */
+	mfspr	r3,PVR
+	srwi	r3,r3,16
+	cmpwi	r3,0x37			/* SStar */
+	beq	97f
+	cmpwi	r3,0x36			/* IStar  */
+	beq	97f
+	cmpwi	r3,0x34			/* Pulsar */
+	bne	98f
+97:	li	r3,H_SET_ASR		/* hcall = H_SET_ASR */
+	HVSC				/* Invoking hcall */
+	b	99f
+98:					/* !(rpa hypervisor) || !(star) */
+	mtasr	r4			/* set the stab location	*/
+99:
+	/* Set SDR1 (hash table pointer) */
+	ld	r3,systemcfg@got(r2)	/* r3 = ptr to systemcfg */
+	ld	r3,0(r3)
+	lwz	r3,PLATFORM(r3)		/* r3 = platform flags */
+	/* Test if bit 0 is set (LPAR bit) */
+	andi.	r3,r3,PLATFORM_LPAR
+	bne	98f			/* branch if result is !0  */
+	LOADADDR(r6,_SDR1)		/* Only if NOT LPAR */
+	sub	r6,r6,r26
+	ld	r6,0(r6)		/* get the value of _SDR1 */
+	mtspr	SDR1,r6			/* set the htab location  */
+98: 
+	LOADADDR(r3,.start_here_common)
+	SET_REG_TO_CONST(r4, MSR_KERNEL)
+	mtspr	SRR0,r3
+	mtspr	SRR1,r4
+	rfid
+	b	.	/* prevent speculative execution */
+#endif /* CONFIG_PPC_MULTIPLATFORM */
+	
+	/* This is where all platforms converge execution */
+_STATIC(start_here_common)
+	/* relocation is on at this point */
+
+	/* The following code sets up the SP and TOC now that we are */
+	/* running with translation enabled. */
+
+	LOADADDR(r3,init_thread_union)
+
+	/* set up the stack */
+	addi	r1,r3,THREAD_SIZE
+	li	r0,0
+	stdu	r0,-STACK_FRAME_OVERHEAD(r1)
+
+	/* Apply the CPUs-specific fixups (nop out sections not relevant
+	 * to this CPU
+	 */
+	li	r3,0
+	bl	.do_cpu_ftr_fixups
+
+	LOADADDR(r26, boot_cpuid)
+	lwz	r26,0(r26)
+
+	LOADADDR(r24, paca) 		/* Get base vaddr of paca array  */
+	mulli	r13,r26,PACA_SIZE	/* Calculate vaddr of right paca */
+	add	r13,r13,r24		/* for this processor.		 */
+	mtspr	SPRG3,r13
+
+	/* ptr to current */
+	LOADADDR(r4,init_task)
+	std	r4,PACACURRENT(r13)
+
+	/* Load the TOC */
+	ld	r2,PACATOC(r13)
+	std	r1,PACAKSAVE(r13)
+
+	bl	.setup_system
+
+	/* Load up the kernel context */
+5:
+#ifdef DO_SOFT_DISABLE
+	li	r5,0
+	stb	r5,PACAPROCENABLED(r13)	/* Soft Disabled */
+	mfmsr	r5
+	ori	r5,r5,MSR_EE		/* Hard Enabled */
+	mtmsrd	r5
+#endif
+
+	bl .start_kernel
+
+_GLOBAL(hmt_init)
+#ifdef CONFIG_HMT
+	LOADADDR(r5, hmt_thread_data)
+	mfspr	r7,PVR
+	srwi	r7,r7,16
+	cmpwi	r7,0x34			/* Pulsar  */
+	beq	90f
+	cmpwi	r7,0x36			/* Icestar */
+	beq	91f
+	cmpwi	r7,0x37			/* SStar   */
+	beq	91f
+	b	101f
+90:	mfspr	r6,PIR
+	andi.	r6,r6,0x1f
+	b	92f
+91:	mfspr	r6,PIR
+	andi.	r6,r6,0x3ff
+92:	sldi	r4,r24,3
+	stwx	r6,r5,r4
+	bl	.hmt_start_secondary
+	b	101f
+
+__hmt_secondary_hold:
+	LOADADDR(r5, hmt_thread_data)
+	clrldi	r5,r5,4
+	li	r7,0
+	mfspr	r6,PIR
+	mfspr	r8,PVR
+	srwi	r8,r8,16
+	cmpwi	r8,0x34
+	bne	93f
+	andi.	r6,r6,0x1f
+	b	103f
+93:	andi.	r6,r6,0x3f
+
+103:	lwzx	r8,r5,r7
+	cmpw	r8,r6
+	beq	104f
+	addi	r7,r7,8
+	b	103b
+
+104:	addi	r7,r7,4
+	lwzx	r9,r5,r7
+	mr	r24,r9
+101:
+#endif
+	mr	r3,r24
+	b	.pSeries_secondary_smp_init
+
+#ifdef CONFIG_HMT
+_GLOBAL(hmt_start_secondary)
+	LOADADDR(r4,__hmt_secondary_hold)
+	clrldi	r4,r4,4
+	mtspr	NIADORM, r4
+	mfspr	r4, MSRDORM
+	li	r5, -65
+	and	r4, r4, r5
+	mtspr	MSRDORM, r4
+	lis	r4,0xffef
+	ori	r4,r4,0x7403
+	mtspr	TSC, r4
+	li	r4,0x1f4
+	mtspr	TST, r4
+	mfspr	r4, HID0
+	ori	r4, r4, 0x1
+	mtspr	HID0, r4
+	mfspr	r4, SPRN_CTRLF
+	oris	r4, r4, 0x40
+	mtspr	SPRN_CTRLT, r4
+	blr
+#endif
+
+#if defined(CONFIG_KEXEC) || (defined(CONFIG_SMP) && !defined(CONFIG_PPC_ISERIES))
+_GLOBAL(smp_release_cpus)
+	/* All secondary cpus are spinning on a common
+	 * spinloop, release them all now so they can start
+	 * to spin on their individual paca spinloops.
+	 * For non SMP kernels, the secondary cpus never
+	 * get out of the common spinloop.
+	 */
+	li	r3,1
+	LOADADDR(r5,__secondary_hold_spinloop)
+	std	r3,0(r5)
+	sync
+	blr
+#endif /* CONFIG_SMP && !CONFIG_PPC_ISERIES */
+
+
+/*
+ * 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"
+
+	.align	PAGE_SHIFT
+
+	.globl	empty_zero_page
+empty_zero_page:
+	.space	PAGE_SIZE
+
+	.globl	swapper_pg_dir
+swapper_pg_dir:
+	.space	PAGE_SIZE
+
+/*
+ * This space gets a copy of optional info passed to us by the bootstrap
+ * Used to pass parameters into the kernel like root=/dev/sda1, etc.
+ */
+	.globl	cmd_line
+cmd_line:
+	.space	COMMAND_LINE_SIZE