16 files changed, 10363 insertions, 0 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
new file mode 100644
index 00000000000..62c4a51a23d
--- /dev/null
+++ b/arch/powerpc/kernel/Makefile
@@ -0,0 +1,18 @@
+#
+# Makefile for the linux kernel.
+#
+
+extra-$(CONFIG_PPC_STD_MMU)	:= head.o
+extra_$(CONFIG_PPC64)		:= head_64.o
+extra-$(CONFIG_40x)		:= head_4xx.o
+extra-$(CONFIG_44x)		:= head_44x.o
+extra-$(CONFIG_FSL_BOOKE)	:= head_fsl_booke.o
+extra-$(CONFIG_8xx)		:= head_8xx.o
+extra-$(CONFIG_6xx)		+= idle_6xx.o
+extra-$(CONFIG_POWER4)		+= idle_power4.o
+extra-$(CONFIG_PPC_FPU)		+= fpu.o
+extra-y				+= vmlinux.lds
+
+obj-y				:= semaphore.o traps.o process.o
+
+obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
new file mode 100644
index 00000000000..16cf0b7ee2b
--- /dev/null
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -0,0 +1,262 @@
+/*
+ * This program is used to generate definitions needed by
+ * assembly language modules.
+ *
+ * We use the technique used in the OSF Mach kernel code:
+ * generate asm statements containing #defines,
+ * compile this file to assembler, and then extract the
+ * #defines from the assembly-language output.
+ *
+ * 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/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/suspend.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/time.h>
+#include <linux/hardirq.h>
+#include <asm/io.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#ifdef CONFIG_PPC64
+#include <asm/paca.h>
+#include <asm/lppaca.h>
+#include <asm/iSeries/HvLpEvent.h>
+#include <asm/rtas.h>
+#include <asm/cache.h>
+#include <asm/systemcfg.h>
+#include <asm/compat.h>
+#endif
+
+#define DEFINE(sym, val) \
+	asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+
+#define BLANK() asm volatile("\n->" : : )
+
+int main(void)
+{
+	/* thread struct on stack */
+	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
+	DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
+	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
+#ifdef CONFIG_PPC32
+	DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
+#endif
+#ifdef CONFIG_PPC64
+	DEFINE(TI_SC_NOERR, offsetof(struct thread_info, syscall_noerror));
+	DEFINE(THREAD_SHIFT, THREAD_SHIFT);
+#endif
+	DEFINE(THREAD_SIZE, THREAD_SIZE);
+
+	/* task_struct->thread */
+	DEFINE(THREAD, offsetof(struct task_struct, thread));
+	DEFINE(THREAD_INFO, offsetof(struct task_struct, thread_info));
+	DEFINE(MM, offsetof(struct task_struct, mm));
+	DEFINE(PTRACE, offsetof(struct task_struct, ptrace));
+	DEFINE(KSP, offsetof(struct thread_struct, ksp));
+	DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));
+	DEFINE(LAST_SYSCALL, offsetof(struct thread_struct, last_syscall));
+	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
+	DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
+	DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
+	DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr));
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+	DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
+	DEFINE(PT_PTRACED, PT_PTRACED);
+#endif
+#ifdef CONFIG_PPC64
+	DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid));
+#endif
+
+#ifdef CONFIG_ALTIVEC
+	DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0]));
+	DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave));
+	DEFINE(THREAD_VSCR, offsetof(struct thread_struct, vscr));
+	DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr));
+#endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_SPE
+	DEFINE(THREAD_EVR0, offsetof(struct thread_struct, evr[0]));
+	DEFINE(THREAD_ACC, offsetof(struct thread_struct, acc));
+	DEFINE(THREAD_SPEFSCR, offsetof(struct thread_struct, spefscr));
+	DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
+#endif /* CONFIG_SPE */
+	/* Interrupt register frame */
+	DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD);
+#ifndef CONFIG_PPC64
+	DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
+#else
+	DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
+
+	/* 288 = # of volatile regs, int & fp, for leaf routines */
+	/* which do not stack a frame.  See the PPC64 ABI.       */
+	DEFINE(INT_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 288);
+#endif
+	/* in fact we only use gpr0 - gpr9 and gpr20 - gpr23 */
+	DEFINE(GPR0, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[0]));
+	DEFINE(GPR1, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[1]));
+	DEFINE(GPR2, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[2]));
+	DEFINE(GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[3]));
+	DEFINE(GPR4, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[4]));
+	DEFINE(GPR5, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[5]));
+	DEFINE(GPR6, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[6]));
+	DEFINE(GPR7, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[7]));
+	DEFINE(GPR8, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[8]));
+	DEFINE(GPR9, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[9]));
+	DEFINE(GPR10, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[10]));
+	DEFINE(GPR11, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[11]));
+	DEFINE(GPR12, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[12]));
+	DEFINE(GPR13, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[13]));
+	DEFINE(GPR14, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[14]));
+	DEFINE(GPR15, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[15]));
+	DEFINE(GPR16, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[16]));
+	DEFINE(GPR17, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[17]));
+	DEFINE(GPR18, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[18]));
+	DEFINE(GPR19, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[19]));
+	DEFINE(GPR20, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[20]));
+	DEFINE(GPR21, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[21]));
+	DEFINE(GPR22, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[22]));
+	DEFINE(GPR23, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[23]));
+	DEFINE(GPR24, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[24]));
+	DEFINE(GPR25, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[25]));
+	DEFINE(GPR26, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[26]));
+	DEFINE(GPR27, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[27]));
+	DEFINE(GPR28, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[28]));
+	DEFINE(GPR29, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[29]));
+	DEFINE(GPR30, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[30]));
+	DEFINE(GPR31, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, gpr[31]));
+	/*
+	 * Note: these symbols include _ because they overlap with special
+	 * register names
+	 */
+	DEFINE(_NIP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, nip));
+	DEFINE(_MSR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, msr));
+	DEFINE(_CTR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ctr));
+	DEFINE(_LINK, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, link));
+	DEFINE(_CCR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, ccr));
+	DEFINE(_MQ, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, mq));
+	DEFINE(_XER, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, xer));
+	DEFINE(_DAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar));
+	DEFINE(_DSISR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr));
+	/* The PowerPC 400-class & Book-E processors have neither the DAR nor the DSISR
+	 * SPRs. Hence, we overload them to hold the similar DEAR and ESR SPRs
+	 * for such processors.  For critical interrupts we use them to
+	 * hold SRR0 and SRR1.
+	 */
+	DEFINE(_DEAR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dar));
+	DEFINE(_ESR, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, dsisr));
+	DEFINE(ORIG_GPR3, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, orig_gpr3));
+	DEFINE(RESULT, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, result));
+	DEFINE(TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap));
+	DEFINE(CLONE_VM, CLONE_VM);
+	DEFINE(CLONE_UNTRACED, CLONE_UNTRACED);
+	DEFINE(MM_PGD, offsetof(struct mm_struct, pgd));
+
+	/* About the CPU features table */
+	DEFINE(CPU_SPEC_ENTRY_SIZE, sizeof(struct cpu_spec));
+	DEFINE(CPU_SPEC_PVR_MASK, offsetof(struct cpu_spec, pvr_mask));
+	DEFINE(CPU_SPEC_PVR_VALUE, offsetof(struct cpu_spec, pvr_value));
+	DEFINE(CPU_SPEC_FEATURES, offsetof(struct cpu_spec, cpu_features));
+	DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup));
+
+#ifdef CONFIG_PPC64
+	DEFINE(MM, offsetof(struct task_struct, mm));
+	DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
+
+	DEFINE(DCACHEL1LINESIZE, offsetof(struct ppc64_caches, dline_size));
+	DEFINE(DCACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_dline_size));
+	DEFINE(DCACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, dlines_per_page));
+	DEFINE(ICACHEL1LINESIZE, offsetof(struct ppc64_caches, iline_size));
+	DEFINE(ICACHEL1LOGLINESIZE, offsetof(struct ppc64_caches, log_iline_size));
+	DEFINE(ICACHEL1LINESPERPAGE, offsetof(struct ppc64_caches, ilines_per_page));
+	DEFINE(PLATFORM, offsetof(struct systemcfg, platform));
+
+	/* paca */
+        DEFINE(PACA_SIZE, sizeof(struct paca_struct));
+        DEFINE(PACAPACAINDEX, offsetof(struct paca_struct, paca_index));
+        DEFINE(PACAPROCSTART, offsetof(struct paca_struct, cpu_start));
+        DEFINE(PACAKSAVE, offsetof(struct paca_struct, kstack));
+	DEFINE(PACACURRENT, offsetof(struct paca_struct, __current));
+        DEFINE(PACASAVEDMSR, offsetof(struct paca_struct, saved_msr));
+        DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real));
+        DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr));
+	DEFINE(PACASTABRR, offsetof(struct paca_struct, stab_rr));
+        DEFINE(PACAR1, offsetof(struct paca_struct, saved_r1));
+	DEFINE(PACATOC, offsetof(struct paca_struct, kernel_toc));
+	DEFINE(PACAPROCENABLED, offsetof(struct paca_struct, proc_enabled));
+	DEFINE(PACASLBCACHE, offsetof(struct paca_struct, slb_cache));
+	DEFINE(PACASLBCACHEPTR, offsetof(struct paca_struct, slb_cache_ptr));
+	DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
+#ifdef CONFIG_HUGETLB_PAGE
+	DEFINE(PACALOWHTLBAREAS, offsetof(struct paca_struct, context.low_htlb_areas));
+	DEFINE(PACAHIGHHTLBAREAS, offsetof(struct paca_struct, context.high_htlb_areas));
+#endif /* CONFIG_HUGETLB_PAGE */
+	DEFINE(PACADEFAULTDECR, offsetof(struct paca_struct, default_decr));
+        DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
+        DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
+        DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb));
+        DEFINE(PACA_EXDSI, offsetof(struct paca_struct, exdsi));
+        DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
+	DEFINE(PACALPPACA, offsetof(struct paca_struct, lppaca));
+	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
+	DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0));
+	DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1));
+	DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
+	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
+
+	/* RTAS */
+	DEFINE(RTASBASE, offsetof(struct rtas_t, base));
+	DEFINE(RTASENTRY, offsetof(struct rtas_t, entry));
+
+	DEFINE(_TRAP, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, trap));
+	DEFINE(SOFTE, STACK_FRAME_OVERHEAD+offsetof(struct pt_regs, softe));
+
+	/* Create extra stack space for SRR0 and SRR1 when calling prom/rtas. */
+	DEFINE(PROM_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
+	DEFINE(RTAS_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs) + 16);
+
+	/* These _only_ to be used with {PROM,RTAS}_FRAME_SIZE!!! */
+	DEFINE(_SRR0, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs));
+	DEFINE(_SRR1, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)+8);
+
+	/* systemcfg offsets for use by vdso */
+	DEFINE(CFG_TB_ORIG_STAMP, offsetof(struct systemcfg, tb_orig_stamp));
+	DEFINE(CFG_TB_TICKS_PER_SEC, offsetof(struct systemcfg, tb_ticks_per_sec));
+	DEFINE(CFG_TB_TO_XS, offsetof(struct systemcfg, tb_to_xs));
+	DEFINE(CFG_STAMP_XSEC, offsetof(struct systemcfg, stamp_xsec));
+	DEFINE(CFG_TB_UPDATE_COUNT, offsetof(struct systemcfg, tb_update_count));
+	DEFINE(CFG_TZ_MINUTEWEST, offsetof(struct systemcfg, tz_minuteswest));
+	DEFINE(CFG_TZ_DSTTIME, offsetof(struct systemcfg, tz_dsttime));
+	DEFINE(CFG_SYSCALL_MAP32, offsetof(struct systemcfg, syscall_map_32));
+	DEFINE(CFG_SYSCALL_MAP64, offsetof(struct systemcfg, syscall_map_64));
+
+	/* timeval/timezone offsets for use by vdso */
+	DEFINE(TVAL64_TV_SEC, offsetof(struct timeval, tv_sec));
+	DEFINE(TVAL64_TV_USEC, offsetof(struct timeval, tv_usec));
+	DEFINE(TVAL32_TV_SEC, offsetof(struct compat_timeval, tv_sec));
+	DEFINE(TVAL32_TV_USEC, offsetof(struct compat_timeval, tv_usec));
+	DEFINE(TZONE_TZ_MINWEST, offsetof(struct timezone, tz_minuteswest));
+	DEFINE(TZONE_TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
+#endif
+
+	DEFINE(pbe_address, offsetof(struct pbe, address));
+	DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
+	DEFINE(pbe_next, offsetof(struct pbe, next));
+
+	DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28);
+	return 0;
+}
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
new file mode 100644
index 00000000000..665d7d34304
--- /dev/null
+++ b/arch/powerpc/kernel/fpu.S
@@ -0,0 +1,133 @@
+/*
+ *  FPU support code, moved here from head.S so that it can be used
+ *  by chips which use other head-whatever.S files.
+ *
+ *  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 <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/*
+ * This task wants to use the FPU now.
+ * On UP, disable FP for the task which had the FPU previously,
+ * and save its floating-point registers in its thread_struct.
+ * Load up this task's FP registers from its thread_struct,
+ * enable the FPU for the current task and return to the task.
+ */
+	.globl	load_up_fpu
+load_up_fpu:
+	mfmsr	r5
+	ori	r5,r5,MSR_FP
+#ifdef CONFIG_PPC64BRIDGE
+	clrldi	r5,r5,1			/* turn off 64-bit mode */
+#endif /* CONFIG_PPC64BRIDGE */
+	SYNC
+	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
+	tophys(r6,0)			/* get __pa constant */
+	addis	r3,r6,last_task_used_math@ha
+	lwz	r4,last_task_used_math@l(r3)
+	cmpwi	0,r4,0
+	beq	1f
+	add	r4,r4,r6
+	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
+	SAVE_32FPRS(0, r4)
+	mffs	fr0
+	stfd	fr0,THREAD_FPSCR-4(r4)
+	lwz	r5,PT_REGS(r4)
+	add	r5,r5,r6
+	lwz	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	li	r10,MSR_FP|MSR_FE0|MSR_FE1
+	andc	r4,r4,r10		/* disable FP for previous task */
+	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+	/* enable use of FP after return */
+	mfspr	r5,SPRN_SPRG3		/* current task's THREAD (phys) */
+	lwz	r4,THREAD_FPEXC_MODE(r5)
+	ori	r9,r9,MSR_FP		/* enable FP for current */
+	or	r9,r9,r4
+	lfd	fr0,THREAD_FPSCR-4(r5)
+	mtfsf	0xff,fr0
+	REST_32FPRS(0, r5)
+#ifndef CONFIG_SMP
+	subi	r4,r5,THREAD
+	sub	r4,r4,r6
+	stw	r4,last_task_used_math@l(r3)
+#endif /* CONFIG_SMP */
+	/* restore registers and return */
+	/* we haven't used ctr or xer or lr */
+	b	fast_exception_return
+
+/*
+ * FP unavailable trap from kernel - print a message, but let
+ * the task use FP in the kernel until it returns to user mode.
+ */
+ 	.globl	KernelFP
+KernelFP:
+	lwz	r3,_MSR(r1)
+	ori	r3,r3,MSR_FP
+	stw	r3,_MSR(r1)		/* enable use of FP after return */
+	lis	r3,86f@h
+	ori	r3,r3,86f@l
+	mr	r4,r2			/* current */
+	lwz	r5,_NIP(r1)
+	bl	printk
+	b	ret_from_except
+86:	.string	"floating point used in kernel (task=%p, pc=%x)\n"
+	.align	4,0
+
+/*
+ * giveup_fpu(tsk)
+ * Disable FP for the task given as the argument,
+ * and save the floating-point registers in its thread_struct.
+ * Enables the FPU for use in the kernel on return.
+ */
+	.globl	giveup_fpu
+giveup_fpu:
+	mfmsr	r5
+	ori	r5,r5,MSR_FP
+	SYNC_601
+	ISYNC_601
+	MTMSRD(r5)			/* enable use of fpu now */
+	SYNC_601
+	isync
+	cmpwi	0,r3,0
+	beqlr-				/* if no previous owner, done */
+	addi	r3,r3,THREAD	        /* want THREAD of task */
+	lwz	r5,PT_REGS(r3)
+	cmpwi	0,r5,0
+	SAVE_32FPRS(0, r3)
+	mffs	fr0
+	stfd	fr0,THREAD_FPSCR-4(r3)
+	beq	1f
+	lwz	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	li	r3,MSR_FP|MSR_FE0|MSR_FE1
+	andc	r4,r4,r3		/* disable FP for previous task */
+	stw	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#ifndef CONFIG_SMP
+	li	r5,0
+	lis	r4,last_task_used_math@ha
+	stw	r5,last_task_used_math@l(r4)
+#endif /* CONFIG_SMP */
+	blr
diff --git a/arch/powerpc/kernel/head.S b/arch/powerpc/kernel/head.S
new file mode 100644
index 00000000000..d05509f197d
--- /dev/null
+++ b/arch/powerpc/kernel/head.S
@@ -0,0 +1,1545 @@
+/*
+ *  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.
+ *  MPC8xx modifications Copyright (C) 1997 Dan Malek (dmalek@jlc.net).
+ *  Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk).
+ *
+ *  This file contains the low-level support and setup for the
+ *  PowerPC platform, including trap and interrupt dispatch.
+ *  (The PPC 8xx embedded CPUs use head_8xx.S instead.)
+ *
+ *  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 <asm/processor.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
+#include <asm/cputable.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_APUS
+#include <asm/amigappc.h>
+#endif
+
+#ifdef CONFIG_PPC64BRIDGE
+#define LOAD_BAT(n, reg, RA, RB)	\
+	ld	RA,(n*32)+0(reg);	\
+	ld	RB,(n*32)+8(reg);	\
+	mtspr	SPRN_IBAT##n##U,RA;	\
+	mtspr	SPRN_IBAT##n##L,RB;	\
+	ld	RA,(n*32)+16(reg);	\
+	ld	RB,(n*32)+24(reg);	\
+	mtspr	SPRN_DBAT##n##U,RA;	\
+	mtspr	SPRN_DBAT##n##L,RB;	\
+
+#else /* CONFIG_PPC64BRIDGE */
+
+/* 601 only have IBAT; cr0.eq is set on 601 when using this macro */
+#define LOAD_BAT(n, reg, RA, RB)	\
+	/* see the comment for clear_bats() -- Cort */ \
+	li	RA,0;			\
+	mtspr	SPRN_IBAT##n##U,RA;	\
+	mtspr	SPRN_DBAT##n##U,RA;	\
+	lwz	RA,(n*16)+0(reg);	\
+	lwz	RB,(n*16)+4(reg);	\
+	mtspr	SPRN_IBAT##n##U,RA;	\
+	mtspr	SPRN_IBAT##n##L,RB;	\
+	beq	1f;			\
+	lwz	RA,(n*16)+8(reg);	\
+	lwz	RB,(n*16)+12(reg);	\
+	mtspr	SPRN_DBAT##n##U,RA;	\
+	mtspr	SPRN_DBAT##n##L,RB;	\
+1:
+#endif /* CONFIG_PPC64BRIDGE */
+
+	.text
+	.stabs	"arch/ppc/kernel/",N_SO,0,0,0f
+	.stabs	"head.S",N_SO,0,0,0f
+0:
+	.globl	_stext
+_stext:
+
+/*
+ * _start is defined this way because the XCOFF loader in the OpenFirmware
+ * on the powermac expects the entry point to be a procedure descriptor.
+ */
+	.text
+	.globl	_start
+_start:
+	/*
+	 * These are here for legacy reasons, the kernel used to
+	 * need to look like a coff function entry for the pmac
+	 * but we're always started by some kind of bootloader now.
+	 *  -- Cort
+	 */
+	nop	/* used by __secondary_hold on prep (mtx) and chrp smp */
+	nop	/* used by __secondary_hold on prep (mtx) and chrp smp */
+	nop
+
+/* PMAC
+ * Enter here with the kernel text, data and bss loaded starting at
+ * 0, running with virtual == physical mapping.
+ * r5 points to the prom entry point (the client interface handler
+ * address).  Address translation is turned on, with the prom
+ * managing the hash table.  Interrupts are disabled.  The stack
+ * pointer (r1) points to just below the end of the half-meg region
+ * from 0x380000 - 0x400000, which is mapped in already.
+ *
+ * If we are booted from MacOS via BootX, we enter with the kernel
+ * image loaded somewhere, and the following values in registers:
+ *  r3: 'BooX' (0x426f6f58)
+ *  r4: virtual address of boot_infos_t
+ *  r5: 0
+ *
+ * APUS
+ *   r3: 'APUS'
+ *   r4: physical address of memory base
+ *   Linux/m68k style BootInfo structure at &_end.
+ *
+ * PREP
+ * This is jumped to on prep systems right after the kernel is relocated
+ * to its proper place in memory by the boot loader.  The expected layout
+ * of the regs is:
+ *   r3: ptr to residual data
+ *   r4: initrd_start or if no initrd then 0
+ *   r5: initrd_end - unused if r4 is 0
+ *   r6: Start of command line string
+ *   r7: End of command line string
+ *
+ * This just gets a minimal mmu environment setup so we can call
+ * start_here() to do the real work.
+ * -- Cort
+ */
+
+	.globl	__start
+__start:
+/*
+ * We have to do any OF calls before we map ourselves to KERNELBASE,
+ * because OF may have I/O devices mapped into that area
+ * (particularly on CHRP).
+ */
+	mr	r31,r3			/* save parameters */
+	mr	r30,r4
+	mr	r29,r5
+	mr	r28,r6
+	mr	r27,r7
+	li	r24,0			/* cpu # */
+
+/*
+ * early_init() does the early machine identification and does
+ * the necessary low-level setup and clears the BSS
+ *  -- Cort <cort@fsmlabs.com>
+ */
+	bl	early_init
+
+/*
+ * On POWER4, we first need to tweak some CPU configuration registers
+ * like real mode cache inhibit or exception base
+ */
+#ifdef CONFIG_POWER4
+	bl	__970_cpu_preinit
+#endif /* CONFIG_POWER4 */
+
+#ifdef CONFIG_APUS
+/* On APUS the __va/__pa constants need to be set to the correct
+ * values before continuing.
+ */
+	mr	r4,r30
+	bl	fix_mem_constants
+#endif /* CONFIG_APUS */
+
+/* Switch MMU off, clear BATs and flush TLB. At this point, r3 contains
+ * the physical address we are running at, returned by early_init()
+ */
+ 	bl	mmu_off
+__after_mmu_off:
+#ifndef CONFIG_POWER4
+	bl	clear_bats
+	bl	flush_tlbs
+
+	bl	initial_bats
+#if !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT)
+	bl	setup_disp_bat
+#endif
+#else /* CONFIG_POWER4 */
+	bl	reloc_offset
+	bl	initial_mm_power4
+#endif /* CONFIG_POWER4 */
+
+/*
+ * Call setup_cpu for CPU 0 and initialize 6xx Idle
+ */
+	bl	reloc_offset
+	li	r24,0			/* cpu# */
+	bl	call_setup_cpu		/* Call setup_cpu for this CPU */
+#ifdef CONFIG_6xx
+	bl	reloc_offset
+	bl	init_idle_6xx
+#endif /* CONFIG_6xx */
+#ifdef CONFIG_POWER4
+	bl	reloc_offset
+	bl	init_idle_power4
+#endif /* CONFIG_POWER4 */
+
+
+#ifndef CONFIG_APUS
+/*
+ * We need to run with _start at physical address 0.
+ * On CHRP, we are loaded at 0x10000 since OF on CHRP uses
+ * the exception vectors at 0 (and therefore this copy
+ * overwrites OF's exception vectors with our own).
+ * If the MMU is already turned on, we copy stuff to KERNELBASE,
+ * otherwise we copy it to 0.
+ */
+	bl	reloc_offset
+	mr	r26,r3
+	addis	r4,r3,KERNELBASE@h	/* current address of _start */
+	cmpwi	0,r4,0			/* are we already running at 0? */
+	bne	relocate_kernel
+#endif /* CONFIG_APUS */
+/*
+ * we now have the 1st 16M of ram mapped with the bats.
+ * prep needs the mmu to be turned on here, but pmac already has it on.
+ * this shouldn't bother the pmac since it just gets turned on again
+ * as we jump to our code at KERNELBASE. -- Cort
+ * Actually no, pmac doesn't have it on any more. BootX enters with MMU
+ * off, and in other cases, we now turn it off before changing BATs above.
+ */
+turn_on_mmu:
+	mfmsr	r0
+	ori	r0,r0,MSR_DR|MSR_IR
+	mtspr	SPRN_SRR1,r0
+	lis	r0,start_here@h
+	ori	r0,r0,start_here@l
+	mtspr	SPRN_SRR0,r0
+	SYNC
+	RFI				/* enables MMU */
+
+/*
+ * We need __secondary_hold as a place to hold the other cpus on
+ * an SMP machine, even when we are running a UP kernel.
+ */
+	. = 0xc0			/* for prep bootloader */
+	li	r3,1			/* MTX only has 1 cpu */
+	.globl	__secondary_hold
+__secondary_hold:
+	/* tell the master we're here */
+	stw	r3,4(0)
+#ifdef CONFIG_SMP
+100:	lwz	r4,0(0)
+	/* wait until we're told to start */
+	cmpw	0,r4,r3
+	bne	100b
+	/* our cpu # was at addr 0 - go */
+	mr	r24,r3			/* cpu # */
+	b	__secondary_start
+#else
+	b	.
+#endif /* CONFIG_SMP */
+
+/*
+ * Exception entry code.  This code runs with address translation
+ * turned off, i.e. using physical addresses.
+ * We assume sprg3 has the physical address of the current
+ * task's thread_struct.
+ */
+#define EXCEPTION_PROLOG	\
+	mtspr	SPRN_SPRG0,r10;	\
+	mtspr	SPRN_SPRG1,r11;	\
+	mfcr	r10;		\
+	EXCEPTION_PROLOG_1;	\
+	EXCEPTION_PROLOG_2
+
+#define EXCEPTION_PROLOG_1	\
+	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel */ \
+	andi.	r11,r11,MSR_PR;	\
+	tophys(r11,r1);			/* use tophys(r1) if kernel */ \
+	beq	1f;		\
+	mfspr	r11,SPRN_SPRG3;	\
+	lwz	r11,THREAD_INFO-THREAD(r11);	\
+	addi	r11,r11,THREAD_SIZE;	\
+	tophys(r11,r11);	\
+1:	subi	r11,r11,INT_FRAME_SIZE	/* alloc exc. frame */
+
+
+#define EXCEPTION_PROLOG_2	\
+	CLR_TOP32(r11);		\
+	stw	r10,_CCR(r11);		/* save registers */ \
+	stw	r12,GPR12(r11);	\
+	stw	r9,GPR9(r11);	\
+	mfspr	r10,SPRN_SPRG0;	\
+	stw	r10,GPR10(r11);	\
+	mfspr	r12,SPRN_SPRG1;	\
+	stw	r12,GPR11(r11);	\
+	mflr	r10;		\
+	stw	r10,_LINK(r11);	\
+	mfspr	r12,SPRN_SRR0;	\
+	mfspr	r9,SPRN_SRR1;	\
+	stw	r1,GPR1(r11);	\
+	stw	r1,0(r11);	\
+	tovirt(r1,r11);			/* set new kernel sp */	\
+	li	r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \
+	MTMSRD(r10);			/* (except for mach check in rtas) */ \
+	stw	r0,GPR0(r11);	\
+	SAVE_4GPRS(3, r11);	\
+	SAVE_2GPRS(7, r11)
+
+/*
+ * Note: code which follows this uses cr0.eq (set if from kernel),
+ * r11, r12 (SRR0), and r9 (SRR1).
+ *
+ * Note2: once we have set r1 we are in a position to take exceptions
+ * again, and we could thus set MSR:RI at that point.
+ */
+
+/*
+ * Exception vectors.
+ */
+#define EXCEPTION(n, label, hdlr, xfer)		\
+	. = n;					\
+label:						\
+	EXCEPTION_PROLOG;			\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;	\
+	xfer(n, hdlr)
+
+#define EXC_XFER_TEMPLATE(n, hdlr, trap, copyee, tfer, ret)	\
+	li	r10,trap;					\
+	stw	r10,TRAP(r11);					\
+	li	r10,MSR_KERNEL;					\
+	copyee(r10, r9);					\
+	bl	tfer;						\
+i##n:								\
+	.long	hdlr;						\
+	.long	ret
+
+#define COPY_EE(d, s)		rlwimi d,s,0,16,16
+#define NOCOPY(d, s)
+
+#define EXC_XFER_STD(n, hdlr)		\
+	EXC_XFER_TEMPLATE(n, hdlr, n, NOCOPY, transfer_to_handler_full,	\
+			  ret_from_except_full)
+
+#define EXC_XFER_LITE(n, hdlr)		\
+	EXC_XFER_TEMPLATE(n, hdlr, n+1, NOCOPY, transfer_to_handler, \
+			  ret_from_except)
+
+#define EXC_XFER_EE(n, hdlr)		\
+	EXC_XFER_TEMPLATE(n, hdlr, n, COPY_EE, transfer_to_handler_full, \
+			  ret_from_except_full)
+
+#define EXC_XFER_EE_LITE(n, hdlr)	\
+	EXC_XFER_TEMPLATE(n, hdlr, n+1, COPY_EE, transfer_to_handler, \
+			  ret_from_except)
+
+/* System reset */
+/* core99 pmac starts the seconary here by changing the vector, and
+   putting it back to what it was (UnknownException) when done.  */
+#if defined(CONFIG_GEMINI) && defined(CONFIG_SMP)
+	. = 0x100
+	b	__secondary_start_gemini
+#else
+	EXCEPTION(0x100, Reset, UnknownException, EXC_XFER_STD)
+#endif
+
+/* Machine check */
+/*
+ * On CHRP, this is complicated by the fact that we could get a
+ * machine check inside RTAS, and we have no guarantee that certain
+ * critical registers will have the values we expect.  The set of
+ * registers that might have bad values includes all the GPRs
+ * and all the BATs.  We indicate that we are in RTAS by putting
+ * a non-zero value, the address of the exception frame to use,
+ * in SPRG2.  The machine check handler checks SPRG2 and uses its
+ * value if it is non-zero.  If we ever needed to free up SPRG2,
+ * we could use a field in the thread_info or thread_struct instead.
+ * (Other exception handlers assume that r1 is a valid kernel stack
+ * pointer when we take an exception from supervisor mode.)
+ *	-- paulus.
+ */
+	. = 0x200
+	mtspr	SPRN_SPRG0,r10
+	mtspr	SPRN_SPRG1,r11
+	mfcr	r10
+#ifdef CONFIG_PPC_CHRP
+	mfspr	r11,SPRN_SPRG2
+	cmpwi	0,r11,0
+	bne	7f
+#endif /* CONFIG_PPC_CHRP */
+	EXCEPTION_PROLOG_1
+7:	EXCEPTION_PROLOG_2
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+#ifdef CONFIG_PPC_CHRP
+	mfspr	r4,SPRN_SPRG2
+	cmpwi	cr1,r4,0
+	bne	cr1,1f
+#endif
+	EXC_XFER_STD(0x200, MachineCheckException)
+#ifdef CONFIG_PPC_CHRP
+1:	b	machine_check_in_rtas
+#endif
+
+/* Data access exception. */
+	. = 0x300
+#ifdef CONFIG_PPC64BRIDGE
+	b	DataAccess
+DataAccessCont:
+#else
+DataAccess:
+	EXCEPTION_PROLOG
+#endif /* CONFIG_PPC64BRIDGE */
+	mfspr	r10,SPRN_DSISR
+	andis.	r0,r10,0xa470		/* weird error? */
+	bne	1f			/* if not, try to put a PTE */
+	mfspr	r4,SPRN_DAR		/* into the hash table */
+	rlwinm	r3,r10,32-15,21,21	/* DSISR_STORE -> _PAGE_RW */
+	bl	hash_page
+1:	stw	r10,_DSISR(r11)
+	mr	r5,r10
+	mfspr	r4,SPRN_DAR
+	EXC_XFER_EE_LITE(0x300, handle_page_fault)
+
+#ifdef CONFIG_PPC64BRIDGE
+/* SLB fault on data access. */
+	. = 0x380
+	b	DataSegment
+#endif /* CONFIG_PPC64BRIDGE */
+
+/* Instruction access exception. */
+	. = 0x400
+#ifdef CONFIG_PPC64BRIDGE
+	b	InstructionAccess
+InstructionAccessCont:
+#else
+InstructionAccess:
+	EXCEPTION_PROLOG
+#endif /* CONFIG_PPC64BRIDGE */
+	andis.	r0,r9,0x4000		/* no pte found? */
+	beq	1f			/* if so, try to put a PTE */
+	li	r3,0			/* into the hash table */
+	mr	r4,r12			/* SRR0 is fault address */
+	bl	hash_page
+1:	mr	r4,r12
+	mr	r5,r9
+	EXC_XFER_EE_LITE(0x400, handle_page_fault)
+
+#ifdef CONFIG_PPC64BRIDGE
+/* SLB fault on instruction access. */
+	. = 0x480
+	b	InstructionSegment
+#endif /* CONFIG_PPC64BRIDGE */
+
+/* External interrupt */
+	EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
+
+/* Alignment exception */
+	. = 0x600
+Alignment:
+	EXCEPTION_PROLOG
+	mfspr	r4,SPRN_DAR
+	stw	r4,_DAR(r11)
+	mfspr	r5,SPRN_DSISR
+	stw	r5,_DSISR(r11)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_EE(0x600, AlignmentException)
+
+/* Program check exception */
+	EXCEPTION(0x700, ProgramCheck, ProgramCheckException, EXC_XFER_STD)
+
+/* Floating-point unavailable */
+	. = 0x800
+FPUnavailable:
+	EXCEPTION_PROLOG
+	bne	load_up_fpu		/* if from user, just load it up */
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_EE_LITE(0x800, KernelFP)
+
+/* Decrementer */
+	EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
+
+	EXCEPTION(0xa00, Trap_0a, UnknownException, EXC_XFER_EE)
+	EXCEPTION(0xb00, Trap_0b, UnknownException, EXC_XFER_EE)
+
+/* System call */
+	. = 0xc00
+SystemCall:
+	EXCEPTION_PROLOG
+	EXC_XFER_EE_LITE(0xc00, DoSyscall)
+
+/* Single step - not used on 601 */
+	EXCEPTION(0xd00, SingleStep, SingleStepException, EXC_XFER_STD)
+	EXCEPTION(0xe00, Trap_0e, UnknownException, EXC_XFER_EE)
+
+/*
+ * The Altivec unavailable trap is at 0x0f20.  Foo.
+ * We effectively remap it to 0x3000.
+ * We include an altivec unavailable exception vector even if
+ * not configured for Altivec, so that you can't panic a
+ * non-altivec kernel running on a machine with altivec just
+ * by executing an altivec instruction.
+ */
+	. = 0xf00
+	b	Trap_0f
+
+	. = 0xf20
+	b	AltiVecUnavailable
+
+Trap_0f:
+	EXCEPTION_PROLOG
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_EE(0xf00, UnknownException)
+
+/*
+ * Handle TLB miss for instruction on 603/603e.
+ * Note: we get an alternate set of r0 - r3 to use automatically.
+ */
+	. = 0x1000
+InstructionTLBMiss:
+/*
+ * r0:	stored ctr
+ * r1:	linux style pte ( later becomes ppc h