Merge git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc-merge

30 files changed, 2900 insertions, 293 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b3ae2993efb8..c04bbd320594 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -4,6 +4,7 @@
 
 ifeq ($(CONFIG_PPC64),y)
 EXTRA_CFLAGS	+= -mno-minimal-toc
+CFLAGS_ioctl32.o += -Ifs/
 endif
 ifeq ($(CONFIG_PPC32),y)
 CFLAGS_prom_init.o      += -fPIC
@@ -11,15 +12,21 @@ CFLAGS_btext.o		+= -fPIC
 endif
 
 obj-y				:= semaphore.o cputable.o ptrace.o syscalls.o \
-				   signal_32.o pmc.o
+				   irq.o signal_32.o pmc.o
 obj-$(CONFIG_PPC64)		+= setup_64.o binfmt_elf32.o sys_ppc32.o \
-				   signal_64.o ptrace32.o systbl.o
+				   signal_64.o ptrace32.o systbl.o \
+				   paca.o ioctl32.o cpu_setup_power4.o \
+				   firmware.o sysfs.o
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_POWER4)		+= idle_power4.o
 obj-$(CONFIG_PPC_OF)		+= of_device.o
-obj-$(CONFIG_PPC_RTAS)		+= rtas.o
+procfs-$(CONFIG_PPC64)		:= proc_ppc64.o
+obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
+rtaspci-$(CONFIG_PPC64)		:= rtas_pci.o
+obj-$(CONFIG_PPC_RTAS)		+= rtas.o $(rtaspci-y)
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
+obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b75757251994..8793102711a8 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -106,7 +106,6 @@ int main(void)
 	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));
 	DEFINE(PLATFORM_LPAR, PLATFORM_LPAR);
 
 	/* paca */
diff --git a/arch/powerpc/kernel/cpu_setup_power4.S b/arch/powerpc/kernel/cpu_setup_power4.S
new file mode 100644
index 000000000000..cca942fe6115
--- /dev/null
+++ b/arch/powerpc/kernel/cpu_setup_power4.S
@@ -0,0 +1,233 @@
+/*
+ * This file contains low level CPU setup functions.
+ *    Copyright (C) 2003 Benjamin Herrenschmidt (benh@kernel.crashing.org)
+ *
+ * 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/cputable.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cache.h>
+
+_GLOBAL(__970_cpu_preinit)
+	/*
+	 * Do nothing if not running in HV mode
+	 */
+	mfmsr	r0
+	rldicl.	r0,r0,4,63
+	beqlr
+
+	/*
+	 * Deal only with PPC970 and PPC970FX.
+	 */
+	mfspr	r0,SPRN_PVR
+	srwi	r0,r0,16
+	cmpwi	r0,0x39
+	beq	1f
+	cmpwi	r0,0x3c
+	beq	1f
+	cmpwi	r0,0x44
+	bnelr
+1:
+
+	/* Make sure HID4:rm_ci is off before MMU is turned off, that large
+	 * pages are enabled with HID4:61 and clear HID5:DCBZ_size and
+	 * HID5:DCBZ32_ill
+	 */
+	li	r0,0
+	mfspr	r3,SPRN_HID4
+	rldimi	r3,r0,40,23	/* clear bit 23 (rm_ci) */
+	rldimi	r3,r0,2,61	/* clear bit 61 (lg_pg_en) */
+	sync
+	mtspr	SPRN_HID4,r3
+	isync
+	sync
+	mfspr	r3,SPRN_HID5
+	rldimi	r3,r0,6,56	/* clear bits 56 & 57 (DCBZ*) */
+	sync
+	mtspr	SPRN_HID5,r3
+	isync
+	sync
+
+	/* Setup some basic HID1 features */
+	mfspr	r0,SPRN_HID1
+	li	r3,0x1200		/* enable i-fetch cacheability */
+	sldi	r3,r3,44		/* and prefetch */
+	or	r0,r0,r3
+	mtspr	SPRN_HID1,r0
+	mtspr	SPRN_HID1,r0
+	isync
+
+	/* Clear HIOR */
+	li	r0,0
+	sync
+	mtspr	SPRN_HIOR,0		/* Clear interrupt prefix */
+	isync
+	blr
+
+_GLOBAL(__setup_cpu_power4)
+	blr
+
+_GLOBAL(__setup_cpu_be)
+        /* Set large page sizes LP=0: 16MB, LP=1: 64KB */
+        addi    r3, 0,  0
+        ori     r3, r3, HID6_LB
+        sldi    r3, r3, 32
+        nor     r3, r3, r3
+        mfspr   r4, SPRN_HID6
+        and     r4, r4, r3
+        addi    r3, 0, 0x02000
+        sldi    r3, r3, 32
+        or      r4, r4, r3
+        mtspr   SPRN_HID6, r4
+	blr
+
+_GLOBAL(__setup_cpu_ppc970)
+	mfspr	r0,SPRN_HID0
+	li	r11,5			/* clear DOZE and SLEEP */
+	rldimi	r0,r11,52,8		/* set NAP and DPM */
+	mtspr	SPRN_HID0,r0
+	mfspr	r0,SPRN_HID0
+	mfspr	r0,SPRN_HID0
+	mfspr	r0,SPRN_HID0
+	mfspr	r0,SPRN_HID0
+	mfspr	r0,SPRN_HID0
+	mfspr	r0,SPRN_HID0
+	sync
+	isync
+	blr
+
+/* Definitions for the table use to save CPU states */
+#define CS_HID0		0
+#define CS_HID1		8
+#define	CS_HID4		16
+#define CS_HID5		24
+#define CS_SIZE		32
+
+	.data
+	.balign	L1_CACHE_BYTES,0
+cpu_state_storage:
+	.space	CS_SIZE
+	.balign	L1_CACHE_BYTES,0
+	.text
+
+/* Called in normal context to backup CPU 0 state. This
+ * does not include cache settings. This function is also
+ * called for machine sleep. This does not include the MMU
+ * setup, BATs, etc... but rather the "special" registers
+ * like HID0, HID1, HID4, etc...
+ */
+_GLOBAL(__save_cpu_setup)
+	/* Some CR fields are volatile, we back it up all */
+	mfcr	r7
+
+	/* Get storage ptr */
+	LOADADDR(r5,cpu_state_storage)
+
+	/* We only deal with 970 for now */
+	mfspr	r0,SPRN_PVR
+	srwi	r0,r0,16
+	cmpwi	r0,0x39
+	beq	1f
+	cmpwi	r0,0x3c
+	beq	1f
+	cmpwi	r0,0x44
+	bne	2f
+
+1:	/* Save HID0,1,4 and 5 */
+	mfspr	r3,SPRN_HID0
+	std	r3,CS_HID0(r5)
+	mfspr	r3,SPRN_HID1
+	std	r3,CS_HID1(r5)
+	mfspr	r3,SPRN_HID4
+	std	r3,CS_HID4(r5)
+	mfspr	r3,SPRN_HID5
+	std	r3,CS_HID5(r5)
+
+2:
+	mtcr	r7
+	blr
+
+/* Called with no MMU context (typically MSR:IR/DR off) to
+ * restore CPU state as backed up by the previous
+ * function. This does not include cache setting
+ */
+_GLOBAL(__restore_cpu_setup)
+	/* Get storage ptr (FIXME when using anton reloc as we
+	 * are running with translation disabled here
+	 */
+	LOADADDR(r5,cpu_state_storage)
+
+	/* We only deal with 970 for now */
+	mfspr	r0,SPRN_PVR
+	srwi	r0,r0,16
+	cmpwi	r0,0x39
+	beq	1f
+	cmpwi	r0,0x3c
+	beq	1f
+	cmpwi	r0,0x44
+	bnelr
+
+1:	/* Before accessing memory, we make sure rm_ci is clear */
+	li	r0,0
+	mfspr	r3,SPRN_HID4
+	rldimi	r3,r0,40,23	/* clear bit 23 (rm_ci) */
+	sync
+	mtspr	SPRN_HID4,r3
+	isync
+	sync
+
+	/* Clear interrupt prefix */
+	li	r0,0
+	sync
+	mtspr	SPRN_HIOR,0
+	isync
+
+	/* Restore HID0 */
+	ld	r3,CS_HID0(r5)
+	sync
+	isync
+	mtspr	SPRN_HID0,r3
+	mfspr	r3,SPRN_HID0
+	mfspr	r3,SPRN_HID0
+	mfspr	r3,SPRN_HID0
+	mfspr	r3,SPRN_HID0
+	mfspr	r3,SPRN_HID0
+	mfspr	r3,SPRN_HID0
+	sync
+	isync
+
+	/* Restore HID1 */
+	ld	r3,CS_HID1(r5)
+	sync
+	isync
+	mtspr	SPRN_HID1,r3
+	mtspr	SPRN_HID1,r3
+	sync
+	isync
+
+	/* Restore HID4 */
+	ld	r3,CS_HID4(r5)
+	sync
+	isync
+	mtspr	SPRN_HID4,r3
+	sync
+	isync
+
+	/* Restore HID5 */
+	ld	r3,CS_HID5(r5)
+	sync
+	isync
+	mtspr	SPRN_HID5,r3
+	sync
+	isync
+	blr
+
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index cc4e9eb1c13f..1d85cedbbb7b 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -52,6 +52,9 @@ extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec);
 #define COMMON_USER		(PPC_FEATURE_32 | PPC_FEATURE_HAS_FPU | \
 				 PPC_FEATURE_HAS_MMU)
 #define COMMON_USER_PPC64	(COMMON_USER | PPC_FEATURE_64)
+#define COMMON_USER_POWER4	(COMMON_USER_PPC64 | PPC_FEATURE_POWER4)
+#define COMMON_USER_POWER5	(COMMON_USER_PPC64 | PPC_FEATURE_POWER5)
+#define COMMON_USER_POWER5_PLUS	(COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS)
 
 
 /* We only set the spe features if the kernel was compiled with
@@ -160,7 +163,7 @@ struct cpu_spec	cpu_specs[] = {
 		.pvr_value		= 0x00350000,
 		.cpu_name		= "POWER4 (gp)",
 		.cpu_features		= CPU_FTRS_POWER4,
-		.cpu_user_features	= COMMON_USER_PPC64,
+		.cpu_user_features	= COMMON_USER_POWER4,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -175,7 +178,7 @@ struct cpu_spec	cpu_specs[] = {
 		.pvr_value		= 0x00380000,
 		.cpu_name		= "POWER4+ (gq)",
 		.cpu_features		= CPU_FTRS_POWER4,
-		.cpu_user_features	= COMMON_USER_PPC64,
+		.cpu_user_features	= COMMON_USER_POWER4,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -190,7 +193,7 @@ struct cpu_spec	cpu_specs[] = {
 		.pvr_value		= 0x00390000,
 		.cpu_name		= "PPC970",
 		.cpu_features		= CPU_FTRS_PPC970,
-		.cpu_user_features	= COMMON_USER_PPC64 |
+		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
@@ -212,7 +215,7 @@ struct cpu_spec	cpu_specs[] = {
 #else
 		.cpu_features		= CPU_FTRS_PPC970,
 #endif
-		.cpu_user_features	= COMMON_USER_PPC64 |
+		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
@@ -230,7 +233,7 @@ struct cpu_spec	cpu_specs[] = {
 		.pvr_value		= 0x00440000,
 		.cpu_name		= "PPC970MP",
 		.cpu_features		= CPU_FTRS_PPC970,
-		.cpu_user_features	= COMMON_USER_PPC64 |
+		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
@@ -245,7 +248,7 @@ struct cpu_spec	cpu_specs[] = {
 		.pvr_value		= 0x003a0000,
 		.cpu_name		= "POWER5 (gr)",
 		.cpu_features		= CPU_FTRS_POWER5,
-		.cpu_user_features	= COMMON_USER_PPC64,
+		.cpu_user_features	= COMMON_USER_POWER5,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -260,7 +263,7 @@ struct cpu_spec	cpu_specs[] = {
 		.pvr_value		= 0x003b0000,
 		.cpu_name		= "POWER5 (gs)",
 		.cpu_features		= CPU_FTRS_POWER5,
-		.cpu_user_features	= COMMON_USER_PPC64,
+		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
@@ -276,7 +279,7 @@ struct cpu_spec	cpu_specs[] = {
 		.cpu_name		= "Cell Broadband Engine",
 		.cpu_features		= CPU_FTRS_CELL,
 		.cpu_user_features	= COMMON_USER_PPC64 |
-			PPC_FEATURE_HAS_ALTIVEC_COMP,
+			PPC_FEATURE_CELL | PPC_FEATURE_HAS_ALTIVEC_COMP,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.cpu_setup		= __setup_cpu_be,
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
new file mode 100644
index 000000000000..65eae752a527
--- /dev/null
+++ b/arch/powerpc/kernel/firmware.c
@@ -0,0 +1,45 @@
+/*
+ *  Extracted from cputable.c
+ *
+ *  Copyright (C) 2001 Ben. Herrenschmidt (benh@kernel.crashing.org)
+ *
+ *  Modifications for ppc64:
+ *      Copyright (C) 2003 Dave Engebretsen <engebret@us.ibm.com>
+ *  Copyright (C) 2005 Stephen Rothwell, IBM Corporation
+ *
+ *  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/firmware.h>
+
+unsigned long ppc64_firmware_features;
+
+#ifdef CONFIG_PPC_PSERIES
+firmware_feature_t firmware_features_table[FIRMWARE_MAX_FEATURES] = {
+	{FW_FEATURE_PFT,		"hcall-pft"},
+	{FW_FEATURE_TCE,		"hcall-tce"},
+	{FW_FEATURE_SPRG0,		"hcall-sprg0"},
+	{FW_FEATURE_DABR,		"hcall-dabr"},
+	{FW_FEATURE_COPY,		"hcall-copy"},
+	{FW_FEATURE_ASR,		"hcall-asr"},
+	{FW_FEATURE_DEBUG,		"hcall-debug"},
+	{FW_FEATURE_PERF,		"hcall-perf"},
+	{FW_FEATURE_DUMP,		"hcall-dump"},
+	{FW_FEATURE_INTERRUPT,		"hcall-interrupt"},
+	{FW_FEATURE_MIGRATE,		"hcall-migrate"},
+	{FW_FEATURE_PERFMON,		"hcall-perfmon"},
+	{FW_FEATURE_CRQ,		"hcall-crq"},
+	{FW_FEATURE_VIO,		"hcall-vio"},
+	{FW_FEATURE_RDMA,		"hcall-rdma"},
+	{FW_FEATURE_LLAN,		"hcall-lLAN"},
+	{FW_FEATURE_BULK,		"hcall-bulk"},
+	{FW_FEATURE_XDABR,		"hcall-xdabr"},
+	{FW_FEATURE_MULTITCE,		"hcall-multi-tce"},
+	{FW_FEATURE_SPLPAR,		"hcall-splpar"},
+};
+#endif
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 4d6001fa1cf2..b780b42c95fc 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -41,20 +41,20 @@ _GLOBAL(load_up_fpu)
 #ifndef CONFIG_SMP
 	LOADBASE(r3, last_task_used_math)
 	toreal(r3)
-	LDL	r4,OFF(last_task_used_math)(r3)
-	CMPI	0,r4,0
+	PPC_LL	r4,OFF(last_task_used_math)(r3)
+	PPC_LCMPI	0,r4,0
 	beq	1f
 	toreal(r4)
 	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
 	SAVE_32FPRS(0, r4)
 	mffs	fr0
 	stfd	fr0,THREAD_FPSCR(r4)
-	LDL	r5,PT_REGS(r4)
+	PPC_LL	r5,PT_REGS(r4)
 	toreal(r5)
-	LDL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 	li	r10,MSR_FP|MSR_FE0|MSR_FE1
 	andc	r4,r4,r10		/* disable FP for previous task */
-	STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
 #endif /* CONFIG_SMP */
 	/* enable use of FP after return */
@@ -77,7 +77,7 @@ _GLOBAL(load_up_fpu)
 #ifndef CONFIG_SMP
 	subi	r4,r5,THREAD
 	fromreal(r4)
-	STL	r4,OFF(last_task_used_math)(r3)
+	PPC_STL	r4,OFF(last_task_used_math)(r3)
 #endif /* CONFIG_SMP */
 	/* restore registers and return */
 	/* we haven't used ctr or xer or lr */
@@ -97,24 +97,24 @@ _GLOBAL(giveup_fpu)
 	MTMSRD(r5)			/* enable use of fpu now */
 	SYNC_601
 	isync
-	CMPI	0,r3,0
+	PPC_LCMPI	0,r3,0
 	beqlr-				/* if no previous owner, done */
 	addi	r3,r3,THREAD	        /* want THREAD of task */
-	LDL	r5,PT_REGS(r3)
-	CMPI	0,r5,0
+	PPC_LL	r5,PT_REGS(r3)
+	PPC_LCMPI	0,r5,0
 	SAVE_32FPRS(0, r3)
 	mffs	fr0
 	stfd	fr0,THREAD_FPSCR(r3)
 	beq	1f
-	LDL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 	li	r3,MSR_FP|MSR_FE0|MSR_FE1
 	andc	r4,r4,r3		/* disable FP for previous task */
-	STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 1:
 #ifndef CONFIG_SMP
 	li	r5,0
 	LOADBASE(r4,last_task_used_math)
-	STL	r5,OFF(last_task_used_math)(r4)
+	PPC_STL	r5,OFF(last_task_used_math)(r4)
 #endif /* CONFIG_SMP */
 	blr
 
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 16ab40daa738..8a8bf79ef044 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -28,7 +28,6 @@
 #include <asm/reg.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>
@@ -1697,25 +1696,14 @@ _GLOBAL(pmac_secondary_start)
  *   SPRG3 = paca virtual address
  */
 _GLOBAL(__secondary_start)
+	/* Set thread priority to MEDIUM */
+	HMT_MEDIUM
 
-	HMT_MEDIUM			/* Set thread priority to MEDIUM */
-
+	/* Load TOC */
 	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	SPRN_SDR1,r6			/* set the htab location	 */
-#endif
-	/* Initialize the first segment table (or SLB) entry		 */
-	ld	r3,PACASTABVIRT(r13)	/* get addr of segment table	 */
-BEGIN_FTR_SECTION
-	bl	.stab_initialize
-END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
-	bl	.slb_initialize
+
+	/* Do early setup for that CPU (stab, slb, hash table pointer) */
+	bl	.early_setup_secondary
 
 	/* Initialize the kernel stack.  Just a repeat for iSeries.	 */
 	LOADADDR(r3,current_set)
@@ -1724,37 +1712,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
 	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,SPRN_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
+	/* Clear backchain so we get nice backtraces */
 	li	r7,0
 	mtlr	r7
 
@@ -1777,6 +1735,7 @@ _GLOBAL(start_secondary_prolog)
 	li	r3,0
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
 	bl	.start_secondary
+	b	.
 #endif
 
 /*
@@ -1896,40 +1855,6 @@ _STATIC(start_here_multiplatform)
 	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,SPRN_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 */
-	add	r6,r6,r26
-	ld	r6,0(r6)		/* get the value of _SDR1 */
-	mtspr	SPRN_SDR1,r6			/* set the htab location  */
-98: 
 	LOADADDR(r3,.start_here_common)
 	SET_REG_TO_CONST(r4, MSR_KERNEL)
 	mtspr	SPRN_SRR0,r3
diff --git a/arch/powerpc/kernel/ioctl32.c b/arch/powerpc/kernel/ioctl32.c
new file mode 100644
index 000000000000..3fa6a93adbd0
--- /dev/null
+++ b/arch/powerpc/kernel/ioctl32.c
@@ -0,0 +1,49 @@
+/*
+ * ioctl32.c: Conversion between 32bit and 64bit native ioctls.
+ *
+ * Based on sparc64 ioctl32.c by:
+ *
+ * Copyright (C) 1997-2000  Jakub Jelinek  (jakub@redhat.com)
+ * Copyright (C) 1998  Eddie C. Dost  (ecd@skynet.be)
+ *
+ * ppc64 changes:
+ *
+ * Copyright (C) 2000  Ken Aaker (kdaaker@rchland.vnet.ibm.com)
+ * Copyright (C) 2001  Anton Blanchard (antonb@au.ibm.com)
+ *
+ * These routines maintain argument size conversion between 32bit and 64bit
+ * ioctls.
+ *
+ * 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.
+ */
+
+#define INCLUDES
+#include "compat_ioctl.c"
+#include <linux/syscalls.h>
+
+#define CODE
+#include "compat_ioctl.c"
+
+#define HANDLE_IOCTL(cmd,handler) { cmd, (ioctl_trans_handler_t)handler, NULL },
+#define COMPATIBLE_IOCTL(cmd) HANDLE_IOCTL(cmd,sys_ioctl)
+
+#define IOCTL_TABLE_START \
+	struct ioctl_trans ioctl_start[] = {
+#define IOCTL_TABLE_END \
+	};
+
+IOCTL_TABLE_START
+#include <linux/compat_ioctl.h>
+#define DECLARES
+#include "compat_ioctl.c"
+
+/* Little p (/dev/rtc, /dev/envctrl, etc.) */
+COMPATIBLE_IOCTL(_IOR('p', 20, int[7])) /* RTCGET */
+COMPATIBLE_IOCTL(_IOW('p', 21, int[7])) /* RTCSET */
+
+IOCTL_TABLE_END
+
+int ioctl_table_size = ARRAY_SIZE(ioctl_start);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
new file mode 100644
index 000000000000..4b7940693f3d
--- /dev/null
+++ b/arch/powerpc/kernel/irq.c
@@ -0,0 +1,478 @@
+/*
+ *  arch/ppc/kernel/irq.c
+ *
+ *  Derived from arch/i386/kernel/irq.c
+ *    Copyright (C) 1992 Linus Torvalds
+ *  Adapted from arch/i386 by Gary Thomas
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *  Updated and modified by Cort Dougan <cort@fsmlabs.com>
+ *    Copyright (C) 1996-2001 Cort Dougan
+ *  Adapted for Power Macintosh by Paul Mackerras
+ *    Copyright (C) 1996 Paul Mackerras (paulus@cs.anu.edu.au)
+ *  Amiga/APUS changes by Jesper Skov (jskov@cygnus.co.uk).
+ *
+ * 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.
+ *
+ * This file contains the code used by various IRQ handling routines:
+ * asking for different IRQ's should be done through these routines
+ * instead of just grabbing them. Thus setups with different IRQ numbers
+ * shouldn't result in any weird surprises, and installing new handlers
+ * should be easier.
+ *
+ * The MPC8xx has an interrupt mask in the SIU.  If a bit is set, the
+ * interrupt is _enabled_.  As expected, IRQ0 is bit 0 in the 32-bit
+ * mask register (of which only 16 are defined), hence the weird shifting
+ * and complement of the cached_irq_mask.  I want to be able to stuff
+ * this right into the SIU SMASK register.
+ * Many of the prep/chrp functions are conditional compiled on CONFIG_8xx
+ * to reduce code space and undefined function references.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/threads.h>
+#include <linux/kernel_stat.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/ptrace.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/timex.h>
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/proc_fs.h>
+#include <linux/random.h>
+#include <linux/seq_file.h>
+#include <linux/cpumask.h>
+#include <linux/profile.h>
+#include <linux/bitops.h>
+#ifdef CONFIG_PPC64
+#include <linux/kallsyms.h>
+#endif
+
+#include <asm/uaccess.h>
+#include <asm/system.h>
+#include <asm/io.h>
+#include <asm/pgtable.h>
+#include <asm/irq.h>
+#include <asm/cache.h>
+#include <asm/prom.h>
+#include <asm/ptrace.h>
+#include <asm/machdep.h>
+#ifdef CONFIG_PPC64
+#include <asm/iseries/it_lp_queue.h>
+#include <asm/paca.h>
+#endif
+
+static int ppc_spurious_interrupts;
+
+#if defined(CONFIG_PPC_ISERIES) && defined(CONFIG_SMP)
+extern void iSeries_smp_message_recv(struct pt_regs *);
+#endif
+
+#ifdef CONFIG_PPC32
+#define NR_MASK_WORDS	((NR_IRQS + 31) / 32)
+
+unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
+atomic_t ppc_n_lost_interrupts;
+
+#ifdef CONFIG_TAU_INT
+extern int tau_initialized;
+extern int tau_interrupts(int);
+#endif
+
+#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_MERGE)
+extern atomic_t ipi_recv;
+extern atomic_t ipi_sent;
+#endif
+#endif /* CONFIG_PPC32 */
+
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(irq_desc);
+
+int distribute_irqs = 1;
+int __irq_offset_value;
+u64 ppc64_interrupt_controller;
+#endif /* CONFIG_PPC64 */
+
+int show_interrupts(struct seq_file *p, void *v)
+{
+	int i = *(loff_t *)v, j;
+	struct irqaction *action;
+	irq_desc_t *desc;
+	unsigned long flags;
+
+	if (i == 0) {
+		seq_puts(p, "           ");
+		for_each_online_cpu(j)
+			seq_printf(p, "CPU%d       ", j);
+		seq_putc(p, '\n');
+	}
+
+	if (i < NR_IRQS) {
+		desc = get_irq_desc(i);
+		spin_lock_irqsave(&desc->lock, flags);
+		action = desc->action;
+		if (!action || !action->handler)
+			goto skip;
+		seq_printf(p, "%3d: ", i);
+#ifdef CONFIG_SMP
+		for_each_online_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+#else
+		seq_printf(p, "%10u ", kstat_irqs(i));
+#endif /* CONFIG_SMP */
+		if (desc->handler)
+			seq_printf(p, " %s ", desc->handler->typename);
+		else
+			seq_puts(p, "  None      ");
+		seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge  ");
+		seq_printf(p, "    %s", action->name);
+		for (action = action->next; action; action = action->next)
+			seq_printf(p, ", %s", action->name);
+		seq_putc(p, '\n');
+skip:
+		spin_unlock_irqrestore(&desc->lock, flags);
+	} else if (i == NR_IRQS) {
+#ifdef CONFIG_PPC32
+#ifdef CONFIG_TAU_INT
+		if (tau_initialized){
+			seq_puts(p, "TAU: ");
+			for (j = 0; j < NR_CPUS; j++)
+				if (cpu_online(j))
+					seq_printf(p, "%10u ", tau_interrupts(j));
+			seq_puts(p, "  PowerPC             Thermal Assist (cpu temp)\n");
+		}
+#endif
+#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_MERGE)
+		/* should this be per processor send/receive? */
+		seq_printf(p, "IPI (recv/sent): %10u/%u\n",
+				atomic_read(&ipi_recv), atomic_read(&ipi_sent));
+#endif
+#endif /* CONFIG_PPC32 */
+		seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+void fixup_irqs(cpumask_t map)
+{
+	unsigned int irq;
+	static int warned;
+
+	for_each_irq(irq) {
+		cpumask_t mask;
+
+		if (irq_desc[irq].status & IRQ_PER_CPU)
+			continue;
+
+		cpus_and(mask, irq_affinity[irq], map);
+		if (any_online_cpu(mask) == NR_CPUS) {
+			printk("Breaking affinity for irq %i\n", irq);
+			mask = map;
+		}
+		if (irq_desc[irq].handler->set_affinity)
+			irq_desc[irq].handler->set_affinity(irq, mask);
+		else if (irq_desc[irq].action && !(warned++))
+			printk("Cannot set affinity for irq %i\n", irq);
+	}
+
+	local_irq_enable();
+	mdelay(1);
+	local_irq_disable();
+}
+#endif
+
+#ifdef CONFIG_PPC_ISERIES
+void do_IRQ(struct pt_regs *regs)
+{
+	struct paca_struct *lpaca;
+
+	irq_enter();
+
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+	/* Debugging check for stack overflow: is there less than 2KB free? */
+	{
+		long sp;
+
+		sp = __get_SP() & (THREAD_SIZE-1);
+
+		if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
+			printk("do_IRQ: stack overflow: %ld\n",
+				sp - sizeof(struct thread_info));
+			dump_stack();
+		}
+	}
+#endif
+
+	lpaca = get_paca();
+#ifdef CONFIG_SMP
+	if (lpaca->lppaca.int_dword.fields.ipi_cnt) {
+		lpaca->lppaca.int_dword.fields.ipi_cnt = 0;
+		iSeries_smp_message_recv(regs);
+	}
+#endif /* CONFIG_SMP */
+	if (hvlpevent_is_pending())
+		process_hvlpevents(regs);
+
+	irq_exit();
+
+	if (lpaca->lppaca.int_dword.fields.decr_int) {
+		lpaca->lppaca.int_dword.fields.decr_int = 0;
+		/* Signal a fake decrementer interrupt */
+		timer_interrupt(regs);
+	}
+}
+
+#else	/* CONFIG_PPC_ISERIES */
+
+void do_IRQ(struct pt_regs *regs)
+{
+	int irq;
+#ifdef CONFIG_IRQSTACKS
+	struct thread_info *curtp, *irqtp;
+#endif
+
+        irq_enter();
+
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+	/* Debugging check for stack overflow: is there less than 2KB free? */
+	{
+		long sp;
+
+		sp = __get_SP() & (THREAD_SIZE-1);
+
+		if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
+			printk("do_IRQ: stack overflow: %ld\n",
+				sp - sizeof(struct thread_info));
+			dump_stack();
+		}
+	}
+#endif
+
+	/*
+	 * Every platform is required to implement ppc_md.get_irq.
+	 * This function will either return an irq number or -1 to
+	 * indicate there are no more pending.
+	 * The value -2 is for buggy hardware and means that this IRQ
+	 * has already been handled. -- Tom
+	 */
+	irq = ppc_md.get_irq(regs);
+
+	if (irq >= 0) {
+#ifdef CONFIG_IRQSTACKS
+		/* Switch to the irq stack to handle this */
+		curtp = current_thread_info();
+		irqtp = hardirq_ctx[smp_processor_id()];
+		if (curtp != irqtp) {
+			irqtp->task = curtp->task;
+			irqtp->flags = 0;
+			call___do_IRQ(irq, regs, irqtp);
+			irqtp->task = NULL;
+			if (irqtp->flags)
+				set_bits(irqtp->flags, &curtp->flags);
+		} else
+#endif
+			__do_IRQ(irq, regs);
+	} else
+#ifdef CONFIG_PPC32
+		if (irq != -2)
+#endif
+			/* That's not SMP safe ... but who cares ? */
+			ppc_spurious_interrupts++;
+        irq_exit();
+}
+
+#endif	/* CONFIG_PPC_ISERIES */
+
+void __init init_IRQ(void)
+{
+#ifdef CONFIG_PPC64
+	static int once = 0;
+
+	if (once)
+		return;
+
+	once++;
+
+#endif
+	ppc_md.init_IRQ();
+#ifdef CONFIG_PPC64
+	irq_ctx_init();
+#endif
+}
+
+#ifdef CONFIG_PPC64
+#ifndef CONFIG_PPC_ISERIES
+/*
+ * Virtual IRQ mapping code, used on systems with XICS interrupt controllers.
+ */
+
+#define UNDEFINED_IRQ 0xffffffff
+unsigned int virt_irq_to_real_map[NR_IRQS];
+
+/*
+ * Don't use virtual irqs 0, 1, 2 for devices.
+ * The pcnet32 driver considers interrupt numbers < 2 to be invalid,
+ * and 2 is the XICS IPI interrupt.
+ * We limit virtual irqs to 17 less than NR_IRQS so that when we
+ * offset them by 16 (to reserve the first 16 for ISA interrupts)
+ * we don't end up with an interrupt number >= NR_IRQS.
+ */
+#define MIN_VIRT_IRQ	3
+#define MAX_VIRT_IRQ	(NR_IRQS - NUM_ISA_INTERRUPTS - 1)
+#define NR_VIRT_IRQS	(MAX_VIRT_IRQ - MIN_VIRT_IRQ + 1)
+
+void
+virt_irq_init(void)
+{
+	int i;
+	for (i = 0; i < NR_IRQS; i++)
+		virt_irq_to_real_map[i] = UNDEFINED_IRQ;
+}
+
+/* Create a mapping for a real_irq if it doesn't already exist.
+ * Return the virtual irq as a convenience.
+ */
+int virt_irq_create_mapping(unsigned int real_irq)
+{
+	unsigned int virq, first_virq;
+	static int warned;
+
+	if (ppc64_interrupt_controller == IC_OPEN_PIC)
+		return real_irq;	/* no mapping for openpic (for now) */
+
+	if (ppc64_interrupt_controller == IC_CELL_PIC)
+		return real_irq;	/* no mapping for iic either */
+
+	/* don't map interrupts < MIN_VIRT_IRQ */
+	if (real_irq < MIN_VIRT_IRQ) {
+		virt_irq_to_real_map[real_irq] = real_irq;
+		return real_irq;
+	}
+
+	/* map to a number between MIN_VIRT_IRQ and MAX_VIRT_IRQ */
+	virq = real_irq;
+	if (virq > MAX_VIRT_IRQ)
+		virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;
+
+	/* search for this number or a free slot */
+	first_virq = virq;
+	while (virt_irq_to_real_map[virq] != UNDEFINED_IRQ) {
+		if (virt_irq_to_real_map[virq] == real_irq)
+			return virq;
+		if (++virq > MAX_VIRT_IRQ)
+			virq = MIN_VIRT_IRQ;
+		if (virq == first_virq)
+			goto nospace;	/* oops, no free slots */
+	}
+
+	virt_irq_to_real_map[virq] = real_irq;
+	return virq;
+
+ nospace:
+	if (!warned) {
+		printk(KERN_CRIT "Interrupt table is full\n");
+		printk(KERN_CRIT "Increase NR_IRQS (currently %d) "
+		       "in your kernel sources and rebuild.\n", NR_IRQS);
+		warned = 1;
+	}
+	return NO_IRQ;
+}
+
+/*
+ * In most cases will get a hit on the very first slot checked in the
+ * virt_irq_to_real_map.  Only when there are a large number of
+ * IRQs will this be expensive.
+ */
+unsigned int real_irq_to_virt_slowpath(unsigned int real_irq)
+{
+	unsigned int virq;
+	unsigned int first_virq;
+
+	virq = real_irq;
+
+	if (virq > MAX_VIRT_IRQ)
+		virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;
+
+	first_virq = virq;
+
+	do {
+		if (virt_irq_to_real_map[virq] == real_irq)
+			return virq;
+
+		virq++;
+
+		if (virq >= MAX_VIRT_IRQ)
+			virq = 0;
+
+	} while (first_virq != virq);
+
+	return NO_IRQ;
+
+}
+
+#endif /* CONFIG_PPC_ISERIES */
+
+#ifdef CONFIG_IRQSTACKS
+struct thread_info *softirq_ctx[NR_CPUS];
+struct thread_info *hardirq_ctx[NR_CPUS];
+
+void irq_ctx_init(void)
+{
+	struct thread_info *tp;
+	int i;
+
+	for_each_cpu(i) {
+		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
+		tp = softirq_ctx[i];
+		tp->cpu = i;
+		tp->preempt_count = SOFTIRQ_OFFSET;
+
+		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
+		tp = hardirq_ctx[i];
+		tp->cpu = i;
+		tp->preempt_count = HARDIRQ_OFFSET;
+	}
+}
+
+void do_softirq(void)
+{
+	unsigned long flags;
+	struct thread_info *curtp, *irqtp;
+
+	if (in_interrupt())
+		return;
+
+	local_irq_save(flags);
+
+	if (local_softirq_pending()) {
+		curtp = current_thread_info();
+		irqtp = softirq_ctx[smp_processor_id()];
+		irqtp->task = curtp->task;
+		call_do_softirq(irqtp);
+		irqtp->task = NULL;
+	}
+
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(do_softirq);
+
+#endif /* CONFIG_IRQSTACKS */
+
+static int __init setup_noirqdistrib(char *str)
+{
+	distribute_irqs = 0;
+	return 1;
+}
+
+__setup("noirqdistrib", setup_noirqdistrib);
+#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
new file mode 100644
index 000000000000..5e954fae031f
--- /dev/null
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -0,0 +1,612 @@
+/*
+ * PowerPC64 LPAR Configuration Information Driver
+ *
+ * Dave Engebretsen engebret@us.ibm.com
+ *    Copyright (c) 2003 Dave Engebretsen
+ * Will Schmidt willschm@us.ibm.com
+ *    SPLPAR updates, Copyright (c) 2003 Will Schmidt IBM Corporation.
+ *    seq_file updates, Copyright (c) 2004 Will Schmidt IBM Corporation.
+ * Nathan Lynch nathanl@austin.ibm.com
+ *    Added lparcfg_write, Copyright (C) 2004 Nathan Lynch IBM Corporation.
+ *
+ *      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.
+ *
+ * This driver creates a proc file at /proc/ppc64/lparcfg which contains
+ * keyword - value pairs that specify the configuration of the partition.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/proc_fs.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <asm/uaccess.h>
+#include <asm/iseries/hv_lp_config.h>
+#include <asm/lppaca.h>
+#include <asm/hvcall.h>
+#include <asm/firmware.h>
+#include <asm/rtas.h>
+#include <asm/system.h>
+#include <asm/time.h>
+#include <asm/iseries/it_exp_vpd_panel.h>
+#include <asm/prom.h>
+#include <asm/systemcfg.h>
+
+#define MODULE_VERS "1.6"
+#define MODULE_NAME "lparcfg"
+
+/* #define LPARCFG_DEBUG */
+
+/* find a better place for this function... */
+void log_plpar_hcall_return(unsigned long rc, char *tag)
+{
+	if (rc == 0)		/* success, return */
+		return;
+/* check for null tag ? */
+	if (rc == H_Hardware)
+		printk(KERN_INFO
+		       "plpar-hcall (%s) failed with hardware fault\n", tag);
+	else if (rc == H_Function)
+		printk(KERN_INFO
+		       "plpar-hcall (%s) failed; function not allowed\n", tag);
+	else if (rc == H_Authority)
+		printk(KERN_INFO
+		       "plpar-hcall (%s) failed; not authorized to this function\n",
+		       tag);
+	else if (rc == H_Parameter)
+		printk(KERN_INFO "plpar-hcall (%s) failed; Bad parameter(s)\n",
+		       tag);
+	else
+		printk(KERN_INFO
+		       "plpar-hcall (%s) failed with unexpected rc(0x%lx)\n",
+		       tag, rc);
+
+}
+
+static struct proc_dir_entry *proc_ppc64_lparcfg;
+#define LPARCFG_BUFF_SIZE 4096
+
+#ifdef CONFIG_PPC_ISERIES
+
+/*
+ * For iSeries legacy systems, the PPA purr function is available from the
+ * emulated_time_base field in the paca.
+ */
+static unsigned long get_purr(void)
+{
+	unsigned long sum_purr = 0;
+	int cpu;
+	struct paca_struct *lpaca;
+
+	for_each_cpu(cpu) {
+		lpaca = paca + cpu;
+		sum_purr += lpaca->lppaca.emulated_time_base;
+
+#ifdef PURR_DEBUG
+		printk(KERN_INFO "get_purr for cpu (%d) has value (%ld) \n",
+			cpu, lpaca->lppaca.emulated_time_base);
+#endif
+	}
+	return sum_purr;
+}
+
+#define lparcfg_write NULL
+
+/*
+ * Methods used to fetch LPAR data when running on an iSeries platform.
+ */
+static int lparcfg_data(struct seq_file *m, void *v)
+{
+	unsigned long pool_id, lp_index;
+	int shared, entitled_capacity, max_entitled_capacity;
+	int processors, max_processors;
+	struct paca_struct *lpaca = get_paca();
+	unsigned long purr = get_purr();
+
+	seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS);
+
+	shared = (int)(lpaca->lppaca_ptr->shared_proc);
+	seq_printf(m, "serial_number=%c%c%c%c%c%c%c\n",
+		   e2a(xItExtVpdPanel.mfgID[2]),
+		   e2a(xItExtVpdPanel.mfgID[3]),
+		   e2a(xItExtVpdPanel.systemSerial[1]),
+		   e2a(xItExtVpdPanel.systemSerial[2]),
+		   e2a(xItExtVpdPanel.systemSerial[3]),
+		   e2a(xItExtVpdPanel.systemSerial[4]),
+		   e2a(xItExtVpdPanel.systemSerial[5]));
+
+	seq_printf(m, "system_type=%c%c%c%c\n",
+		   e2a(xItExtVpdPanel.machineType[0]),
+		   e2a(xItExtVpdPanel.machineType[1]),
+		   e2a(xItExtVpdPanel.machineType[2]),
+		   e2a(xItExtVpdPanel.machineType[3]));
+
+	lp_index = HvLpConfig_getLpIndex();
+	seq_printf(m, "partition_id=%d\n", (int)lp_index);
+
+	seq_printf(m, "system_active_processors=%d\n",
+		   (int)HvLpConfig_getSystemPhysicalProcessors());
+
+	seq_printf(m, "system_potential_processors=%d\n",
+		   (int)HvLpConfig_getSystemPhysicalProcessors());
+
+	processors = (int)HvLpConfig_getPhysicalProcessors();
+	seq_printf(m, "partition_active_processors=%d\n", processors);
+
+	max_processors = (int)HvLpConfig_getMaxPhysicalProcessors();
+	seq_printf(m, "partition_potential_processors=%d\n", max_processors);
+
+	if (shared) {
+		entitled_capacity = HvLpConfig_getSharedProcUnits();
+		max_entitled_capacity = HvLpConfig_getMaxSharedProcUnits();
+	} else {
+		entitled_capacity = processors * 100;
+		max_entitled_capacity = max_processors * 100;
+	}
+	seq_printf(m, "partition_entitled_capacity=%d\n", entitled_capacity);
+
+	seq_printf(m, "partition_max_entitled_capacity=%d\n",
+		   max_entitled_capacity);
+
+	if (shared) {
+		pool_id = HvLpConfig_getSharedPoolIndex();
+		seq_printf(m, "pool=%d\n", (int)pool_id);
+		seq_printf(m, "pool_capacity=%d\n",
+			   (int)(HvLpConfig_getNumProcsInSharedPool(pool_id) *
+				 100));
+		seq_printf(m, "purr=%ld\n", purr);
+	}
+
+	seq_printf(m, "shared_processor_mode=%d\n", shared);
+
+	return 0;
+}
+#endif				/* CONFIG_PPC_ISERIES */
+
+#ifdef CONFIG_PPC_PSERIES
+/*
+ * Methods used to fetch LPAR data when running on a pSeries platform.
+ */
+
+/*
+ * H_GET_PPP hcall returns info in 4 parms.
+ *  entitled_capacity,unallocated_capacity,
+ *  aggregation, resource_capability).
+ *
+ *  R4 = Entitled Processor Capacity Percentage.
+ *  R5 = Unallocated Processor Capacity Percentage.
+ *  R6 (AABBCCDDEEFFGGHH).
+ *      XXXX - reserved (0)
+ *          XXXX - reserved (0)
+ *              XXXX - Group Number
+ *                  XXXX - Pool Number.
+ *  R7 (IIJJKKLLMMNNOOPP).
+ *      XX - reserved. (0)
+ *        XX - bit 0-6 reserved (0).   bit 7 is Capped indicator.
+ *          XX - variable processor Capacity Weight
+ *            XX - Unallocated Variable Processor Capacity Weight.
+ *              XXXX - Active processors in Physical Processor Pool.
+ *                  XXXX  - Processors active on platform.
+ */
+static unsigned int h_get_ppp(unsigned long *entitled,
+			      unsigned long *unallocated,
+			      unsigned long *aggregation,
+			      unsigned long *resource)
+{
+	unsigned long rc;
+	rc = plpar_hcall_4out(H_GET_PPP, 0, 0, 0, 0, entitled, unallocated,
+			      aggregation, resource);
+
+	log_plpar_hcall_return(rc, "H_GET_PPP");
+
+	return rc;
+}
+
+static void h_pic(unsigned long *pool_idle_time, unsigned long *num_procs)
+{
+	unsigned long rc;
+	unsigned long dummy;
+	rc = plpar_hcall(H_PIC, 0, 0, 0, 0, pool_idle_time, num_procs, &dummy);
+
+	log_plpar_hcall_return(rc, "H_PIC");
+}
+
+static unsigned long get_purr(void);
+
+/* Track sum of all purrs across all processors. This is used to further */
+/* calculate usage values by different applications                       */
+
+static unsigned long get_purr(void)
+{
+	unsigned long sum_purr = 0;
+	int cpu;
+	struct cpu_usage *cu;
+
+	for_each_cpu(cpu) {
+		cu = &per_cpu(cpu_usage_array, cpu);
+		sum_purr += cu->current_tb;
+	}
+	return sum_purr;
+}
+
+#define SPLPAR_CHARACTERISTICS_TOKEN 20
+#define SPLPAR_MAXLENGTH 1026*(sizeof(char))
+
+/*
+ * parse_system_parameter_string()
+ * Retrieve the potential_processors, max_entitled_capacity and friends
+ * through the get-system-parameter rtas call.  Replace keyword strings as
+ * necessary.
+ */
+static void parse_system_parameter_string(struct seq_file *m)
+{
+	int call_status;
+
+	char *local_buffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
+	if (!local_buffer) {
+		printk(KERN_ERR "%s %s kmalloc failure at line %d \n",
+		       __FILE__, __FUNCTION__, __LINE__);
+		return;
+	}
+
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, SPLPAR_MAXLENGTH);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				SPLPAR_CHARACTERISTICS_TOKEN,
+				__pa(rtas_data_buf));
+	memcpy(local_buffer, rtas_data_buf, SPLPAR_MAXLENGTH);
+	spin_unlock(&rtas_data_buf_lock);
+
+	if (call_status != 0) {
+		printk(KERN_INFO
+		       "%s %s Error calling get-system-parameter (0x%x)\n",
+		       __FILE__, __FUNCTION__, call_status);
+	} else {
+		int splpar_strlen;
+		int idx, w_idx;
+		char *workbuffer = kmalloc(SPLPAR_MAXLENGTH, GFP_KERNEL);
+		if (!workbuffer) {
+			printk(KERN_ERR "%s %s kmalloc failure at line %d \n",
+			       __FILE__, __FUNCTION__, __LINE__);
+			kfree(local_buffer);
+			return;
+		}
+#ifdef LPARCFG_DEBUG
+		printk(KERN_INFO "success calling get-system-parameter \n");
+#endif
+		splpar_strlen = local_buffer[0] * 16 + local_buffer[1];
+		local_buffer += 2;	/* step over strlen value */
+
+		memset(workbuffer, 0, SPLPAR_MAXLENGTH);
+		w_idx = 0;
+		idx = 0;
+		while ((*local_buffer) && (idx < splpar_strlen)) {
+			workbuffer[w_idx++] = local_buffer[idx++];
+			if ((local_buffer[idx] == ',')
+			    || (local_buffer[idx] == '\0')) {
+				workbuffer[w_idx] = '\0';
+				if (w_idx) {
+					/* avoid the empty string */
+					seq_printf(m, "%s\n", workbuffer);
+				}
+				memset(workbuffer, 0, SPLPAR_MAXLENGTH);
+				idx++;	/* skip the comma */
+				w_idx = 0;
+			} else if (local_buffer[idx] == '=') {
+				/* code here to replace workbuffer contents
+				   with different keyword strings */
+				if (0 == strcmp(workbuffer, "MaxEntCap")) {
+					strcpy(workbuffer,
+					       "partition_max_entitled_capacity");
+					w_idx = strlen(workbuffer);
+				}
+				if (0 == strcmp(workbuffer, "MaxPlatProcs")) {
+					strcpy(workbuffer,
+					       "system_potential_processors");
+					w_idx = strlen(workbuffer);
+				}
+			}
+		}
+		kfree(workbuffer);
+		local_buffer -= 2;	/* back up over strlen value */
+	}
+	kfree(local_buffer);
+}
+
+static int lparcfg_count_active_processors(void);
+
+/* Return the number of processors in the system.
+ * This function reads through the device tree and counts
+ * the virtual processors, this does not include threads.
+ */
+static int lparcfg_count_active_processors(void)
+{
+	struct device_node *cpus_dn = NULL;
+	int count = 0;
+
+	while ((cpus_dn = of_find_node_by_type(cpus_dn, "cpu"))) {
+#ifdef LPARCFG_DEBUG
+		printk(KERN_ERR "cpus_dn %p \n", cpus_dn);
+#endif
+		count++;
+	}
+	return count;
+}
+
+static int lparcfg_data(struct seq_file *m, void *v)
+{
+	int partition_potential_processors;
+	int partition_active_processors;
+	struct device_node *rootdn;
+	const char *model = "";
+	const char *system_id = "";
+	unsigned int *lp_index_ptr, lp_index = 0;
+	struct device_node *rtas_node;
+	int *lrdrp;
+
+	rootdn = find_path_device("/");
+	if (rootdn) {
+		model = get_property(rootdn, "model", NULL);
+		system_id = get_property(rootdn, "system-id", NULL);
+		lp_index_ptr = (unsigned int *)
+		    get_property(rootdn, "ibm,partition-no", NULL);
+		if (lp_index_ptr)
+			lp_index = *lp_index_ptr;
+	}
+
+	seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS);
+
+	seq_printf(m, "serial_number=%s\n", system_id);
+
+	seq_printf(m, "system_type=%s\n", model);
+
+	seq_printf(m, "partition_id=%d\n", (int)lp_index);
+
+	rtas_node = find_path_device("/rtas");
+	lrdrp = (int *)get_property(rtas_node, "ibm,lrdr-capacity", NULL);
+
+	if (lrdrp == NULL) {
+		partition_potential_processors = _systemcfg->processorCount;
+	} else {
+		partition_potential_processors = *(lrdrp + 4);
+	}
+
+	partition_active_processors = lparcfg_count_active_processors();
+
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		unsigned long h_entitled, h_unallocated;
+		unsigned long h_aggregation, h_resource;
+		unsigned long pool_idle_time, pool_procs;
+		unsigned long purr;
+
+		h_get_ppp(&h_entitled, &h_unallocated, &h_aggregation,
+			  &h_resource);
+
+		seq_printf(m, "R4=0x%lx\n", h_entitled);
+		seq_printf(m, "R5=0x%lx\n", h_unallocated);
+		seq_printf(m, "R6=0x%lx\n", h_aggregation);
+		seq_printf(m, "R7=0x%lx\n", h_resource);
+
+		purr = get_purr();
+
+		/* this call handles the ibm,get-system-parameter contents */
+		parse_system_parameter_string(m);
+
+		seq_printf(m, "partition_entitled_capacity=%ld\n", h_entitled);
+
+		seq_printf(m, "group=%ld\n", (h_aggregation >> 2 * 8) & 0xffff);
+
+		seq_printf(m, "system_active_processors=%ld\n",
+			   (h_resource >> 0 * 8) & 0xffff);
+
+		/* pool related entries are apropriate for shared configs */
+		if (paca[0].lppaca.shared_proc) {
+
+			h_pic(&pool_idle_time, &pool_procs);
+
+			seq_printf(m, "pool=%ld\n",
+				   (h_aggregation >> 0 * 8) & 0xffff);
+
+			/* report pool_capacity in percentage */
+			seq_printf(m, "pool_capacity=%ld\n",
+				   ((h_resource >> 2 * 8) & 0xffff) * 100);
+
+			seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time);
+
+			seq_printf(m, "pool_num_procs=%ld\n", pool_procs);
+		}
+
+		seq_printf(m, "unallocated_capacity_weight=%ld\n",
+			   (h_resource >> 4 * 8) & 0xFF);
+
+		seq_printf(m, "capacity_weight=%ld\n",
+			   (h_resource >> 5 * 8) & 0xFF);
+
+		seq_printf(m, "capped=%ld\n", (h_resource >> 6 * 8) & 0x01);
+
+		seq_printf(m, "unallocated_capacity=%ld\n", h_unallocated);
+
+		seq_printf(m, "purr=%ld\n", purr);
+
+	} else {		/* non SPLPAR case */
+
+		seq_printf(m, "system_active_processors=%d\n",
+			   partition_potential_processors);
+
+		seq_printf(m, "system_potential_processors=%d\n",
+			   partition_potential_processors);
+
+		seq_printf(m, "partition_max_entitled_capacity=%d\n",
+			   partition_potential_processors * 100);
+
+		seq_printf(m, "partition_entitled_capacity=%d\n",
+			   partition_active_processors * 100);
+	}
+
+	seq_printf(m, "partition_active_processors=%d\n",
+		   partition_active_processors);
+
+	seq_printf(m, "partition_potential_processors=%d\n",
+		   partition_potential_processors);
+
+	seq_printf(m, "shared_processor_mode=%d\n", paca[0].lppaca.shared_proc);
+
+	return 0;
+}
+
+/*
+ * Interface for changing system parameters (variable capacity weight
+ * and entitled capacity).  Format of input is "param_name=value";
+ * anything after value is ignored.  Valid parameters at this time are
+ * "partition_entitled_capacity" and "capacity_weight".  We use
+ * H_SET_PPP to alter parameters.
+ *
+ * This function should be invoked only on systems with
+ * FW_FEATURE_SPLPAR.
+ */
+static ssize_t lparcfg_write(struct file *file, const char __user * buf,
+			     size_t count, loff_t * off)
+{
+	char *kbuf;
+	char *tmp;
+	u64 new_entitled, *new_entitled_ptr = &new_entitled;
+	u8 new_weight, *new_weight_ptr = &new_weight;
+
+	unsigned long current_entitled;	/* parameters for h_get_ppp */
+	unsigned long dummy;
+	unsigned long resource;
+	u8 current_weight;
+
+	ssize_t retval = -ENOMEM;
+
+	kbuf = kmalloc(count, GFP_KERNEL);
+	if (!kbuf)
+		goto out;
+
+	retval = -EFAULT;
+	if (copy_from_user(kbuf, buf, count))
+		goto out;
+
+	retval = -EINVAL;
+	kbuf[count - 1] = '\0';
+	tmp = strchr(kbuf, '=');
+	if (!tmp)
+		goto out;
+
+	*tmp++ = '\0';
+
+	if (!strcmp(kbuf, "partition_entitled_capacity")) {
+		char *endp;
+		*new_entitled_ptr = (u64) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			goto out;
+		new_weight_ptr = &current_weight;
+	} else if (!strcmp(kbuf, "capacity_weight")) {
+		char *endp;
+		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
+		if (endp == tmp)
+			goto out;
+		new_entitled_ptr = &current_entitled;
+	} else
+		goto out;
+
+	/* Get our current parameters */
+	retval = h_get_ppp(&current_entitled, &dummy, &dummy, &resource);
+	if (retval) {
+		retval = -EIO;
+		goto out;
+	}
+
+	current_weight = (resource >> 5 * 8) & 0xFF;
+
+	pr_debug("%s: current_entitled = %lu, current_weight = %lu\n",
+		 __FUNCTION__, current_entitled, current_weight);
+
+	pr_debug("%s: new_entitled = %lu, new_weight = %lu\n",
+		 __FUNCTION__, *new_entitled_ptr, *new_weight_ptr);
+
+	retval = plpar_hcall_norets(H_SET_PPP, *new_entitled_ptr,
+				    *new_weight_ptr);
+
+	if (retval == H_Success || retval == H_Constrained) {
+		retval = count;
+	} else if (retval == H_Busy) {
+		retval = -EBUSY;
+	} else if (retval == H_Hardware) {
+		retval = -EIO;
+	} else if (retval == H_Parameter) {
+		retval = -EINVAL;
+	} else {
+		printk(KERN_WARNING "%s: received unknown hv return code %ld",
+		       __FUNCTION__, retval);
+		retval = -EIO;
+	}
+
+      out:
+	kfree(kbuf);
+	return retval;
+}
+
+#endif				/* CONFIG_PPC_PSERIES */
+
+static int lparcfg_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, lparcfg_data, NULL);
+}
+
+struct file_operations lparcfg_fops = {
+      .owner	= THIS_MODULE,
+      .read	= seq_read,
+      .open	= lparcfg_open,
+      .release	= single_release,
+};
+
+int __init lparcfg_init(void)
+{
+	struct proc_dir_entry *ent;
+	mode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
+
+	/* Allow writing if we have FW_FEATURE_SPLPAR */
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		lparcfg_fops.write = lparcfg_write;
+		mode |= S_IWUSR;
+	}
+
+	ent = create_proc_entry("ppc64/lparcfg", mode, NULL);
+	if (ent) {
+		ent->proc_fops = &lparcfg_fops;
+		ent->data = kmalloc(LPARCFG_BUFF_SIZE, GFP_KERNEL);
+		if (!ent->data) {
+			printk(KERN_ERR
+			       "Failed to allocate buffer for lparcfg\n");
+			remove_proc_entry("lparcfg", ent->parent);
+			return -ENOMEM;
+		}
+	} else {
+		printk(KERN_ERR "Failed to create ppc64/lparcfg\n");
+		return -EIO;
+	}
+
+	proc_ppc64_lparcfg = ent;
+	return 0;
+}
+
+void __exit lparcfg_cleanup(void)
+{
+	if (proc_ppc64_lparcfg) {
+		kfree(proc_ppc64_lparcfg->data);
+		remove_proc_entry("lparcfg", proc_ppc64_lparcfg->parent);
+	}
+}
+
+module_init(lparcfg_init);
+module_exit(lparcfg_cleanup);
+MODULE_DESCRIPTION("Interface for LPAR configuration data");
+MODULE_AUTHOR("Dave Engebretsen");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 3bedb532aed9..f6d84a75ed26 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -519,7 +519,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE)
  *
  * flush_icache_range(unsigned long start, unsigned long stop)
  */
-_GLOBAL(flush_icache_range)
+_GLOBAL(__flush_icache_range)
 BEGIN_FTR_SECTION
 	blr				/* for 601, do nothing */
 END_FTR_SECTION_IFCLR(CPU_FTR_SPLIT_ID_CACHE)
@@ -607,27 +607,6 @@ _GLOBAL(invalidate_dcache_range)
 	sync				/* wait for dcbi's to get to ram */
 	blr
 
-#ifdef CONFIG_NOT_COHERENT_CACHE
-/*
- * 40x cores have 8K or 16K dcache and 32 byte line size.
- * 44x has a 32K dcache and 32 byte line size.
- * 8xx has 1, 2, 4, 8K variants.
- * For now, cover the worst case of the 44x.
- * Must be called with external interrupts disabled.
- */
-#define CACHE_NWAYS	64
-#define CACHE_NLINES	16
-
-_GLOBAL(flush_dcache_all)
-	li	r4, (2 * CACHE_NWAYS * CACHE_NLINES)
-	mtctr	r4
-	lis     r5, KERNELBASE@h
-1:	lwz	r3, 0(r5)		/* Load one word from every line */
-	addi	r5, r5, L1_CACHE_BYTES
-	bdnz    1b
-	blr
-#endif /* CONFIG_NOT_COHERENT_CACHE */
-
 /*
  * Flush a particular page from the data cache to RAM.
  * Note: this is necessary because the instruction cache does *not*
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index ae1433da09b2..ae48a002f81a 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -89,12 +89,12 @@ _GLOBAL(call_do_softirq)
 	mtlr	r0
 	blr
 
-_GLOBAL(call_handle_IRQ_event)
+_GLOBAL(call___do_IRQ)
 	mflr	r0
 	std	r0,16(r1)
-	stdu	r1,THREAD_SIZE-112(r6)
-	mr	r1,r6
-	bl	.handle_IRQ_event
+	stdu	r1,THREAD_SIZE-112(r5)
+	mr	r1,r5
+	bl	.__do_IRQ
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
new file mode 100644
index 000000000000..3cf2517c5f91
--- /dev/null
+++ b/arch/powerpc/kernel/paca.c
@@ -0,0 +1,142 @@
+/*
+ * c 2001 PPC 64 Team, IBM Corp
+ *
+ *      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/types.h>
+#include <linux/threads.h>
+#include <linux/module.h>
+
+#include <asm/processor.h>
+#include <asm/ptrace.h>
+#include <asm/page.h>
+#include <asm/systemcfg.h>
+#include <asm/lppaca.h>
+#include <asm/iseries/it_lp_queue.h>
+#include <asm/paca.h>
+
+static union {
+	struct systemcfg	data;
+	u8			page[PAGE_SIZE];
+} systemcfg_store __attribute__((__section__(".data.page.aligned")));
+struct systemcfg *_systemcfg = &systemcfg_store.data;
+
+
+/* This symbol is provided by the linker - let it fill in the paca
+ * field correctly */
+extern unsigned long __toc_start;
+
+/* The Paca is an array with one entry per processor.  Each contains an
+ * lppaca, which contains the information shared between the
+ * hypervisor and Linux.  Each also contains an ItLpRegSave area which
+ * is used by the hypervisor to save registers.
+ * On systems with hardware multi-threading, there are two threads
+ * per processor.  The Paca array must contain an entry for each thread.
+ * The VPD Areas will give a max logical processors = 2 * max physical
+ * processors.  The processor VPD array needs one entry per physical
+ * processor (not thread).
+ */
+#define PACA_INIT_COMMON(number, start, asrr, asrv)			    \
+	.lock_token = 0x8000,						    \
+	.paca_index = (number),		/* Paca Index */		    \
+	.default_decr = 0x00ff0000,	/* Initial Decr */		    \
+	.kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL,		    \
+	.stab_real = (asrr), 		/* Real pointer to segment table */ \
+	.stab_addr = (asrv),		/* Virt pointer to segment table */ \
+	.cpu_start = (start),		/* Processor start */		    \
+	.hw_cpu_id = 0xffff,						    \
+	.lppaca = {							    \
+		.desc = 0xd397d781,	/* "LpPa" */			    \
+		.size = sizeof(struct lppaca),				    \
+		.dyn_proc_status = 2,					    \
+		.decr_val = 0x00ff0000,					    \
+		.fpregs_in_use = 1,					    \
+		.end_of_quantum = 0xfffffffffffffffful,			    \
+		.slb_count = 64,					    \
+		.vmxregs_in_use = 0,					    \
+	},								    \
+
+#ifdef CONFIG_PPC_ISERIES
+#define PACA_INIT_ISERIES(number)					    \
+	.lppaca_ptr = &paca[number].lppaca,				    \
+	.reg_save_ptr = &paca[number].reg_save,				    \
+	.reg_save = {							    \
+		.xDesc = 0xd397d9e2,	/* "LpRS" */			    \
+		.xSize = sizeof(struct ItLpRegSave)			    \
+	}
+
+#define PACA_INIT(number)						    \
+{									    \
+	PACA_INIT_COMMON(number, 0, 0, 0)				    \
+	PACA_INIT_ISERIES(number)					    \
+}
+
+#define BOOTCPU_PACA_INIT(number)					    \
+{									    \
+	PACA_INIT_COMMON(number, 1, 0, (u64)&initial_stab)		    \
+	PACA_INIT_ISERIES(number)					    \
+}
+
+#else
+#define PACA_INIT(number)						    \
+{									    \
+	PACA_INIT_COMMON(number, 0, 0, 0)				    \
+}
+
+#define BOOTCPU_PACA_INIT(number)					    \
+{									    \
+	PACA_INIT_COMMON(number, 1, STAB0_PHYS_ADDR, (u64)&initial_stab)    \
+}
+#endif
+
+struct paca_struct paca[] = {
+	BOOTCPU_PACA_INIT(0),
+#if NR_CPUS > 1
+	PACA_INIT(  1), PACA_INIT(  2), PACA_INIT(  3),
+#if NR_CPUS > 4
+	PACA_INIT(  4), PACA_INIT(  5), PACA_INIT(  6), PACA_INIT(  7),
+#if NR_CPUS > 8
+	PACA_INIT(  8), PACA_INIT(  9), PACA_INIT( 10), PACA_INIT( 11),
+	PACA_INIT( 12), PACA_INIT( 13), PACA_INIT( 14), PACA_INIT( 15),
+	PACA_INIT( 16), PACA_INIT( 17), PACA_INIT( 18), PACA_INIT( 19),
+	PACA_INIT( 20), PACA_INIT( 21), PACA_INIT( 22), PACA_INIT( 23),
+	PACA_INIT( 24), PACA_INIT( 25), PACA_INIT( 26), PACA_INIT( 27),
+	PACA_INIT( 28), PACA_INIT( 29), PACA_INIT( 30), PACA_INIT( 31),
+#if NR_CPUS > 32
+	PACA_INIT( 32), PACA_INIT( 33), PACA_INIT( 34), PACA_INIT( 35),
+	PACA_INIT( 36), PACA_INIT( 37), PACA_INIT( 38), PACA_INIT( 39),
+	PACA_INIT( 40), PACA_INIT( 41), PACA_INIT( 42), PACA_INIT( 43),
+	PACA_INIT( 44), PACA_INIT( 45), PACA_INIT( 46), PACA_INIT( 47),
+	PACA_INIT( 48), PACA_INIT( 49), PACA_INIT( 50), PACA_INIT( 51),
+	PACA_INIT( 52), PACA_INIT( 53), PACA_INIT( 54), PACA_INIT( 55),
+	PACA_INIT( 56), PACA_INIT( 57), PACA_INIT( 58), PACA_INIT( 59),
+	PACA_INIT( 60), PACA_INIT( 61), PACA_INIT( 62), PACA_INIT( 63),
+#if NR_CPUS > 64
+	PACA_INIT( 64), PACA_INIT( 65), PACA_INIT( 66), PACA_INIT( 67),
+	PACA_INIT( 68), PACA_INIT( 69), PACA_INIT( 70), PACA_INIT( 71),
+	PACA_INIT( 72), PACA_INIT( 73), PACA_INIT( 74), PACA_INIT( 75),
+	PACA_INIT( 76), PACA_INIT( 77), PACA_INIT( 78), PACA_INIT( 79),
+	PACA_INIT( 80), PACA_INIT( 81), PACA_INIT( 82), PACA_INIT( 83),
+	PACA_INIT( 84), PACA_INIT( 85), PACA_INIT( 86), PACA_INIT( 87),
+	PACA_INIT( 88), PACA_INIT( 89), PACA_INIT( 90), PACA_INIT( 91),
+	PACA_INIT( 92), PACA_INIT( 93), PACA_INIT( 94), PACA_INIT( 95),
+	PACA_INIT( 96), PACA_INIT( 97), PACA_INIT( 98), PACA_INIT( 99),
+	PACA_INIT(100), PACA_INIT(101), PACA_INIT(102), PACA_INIT(103),
+	PACA_INIT(104), PACA_INIT(105), PACA_INIT(106), PACA_INIT(107),
+	PACA_INIT(108), PACA_INIT(109), PACA_INIT(110), PACA_INIT(111),
+	PACA_INIT(112), PACA_INIT(113), PACA_INIT(114), PACA_INIT(115),
+	PACA_INIT(116), PACA_INIT(117), PACA_INIT(118), PACA_INIT(119),
+	PACA_INIT(120), PACA_INIT(121), PACA_INIT(122), PACA_INIT(123),
+	PACA_INIT(124), PACA_INIT(125), PACA_INIT(126), PACA_INIT(127),
+#endif
+#endif
+#endif
+#endif
+#endif
+};
+EXPORT_SYMBOL(paca);
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 47d6f7e2ea9f..5dcf4ba05ee8 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -44,6 +44,7 @@
 #include <asm/cputable.h>
 #include <asm/btext.h>
 #include <asm/div64.h>
+#include <asm/signal.h>
 
 #ifdef  CONFIG_8xx
 #include <asm/commproc.h>
@@ -56,7 +57,6 @@ extern void machine_check_exception(struct pt_regs *regs);
 extern void alignment_exception(struct pt_regs *regs);
 extern void program_check_exception(struct pt_regs *regs);
 extern void single_step_exception(struct pt_regs *regs);
-extern int do_signal(sigset_t *, struct pt_regs *);
 extern int pmac_newworld;
 extern int sys_sigreturn(struct pt_regs *regs);
 
@@ -188,9 +188,6 @@ EXPORT_SYMBOL(adb_try_handler_change);
 EXPORT_SYMBOL(cuda_request);
 EXPORT_SYMBOL(cuda_poll);
 #endif /* CONFIG_ADB_CUDA */
-#if defined(CONFIG_PPC_MULTIPLATFORM) && defined(CONFIG_PPC32)
-EXPORT_SYMBOL(_machine);
-#endif
 #ifdef CONFIG_PPC_PMAC
 EXPORT_SYMBOL(sys_ctrler);
 #endif
diff --git a/arch/powerpc/kernel/proc_ppc64.c b/arch/powerpc/kernel/proc_ppc64.c
new file mode 100644
index 000000000000..a1c19502fe8b
--- /dev/null
+++ b/arch/powerpc/kernel/proc_ppc64.c
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen IBM Corporation
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/config.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+
+#include <asm/systemcfg.h>
+#include <asm/rtas.h>
+#include <asm/uaccess.h>
+#include <asm/prom.h>
+
+static loff_t  page_map_seek( struct file *file, loff_t off, int whence);
+static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes,
+			      loff_t *ppos);
+static int     page_map_mmap( struct file *file, struct vm_area_struct *vma );
+
+static struct file_operations page_map_fops = {
+	.llseek	= page_map_seek,
+	.read	= page_map_read,
+	.mmap	= page_map_mmap
+};
+
+/*
+ * Create the ppc64 and ppc64/rtas directories early. This allows us to
+ * assume that they have been previously created in drivers.
+ */
+static int __init proc_ppc64_create(void)
+{
+	struct proc_dir_entry *root;
+
+	root = proc_mkdir("ppc64", NULL);
+	if (!root)
+		return 1;
+
+	if (!(platform_is_pseries() || _machine == PLATFORM_CELL))
+		return 0;
+
+	if (!proc_mkdir("rtas", root))
+		return 1;
+
+	if (!proc_symlink("rtas", NULL, "ppc64/rtas"))
+		return 1;
+
+	return 0;
+}
+core_initcall(proc_ppc64_create);
+
+static int __init proc_ppc64_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = create_proc_entry("ppc64/systemcfg", S_IFREG|S_IRUGO, NULL);
+	if (!pde)
+		return 1;
+	pde->nlink = 1;
+	pde->data = _systemcfg;
+	pde->size = PAGE_SIZE;
+	pde->proc_fops = &page_map_fops;
+
+	return 0;
+}
+__initcall(proc_ppc64_init);
+
+static loff_t page_map_seek( struct file *file, loff_t off, int whence)
+{
+	loff_t new;
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+
+	switch(whence) {
+	case 0:
+		new = off;
+		break;
+	case 1:
+		new = file->f_pos + off;
+		break;
+	case 2:
+		new = dp->size + off;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if ( new < 0 || new > dp->size )
+		return -EINVAL;
+	return (file->f_pos = new);
+}
+
+static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes,
+			      loff_t *ppos)
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+	return simple_read_from_buffer(buf, nbytes, ppos, dp->data, dp->size);
+}
+
+static int page_map_mmap( struct file *file, struct vm_area_struct *vma )
+{
+	struct proc_dir_entry *dp = PDE(file->f_dentry->d_inode);
+
+	vma->vm_flags |= VM_SHM | VM_LOCKED;
+
+	if ((vma->vm_end - vma->vm_start) > dp->size)
+		return -EINVAL;
+
+	remap_pfn_range(vma, vma->vm_start, __pa(dp->data) >> PAGE_SHIFT,
+						dp->size, vma->vm_page_prot);
+	return 0;
+}
+
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f645adb57534..6a5b468edb4d 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -48,9 +48,6 @@
 #include <asm/machdep.h>
 #include <asm/pSeries_reconfig.h>
 #include <asm/pci-bridge.h>
-#ifdef CONFIG_PPC64
-#include <asm/systemcfg.h>
-#endif
 
 #ifdef DEBUG
 #define DBG(fmt...) printk(KERN_ERR fmt)
@@ -74,10 +71,6 @@ struct isa_reg_property {
 typedef int interpret_func(struct device_node *, unsigned long *,
 			   int, int, int);
 
-extern struct rtas_t rtas;
-extern struct lmb lmb;
-extern unsigned long klimit;
-
 static int __initdata dt_root_addr_cells;
 static int __initdata dt_root_size_cells;
 
@@ -391,7 +384,7 @@ static int __devinit finish_node_interrupts(struct device_node *np,
 
 #ifdef CONFIG_PPC64
 		/* We offset irq numbers for the u3 MPIC by 128 in PowerMac */
-		if (systemcfg->platform == PLATFORM_POWERMAC && ic && ic->parent) {
+		if (_machine == PLATFORM_POWERMAC && ic && ic->parent) {
 			char *name = get_property(ic->parent, "name", NULL);
 			if (name && !strcmp(name, "u3"))
 				np->intrs[intrcount].line += 128;
@@ -1087,9 +1080,9 @@ void __init unflatten_device_tree(void)
 static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth, void *data)
 {
-	char *type = of_get_flat_dt_prop(node, "device_type", NULL);
 	u32 *prop;
-	unsigned long size = 0;
+	unsigned long size;
+	char *type = of_get_flat_dt_prop(node, "device_type", &size);
 
 	/* We are scanning "cpu" nodes only */
 	if (type == NULL || strcmp(type, "cpu") != 0)
@@ -1115,7 +1108,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 
 #ifdef CONFIG_ALTIVEC
 	/* Check if we have a VMX and eventually update CPU features */
-	prop = (u32 *)of_get_flat_dt_prop(node, "ibm,vmx", &size);
+	prop = (u32 *)of_get_flat_dt_prop(node, "ibm,vmx", NULL);
 	if (prop && (*prop) > 0) {
 		cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
 		cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
@@ -1161,13 +1154,9 @@ static int __init early_init_dt_scan_chosen(unsigned long node,
 	prop = (u32 *)of_get_flat_dt_prop(node, "linux,platform", NULL);
 	if (prop == NULL)
 		return 0;
-#ifdef CONFIG_PPC64
-	systemcfg->platform = *prop;
-#else
 #ifdef CONFIG_PPC_MULTIPLATFORM
 	_machine = *prop;
 #endif
-#endif
 
 #ifdef CONFIG_PPC64
 	/* check if iommu is forced on or off */
@@ -1264,7 +1253,14 @@ static int __init early_init_dt_scan_memory(unsigned long node,
 	unsigned long l;
 
 	/* We are scanning "memory" nodes only */
-	if (type == NULL || strcmp(type, "memory") != 0)
+	if (type == NULL) {
+		/*
+		 * The longtrail doesn't have a device_type on the
+		 * /memory node, so look for the node called /memory@0.
+		 */
+		if (depth != 1 || strcmp(uname, "memory@0") != 0)
+			return 0;
+	} else if (strcmp(type, "memory") != 0)
 		return 0;
 
 	reg = (cell_t *)of_get_flat_dt_prop(node, "reg", &l);
@@ -1339,9 +1335,6 @@ void __init early_init_devtree(void *params)
 	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
 	lmb_enforce_memory_limit(memory_limit);
 	lmb_analyze();
-#ifdef CONFIG_PPC64
-	systemcfg->physicalMemorySize = lmb_phys_mem_size();
-#endif
 	lmb_reserve(0, __pa(klimit));
 
 	DBG("Phys. mem: %lx\n", lmb_phys_mem_size());
@@ -1908,7 +1901,7 @@ static int of_finish_dynamic_node(struct device_node *node,
 	/* We don't support that function on PowerMac, at least
 	 * not yet
 	 */
-	if (systemcfg->platform == PLATFORM_POWERMAC)
+	if (_machine == PLATFORM_POWERMAC)
 		return -ENODEV;
 
 	/* fix up new node's linux_phandle field */
@@ -1992,9 +1985,11 @@ int prom_add_property(struct device_node* np, struct property* prop)
 	*next = prop;
 	write_unlock(&devtree_lock);
 
+#ifdef CONFIG_PROC_DEVICETREE
 	/* try to add to proc as well if it was initialized */
 	if (np->pde)
 		proc_device_tree_add_prop(np->pde, prop);
+#endif /* CONFIG_PROC_DEVICETREE */
 
 	return 0;
 }
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 6dc33d19fc2a..4ce0105c308e 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -94,11 +94,17 @@ extern const struct linux_logo logo_linux_clut224;
 #ifdef CONFIG_PPC64
 #define RELOC(x)        (*PTRRELOC(&(x)))
 #define ADDR(x)		(u32) add_reloc_offset((unsigned long)(x))
+#define OF_WORKAROUNDS	0
 #else
 #define RELOC(x)	(x)
 #define ADDR(x)		(u32) (x)
+#define OF_WORKAROUNDS	of_workarounds
+int of_workarounds;
 #endif
 
+#define OF_WA_CLAIM	1	/* do phys/virt claim separately, then map */
+#define OF_WA_LONGTRAIL	2	/* work around longtrail bugs */
+
 #define PROM_BUG() do {						\
         prom_printf("kernel BUG at %s line 0x%x!\n",		\
 		    RELOC(__FILE__), __LINE__);			\
@@ -111,11 +117,6 @@ extern const struct linux_logo logo_linux_clut224;
 #define prom_debug(x...)
 #endif
 
-#ifdef CONFIG_PPC32
-#define PLATFORM_POWERMAC	_MACH_Pmac
-#define PLATFORM_CHRP		_MACH_chrp
-#endif
-
 
 typedef u32 prom_arg_t;
 
@@ -128,10 +129,11 @@ struct prom_args {
 
 struct prom_t {
 	ihandle root;
-	ihandle chosen;
+	phandle chosen;
 	int cpu;
 	ihandle stdout;
 	ihandle mmumap;
+	ihandle memory;
 };
 
 struct mem_map_entry {
@@ -360,16 +362,36 @@ static void __init prom_printf(const char *format, ...)
 static unsigned int __init prom_claim(unsigned long virt, unsigned long size,
 				unsigned long align)
 {
-	int ret;
 	struct prom_t *_prom = &RELOC(prom);
 
-	ret = call_prom("claim", 3, 1, (prom_arg_t)virt, (prom_arg_t)size,
-			(prom_arg_t)align);
-	if (ret != -1 && _prom->mmumap != 0)
-		/* old pmacs need us to map as well */
+	if (align == 0 && (OF_WORKAROUNDS & OF_WA_CLAIM)) {
+		/*
+		 * Old OF requires we claim physical and virtual separately
+		 * and then map explicitly (assuming virtual mode)
+		 */
+		int ret;
+		prom_arg_t result;
+
+		ret = call_prom_ret("call-method", 5, 2, &result,
+				    ADDR("claim"), _prom->memory,
+				    align, size, virt);
+		if (ret != 0 || result == -1)
+			return -1;
+		ret = call_prom_ret("call-method", 5, 2, &result,
+				    ADDR("claim"), _prom->mmumap,
+				    align, size, virt);
+		if (ret != 0) {
+			call_prom("call-method", 4, 1, ADDR("release"),
+				  _prom->memory, size, virt);
+			return -1;
+		}
+		/* the 0x12 is M (coherence) + PP == read/write */
 		call_prom("call-method", 6, 1,
-			  ADDR("map"), _prom->mmumap, 0, size, virt, virt);
-	return ret;
+			  ADDR("map"), _prom->mmumap, 0x12, size, virt, virt);
+		return virt;
+	}
+	return call_prom("claim", 3, 1, (prom_arg_t)virt, (prom_arg_t)size,
+			 (prom_arg_t)align);
 }
 
 static void __init __attribute__((noreturn)) prom_panic(const char *reason)
@@ -415,11 +437,52 @@ static int inline prom_getproplen(phandle node, const char *pname)
 	return call_prom("getproplen", 2, 1, node, ADDR(pname));
 }
 
-static int inline prom_setprop(phandle node, const char *pname,
-			       void *value, size_t valuelen)
+static void add_string(char **str, const char *q)
 {
-	return call_prom("setprop", 4, 1, node, ADDR(pname),
-			 (u32)(unsigned long) value, (u32) valuelen);
+	char *p = *str;
+
+	while (*q)
+		*p++ = *q++;
+	*p++ = ' ';
+	*str = p;
+}
+
+static char *tohex(unsigned int x)
+{
+	static char digits[] = "0123456789abcdef";
+	static char result[9];
+	int i;
+
+	result[8] = 0;
+	i = 8;
+	do {
+		--i;
+		result[i] = digits[x & 0xf];
+		x >>= 4;
+	} while (x != 0 && i > 0);
+	return &result[i];
+}
+
+static int __init prom_setprop(phandle node, const char *nodename,
+			       const char *pname, void *value, size_t valuelen)
+{
+	char cmd[256], *p;
+
+	if (!(OF_WORKAROUNDS & OF_WA_LONGTRAIL))
+		return call_prom("setprop", 4, 1, node, ADDR(pname),
+				 (u32)(unsigned long) value, (u32) valuelen);
+
+	/* gah... setprop doesn't work on longtrail, have to use interpret */
+	p = cmd;
+	add_string(&p, "dev");
+	add_string(&p, nodename);
+	add_string(&p, tohex((u32)(unsigned long) value));
+	add_string(&p, tohex(valuelen));
+	add_string(&p, tohex(ADDR(pname)));
+	add_string(&p, tohex(strlen(RELOC(pname))));
+	add_string(&p, "property");
+	*p = 0;
+	return call_prom("interpret", 1, 1, (u32)(unsigned long) cmd);
 }
 
 /* We can't use the standard versions because of RELOC headaches. */
@@ -980,7 +1043,7 @@ static void __init prom_instantiate_rtas(void)
 
 	rtas_inst = call_prom("open", 1, 1, ADDR("/rtas"));
 	if (!IHANDLE_VALID(rtas_inst)) {
-		prom_printf("opening rtas package failed");
+		prom_printf("opening rtas package failed (%x)\n", rtas_inst);
 		return;
 	}
 
@@ -988,7 +1051,7 @@ static void __init prom_instantiate_rtas(void)
 
 	if (call_prom_ret("call-method", 3, 2, &entry,
 			  ADDR("instantiate-rtas"),
-			  rtas_inst, base) == PROM_ERROR
+			  rtas_inst, base) != 0
 	    || entry == 0) {
 		prom_printf(" failed\n");
 		return;
@@ -997,8 +1060,10 @@ static void __init prom_instantiate_rtas(void)
 
 	reserve_mem(base, size);
 
-	prom_setprop(rtas_node, "linux,rtas-base", &base, sizeof(base));
-	prom_setprop(rtas_node, "linux,rtas-entry", &entry, sizeof(entry));
+	prom_setprop(rtas_node, "/rtas", "linux,rtas-base",
+		     &base, sizeof(base));
+	prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
+		     &entry, sizeof(entry));
 
 	prom_debug("rtas base     = 0x%x\n", base);
 	prom_debug("rtas entry    = 0x%x\n", entry);
@@ -1089,10 +1154,6 @@ static void __init prom_initialize_tce_table(void)
 		if (base < local_alloc_bottom)
 			local_alloc_bottom = base;
 
-		/* Save away the TCE table attributes for later use. */
-		prom_setprop(node, "linux,tce-base", &base, sizeof(base));
-		prom_setprop(node, "linux,tce-size", &minsize, sizeof(minsize));
-
 		/* It seems OF doesn't null-terminate the path :-( */
 		memset(path, 0, sizeof(path));
 		/* Call OF to setup the TCE hardware */
@@ -1101,6 +1162,10 @@ static void __init prom_initialize_tce_table(void)
 			prom_printf("package-to-path failed\n");
 		}
 
+		/* Save away the TCE table attributes for later use. */
+		prom_setprop(node, path, "linux,tce-base", &base, sizeof(base));
+		prom_setprop(node, path, "linux,tce-size", &minsize, sizeof(minsize));
+
 		prom_debug("TCE table: %s\n", path);
 		prom_debug("\tnode = 0x%x\n", node);
 		prom_debug("\tbase = 0x%x\n", base);
@@ -1342,6 +1407,7 @@ static void __init prom_init_client_services(unsigned long pp)
 /*
  * For really old powermacs, we need to map things we claim.
  * For that, we need the ihandle of the mmu.
+ * Also, on the longtrail, we need to work around other bugs.
  */
 static void __init prom_find_mmu(void)
 {
@@ -1355,12 +1421,19 @@ static void __init prom_find_mmu(void)
 	if (prom_getprop(oprom, "model", version, sizeof(version)) <= 0)
 		return;
 	version[sizeof(version) - 1] = 0;
-	prom_printf("OF version is '%s'\n", version);
 	/* XXX might need to add other versions here */
-	if (strcmp(version, "Open Firmware, 1.0.5") != 0)
+	if (strcmp(version, "Open Firmware, 1.0.5") == 0)
+		of_workarounds = OF_WA_CLAIM;
+	else if (strncmp(version, "FirmWorks,3.", 12) == 0) {
+		of_workarounds = OF_WA_CLAIM | OF_WA_LONGTRAIL;
+		call_prom("interpret", 1, 1, "dev /memory 0 to allow-reclaim");
+	} else
 		return;
+	_prom->memory = call_prom("open", 1, 1, ADDR("/memory"));
 	prom_getprop(_prom->chosen, "mmu", &_prom->mmumap,
 		     sizeof(_prom->mmumap));
+	if (!IHANDLE_VALID(_prom->memory) || !IHANDLE_VALID(_prom->mmumap))
+		of_workarounds &= ~OF_WA_CLAIM;		/* hmmm */
 }
 #else
 #define prom_find_mmu()
@@ -1382,16 +1455,17 @@ static void __init prom_init_stdout(void)
 	memset(path, 0, 256);
 	call_prom("instance-to-path", 3, 1, _prom->stdout, path, 255);
 	val = call_prom("instance-to-package", 1, 1, _prom->stdout);
-	prom_setprop(_prom->chosen, "linux,stdout-package", &val, sizeof(val));
+	prom_setprop(_prom->chosen, "/chosen", "linux,stdout-package",
+		     &val, sizeof(val));
 	prom_printf("OF stdout device is: %s\n", RELOC(of_stdout_device));
-	prom_setprop(_prom->chosen, "linux,stdout-path",
-		     RELOC(of_stdout_device), strlen(RELOC(of_stdout_device))+1);
+	prom_setprop(_prom->chosen, "/chosen", "linux,stdout-path",
+		     path, strlen(path) + 1);
 
 	/* If it's a display, note it */
 	memset(type, 0, sizeof(type));
 	prom_getprop(val, "device_type", type, sizeof(type));
 	if (strcmp(type, RELOC("display")) == 0)
-		prom_setprop(val, "linux,boot-display", NULL, 0);
+		prom_setprop(val, path, "linux,boot-display", NULL, 0);
 }
 
 static void __init prom_close_stdin(void)
@@ -1514,7 +1588,7 @@ static void __init prom_check_displays(void)
 
 		/* Success */
 		prom_printf("done\n");
-		prom_setprop(node, "linux,opened", NULL, 0);
+		prom_setprop(node, path, "linux,opened", NULL, 0);
 
 		/* Setup a usable color table when the appropriate
 		 * method is available. Should update this to set-colors */
@@ -1884,9 +1958,11 @@ static void __init fixup_device_tree(void)
 	/* interrupt on this revision of u3 is number 0 and level */
 	interrupts[0] = 0;
 	interrupts[1] = 1;
-	prom_setprop(i2c, "interrupts", &interrupts, sizeof(interrupts));
+	prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupts",
+		     &interrupts, sizeof(interrupts));
 	parent = (u32)mpic;
-	prom_setprop(i2c, "interrupt-parent", &parent, sizeof(parent));
+	prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupt-parent",
+		     &parent, sizeof(parent));
 #endif
 }
 
@@ -1922,11 +1998,11 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
 		RELOC(prom_initrd_end) = RELOC(prom_initrd_start) + r4;
 
 		val = RELOC(prom_initrd_start);
-		prom_setprop(_prom->chosen, "linux,initrd-start", &val,
-			     sizeof(val));
+		prom_setprop(_prom->chosen, "/chosen", "linux,initrd-start",
+			     &val, sizeof(val));
 		val = RELOC(prom_initrd_end);
-		prom_setprop(_prom->chosen, "linux,initrd-end", &val,
-			     sizeof(val));
+		prom_setprop(_prom->chosen, "/chosen", "linux,initrd-end",
+			     &val, sizeof(val));
 
 		reserve_mem(RELOC(prom_initrd_start),
 			    RELOC(prom_initrd_end) - RELOC(prom_initrd_start));
@@ -1969,14 +2045,15 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	prom_init_client_services(pp);
 
 	/*
-	 * Init prom stdout device
+	 * See if this OF is old enough that we need to do explicit maps
+	 * and other workarounds
 	 */
-	prom_init_stdout();
+	prom_find_mmu();
 
 	/*
-	 * See if this OF is old enough that we need to do explicit maps
+	 * Init prom stdout device
 	 */
-	prom_find_mmu();
+	prom_init_stdout();
 
 	/*
 	 * Check for an initrd
@@ -1989,14 +2066,15 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	RELOC(of_platform) = prom_find_machine_type();
 	getprop_rval = RELOC(of_platform);
-	prom_setprop(_prom->chosen, "linux,platform",
+	prom_setprop(_prom->chosen, "/chosen", "linux,platform",
 		     &getprop_rval, sizeof(getprop_rval));
 
 #ifdef CONFIG_PPC_PSERIES
 	/*
 	 * On pSeries, inform the firmware about our capabilities
 	 */
-	if (RELOC(of_platform) & PLATFORM_PSERIES)
+	if (RELOC(of_platform) == PLATFORM_PSERIES ||
+	    RELOC(of_platform) == PLATFORM_PSERIES_LPAR)
 		prom_send_capabilities();
 #endif
 
@@ -2050,21 +2128,23 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * Fill in some infos for use by the kernel later on
 	 */
 	if (RELOC(prom_memory_limit))
-		prom_setprop(_prom->chosen, "linux,memory-limit",
+		prom_setprop(_prom->chosen, "/chosen", "linux,memory-limit",
 			     &RELOC(prom_memory_limit),
 			     sizeof(prom_memory_limit));
 #ifdef CONFIG_PPC64
 	if (RELOC(ppc64_iommu_off))
-		prom_setprop(_prom->chosen, "linux,iommu-off", NULL, 0);
+		prom_setprop(_prom->chosen, "/chosen", "linux,iommu-off",
+			     NULL, 0);
 
 	if (RELOC(iommu_force_on))
-		prom_setprop(_prom->chosen, "linux,iommu-force-on", NULL, 0);
+		prom_setprop(_prom->chosen, "/chosen", "linux,iommu-force-on",
+			     NULL, 0);
 
 	if (RELOC(prom_tce_alloc_start)) {
-		prom_setprop(_prom->chosen, "linux,tce-alloc-start",
+		prom_setprop(_prom->chosen, "/chosen", "linux,tce-alloc-start",
 			     &RELOC(prom_tce_alloc_start),
 			     sizeof(prom_tce_alloc_start));
-		prom_setprop(_prom->chosen, "linux,tce-alloc-end",
+		prom_setprop(_prom->chosen, "/chosen", "linux,tce-alloc-end",
 			     &RELOC(prom_tce_alloc_end),
 			     sizeof(prom_tce_alloc_end));
 	}
@@ -2081,8 +2161,13 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	prom_printf("copying OF device tree ...\n");
 	flatten_device_tree();
 
-	/* in case stdin is USB and still active on IBM machines... */
-	prom_close_stdin();
+	/*
+	 * in case stdin is USB and still active on IBM machines...
+	 * Unfortunately quiesce crashes on some powermacs if we have
+	 * closed stdin already (in particular the powerbook 101).
+	 */
+	if (RELOC(of_platform) != PLATFORM_POWERMAC)
+		prom_close_stdin();
 
 	/*
 	 * Call OF "quiesce" method to shut down pending DMA's from
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 5bdd5b079d96..ae1a36449ccd 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -259,7 +259,7 @@ static int __init proc_rtas_init(void)
 {
 	struct proc_dir_entry *entry;
 
-	if (!(systemcfg->platform & PLATFORM_PSERIES))
+	if (_machine != PLATFORM_PSERIES && _machine != PLATFORM_PSERIES_LPAR)
 		return 1;
 
 	rtas_node = of_find_node_by_name(NULL, "rtas");
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 9d4e07f6f1ec..4283fa33f784 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -29,9 +29,6 @@
 #include <asm/delay.h>
 #include <asm/uaccess.h>
 #include <asm/lmb.h>
-#ifdef CONFIG_PPC64
-#include <asm/systemcfg.h>
-#endif
 
 struct rtas_t rtas = {
 	.lock = SPIN_LOCK_UNLOCKED
@@ -671,7 +668,7 @@ void __init rtas_initialize(void)
 	 * the stop-self token if any
 	 */
 #ifdef CONFIG_PPC64
-	if (systemcfg->platform == PLATFORM_PSERIES_LPAR)
+	if (_machine == PLATFORM_PSERIES_LPAR)
 		rtas_region = min(lmb.rmo_size, RTAS_INSTANTIATE_MAX);
 #endif
 	rtas_rmo_buf = lmb_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region);
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
new file mode 100644
index 000000000000..0e5a8e116653
--- /dev/null
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -0,0 +1,513 @@
+/*
+ * arch/ppc64/kernel/rtas_pci.c
+ *
+ * Copyright (C) 2001 Dave Engebretsen, IBM Corporation
+ * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * RTAS specific routines for PCI.
+ *
+ * Based on code from pci.c, chrp_pci.c and pSeries_pci.c
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/threads.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+
+#include <asm/io.h>
+#include <asm/pgtable.h>
+#include <asm/irq.h>
+#include <asm/prom.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <asm/iommu.h>
+#include <asm/rtas.h>
+#include <asm/mpic.h>
+#include <asm/ppc-pci.h>
+
+/* RTAS tokens */
+static int read_pci_config;
+static int write_pci_config;
+static int ibm_read_pci_config;
+static int ibm_write_pci_config;
+
+static inline int config_access_valid(struct pci_dn *dn, int where)
+{
+	if (where < 256)
+		return 1;
+	if (where < 4096 && dn->pci_ext_config_space)
+		return 1;
+
+	return 0;
+}
+
+static int of_device_available(struct device_node * dn)
+{
+        char * status;
+
+        status = get_property(dn, "status", NULL);
+
+        if (!status)
+                return 1;
+
+        if (!strcmp(status, "okay"))
+                return 1;
+
+        return 0;
+}
+
+static int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+{
+	int returnval = -1;
+	unsigned long buid, addr;
+	int ret;
+
+	if (!pdn)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (!config_access_valid(pdn, where))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	addr = ((where & 0xf00) << 20) | (pdn->busno << 16) |
+		(pdn->devfn << 8) | (where & 0xff);
+	buid = pdn->phb->buid;
+	if (buid) {
+		ret = rtas_call(ibm_read_pci_config, 4, 2, &returnval,
+				addr, BUID_HI(buid), BUID_LO(buid), size);
+	} else {
+		ret = rtas_call(read_pci_config, 2, 2, &returnval, addr, size);
+	}
+	*val = returnval;
+
+	if (ret)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (returnval == EEH_IO_ERROR_VALUE(size) &&
+	    eeh_dn_check_failure (pdn->node, NULL))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int rtas_pci_read_config(struct pci_bus *bus,
+				unsigned int devfn,
+				int where, int size, u32 *val)
+{
+	struct device_node *busdn, *dn;
+
+	if (bus->self)
+		busdn = pci_device_to_OF_node(bus->self);
+	else
+		busdn = bus->sysdata;	/* must be a phb */
+
+	/* Search only direct children of the bus */
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		struct pci_dn *pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn
+		    && of_device_available(dn))
+			return rtas_read_config(pdn, where, size, val);
+	}
+
+	return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
+int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
+{
+	unsigned long buid, addr;
+	int ret;
+
+	if (!pdn)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	if (!config_access_valid(pdn, where))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	addr = ((where & 0xf00) << 20) | (pdn->busno << 16) |
+		(pdn->devfn << 8) | (where & 0xff);
+	buid = pdn->phb->buid;
+	if (buid) {
+		ret = rtas_call(ibm_write_pci_config, 5, 1, NULL, addr,
+			BUID_HI(buid), BUID_LO(buid), size, (ulong) val);
+	} else {
+		ret = rtas_call(write_pci_config, 3, 1, NULL, addr, size, (ulong)val);
+	}
+
+	if (ret)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int rtas_pci_write_config(struct pci_bus *bus,
+				 unsigned int devfn,
+				 int where, int size, u32 val)
+{
+	struct device_node *busdn, *dn;
+
+	if (bus->self)
+		busdn = pci_device_to_OF_node(bus->self);
+	else
+		busdn = bus->sysdata;	/* must be a phb */
+
+	/* Search only direct children of the bus */
+	for (dn = busdn->child; dn; dn = dn->sibling) {
+		struct pci_dn *pdn = PCI_DN(dn);
+		if (pdn && pdn->devfn == devfn
+		    && of_device_available(dn))
+			return rtas_write_config(pdn, where, size, val);
+	}
+	return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
+struct pci_ops rtas_pci_ops = {
+	rtas_pci_read_config,
+	rtas_pci_write_config
+};
+
+int is_python(struct device_node *dev)
+{
+	char *model = (char *)get_property(dev, "model", NULL);
+
+	if (model && strstr(model, "Python"))
+		return 1;
+
+	return 0;
+}
+
+static int get_phb_reg_prop(struct device_node *dev,
+			    unsigned int addr_size_words,
+			    struct reg_property64 *reg)
+{
+	unsigned int *ui_ptr = NULL, len;
+
+	/* Found a PHB, now figure out where his registers are mapped. */
+	ui_ptr = (unsigned int *)get_property(dev, "reg", &len);
+	if (ui_ptr == NULL)
+		return 1;
+
+	if (addr_size_words == 1) {
+		reg->address = ((struct reg_property32 *)ui_ptr)->address;
+		reg->size    = ((struct reg_property32 *)ui_ptr)->size;
+	} else {
+		*reg = *((struct reg_property64 *)ui_ptr);
+	}
+
+	return 0;
+}
+
+static void python_countermeasures(struct device_node *dev,
+				   unsigned int addr_size_words)
+{
+	struct reg_property64 reg_struct;
+	void __iomem *chip_regs;
+	volatile u32 val;
+
+	if (get_phb_reg_prop(dev, addr_size_words, &reg_struct))
+		return;
+
+	/* Python's register file is 1 MB in size. */
+	chip_regs = ioremap(reg_struct.address & ~(0xfffffUL), 0x100000);
+
+	/*
+	 * Firmware doesn't always clear this bit which is critical
+	 * for good performance - Anton
+	 */
+
+#define PRG_CL_RESET_VALID 0x00010000
+
+	val = in_be32(chip_regs + 0xf6030);
+	if (val & PRG_CL_RESET_VALID) {
+		printk(KERN_INFO "Python workaround: ");
+		val &= ~PRG_CL_RESET_VALID;
+		out_be32(chip_regs + 0xf6030, val);
+		/*
+		 * We must read it back for changes to
+		 * take effect
+		 */
+		val = in_be32(chip_regs + 0xf6030);
+		printk("reg0: %x\n", val);
+	}
+
+	iounmap(chip_regs);
+}
+
+void __init init_pci_config_tokens (void)
+{
+	read_pci_config = rtas_token("read-pci-config");
+	write_pci_config = rtas_token("write-pci-config");
+	ibm_read_pci_config = rtas_token("ibm,read-pci-config");
+	ibm_write_pci_config = rtas_token("ibm,write-pci-config");
+}
+
+unsigned long __devinit get_phb_buid (struct device_node *phb)
+{
+	int addr_cells;
+	unsigned int *buid_vals;
+	unsigned int len;
+	unsigned long buid;
+
+	if (ibm_read_pci_config == -1) return 0;
+
+	/* PHB's will always be children of the root node,
+	 * or so it is promised by the current firmware. */
+	if (phb->parent == NULL)
+		return 0;
+	if (phb->parent->parent)
+		return 0;
+
+	buid_vals = (unsigned int *) get_property(phb, "reg", &len);
+	if (buid_vals == NULL)
+		return 0;
+
+	addr_cells = prom_n_addr_cells(phb);
+	if (addr_cells == 1) {
+		buid = (unsigned long) buid_vals[0];
+	} else {
+		buid = (((unsigned long)buid_vals[0]) << 32UL) |
+			(((unsigned long)buid_vals[1]) & 0xffffffff);
+	}
+	return buid;
+}
+
+static int phb_set_bus_ranges(struct device_node *dev,
+			      struct pci_controller *phb)
+{
+	int *bus_range;
+	unsigned int len;
+
+	bus_range = (int *) get_property(dev, "bus-range", &len);
+	if (bus_range == NULL || len < 2 * sizeof(int)) {
+		return 1;
+ 	}
+
+	phb->first_busno =  bus_range[0];
+	phb->last_busno  =  bus_range[1];
+
+	return 0;
+}
+
+static int __devinit setup_phb(struct device_node *dev,
+			       struct pci_controller *phb,
+			       unsigned int addr_size_words)
+{
+	pci_setup_pci_controller(phb);
+
+	if (is_python(dev))
+		python_countermeasures(dev, addr_size_words);
+
+	if (phb_set_bus_ranges(dev, phb))
+		return 1;
+
+	phb->arch_data = dev;
+	phb->ops = &rtas_pci_ops;
+	phb->buid = get_phb_buid(dev);
+
+	return 0;
+}
+
+static void __devinit add_linux_pci_domain(struct device_node *dev,
+					   struct pci_controller *phb,
+					   struct property *of_prop)
+{
+	memset(of_prop, 0, sizeof(struct property));
+	of_prop->name = "linux,pci-domain";
+	of_prop->length = sizeof(phb->global_number);
+	of_prop->value = (unsigned char *)&of_prop[1];
+	memcpy(of_prop->value, &phb->global_number, sizeof(phb->global_number));
+	prom_add_property(dev, of_prop);
+}
+
+static struct pci_controller * __init alloc_phb(struct device_node *dev,
+						unsigned int addr_size_words)
+{
+	struct pci_controller *phb;
+	struct property *of_prop;
+
+	phb = alloc_bootmem(sizeof(struct pci_controller));
+	if (phb == NULL)
+		return NULL;
+
+	of_prop = alloc_bootmem(sizeof(struct property) +
+				sizeof(phb->global_number));
+	if (!of_prop)
+		return NULL;
+
+	if (setup_phb(dev, phb, addr_size_words))
+		return NULL;
+
+	add_linux_pci_domain(dev, phb, of_prop);
+
+	return phb;
+}
+
+static struct pci_controller * __devinit alloc_phb_dynamic(struct device_node *dev, unsigned int addr_size_words)
+{
+	struct pci_controller *phb;
+
+	phb = (struct pci_controller *)kmalloc(sizeof(struct pci_controller),
+					       GFP_KERNEL);
+	if (phb == NULL)
+		return NULL;
+
+	if (setup_phb(dev, phb, addr_size_words))
+		return NULL;
+
+	phb->is_dynamic = 1;
+
+	/* TODO: linux,pci-domain? */
+
+ 	return phb;
+}
+
+unsigned long __init find_and_init_phbs(void)
+{
+	struct device_node *node;
+	struct pci_controller *phb;
+	unsigned int root_size_cells = 0;
+	unsigned int index;
+	unsigned int *opprop = NULL;
+	struct device_node *root = of_find_node_by_path("/");
+
+	if (ppc64_interrupt_controller == IC_OPEN_PIC) {
+		opprop = (unsigned int *)get_property(root,
+				"platform-open-pic", NULL);
+	}
+
+	root_size_cells = prom_n_size_cells(root);
+
+	index = 0;
+
+	for (node = of_get_next_child(root, NULL);
+	     node != NULL;
+	     node = of_get_next_child(root, node)) {
+		if (node->type == NULL || strcmp(node->type, "pci") != 0)
+			continue;
+
+		phb = alloc_phb(node, root_size_cells);
+		if (!phb)
+			continue;
+
+		pci_process_bridge_OF_ranges(phb, node, 0);
+		pci_setup_phb_io(phb, index == 0);
+#ifdef CONFIG_PPC_PSERIES
+		if (ppc64_interrupt_controller == IC_OPEN_PIC && pSeries_mpic) {
+			int addr = root_size_cells * (index + 2) - 1;
+			mpic_assign_isu(pSeries_mpic, index, opprop[addr]);
+		}
+#endif
+		index++;
+	}
+
+	of_node_put(root);
+	pci_devs_phb_init();
+
+	/*
+	 * pci_probe_only and pci_assign_all_buses can be set via properties
+	 * in chosen.
+	 */
+	if (of_chosen) {
+		int *prop;
+
+		prop = (int *)get_property(of_chosen, "linux,pci-probe-only",
+					   NULL);
+		if (prop)
+			pci_probe_only = *prop;
+
+		prop = (int *)get_property(of_chosen,
+					   "linux,pci-assign-all-buses", NULL);
+		if (prop)
+			pci_assign_all_buses = *prop;
+	}
+
+	return 0;
+}
+
+struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
+{
+	struct device_node *root = of_find_node_by_path("/");
+	unsigned int root_size_cells = 0;
+	struct pci_controller *phb;
+	int primary;
+
+	root_size_cells = prom_n_size_cells(root);
+
+	primary = list_empty(&hose_list);
+	phb = alloc_phb_dynamic(dn, root_size_cells);
+	if (!phb)
+		return NULL;
+
+	pci_process_bridge_OF_ranges(phb, dn, primary);
+
+	pci_setup_phb_io_dynamic(phb, primary);
+	of_node_put(root);
+
+	pci_devs_phb_init_dynamic(phb);
+	scan_phb(phb);
+
+	return phb;
+}
+EXPORT_SYMBOL(init_phb_dynamic);
+
+/* RPA-specific bits for removing PHBs */
+int pcibios_remove_root_bus(struct pci_controller *phb)
+{
+	struct pci_bus *b = phb->bus;
+	struct resource *res;
+	int rc, i;
+
+	res = b->resource[0];
+	if (!res->flags) {
+		printk(KERN_ERR "%s: no IO resource for PHB %s\n", __FUNCTION__,
+				b->name);
+		return 1;
+	}
+
+	rc = unmap_bus_range(b);
+	if (rc) {
+		printk(KERN_ERR "%s: failed to unmap IO on bus %s\n",
+			__FUNCTION__, b->name);
+		return 1;
+	}
+
+	if (release_resource(res)) {
+		printk(KERN_ERR "%s: failed to release IO on bus %s\n",
+				__FUNCTION__, b->name);
+		return 1;
+	}
+
+	for (i = 1; i < 3; ++i) {
+		res = b->resource[i];
+		if (!res->flags && i == 0) {
+			printk(KERN_ERR "%s: no MEM resource for PHB %s\n",
+				__FUNCTION__, b->name);
+			return 1;
+		}
+		if (res->flags && release_resource(res)) {
+			printk(KERN_ERR
+			       "%s: failed to release IO %d on bus %s\n",
+				__FUNCTION__, i, b->name);
+			return 1;
+		}
+	}
+
+	list_del(&phb->list_node);
+	if (phb->is_dynamic)
+		kfree(phb);
+
+	return 0;
+}
+EXPORT_SYMBOL(pcibios_remove_root_bus);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index e22856ecb5a0..bae4bff138f1 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -33,6 +33,7 @@
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/processor.h>
+#include <asm/systemcfg.h>
 #include <asm/pgtable.h>
 #include <asm/smp.h>
 #include <asm/elf.h>
@@ -51,6 +52,9 @@
 #include <asm/page.h>
 #include <asm/mmu.h>
 #include <asm/lmb.h>
+#include <asm/xmon.h>
+
+#include "setup.h"
 
 #undef DEBUG
 
@@ -60,6 +64,13 @@
 #define DBG(fmt...)
 #endif
 
+#ifdef CONFIG_PPC_MULTIPLATFORM
+int _machine = 0;
+EXPORT_SYMBOL(_machine);
+#endif
+
+unsigned long klimit = (unsigned long) _end;
+
 /*
  * This still seems to be needed... -- paulus
  */ 
@@ -510,8 +521,8 @@ void __init smp_setup_cpu_maps(void)
 	 * On pSeries LPAR, we need to know how many cpus
 	 * could possibly be added to this partition.
 	 */
-	if (systemcfg->platform == PLATFORM_PSERIES_LPAR &&
-				(dn = of_find_node_by_path("/rtas"))) {
+	if (_machine == PLATFORM_PSERIES_LPAR &&
+	    (dn = of_find_node_by_path("/rtas"))) {
 		int num_addr_cell, num_size_cell, maxcpus;
 		unsigned int *ireg;
 
@@ -555,7 +566,27 @@ void __init smp_setup_cpu_maps(void)
 			cpu_set(cpu ^ 0x1, cpu_sibling_map[cpu]);
 	}
 
-	systemcfg->processorCount = num_present_cpus();
+	_systemcfg->processorCount = num_present_cpus();
 #endif /* CONFIG_PPC64 */
 }
 #endif /* CONFIG_SMP */
+
+#ifdef CONFIG_XMON
+static int __init early_xmon(char *p)
+{
+	/* ensure xmon is enabled */
+	if (p) {
+		if (strncmp(p, "on", 2) == 0)
+			xmon_init(1);
+		if (strncmp(p, "off", 3) == 0)
+			xmon_init(0);
+		if (strncmp(p, "early", 5) != 0)
+			return 0;
+	}
+	xmon_init(1);
+	debugger(NULL);
+
+	return 0;
+}
+early_param("xmon", early_xmon);
+#endif
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
new file mode 100644
index 000000000000..2ebba755272e
--- /dev/null
+++ b/arch/powerpc/kernel/setup.h
@@ -0,0 +1,6 @@
+#ifndef _POWERPC_KERNEL_SETUP_H
+#define _POWERPC_KERNEL_SETUP_H
+
+void check_for_initrd(void);
+
+#endif /* _POWERPC_KERNEL_SETUP_H */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 3af2631e3fab..c98cfcc9cd9a 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -40,6 +40,8 @@
 #include <asm/xmon.h>
 #include <asm/time.h>
 
+#include "setup.h"
+
 #define DBG(fmt...)
 
 #if defined CONFIG_KGDB
@@ -70,8 +72,6 @@ unsigned int DMA_MODE_WRITE;
 int have_of = 1;
 
 #ifdef CONFIG_PPC_MULTIPLATFORM
-int _machine = 0;
-
 extern void prep_init(void);
 extern void pmac_init(void);
 extern void chrp_init(void);
@@ -279,7 +279,6 @@ arch_initcall(ppc_init);
 /* Warning, IO base is not yet inited */
 void __init setup_arch(char **cmdline_p)
 {
-	extern char *klimit;
 	extern void do_init_bootmem(void);
 
 	/* so udelay does something sensible, assume <= 1000 bogomips */
@@ -303,14 +302,9 @@ void __init setup_arch(char **cmdline_p)
 		pmac_feature_init();	/* New cool way */
 #endif
 
-#ifdef CONFIG_XMON
-	xmon_map_scc();
-	if (strstr(cmd_line, "xmon")) {
-		xmon_init(1);
-		debugger(NULL);
-	}
-#endif /* CONFIG_XMON */
-	if ( ppc_md.progress ) ppc_md.progress("setup_arch: enter", 0x3eab);
+#ifdef CONFIG_XMON_DEFAULT
+	xmon_init(1);
+#endif
 
 #if defined(CONFIG_KGDB)
 	if (ppc_md.kgdb_map_scc)
@@ -343,7 +337,7 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.start_code = PAGE_OFFSET;
 	init_mm.end_code = (unsigned long) _etext;
 	init_mm.end_data = (unsigned long) _edata;
-	init_mm.brk = (unsigned long) klimit;
+	init_mm.brk = klimit;
 
 	/* Save unparsed command line copy for /proc/cmdline */
 	strlcpy(saved_command_line, cmd_line, COMMAND_LINE_SIZE);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 0471e843b6c5..6791668213e7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -61,6 +61,8 @@
 #include <asm/xmon.h>
 #include <asm/udbg.h>
 
+#include "setup.h"
+
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
 #else
@@ -94,15 +96,6 @@ extern void udbg_init_maple_realmode(void);
 	do { udbg_putc = call_rtas_display_status_delay; } while(0)
 #endif
 
-/* extern void *stab; */
-extern unsigned long klimit;
-
-extern void mm_init_ppc64(void);
-extern void stab_initialize(unsigned long stab);
-extern void htab_initialize(void);
-extern void early_init_devtree(void *flat_dt);
-extern void unflatten_device_tree(void);
-
 int have_of = 1;
 int boot_cpuid = 0;
 int boot_cpuid_phys = 0;
@@ -254,11 +247,10 @@ void __init early_setup(unsigned long dt_ptr)
 	 * Iterate all ppc_md structures until we find the proper
 	 * one for the current machine type
 	 */
-	DBG("Probing machine type for platform %x...\n",
-	    systemcfg->platform);
+	DBG("Probing machine type for platform %x...\n", _machine);
 
 	for (mach = machines; *mach; mach++) {
-		if ((*mach)->probe(systemcfg->platform))
+		if ((*mach)->probe(_machine))
 			break;
 	}
 	/* What can we do if we didn't find ? */
@@ -290,6 +282,28 @@ void __init early_setup(unsigned long dt_ptr)
 	DBG(" <- early_setup()\n");
 }
 
+#ifdef CONFIG_SMP
+void early_setup_secondary(void)
+{
+	struct paca_struct *lpaca = get_paca();
+
+	/* Mark enabled in PACA */
+	lpaca->proc_enabled = 0;
+
+	/* Initialize hash table for that CPU */
+	htab_initialize_secondary();
+
+	/* Initialize STAB/SLB. We use a virtual address as it works
+	 * in real mode on pSeries and we want a virutal address on
+	 * iSeries anyway
+	 */
+	if (cpu_has_feature(CPU_FTR_SLB))
+		slb_initialize();
+	else
+		stab_initialize(lpaca->stab_addr);
+}
+
+#endif /* CONFIG_SMP */
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
 void smp_release_cpus(void)
@@ -315,7 +329,8 @@ void smp_release_cpus(void)
 #endif /* CONFIG_SMP || CONFIG_KEXEC */
 
 /*
- * Initialize some remaining members of the ppc64_caches and systemcfg structures
+ * Initialize some remaining members of the ppc64_caches and systemcfg
+ * structures
  * (at least until we get rid of them completely). This is mostly some
  * cache informations about the CPU that will be used by cache flush
  * routines and/or provided to userland
@@ -340,7 +355,7 @@ static void __init initialize_cache_info(void)
 			const char *dc, *ic;
 
 			/* Then read cache informations */
-			if (systemcfg->platform == PLATFORM_POWERMAC) {
+			if (_machine == PLATFORM_POWERMAC) {
 				dc = "d-cache-block-size";
 				ic = "i-cache-block-size";
 			} else {
@@ -360,8 +375,8 @@ static void __init initialize_cache_info(void)
 				DBG("Argh, can't find dcache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
-			systemcfg->dcache_size = ppc64_caches.dsize = size;
-			systemcfg->dcache_line_size =
+			_systemcfg->dcache_size = ppc64_caches.dsize = size;
+			_systemcfg->dcache_line_size =
 				ppc64_caches.dline_size = lsize;
 			ppc64_caches.log_dline_size = __ilog2(lsize);
 			ppc64_caches.dlines_per_page = PAGE_SIZE / lsize;
@@ -378,8 +393,8 @@ static void __init initialize_cache_info(void)
 				DBG("Argh, can't find icache properties ! "
 				    "sizep: %p, lsizep: %p\n", sizep, lsizep);
 
-			systemcfg->icache_size = ppc64_caches.isize = size;
-			systemcfg->icache_line_size =
+			_systemcfg->icache_size = ppc64_caches.isize = size;
+			_systemcfg->icache_line_size =
 				ppc64_caches.iline_size = lsize;
 			ppc64_caches.log_iline_size = __ilog2(lsize);
 			ppc64_caches.ilines_per_page = PAGE_SIZE / lsize;
@@ -387,10 +402,12 @@ static void __init initialize_cache_info(void)
 	}
 
 	/* Add an eye catcher and the systemcfg layout version number */
-	strcpy(systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
-	systemcfg->version.major = SYSTEMCFG_MAJOR;
-	systemcfg->version.minor = SYSTEMCFG_MINOR;
-	systemcfg->processor = mfspr(SPRN_PVR);
+	strcpy(_systemcfg->eye_catcher, "SYSTEMCFG:PPC64");
+	_systemcfg->version.major = SYSTEMCFG_MAJOR;
+	_systemcfg->version.minor = SYSTEMCFG_MINOR;
+	_systemcfg->processor = mfspr(SPRN_PVR);
+	_systemcfg->platform = _machine;
+	_systemcfg->physicalMemorySize = lmb_phys_mem_size();
 
 	DBG(" <- initialize_cache_info()\n");
 }
@@ -479,10 +496,10 @@ void __init setup_system(void)
 	printk("-----------------------------------------------------\n");
 	printk("ppc64_pft_size                = 0x%lx\n", ppc64_pft_size);
 	printk("ppc64_interrupt_controller    = 0x%ld\n", ppc64_interrupt_controller);
-	printk("systemcfg                     = 0x%p\n", systemcfg);
-	printk("systemcfg->platform           = 0x%x\n", systemcfg->platform);
-	printk("systemcfg->processorCount     = 0x%lx\n", systemcfg->processorCount);
-	printk("systemcfg->physicalMemorySize = 0x%lx\n", systemcfg->physicalMemorySize);
+	printk("systemcfg                     = 0x%p\n", _systemcfg);
+	printk("systemcfg->platform           = 0x%x\n", _systemcfg->platform);
+	printk("systemcfg->processorCount     = 0x%lx\n", _systemcfg->processorCount);
+	printk("systemcfg->physicalMemorySize = 0x%lx\n", _systemcfg->physicalMemorySize);
 	printk("ppc64_caches.dcache_line_size = 0x%x\n",
 			ppc64_caches.dline_size);
 	printk("ppc64_caches.icache_line_size = 0x%x\n",
@@ -564,12 +581,12 @@ void __init setup_syscall_map(void)
 	for (i = 0; i < __NR_syscalls; i++) {
 		if (sys_call_table[i*2] != sys_ni_syscall) {
 			count64++;
-			systemcfg->syscall_map_64[i >> 5] |=
+			_systemcfg->syscall_map_64[i >> 5] |=
 				0x80000000UL >> (i & 0x1f);
 		}
 		if (sys_call_table[i*2+1] != sys_ni_syscall) {
 			count32++;
-			systemcfg->syscall_map_32[i >> 5] |=
+			_systemcfg->syscall_map_32[i >> 5] |=
 				0x80000000UL >> (i & 0x1f);
 		}
 	}
@@ -858,26 +875,6 @@ int check_legacy_ioport(unsigned long base_port)
 }
 EXPORT_SYMBOL(check_legacy_ioport);
 
-#ifdef CONFIG_XMON
-static int __init early_xmon(char *p)
-{
-	/* ensure xmon is enabled */
-	if (p) {
-		if (strncmp(p, "on", 2) == 0)
-			xmon_init(1);
-		if (strncmp(p, "off", 3) == 0)
-			xmon_init(0);
-		if (strncmp(p, "early", 5) != 0)
-			return 0;
-	}
-	xmon_init(1);
-	debugger(NULL);
-
-	return 0;
-}
-early_param("xmon", early_xmon);
-#endif
-
 void cpu_die(void)
 {
 	if (ppc_md.cpu_die)
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 081d931eae48..a7c4515f320f 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -42,6 +42,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
+#include <asm/sigcontext.h>
 #ifdef CONFIG_PPC64
 #include "ppc32.h"
 #include <asm/unistd.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 36d67a8d7cbb..e28a139c29d0 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -44,6 +44,7 @@
 #include <asm/cputable.h>
 #include <asm/system.h>
 #include <asm/mpic.h>
+#include <asm/systemcfg.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #endif
@@ -368,9 +369,11 @@ int generic_cpu_disable(void)
 	if (cpu == boot_cpuid)
 		return -EBUSY;
 
-	systemcfg->processorCount--;
 	cpu_clear(cpu, cpu_online_map);
+#ifdef CONFIG_PPC64
+	_systemcfg->processorCount--;
 	fixup_irqs(cpu_online_map);
+#endif
 	return 0;
 }
 
@@ -388,9 +391,11 @@ int generic_cpu_enable(unsigned int cpu)
 	while (!cpu_online(cpu))
 		cpu_relax();
 
+#ifdef CONFIG_PPC64
 	fixup_irqs(cpu_online_map);
 	/* counter the irq disable in fixup_irqs */
 	local_irq_enable();
+#endif
 	return 0;
 }
 
@@ -419,7 +424,9 @@ void generic_mach_cpu_die(void)
 	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
 		cpu_relax();
 
+#ifdef CONFIG_PPC64
 	flush_tlb_pending();
+#endif
 	cpu_set(cpu, cpu_online_map);
 	local_irq_enable();
 }
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index a8210ed5c686..9c921d1c4084 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -52,7 +52,6 @@
 #include <asm/semaphore.h>
 #include <asm/time.h>
 #include <asm/mmu_context.h>
-#include <asm/systemcfg.h>
 #include <asm/ppc-pci.h>
 
 /* readdir & getdents */
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
new file mode 100644
index 000000000000..850af198fb5f
--- /dev/null
+++ b/arch/powerpc/kernel/sysfs.c
@@ -0,0 +1,384 @@
+#include <linux/config.h>
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/nodemask.h>
+#include <linux/cpumask.h>
+#include <linux/notifier.h>
+
+#include <asm/current.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/firmware.h>
+#include <asm/hvcall.h>
+#include <asm/prom.h>
+#include <asm/systemcfg.h>
+#include <asm/paca.h>
+#include <asm/lppaca.h>
+#include <asm/machdep.h>
+#include <asm/smp.h>
+
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+/* SMT stuff */
+
+#ifdef CONFIG_PPC_MULTIPLATFORM
+/* default to snooze disabled */
+DEFINE_PER_CPU(unsigned long, smt_snooze_delay);
+
+static ssize_t store_smt_snooze_delay(struct sys_device *dev, const char *buf,
+				      size_t count)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
+	ssize_t ret;
+	unsigned long snooze;
+
+	ret = sscanf(buf, "%lu", &snooze);
+	if (ret != 1)
+		return -EINVAL;
+
+	per_cpu(smt_snooze_delay, cpu->sysdev.id) = snooze;
+
+	return count;
+}
+
+static ssize_t show_smt_snooze_delay(struct sys_device *dev, char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
+
+	return sprintf(buf, "%lu\n", per_cpu(smt_snooze_delay, cpu->sysdev.id));
+}
+
+static SYSDEV_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay,
+		   store_smt_snooze_delay);
+
+/* Only parse OF options if the matching cmdline option was not specified */
+static int smt_snooze_cmdline;
+
+static int __init smt_setup(void)
+{
+	struct device_node *options;
+	unsigned int *val;
+	unsigned int cpu;
+
+	if (!cpu_has_feature(CPU_FTR_SMT))
+		return 1;
+
+	options = find_path_device("/options");
+	if (!options)
+		return 1;
+
+	val = (unsigned int *)get_property(options, "ibm,smt-snooze-delay",
+					   NULL);
+	if (!smt_snooze_cmdline && val) {
+		for_each_cpu(cpu)
+			per_cpu(smt_snooze_delay, cpu) = *val;
+	}
+
+	return 1;
+}
+__initcall(smt_setup);
+
+static int __init setup_smt_snooze_delay(char *str)
+{
+	unsigned int cpu;
+	int snooze;
+
+	if (!cpu_has_feature(CPU_FTR_SMT))
+		return 1;
+
+	smt_snooze_cmdline = 1;
+
+	if (get_option(&str, &snooze)) {
+		for_each_cpu(cpu)
+			per_cpu(smt_snooze_delay, cpu) = snooze;
+	}
+
+	return 1;
+}
+__setup("smt-snooze-delay=", setup_smt_snooze_delay);
+
+#endif /* CONFIG_PPC_MULTIPLATFORM */
+
+/*
+ * Enabling PMCs will slow partition context switch times so we only do
+ * it the first time we write to the PMCs.
+ */
+
+static DEFINE_PER_CPU(char, pmcs_enabled);
+
+void ppc64_enable_pmcs(void)
+{
+	/* Only need to enable them once */
+	if (__get_cpu_var(pmcs_enabled))
+		return;
+
+	__get_cpu_var(pmcs_enabled) = 1;
+
+	if (ppc_md.enable_pmcs)
+		ppc_md.enable_pmcs();
+}
+EXPORT_SYMBOL(ppc64_enable_pmcs);
+
+/* XXX convert to rusty's on_one_cpu */
+static unsigned long run_on_cpu(unsigned long cpu,
+			        unsigned long (*func)(unsigned long),
+				unsigned long arg)
+{
+	cpumask_t old_affinity = current->cpus_allowed;
+	unsigned long ret;
+
+	/* should return -EINVAL to userspace */
+	if (set_cpus_allowed(current, cpumask_of_cpu(cpu)))
+		return 0;
+
+	ret = func(arg);
+
+	set_cpus_allowed(current, old_affinity);
+
+	return ret;
+}
+
+#define SYSFS_PMCSETUP(NAME, ADDRESS) \
+static unsigned long read_##NAME(unsigned long junk) \
+{ \
+	return mfspr(ADDRESS); \
+} \
+static unsigned long write_##NAME(unsigned long val) \
+{ \
+	ppc64_enable_pmcs(); \
+	mtspr(ADDRESS, val); \
+	return 0; \
+} \
+static ssize_t show_##NAME(struct sys_device *dev, char *buf) \
+{ \
+	struct cpu *cpu = container_of(dev, struct cpu, sysdev); \
+	unsigned long val = run_on_cpu(cpu->sysdev.id, read_##NAME, 0); \
+	return sprintf(buf, "%lx\n", val); \
+} \
+static ssize_t __attribute_used__ \
+	store_##NAME(struct sys_device *dev, const char *buf, size_t count) \
+{ \
+	struct cpu *cpu = container_of(dev, struct cpu, sysdev); \
+	unsigned long val; \
+	int ret = sscanf(buf, "%lx", &val); \
+	if (ret != 1) \
+		return -EINVAL; \
+	run_on_cpu(cpu->sysdev.id, write_##NAME, val); \
+	return count; \
+}
+
+SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
+SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
+SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
+SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
+SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
+SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
+SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
+SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
+SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
+SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
+SYSFS_PMCSETUP(purr, SPRN_PURR);
+
+static SYSDEV_ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0);
+static SYSDEV_ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1);
+static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
+static SYSDEV_ATTR(pmc1, 0600, show_pmc1, store_pmc1);
+static SYSDEV_ATTR(pmc2, 0600, show_pmc2, store_pmc2);
+static SYSDEV_ATTR(pmc3, 0600, show_pmc3, store_pmc3);
+static SYSDEV_ATTR(pmc4, 0600, show_pmc4, store_pmc4);
+static SYSDEV_ATTR(pmc5, 0600, show_pmc5, store_pmc5);
+static SYSDEV_ATTR(pmc6, 0600, show_pmc6, store_pmc6);
+static SYSDEV_ATTR(pmc7, 0600, show_pmc7, store_pmc7);
+static SYSDEV_ATTR(pmc8, 0600, show_pmc8, store_pmc8);
+static SYSDEV_ATTR(purr, 0600, show_purr, NULL);
+
+static void register_cpu_online(unsigned int cpu)
+{
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct sys_device *s = &c->sysdev;
+
+#ifndef CONFIG_PPC_ISERIES
+	if (cpu_has_feature(CPU_FTR_SMT))
+		sysdev_create_file(s, &attr_smt_snooze_delay);
+#endif
+
+	/* PMC stuff */
+
+	sysdev_create_file(s, &attr_mmcr0);
+	sysdev_create_file(s, &attr_mmcr1);
+
+	if (cpu_has_feature(CPU_FTR_MMCRA))
+		sysdev_create_file(s, &attr_mmcra);
+
+	if (cur_cpu_spec->num_pmcs >= 1)
+		sysdev_create_file(s, &attr_pmc1);
+	if (cur_cpu_spec->num_pmcs >= 2)
+		sysdev_create_file(s, &attr_pmc2);
+	if (cur_cpu_spec->num_pmcs >= 3)
+		sysdev_create_file(s, &attr_pmc3);
+	if (cur_cpu_spec->num_pmcs >= 4)
+		sysdev_create_file(s, &attr_pmc4);
+	if (cur_cpu_spec->num_pmcs >= 5)
+		sysdev_create_file(s, &attr_pmc5);
+	if (cur_cpu_spec->num_pmcs >= 6)
+		sysdev_create_file(s, &attr_pmc6);
+	if (cur_cpu_spec->num_pmcs >= 7)
+		sysdev_create_file(s, &attr_pmc7);
+	if (cur_cpu_spec->num_pmcs >= 8)
+		sysdev_create_file(s, &attr_pmc8);
+
+	if (cpu_has_feature(CPU_FTR_SMT))
+		sysdev_create_file(s, &attr_purr);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void unregister_cpu_online(unsigned int cpu)
+{
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct sys_device *s = &c->sysdev;
+
+	BUG_ON(c->no_control);
+
+#ifndef CONFIG_PPC_ISERIES
+	if (cpu_has_feature(CPU_FTR_SMT))
+		sysdev_remove_file(s, &attr_smt_snooze_delay);
+#endif
+
+	/* PMC stuff */
+
+	sysdev_remove_file(s, &attr_mmcr0);
+	sysdev_remove_file(s, &attr_mmcr1);
+
+	if (cpu_has_feature(CPU_FTR_MMCRA))
+		sysdev_remove_file(s, &attr_mmcra);
+
+	if (cur_cpu_spec->num_pmcs >= 1)
+		sysdev_remove_file(s, &attr_pmc1);
+	if (cur_cpu_spec->num_pmcs >= 2)
+		sysdev_remove_file(s, &attr_pmc2);
+	if (cur_cpu_spec->num_pmcs >= 3)
+		sysdev_remove_file(s, &attr_pmc3);
+	if (cur_cpu_spec->num_pmcs >= 4)
+		sysdev_remove_file(s, &attr_pmc4);
+	if (cur_cpu_spec->num_pmcs >= 5)
+		sysdev_remove_file(s, &attr_pmc5);
+	if (cur_cpu_spec->num_pmcs >= 6)
+		sysdev_remove_file(s, &attr_pmc6);
+	if (cur_cpu_spec->num_pmcs >= 7)
+		sysdev_remove_file(s, &attr_pmc7);
+	if (cur_cpu_spec->num_pmcs >= 8)
+		sysdev_remove_file(s, &attr_pmc8);
+
+	if (cpu_has_feature(CPU_FTR_SMT))
+		sysdev_remove_file(s, &attr_purr);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static int __devinit sysfs_cpu_notify(struct notifier_block *self,
+				      unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned int)(long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+		register_cpu_online(cpu);
+		break;
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DEAD:
+		unregister_cpu_online(cpu);
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __devinitdata sysfs_cpu_nb = {
+	.notifier_call	= sysfs_cpu_notify,
+};
+
+/* NUMA stuff */
+
+#ifdef CONFIG_NUMA
+static struct node node_devices[MAX_NUMNODES];
+
+static void register_nodes(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		if (node_online(i)) {
+			int p_node = parent_node(i);
+			struct node *parent = NULL;
+
+			if (p_node != i)
+				parent = &node_devices[p_node];
+
+			register_node(&node_devices[i], i, parent);
+		}
+	}
+}
+#else
+static void register_nodes(void)
+{
+	return;
+}
+#endif
+
+/* Only valid if CPU is present. */
+static ssize_t show_physical_id(struct sys_device *dev, char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
+
+	return sprintf(buf, "%d\n", get_hard_smp_processor_id(cpu->sysdev.id));
+}
+static SYSDEV_ATTR(physical_id, 0444, show_physical_id, NULL);
+
+static int __init topology_init(void)
+{
+	int cpu;
+	struct node *parent = NULL;
+
+	register_nodes();
+
+	register_cpu_notifier(&sysfs_cpu_nb);
+
+	for_each_cpu(cpu) {
+		struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+#ifdef CONFIG_NUMA
+		/* The node to which a cpu belongs can't be known
+		 * until the cpu is made present.
+		 */
+		parent = NULL;
+		if (cpu_present(cpu))
+			parent = &node_devices[cpu_to_node(cpu)];
+#endif
+		/*
+		 * For now, we just see if the system supports making
+		 * the RTAS calls for CPU hotplug.  But, there may be a
+		 * more comprehensive way to do this for an individual
+		 * CPU.  For instance, the boot cpu might never be valid
+		 * for hotplugging.
+		 */
+		if (!ppc_md.cpu_die)
+			c->no_control = 1;
+
+		if (cpu_online(cpu) || (c->no_control == 0)) {
+			register_cpu(c, cpu, parent);
+
+			sysdev_create_file(&c->sysdev, &attr_physical_id);
+		}
+
+		if (cpu_online(cpu))
+			register_cpu_online(cpu);
+	}
+
+	return 0;
+}
+__initcall(topology_init);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index a6282b625b44..260b6ecd26a9 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -271,13 +271,13 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
 	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
 	 * loops back and reads them again until this criteria is met.
 	 */
-	++(systemcfg->tb_update_count);
+	++(_systemcfg->tb_update_count);
 	smp_wmb();
-	systemcfg->tb_orig_stamp = new_tb_stamp;
-	systemcfg->stamp_xsec = new_stamp_xsec;
-	systemcfg->tb_to_xs = new_tb_to_xs;
+	_systemcfg->tb_orig_stamp = new_tb_stamp;
+	_systemcfg->stamp_xsec = new_stamp_xsec;
+	_systemcfg->tb_to_xs = new_tb_to_xs;
 	smp_wmb();
-	++(systemcfg->tb_update_count);
+	++(_systemcfg->tb_update_count);
 #endif
 }
 
@@ -357,8 +357,9 @@ static void iSeries_tb_recal(void)
 				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
 				tb_to_xs = divres.result_low;
 				do_gtod.varp->tb_to_xs = tb_to_xs;
-				systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
-				systemcfg->tb_to_xs = tb_to_xs;
+				_systemcfg->tb_ticks_per_sec =
+					tb_ticks_per_sec;
+				_systemcfg->tb_to_xs = tb_to_xs;
 			}
 			else {
 				printk( "Titan recalibrate: FAILED (difference > 4 percent)\n"
@@ -483,6 +484,8 @@ void __init smp_space_timers(unsigned int max_cpus)
 	unsigned long offset = tb_ticks_per_jiffy / max_cpus;
 	unsigned long previous_tb = per_cpu(last_jiffy, boot_cpuid);
 
+	/* make sure tb > per_cpu(last_jiffy, cpu) for all cpus always */
+	previous_tb -= tb_ticks_per_jiffy;
 	for_each_cpu(i) {
 		if (i != boot_cpuid) {
 			previous_tb += offset;
@@ -559,8 +562,8 @@ int do_settimeofday(struct timespec *tv)
 	update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs);
 
 #ifdef CONFIG_PPC64
-	systemcfg->tz_minuteswest = sys_tz.tz_minuteswest;
-	systemcfg->tz_dsttime = sys_tz.tz_dsttime;
+	_systemcfg->tz_minuteswest = sys_tz.tz_minuteswest;
+	_systemcfg->tz_dsttime = sys_tz.tz_dsttime;
 #endif
 
 	write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -711,11 +714,11 @@ void __init time_init(void)
 	do_gtod.varp->tb_to_xs = tb_to_xs;
 	do_gtod.tb_to_us = tb_to_us;
 #ifdef CONFIG_PPC64
-	systemcfg->tb_orig_stamp = tb_last_jiffy;
-	systemcfg->tb_update_count = 0;
-	systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
-	systemcfg->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC;
-	systemcfg->tb_to_xs = tb_to_xs;
+	_systemcfg->tb_orig_stamp = tb_last_jiffy;
+	_systemcfg->tb_update_count = 0;
+	_systemcfg->tb_ticks_per_sec = tb_ticks_per_sec;
+	_systemcfg->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC;
+	_systemcfg->tb_to_xs = tb_to_xs;
 #endif
 
 	time_freq = 0;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 0578f8387603..2020bb7648fb 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -129,7 +129,7 @@ int die(const char *str, struct pt_regs *regs, long err)
 	nl = 1;
 #endif
 #ifdef CONFIG_PPC64
-	switch (systemcfg->platform) {
+	switch (_machine) {
 	case PLATFORM_PSERIES:
 		printk("PSERIES ");
 		nl = 1;