Merge branch 'linus' into perf/urgent

Merge reason: Fix upstream breakage introduced by:

 de5d9bf: Move list types from <linux/list.h> to <linux/types.h>.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

35 files changed, 1151 insertions, 1800 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 58d0572de6f..1dda7012914 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -34,13 +34,14 @@ obj-y				+= vdso32/
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o nvram_64.o firmware.o
+obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
-obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o
+obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
-obj-$(CONFIG_PPC_OF)		+= of_device.o of_platform.o prom_parse.o
+obj-$(CONFIG_PPC_OF)		+= of_platform.o prom_parse.o
 obj-$(CONFIG_PPC_CLOCK)		+= clock.o
 procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
@@ -67,6 +68,7 @@ obj64-$(CONFIG_HIBERNATION)	+= swsusp_asm64.o
 obj-$(CONFIG_MODULES)		+= module.o module_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_44x)		+= cpu_setup_44x.o
 obj-$(CONFIG_FSL_BOOKE)		+= cpu_setup_fsl_booke.o dbell.o
+obj-$(CONFIG_PPC_BOOK3E_64)	+= dbell.o
 
 extra-y				:= head_$(CONFIG_WORD_SIZE).o
 extra-$(CONFIG_PPC_BOOK3E_32)	:= head_new_booke.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 496cc5b3984..1c0607ddccc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -194,7 +194,6 @@ int main(void)
 	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
-	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
@@ -342,6 +341,7 @@ int main(void)
 	DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
 	DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
 	DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime));
+	DEFINE(STAMP_SEC_FRAC, offsetof(struct vdso_data, stamp_sec_fraction));
 	DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
 	DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
 	DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 87aa0f3c604..65e2b4e10f9 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1364,10 +1364,10 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check		= machine_check_4xx,
 		.platform		= "ppc405",
 	},
-	{	/* 405EX */
-		.pvr_mask		= 0xffff0004,
-		.pvr_value		= 0x12910004,
-		.cpu_name		= "405EX",
+	{	/* 405EX Rev. A/B with Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x12910007,
+		.cpu_name		= "405EX Rev. A/B",
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
@@ -1377,10 +1377,114 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check		= machine_check_4xx,
 		.platform		= "ppc405",
 	},
-	{	/* 405EXr */
-		.pvr_mask		= 0xffff0004,
+	{	/* 405EX Rev. C without Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x1291000d,
+		.cpu_name		= "405EX Rev. C",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EX Rev. C with Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x1291000f,
+		.cpu_name		= "405EX Rev. C",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EX Rev. D without Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x12910003,
+		.cpu_name		= "405EX Rev. D",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EX Rev. D with Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x12910005,
+		.cpu_name		= "405EX Rev. D",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EXr Rev. A/B without Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x12910001,
+		.cpu_name		= "405EXr Rev. A/B",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EXr Rev. C without Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x12910009,
+		.cpu_name		= "405EXr Rev. C",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EXr Rev. C with Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x1291000b,
+		.cpu_name		= "405EXr Rev. C",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EXr Rev. D without Security */
+		.pvr_mask		= 0xffff000f,
 		.pvr_value		= 0x12910000,
-		.cpu_name		= "405EXr",
+		.cpu_name		= "405EXr Rev. D",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
+	{	/* 405EXr Rev. D with Security */
+		.pvr_mask		= 0xffff000f,
+		.pvr_value		= 0x12910002,
+		.cpu_name		= "405EXr Rev. D",
 		.cpu_features		= CPU_FTRS_40X,
 		.cpu_user_features	= PPC_FEATURE_32 |
 			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 40f524643ba..8e05c16344e 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -128,9 +128,9 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 	if (!csize)
 		return 0;
 
-	csize = min(csize, PAGE_SIZE);
+	csize = min_t(size_t, csize, PAGE_SIZE);
 
-	if (pfn < max_pfn) {
+	if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
 		vaddr = __va(pfn << PAGE_SHIFT);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 	} else {
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 1493734cd87..3307a52d797 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -13,32 +13,88 @@
 #include <linux/kernel.h>
 #include <linux/smp.h>
 #include <linux/threads.h>
+#include <linux/percpu.h>
 
 #include <asm/dbell.h>
+#include <asm/irq_regs.h>
 
 #ifdef CONFIG_SMP
-unsigned long dbell_smp_message[NR_CPUS];
+struct doorbell_cpu_info {
+	unsigned long	messages;	/* current messages bits */
+	unsigned int	tag;		/* tag value */
+};
 
-void smp_dbell_message_pass(int target, int msg)
+static DEFINE_PER_CPU(struct doorbell_cpu_info, doorbell_cpu_info);
+
+void doorbell_setup_this_cpu(void)
+{
+	struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info);
+
+	info->messages = 0;
+	info->tag = mfspr(SPRN_PIR) & 0x3fff;
+}
+
+void doorbell_message_pass(int target, int msg)
 {
+	struct doorbell_cpu_info *info;
 	int i;
 
-	if(target < NR_CPUS) {
-		set_bit(msg, &dbell_smp_message[target]);
-		ppc_msgsnd(PPC_DBELL, 0, target);
+	if (target < NR_CPUS) {
+		info = &per_cpu(doorbell_cpu_info, target);
+		set_bit(msg, &info->messages);
+		ppc_msgsnd(PPC_DBELL, 0, info->tag);
 	}
-	else if(target == MSG_ALL_BUT_SELF) {
+	else if (target == MSG_ALL_BUT_SELF) {
 		for_each_online_cpu(i) {
 			if (i == smp_processor_id())
 				continue;
-			set_bit(msg, &dbell_smp_message[i]);
-			ppc_msgsnd(PPC_DBELL, 0, i);
+			info = &per_cpu(doorbell_cpu_info, i);
+			set_bit(msg, &info->messages);
+			ppc_msgsnd(PPC_DBELL, 0, info->tag);
 		}
 	}
 	else { /* target == MSG_ALL */
-		for_each_online_cpu(i)
-			set_bit(msg, &dbell_smp_message[i]);
+		for_each_online_cpu(i) {
+			info = &per_cpu(doorbell_cpu_info, i);
+			set_bit(msg, &info->messages);
+		}
 		ppc_msgsnd(PPC_DBELL, PPC_DBELL_MSG_BRDCAST, 0);
 	}
 }
-#endif
+
+void doorbell_exception(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info);
+	int msg;
+
+	/* Warning: regs can be NULL when called from irq enable */
+
+	if (!info->messages || (num_online_cpus() < 2))
+		goto out;
+
+	for (msg = 0; msg < 4; msg++)
+		if (test_and_clear_bit(msg, &info->messages))
+			smp_message_recv(msg);
+
+out:
+	set_irq_regs(old_regs);
+}
+
+void doorbell_check_self(void)
+{
+	struct doorbell_cpu_info *info = &__get_cpu_var(doorbell_cpu_info);
+
+	if (!info->messages)
+		return;
+
+	ppc_msgsnd(PPC_DBELL, 0, info->tag);
+}
+
+#else /* CONFIG_SMP */
+void doorbell_exception(struct pt_regs *regs)
+{
+	printk(KERN_WARNING "Received doorbell on non-smp system\n");
+}
+#endif /* CONFIG_SMP */
+
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 02f724f3675..4295e0b94b2 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -82,17 +82,9 @@ static struct notifier_block ppc_swiotlb_plat_bus_notifier = {
 	.priority = 0,
 };
 
-static struct notifier_block ppc_swiotlb_of_bus_notifier = {
-	.notifier_call = ppc_swiotlb_bus_notify,
-	.priority = 0,
-};
-
 int __init swiotlb_setup_bus_notifier(void)
 {
 	bus_register_notifier(&platform_bus_type,
 			      &ppc_swiotlb_plat_bus_notifier);
-	bus_register_notifier(&of_platform_bus_type,
-			      &ppc_swiotlb_of_bus_notifier);
-
 	return 0;
 }
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 24dcc0ecf24..5c43063d250 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -191,6 +191,12 @@ exc_##n##_bad_stack:							    \
 	sth	r1,PACA_TRAP_SAVE(r13);	/* store trap */		    \
 	b	bad_stack_book3e;	/* bad stack error */
 
+/* WARNING: If you change the layout of this stub, make sure you chcek
+	*   the debug exception handler which handles single stepping
+	*   into exceptions from userspace, and the MM code in
+	*   arch/powerpc/mm/tlb_nohash.c which patches the branch here
+	*   and would need to be updated if that branch is moved
+	*/
 #define	EXCEPTION_STUB(loc, label)					\
 	. = interrupt_base_book3e + loc;				\
 	nop;	/* To make debug interrupts happy */			\
@@ -204,11 +210,30 @@ exc_##n##_bad_stack:							    \
 	lis	r,TSR_FIS@h;						\
 	mtspr	SPRN_TSR,r
 
+/* Used by asynchronous interrupt that may happen in the idle loop.
+ *
+ * This check if the thread was in the idle loop, and if yes, returns
+ * to the caller rather than the PC. This is to avoid a race if
+ * interrupts happen before the wait instruction.
+ */
+#define CHECK_NAPPING()							\
+	clrrdi	r11,r1,THREAD_SHIFT;					\
+	ld	r10,TI_LOCAL_FLAGS(r11);				\
+	andi.	r9,r10,_TLF_NAPPING;					\
+	beq+	1f;							\
+	ld	r8,_LINK(r1);						\
+	rlwinm	r7,r10,0,~_TLF_NAPPING;					\
+	std	r8,_NIP(r1);						\
+	std	r7,TI_LOCAL_FLAGS(r11);					\
+1:
+
+
 #define MASKABLE_EXCEPTION(trapnum, label, hdlr, ack)			\
 	START_EXCEPTION(label);						\
 	NORMAL_EXCEPTION_PROLOG(trapnum, PROLOG_ADDITION_MASKABLE)	\
 	EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE_ALL)		\
 	ack(r8);							\
+	CHECK_NAPPING();						\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
 	bl	hdlr;							\
 	b	.ret_from_except_lite;
@@ -246,11 +271,9 @@ interrupt_base_book3e:					/* fake trap */
 	EXCEPTION_STUB(0x1a0, watchdog)			/* 0x09f0 */
 	EXCEPTION_STUB(0x1c0, data_tlb_miss)
 	EXCEPTION_STUB(0x1e0, instruction_tlb_miss)
+	EXCEPTION_STUB(0x280, doorbell)
+	EXCEPTION_STUB(0x2a0, doorbell_crit)
 
-#if 0
-	EXCEPTION_STUB(0x280, processor_doorbell)
-	EXCEPTION_STUB(0x220, processor_doorbell_crit)
-#endif
 	.globl interrupt_end_book3e
 interrupt_end_book3e:
 
@@ -259,6 +282,7 @@ interrupt_end_book3e:
 	CRIT_EXCEPTION_PROLOG(0x100, PROLOG_ADDITION_NONE)
 //	EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE_ALL)
 //	bl	special_reg_save_crit
+//	CHECK_NAPPING();
 //	addi	r3,r1,STACK_FRAME_OVERHEAD
 //	bl	.critical_exception
 //	b	ret_from_crit_except
@@ -270,6 +294,7 @@ interrupt_end_book3e:
 //	EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE_ALL)
 //	bl	special_reg_save_mc
 //	addi	r3,r1,STACK_FRAME_OVERHEAD
+//	CHECK_NAPPING();
 //	bl	.machine_check_exception
 //	b	ret_from_mc_except
 	b	.
@@ -340,6 +365,7 @@ interrupt_end_book3e:
 	CRIT_EXCEPTION_PROLOG(0x9f0, PROLOG_ADDITION_NONE)
 //	EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE_ALL)
 //	bl	special_reg_save_crit
+//	CHECK_NAPPING();
 //	addi	r3,r1,STACK_FRAME_OVERHEAD
 //	bl	.unknown_exception
 //	b	ret_from_crit_except
@@ -428,6 +454,20 @@ interrupt_end_book3e:
 kernel_dbg_exc:
 	b	.	/* NYI */
 
+/* Doorbell interrupt */
+	MASKABLE_EXCEPTION(0x2070, doorbell, .doorbell_exception, ACK_NONE)
+
+/* Doorbell critical Interrupt */
+	START_EXCEPTION(doorbell_crit);
+	CRIT_EXCEPTION_PROLOG(0x2080, PROLOG_ADDITION_NONE)
+//	EXCEPTION_COMMON(0x2080, PACA_EXCRIT, INTS_DISABLE_ALL)
+//	bl	special_reg_save_crit
+//	CHECK_NAPPING();
+//	addi	r3,r1,STACK_FRAME_OVERHEAD
+//	bl	.doorbell_critical_exception
+//	b	ret_from_crit_except
+	b	.
+
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -563,6 +603,8 @@ BAD_STACK_TRAMPOLINE(0xd00)
 BAD_STACK_TRAMPOLINE(0xe00)
 BAD_STACK_TRAMPOLINE(0xf00)
 BAD_STACK_TRAMPOLINE(0xf20)
+BAD_STACK_TRAMPOLINE(0x2070)
+BAD_STACK_TRAMPOLINE(0x2080)
 
 	.globl	bad_stack_book3e
 bad_stack_book3e:
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3e423fbad6b..f53029a0155 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -828,6 +828,7 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 
 /* We have a data breakpoint exception - handle it */
 handle_dabr_fault:
+	bl	.save_nvgprs
 	ld      r4,_DAR(r1)
 	ld      r5,_DSISR(r1)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
new file mode 100644
index 00000000000..5ecd0401cdb
--- /dev/null
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -0,0 +1,364 @@
+/*
+ * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility,
+ * using the CPU's debug registers. Derived from
+ * "arch/x86/kernel/hw_breakpoint.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.
+ *
+ * Copyright 2010 IBM Corporation
+ * Author: K.Prasad <prasad@linux.vnet.ibm.com>
+ *
+ */
+
+#include <linux/hw_breakpoint.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/percpu.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/hw_breakpoint.h>
+#include <asm/processor.h>
+#include <asm/sstep.h>
+#include <asm/uaccess.h>
+
+/*
+ * Stores the breakpoints currently in use on each breakpoint address
+ * register for every cpu
+ */
+static DEFINE_PER_CPU(struct perf_event *, bp_per_reg);
+
+/*
+ * Returns total number of data or instruction breakpoints available.
+ */
+int hw_breakpoint_slots(int type)
+{
+	if (type == TYPE_DATA)
+		return HBP_NUM;
+	return 0;		/* no instruction breakpoints available */
+}
+
+/*
+ * Install a perf counter breakpoint.
+ *
+ * We seek a free debug address register and use it for this
+ * breakpoint.
+ *
+ * Atomic: we hold the counter->ctx->lock and we only handle variables
+ * and registers local to this cpu.
+ */
+int arch_install_hw_breakpoint(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+
+	*slot = bp;
+
+	/*
+	 * Do not install DABR values if the instruction must be single-stepped.
+	 * If so, DABR will be populated in single_step_dabr_instruction().
+	 */
+	if (current->thread.last_hit_ubp != bp)
+		set_dabr(info->address | info->type | DABR_TRANSLATION);
+
+	return 0;
+}
+
+/*
+ * Uninstall the breakpoint contained in the given counter.
+ *
+ * First we search the debug address register it uses and then we disable
+ * it.
+ *
+ * Atomic: we hold the counter->ctx->lock and we only handle variables
+ * and registers local to this cpu.
+ */
+void arch_uninstall_hw_breakpoint(struct perf_event *bp)
+{
+	struct perf_event **slot = &__get_cpu_var(bp_per_reg);
+
+	if (*slot != bp) {
+		WARN_ONCE(1, "Can't find the breakpoint");
+		return;
+	}
+
+	*slot = NULL;
+	set_dabr(0);
+}
+
+/*
+ * Perform cleanup of arch-specific counters during unregistration
+ * of the perf-event
+ */
+void arch_unregister_hw_breakpoint(struct perf_event *bp)
+{
+	/*
+	 * If the breakpoint is unregistered between a hw_breakpoint_handler()
+	 * and the single_step_dabr_instruction(), then cleanup the breakpoint
+	 * restoration variables to prevent dangling pointers.
+	 */
+	if (bp->ctx->task)
+		bp->ctx->task->thread.last_hit_ubp = NULL;
+}
+
+/*
+ * Check for virtual address in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct perf_event *bp)
+{
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+
+	return is_kernel_addr(info->address);
+}
+
+int arch_bp_generic_fields(int type, int *gen_bp_type)
+{
+	switch (type) {
+	case DABR_DATA_READ:
+		*gen_bp_type = HW_BREAKPOINT_R;
+		break;
+	case DABR_DATA_WRITE:
+		*gen_bp_type = HW_BREAKPOINT_W;
+		break;
+	case (DABR_DATA_WRITE | DABR_DATA_READ):
+		*gen_bp_type = (HW_BREAKPOINT_W | HW_BREAKPOINT_R);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Validate the arch-specific HW Breakpoint register settings
+ */
+int arch_validate_hwbkpt_settings(struct perf_event *bp)
+{
+	int ret = -EINVAL;
+	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
+
+	if (!bp)
+		return ret;
+
+	switch (bp->attr.bp_type) {
+	case HW_BREAKPOINT_R:
+		info->type = DABR_DATA_READ;
+		break;
+	case HW_BREAKPOINT_W:
+		info->type = DABR_DATA_WRITE;
+		break;
+	case HW_BREAKPOINT_R | HW_BREAKPOINT_W:
+		info->type = (DABR_DATA_READ | DABR_DATA_WRITE);
+		break;
+	default:
+		return ret;
+	}
+
+	info->address = bp->attr.bp_addr;
+	info->len = bp->attr.bp_len;
+
+	/*
+	 * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
+	 * and breakpoint addresses are aligned to nearest double-word
+	 * HW_BREAKPOINT_ALIGN by rounding off to the lower address, the
+	 * 'symbolsize' should satisfy the check below.
+	 */
+	if (info->len >
+	    (HW_BREAKPOINT_LEN - (info->address & HW_BREAKPOINT_ALIGN)))
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * Restores the breakpoint on the debug registers.
+ * Invoke this function if it is known that the execution context is
+ * about to change to cause loss of MSR_SE settings.
+ */
+void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
+{
+	struct arch_hw_breakpoint *info;
+
+	if (likely(!tsk->thread.last_hit_ubp))
+		return;
+
+	info = counter_arch_bp(tsk->thread.last_hit_ubp);
+	regs->msr &= ~MSR_SE;
+	set_dabr(info->address | info->type | DABR_TRANSLATION);
+	tsk->thread.last_hit_ubp = NULL;
+}
+
+/*
+ * Handle debug exception notifications.
+ */
+int __kprobes hw_breakpoint_handler(struct die_args *args)
+{
+	int rc = NOTIFY_STOP;
+	struct perf_event *bp;
+	struct pt_regs *regs = args->regs;
+	int stepped = 1;
+	struct arch_hw_breakpoint *info;
+	unsigned int instr;
+	unsigned long dar = regs->dar;
+
+	/* Disable breakpoints during exception handling */
+	set_dabr(0);
+
+	/*
+	 * The counter may be concurrently released but that can only
+	 * occur from a call_rcu() path. We can then safely fetch
+	 * the breakpoint, use its callback, touch its counter
+	 * while we are in an rcu_read_lock() path.
+	 */
+	rcu_read_lock();
+
+	bp = __get_cpu_var(bp_per_reg);
+	if (!bp)
+		goto out;
+	info = counter_arch_bp(bp);
+
+	/*
+	 * Return early after invoking user-callback function without restoring
+	 * DABR if the breakpoint is from ptrace which always operates in
+	 * one-shot mode. The ptrace-ed process will receive the SIGTRAP signal
+	 * generated in do_dabr().
+	 */
+	if (bp->overflow_handler == ptrace_triggered) {
+		perf_bp_event(bp, regs);
+		rc = NOTIFY_DONE;
+		goto out;
+	}
+
+	/*
+	 * Verify if dar lies within the address range occupied by the symbol
+	 * being watched to filter extraneous exceptions.  If it doesn't,
+	 * we still need to single-step the instruction, but we don't
+	 * generate an event.
+	 */
+	info->extraneous_interrupt = !((bp->attr.bp_addr <= dar) &&
+			(dar - bp->attr.bp_addr < bp->attr.bp_len));
+
+	/* Do not emulate user-space instructions, instead single-step them */
+	if (user_mode(regs)) {
+		bp->ctx->task->thread.last_hit_ubp = bp;
+		regs->msr |= MSR_SE;
+		goto out;
+	}
+
+	stepped = 0;
+	instr = 0;
+	if (!__get_user_inatomic(instr, (unsigned int *) regs->nip))
+		stepped = emulate_step(regs, instr);
+
+	/*
+	 * emulate_step() could not execute it. We've failed in reliably
+	 * handling the hw-breakpoint. Unregister it and throw a warning
+	 * message to let the user know about it.
+	 */
+	if (!stepped) {
+		WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
+			"0x%lx will be disabled.", info->address);
+		perf_event_disable(bp);
+		goto out;
+	}
+	/*
+	 * As a policy, the callback is invoked in a 'trigger-after-execute'
+	 * fashion
+	 */
+	if (!info->extraneous_interrupt)
+		perf_bp_event(bp, regs);
+
+	set_dabr(info->address | info->type | DABR_TRANSLATION);
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+/*
+ * Handle single-step exceptions following a DABR hit.
+ */
+int __kprobes single_step_dabr_instruction(struct die_args *args)
+{
+	struct pt_regs *regs = args->regs;
+	struct perf_event *bp = NULL;
+	struct arch_hw_breakpoint *bp_info;
+
+	bp = current->thread.last_hit_ubp;
+	/*
+	 * Check if we are single-stepping as a result of a
+	 * previous HW Breakpoint exception
+	 */
+	if (!bp)
+		return NOTIFY_DONE;
+
+	bp_info = counter_arch_bp(bp);
+
+	/*
+	 * We shall invoke the user-defined callback function in the single
+	 * stepping handler to confirm to 'trigger-after-execute' semantics
+	 */
+	if (!bp_info->extraneous_interrupt)
+		perf_bp_event(bp, regs);
+
+	set_dabr(bp_info->address | bp_info->type | DABR_TRANSLATION);
+	current->thread.last_hit_ubp = NULL;
+
+	/*
+	 * If the process was being single-stepped by ptrace, let the
+	 * other single-step actions occur (e.g. generate SIGTRAP).
+	 */
+	if (test_thread_flag(TIF_SINGLESTEP))
+		return NOTIFY_DONE;
+
+	return NOTIFY_STOP;
+}
+
+/*
+ * Handle debug exception notifications.
+ */
+int __kprobes hw_breakpoint_exceptions_notify(
+		struct notifier_block *unused, unsigned long val, void *data)
+{
+	int ret = NOTIFY_DONE;
+
+	switch (val) {
+	case DIE_DABR_MATCH:
+		ret = hw_breakpoint_handler(data);
+		break;
+	case DIE_SSTEP:
+		ret = single_step_dabr_instruction(data);
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * Release the user breakpoints used by ptrace
+ */
+void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
+{
+	struct thread_struct *t = &tsk->thread;
+
+	unregister_hw_breakpoint(t->ptrace_bps[0]);
+	t->ptrace_bps[0] = NULL;
+}
+
+void hw_breakpoint_pmu_read(struct perf_event *bp)
+{
+	/* TODO */
+}
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 21266abfbda..9b626cfffce 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -140,19 +140,19 @@ static struct dma_map_ops ibmebus_dma_ops = {
 
 static int ibmebus_match_path(struct device *dev, void *data)
 {
-	struct device_node *dn = to_of_device(dev)->dev.of_node;
+	struct device_node *dn = to_platform_device(dev)->dev.of_node;
 	return (dn->full_name &&
 		(strcasecmp((char *)data, dn->full_name) == 0));
 }
 
 static int ibmebus_match_node(struct device *dev, void *data)
 {
-	return to_of_device(dev)->dev.of_node == data;
+	return to_platform_device(dev)->dev.of_node == data;
 }
 
 static int ibmebus_create_device(struct device_node *dn)
 {
-	struct of_device *dev;
+	struct platform_device *dev;
 	int ret;
 
 	dev = of_device_alloc(dn, NULL, &ibmebus_bus_device);
@@ -298,7 +298,7 @@ static ssize_t ibmebus_store_remove(struct bus_type *bus,
 
 	if ((dev = bus_find_device(&ibmebus_bus_type, NULL, path,
 				   ibmebus_match_path))) {
-		of_device_unregister(to_of_device(dev));
+		of_device_unregister(to_platform_device(dev));
 
 		kfree(path);
 		return count;
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
new file mode 100644
index 00000000000..16c002d6bdf
--- /dev/null
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2010 IBM Corp, Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ *
+ * Generic idle routine for Book3E processors
+ *
+ * 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/threads.h>
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/ppc-opcode.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+/* 64-bit version only for now */
+#ifdef CONFIG_PPC64
+
+_GLOBAL(book3e_idle)
+	/* Save LR for later */
+	mflr	r0
+	std	r0,16(r1)
+
+	/* Hard disable interrupts */
+	wrteei	0
+
+	/* Now check if an interrupt came in while we were soft disabled
+	 * since we may otherwise lose it (doorbells etc...). We know
+	 * that since PACAHARDIRQEN will have been cleared in that case.
+	 */
+	lbz	r3,PACAHARDIRQEN(r13)
+	cmpwi	cr0,r3,0
+	beqlr
+
+	/* Now we are going to mark ourselves as soft and hard enables in
+	 * order to be able to take interrupts while asleep. We inform lockdep
+	 * of that. We don't actually turn interrupts on just yet tho.
+	 */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	stdu    r1,-128(r1)
+	bl	.trace_hardirqs_on
+#endif
+	li	r0,1
+	stb	r0,PACASOFTIRQEN(r13)
+	stb	r0,PACAHARDIRQEN(r13)
+	
+	/* Interrupts will make use return to LR, so get something we want
+	 * in there
+	 */
+	bl	1f
+
+	/* Hard disable interrupts again */
+	wrteei	0
+
+	/* Mark them off again in the PACA as well */
+	li	r0,0
+	stb	r0,PACASOFTIRQEN(r13)
+	stb	r0,PACAHARDIRQEN(r13)
+
+	/* Tell lockdep about it */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	.trace_hardirqs_off
+	addi    r1,r1,128
+#endif
+	ld	r0,16(r1)
+	mtlr	r0
+	blr
+
+1:	/* Let's set the _TLF_NAPPING flag so interrupts make us return
+	 * to the right spot
+	*/
+	clrrdi	r11,r1,THREAD_SHIFT
+	ld	r10,TI_LOCAL_FLAGS(r11)
+	ori	r10,r10,_TLF_NAPPING
+	std	r10,TI_LOCAL_FLAGS(r11)
+
+	/* We can now re-enable hard interrupts and go to sleep */
+	wrteei	1
+1:	PPC_WAIT(0)
+	b	1b
+
+#endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 77be3d058a6..d3ce67cf03b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -53,6 +53,8 @@
 #include <linux/bootmem.h>
 #include <linux/pci.h>
 #include <linux/debugfs.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -64,6 +66,8 @@
 #include <asm/ptrace.h>
 #include <asm/machdep.h>
 #include <asm/udbg.h>
+#include <asm/dbell.h>
+
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/firmware.h>
@@ -153,14 +157,28 @@ notrace void raw_local_irq_restore(unsigned long en)
 	if (get_hard_enabled())
 		return;
 
+#if defined(CONFIG_BOOKE) && defined(CONFIG_SMP)
+	/* Check for pending doorbell interrupts and resend to ourself */
+	doorbell_check_self();
+#endif
+
 	/*
 	 * Need to hard-enable interrupts here.  Since currently disabled,
 	 * no need to take further asm precautions against preemption; but
 	 * use local_paca instead of get_paca() to avoid preemption checking.
 	 */
 	local_paca->hard_enabled = en;
+
+#ifndef CONFIG_BOOKE
+	/* On server, re-trigger the decrementer if it went negative since
+	 * some processors only trigger on edge transitions of the sign bit.
+	 *
+	 * BookE has a level sensitive decrementer (latches in TSR) so we
+	 * don't need that
+	 */
 	if ((int)mfspr(SPRN_DEC) < 0)
 		mtspr(SPRN_DEC, 1);
+#endif /* CONFIG_BOOKE */
 
 	/*
 	 * Force the delivery of pending soft-disabled interrupts on PS3.
@@ -804,18 +822,6 @@ unsigned int irq_create_of_mapping(struct device_node *controller,
 }
 EXPORT_SYMBOL_GPL(irq_create_of_mapping);
 
-unsigned int irq_of_parse_and_map(struct device_node *dev, int index)
-{
-	struct of_irq oirq;
-
-	if (of_irq_map_one(dev, index, &oirq))
-		return NO_IRQ;
-
-	return irq_create_of_mapping(oirq.controller, oirq.specifier,
-				     oirq.size);
-}
-EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
-
 void irq_dispose_mapping(unsigned int virq)
 {
 	struct irq_host *host;
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 82a7b228c81..7f61a3ac787 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -129,7 +129,7 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs)
 		return 0;
 
 	if (*(u32 *) (regs->nip) == *(u32 *) (&arch_kgdb_ops.gdb_bpt_instr))
-		regs->nip += 4;
+		regs->nip += BREAK_INSTR_SIZE;
 
 	return 1;
 }
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 035ada5443e..c1fd0f9658f 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -4,6 +4,7 @@
 #include <linux/serial_core.h>
 #include <linux/console.h>
 #include <linux/pci.h>
+#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <asm/io.h>
 #include <asm/mmu.h>
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 89f005116aa..dd6c141f166 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -45,6 +45,18 @@ void machine_kexec_cleanup(struct kimage *image)
 		ppc_md.machine_kexec_cleanup(image);
 }
 
+void arch_crash_save_vmcoreinfo(void)
+{
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+	VMCOREINFO_SYMBOL(node_data);
+	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
+#endif
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+	VMCOREINFO_SYMBOL(contig_page_data);
+#endif
+}
+
 /*
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
@@ -144,24 +156,24 @@ int overlaps_crashkernel(unsigned long start, unsigned long size)
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static unsigned long kernel_end;
-static unsigned long crashk_size;
+static phys_addr_t kernel_end;
+static phys_addr_t crashk_size;
 
 static struct property kernel_end_prop = {
 	.name = "linux,kernel-end",
-	.length = sizeof(unsigned long),
+	.length = sizeof(phys_addr_t),
 	.value = &kernel_end,
 };
 
 static struct property crashk_base_prop = {
 	.name = "linux,crashkernel-base",
-	.length = sizeof(unsigned long),
+	.length = sizeof(phys_addr_t),
 	.value = &crashk_res.start,
 };
 
 static struct property crashk_size_prop = {
 	.name = "linux,crashkernel-size",
-	.length = sizeof(unsigned long),
+	.length = sizeof(phys_addr_t),
 	.value = &crashk_size,
 };
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index ed31a29c4ff..583af70c4b1 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -15,6 +15,8 @@
 #include <linux/thread_info.h>
 #include <linux/init_task.h>
 #include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/cpu.h>
 
 #include <asm/page.h>
 #include <asm/current.h>
@@ -25,6 +27,7 @@
 #include <asm/sections.h>	/* _end */
 #include <asm/prom.h>
 #include <asm/smp.h>
+#include <asm/hw_breakpoint.h>
 
 int default_machine_kexec_prepare(struct kimage *image)
 {
@@ -165,6 +168,7 @@ static void kexec_smp_down(void *arg)
 	while(kexec_all_irq_disabled == 0)
 		cpu_relax();
 	mb(); /* make sure all irqs are disabled before this */
+	hw_breakpoint_disable();
 	/*
 	 * Now every CPU has IRQs off, we can clear out any pending
 	 * IPIs and be sure that no more will come in after this.
@@ -180,8 +184,22 @@ static void kexec_prepare_cpus_wait(int wait_state)
 {
 	int my_cpu, i, notified=-1;
 
+	hw_breakpoint_disable();
 	my_cpu = get_cpu();
-	/* Make sure each CPU has atleast made it to the state we need */
+	/* Make sure each CPU has at least made it to the state we need.
+	 *
+	 * FIXME: There is a (slim) chance of a problem if not all of the CPUs
+	 * are correctly onlined.  If somehow we start a CPU on boot with RTAS
+	 * start-cpu, but somehow that CPU doesn't write callin_cpu_map[] in
+	 * time, the boot CPU will timeout.  If it does eventually execute
+	 * stuff, the secondary will start up (paca[].cpu_start was written) and
+	 * get into a peculiar state.  If the platform supports
+	 * smp_ops->take_timebase(), the secondary CPU will probably be spinning
+	 * in there.  If not (i.e. pseries), the secondary will continue on and
+	 * try to online itself/idle/etc. If it survives that, we need to find
+	 * these possible-but-not-online-but-should-be CPUs and chaperone them
+	 * into kexec_smp_wait().
+	 */
 	for_each_online_cpu(i) {
 		if (i == my_cpu)
 			continue;
@@ -189,9 +207,9 @@ static void kexec_prepare_cpus_wait(int wait_state)
 		while (paca[i].kexec_state < wait_state) {
 			barrier();
 			if (i != notified) {
-				printk( "kexec: waiting for cpu %d (physical"
-						" %d) to enter %i state\n",
-					i, paca[i].hw_cpu_id, wait_state);
+				printk(KERN_INFO "kexec: waiting for cpu %d "
+				       "(physical %d) to enter %i state\n",
+				       i, paca[i].hw_cpu_id, wait_state);
 				notified = i;
 			}
 		}
@@ -199,9 +217,32 @@ static void kexec_prepare_cpus_wait(int wait_state)
 	mb();
 }
 
-static void kexec_prepare_cpus(void)
+/*
+ * We need to make sure each present CPU is online.  The next kernel will scan
+ * the device tree and assume primary threads are online and query secondary
+ * threads via RTAS to online them if required.  If we don't online primary
+ * threads, they will be stuck.  However, we also online secondary threads as we
+ * may be using 'cede offline'.  In this case RTAS doesn't see the secondary
+ * threads as offline -- and again, these CPUs will be stuck.
+ *
+ * So, we online all CPUs that should be running, including secondary threads.
+ */
+static void wake_offline_cpus(void)
 {
+	int cpu = 0;
 
+	for_each_present_cpu(cpu) {
+		if (!cpu_online(cpu)) {
+			printk(KERN_INFO "kexec: Waking offline cpu %d.\n",
+			       cpu);
+			cpu_up(cpu);
+		}
+	}
+}
+
+static void kexec_prepare_cpus(void)
+{
+	wake_offline_cpus();
 	smp_call_function(kexec_smp_down, NULL, /* wait */0);
 	local_irq_disable();
 	mb(); /* make sure IRQs are disabled before we say they are */
@@ -215,7 +256,10 @@ static void kexec_prepare_cpus(void)
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(0, 0);
 
-	/* Before removing MMU mapings make sure all CPUs have entered real mode */
+	/*
+	 * Before removing MMU mappings make sure all CPUs have entered real
+	 * mode:
+	 */
 	kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);
 
 	put_cpu();
@@ -257,6 +301,12 @@ static void kexec_prepare_cpus(void)
 static union thread_union kexec_stack __init_task_data =
 	{ };
 
+/*
+ * For similar reasons to the stack above, the kexecing CPU needs to be on a
+ * static PACA; we switch to kexec_paca.
+ */
+struct paca_struct kexec_paca;
+
 /* Our assembly helper, in kexec_stub.S */
 extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
 					void *image, void *control,
@@ -278,12 +328,28 @@ void default_machine_kexec(struct kimage *image)
 	if (crashing_cpu == -1)
 		kexec_prepare_cpus();
 
+	pr_debug("kexec: Starting switchover sequence.\n");
+
 	/* switch to a staticly allocated stack.  Based on irq stack code.
 	 * XXX: the task struct will likely be invalid once we do the copy!
 	 */
 	kexec_stack.thread_info.task = current_thread_info()->task;
 	kexec_stack.thread_info.flags = 0;
 
+	/* We need a static PACA, too; copy this CPU's PACA over and switch to
+	 * it.  Also poison per_cpu_offset to catch anyone using non-static
+	 * data.
+	 */
+	memcpy(&kexec_paca, get_paca(), sizeof(struct paca_struct));
+	kexec_paca.data_offset = 0xedeaddeadeeeeeeeUL;
+	paca = (struct paca_struct *)RELOC_HIDE(&kexec_paca, 0) -
+		kexec_paca.paca_index;
+	setup_paca(&kexec_paca);
+
+	/* XXX: If anyone does 'dynamic lppacas' this will also need to be
+	 * switched to a static version!
+	 */
+
 	/* Some things are best done in assembly.  Finding globals with
 	 * a toc is easier in C, so pass in what we can.
 	 */
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
deleted file mode 100644
index df78e0236a0..00000000000
--- a/arch/powerpc/kernel/of_device.c
+++ /dev/null
@@ -1,133 +0,0 @@
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mod_devicetable.h>
-#include <linux/slab.h>
-#include <linux/of_device.h>
-
-#include <asm/errno.h>
-#include <asm/dcr.h>
-
-static void of_device_make_bus_id(struct of_device *dev)
-{
-	static atomic_t bus_no_reg_magic;
-	struct device_node *node = dev->dev.of_node;
-	const u32 *reg;
-	u64 addr;
-	int magic;
-
-	/*
-	 * If it's a DCR based device, use 'd' for native DCRs
-	 * and 'D' for MMIO DCRs.
-	 */
-#ifdef CONFIG_PPC_DCR
-	reg = of_get_property(node, "dcr-reg", NULL);
-	if (reg) {
-#ifdef CONFIG_PPC_DCR_NATIVE
-		dev_set_name(&dev->dev, "d%x.%s", *reg, node->name);
-#else /* CONFIG_PPC_DCR_NATIVE */
-		addr = of_translate_dcr_address(node, *reg, NULL);
-		if (addr != OF_BAD_ADDR) {
-			dev_set_name(&dev->dev, "D%llx.%s",
-				     (unsigned long long)addr, node->name);
-			return;
-		}
-#endif /* !CONFIG_PPC_DCR_NATIVE */
-	}
-#endif /* CONFIG_PPC_DCR */
-
-	/*
-	 * For MMIO, get the physical address
-	 */
-	reg = of_get_property(node, "reg", NULL);
-	if (reg) {
-		addr = of_translate_address(node, reg);
-		if (addr != OF_BAD_ADDR) {
-			dev_set_name(&dev->dev, "%llx.%s",
-				     (unsigned long long)addr, node->name);
-			return;
-		}
-	}
-
-	/*
-	 * No BusID, use the node name and add a globally incremented
-	 * counter (and pray...)
-	 */
-	magic = atomic_add_return(1, &bus_no_reg_magic);
-	dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1);
-}
-
-struct of_device *of_device_alloc(struct device_node *np,
-				  const char *bus_id,
-				  struct device *parent)
-{
-	struct of_device *dev;
-
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return NULL;
-
-	dev->dev.of_node = of_node_get(np);
-	dev->dev.dma_mask = &dev->archdata.dma_mask;
-	dev->dev.parent = parent;
-	dev->dev.release = of_release_dev;
-
-	if (bus_id)
-		dev_set_name(&dev->dev, "%s", bus_id);
-	else
-		of_device_make_bus_id(dev);
-
-	return dev;
-}
-EXPORT_SYMBOL(of_device_alloc);
-
-int of_device_uevent(struct device *dev, struct kobj_uevent_env *env)
-{
-	struct of_device *ofdev;
-	const char *compat;
-	int seen = 0, cplen, sl;
-
-	if (!dev)
-		return -ENODEV;
-
-	ofdev = to_of_device(dev);
-
-	if (add_uevent_var(env, "OF_NAME=%s", ofdev->dev.of_node->name))
-		return -ENOMEM;
-
-	if (add_uevent_var(env, "OF_TYPE=%s", ofdev->dev.of_node->type))
-		return -ENOMEM;
-
-        /* Since the compatible field can contain pretty much anything
-         * it's not really legal to split it out with commas. We split it
-         * up using a number of environment variables instead. */
-
-	compat = of_get_property(ofdev->dev.of_node, "compatible", &cplen);
-	while (compat && *compat && cplen > 0) {
-		if (add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat))
-			return -ENOMEM;
-
-		sl = strlen (compat) + 1;
-		compat += sl;
-		cplen -= sl;
-		seen++;
-	}
-
-	if (add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen))
-		return -ENOMEM;
-
-	/* modalias is trickier, we add it in 2 steps */
-	if (add_uevent_var(env, "MODALIAS="))
-		return -ENOMEM;
-	sl = of_device_get_modalias(ofdev, &env->buf[env->buflen-1],
-				    sizeof(env->buf) - env->buflen);
-	if (sl >= (sizeof(env->buf) - env->buflen))
-		return -ENOMEM;
-	env->buflen += sl;
-
-	return 0;
-}
-EXPORT_SYMBOL(of_device_uevent);
-EXPORT_SYMBOL(of_device_get_modalias);
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 487a98851ba..b2c363ef38a 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -28,207 +28,6 @@
 #include <asm/ppc-pci.h>
 #include <asm/atomic.h>
 
-/*
- * The list of OF IDs below is used for matching bus types in the
- * system whose devices are to be exposed as of_platform_devices.
- *
- * This is the default list valid for most platforms. This file provides
- * functions who can take an explicit list if necessary though
- *
- * The search is always performed recursively looking for children of
- * the provided device_node and recursively if such a children matches
- * a bus type in the list
- */
-
-static const struct of_device_id of_default_bus_ids[] = {
-	{ .type = "soc", },
-	{ .compatible = "soc", },
-	{ .type = "spider", },
-	{ .type = "axon", },
-	{ .type = "plb5", },
-	{ .type = "plb4", },
-	{ .type = "opb", },
-	{ .type = "ebc", },
-	{},
-};
-
-struct bus_type of_platform_bus_type = {
-       .uevent	= of_device_uevent,
-};
-EXPORT_SYMBOL(of_platform_bus_type);
-
-static int __init of_bus_driver_init(void)
-{
-	return of_bus_type_init(&of_platform_bus_type, "of_platform");
-}
-
-postcore_initcall(of_bus_driver_init);
-
-struct of_device* of_platform_device_create(struct device_node *np,
-					    const char *bus_id,
-					    struct device *parent)
-{
-	struct of_device *dev;
-
-	dev = of_device_alloc(np, bus_id, parent);
-	if (!dev)
-		return NULL;
-
-	dev->archdata.dma_mask = 0xffffffffUL;
-	dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
-
-	dev->dev.bus = &of_platform_bus_type;
-
-	/* We do not fill the DMA ops for platform devices by default.
-	 * This is currently the responsibility of the platform code
-	 * to do such, possibly using a device notifier
-	 */
-
-	if (of_device_register(dev) != 0) {
-		of_device_free(dev);
-		return NULL;
-	}
-
-	return dev;
-}
-EXPORT_SYMBOL(of_platform_device_create);
-
-
-
-/**
- * of_platform_bus_create - Create an OF device for a bus node and all its
- * children. Optionally recursively instanciate matching busses.
- * @bus: device node of the bus to instanciate
- * @matches: match table, NULL to use the default, OF_NO_DEEP_PROBE to
- * disallow recursive creation of child busses
- */
-static int of_platform_bus_create(const struct device_node *bus,
-				  const struct of_device_id *matches,
-				  struct device *parent)
-{
-	struct device_node *child;
-	struct of_device *dev;
-	int rc = 0;
-
-	for_each_child_of_node(bus, child) {
-		pr_debug("   create child: %s\n", child->full_name);
-		dev = of_platform_device_create(child, NULL, parent);
-		if (dev == NULL)
-			rc = -ENOMEM;
-		else if (!of_match_node(matches, child))
-			continue;
-		if (rc == 0) {
-			pr_debug("   and sub busses\n");
-			rc = of_platform_bus_create(child, matches, &dev->dev);
-		} if (rc) {
-			of_node_put(child);
-			break;
-		}
-	}
-	return rc;
-}
-
-/**
- * of_platform_bus_probe - Probe the device-tree for platform busses
- * @root: parent of the first level to probe or NULL for the root of the tree
- * @matches: match table, NULL to use the default
- * @parent: parent to hook devices from, NULL for toplevel
- *
- * Note that children of the provided root are not instanciated as devices
- * unless the specified root itself matches the bus list and is not NULL.
- */
-
-int of_platform_bus_probe(struct device_node *root,
-			  const struct of_device_id *matches,
-			  struct device *parent)
-{
-	struct device_node *child;
-	struct of_device *dev;
-	int rc = 0;
-
-	if (matches == NULL)
-		matches = of_default_bus_ids;
-	if (matches == OF_NO_DEEP_PROBE)
-		return -EINVAL;
-	if (root == NULL)
-		root = of_find_node_by_path("/");
-	else
-		of_node_get(root);
-
-	pr_debug("of_platform_bus_probe()\n");
-	pr_debug(" starting at: %s\n", root->full_name);
-
-	/* Do a self check of bus type, if there's a match, create
-	 * children
-	 */
-	if (of_match_node(matches, root)) {
-		pr_debug(" root match, create all sub devices\n");
-		dev = of_platform_device_create(root, NULL, parent);
-		if (dev == NULL) {
-			rc = -ENOMEM;
-			goto bail;
-		}
-		pr_debug(" create all sub busses\n");
-		rc = of_platform_bus_create(root, matches, &dev->dev);
-		goto bail;
-	}
-	for_each_child_of_node(root, child) {
-		if (!of_match_node(matches, child))
-			continue;
-
-		pr_debug("  match: %s\n", child->full_name);
-		dev = of_platform_device_create(child, NULL, parent);
-		if (dev == NULL)
-			rc = -ENOMEM;
-		else
-			rc = of_platform_bus_create(child, matches, &dev->dev);
-		if (rc) {
-			of_node_put(child);
-			break;
-		}
-	}
- bail:
-	of_node_put(root);
-	return rc;
-}
-EXPORT_SYMBOL(of_platform_bus_probe);
-
-static int of_dev_node_match(struct device *dev, void *data)
-{
-	return to_of_device(dev)->dev.of_node == data;
-}
-
-struct of_device *of_find_device_by_node(struct device_node *np)
-{
-	struct device *dev;
-
-	dev = bus_find_device(&of_platform_bus_type,
-			      NULL, np, of_dev_node_match);
-	if (dev)
-		return to_of_device(dev);
-	return NULL;
-}
-EXPORT_SYMBOL(of_find_device_by_node);
-
-static int of_dev_phandle_match(struct device *dev, void *data)
-{
-	phandle *ph = data;
-	return to_of_device(dev)->dev.of_node->phandle == *ph;
-}
-
-struct of_device *of_find_device_by_phandle(phandle ph)
-{
-	struct device *dev;
-
-	dev = bus_find_device(&of_platform_bus_type,
-			      NULL, &ph, of_dev_phandle_match);
-	if (dev)
-		return to_of_device(dev);
-	return NULL;
-}
-EXPORT_SYMBOL(of_find_device_by_phandle);
-
-
 #ifdef CONFIG_PPC_OF_PLATFORM_PCI
 
 /* The probing of PCI controllers from of_platform is currently
@@ -237,7 +36,7 @@ EXPORT_SYMBOL(of_find_device_by_phandle);
  * lacking some bits needed here.
  */
 
-static int __devinit of_pci_phb_probe(struct of_device *dev,
+static int __devinit of_pci_phb_probe(struct platform_device *dev,
 				      const struct of_device_id *match)
 {
 	struct pci_controller *phb;
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 139a773853f..d0a26f1770f 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -105,6 +105,16 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 #endif /* CONFIG_PPC_STD_MMU_64 */
 }
 
+/* Put the paca pointer into r13 and SPRG_PACA */
+void setup_paca(struct paca_struct *new_paca)
+{
+	local_paca = new_paca;
+	mtspr(SPRN_SPRG_PACA, local_paca);
+#ifdef CONFIG_PPC_BOOK3E
+	mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
+#endif
+}
+
 static int __initdata paca_size;
 
 void __init allocate_pacas(void)
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 5b38f6ae2b2..9021c4ad4bb 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/of_address.h>
 #include <linux/mm.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 3b4dcc82a4c..ab3e392ac63 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -101,10 +101,6 @@ EXPORT_SYMBOL(pci_dram_offset);
 EXPORT_SYMBOL(start_thread);
 EXPORT_SYMBOL(kernel_thread);
 
-#ifdef CONFIG_PPC_FPU
-EXPORT_SYMBOL_GPL(cvt_df);
-EXPORT_SYMBOL_GPL(cvt_fd);
-#endif
 EXPORT_SYMBOL(giveup_fpu);
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 773424df828..e78a5add7f1 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -37,6 +37,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/personality.h>
 #include <linux/random.h>
+#include <linux/hw_breakpoint.h>
 
 #include <asm/pgtable.h>
 #include <asm/uaccess.h>
@@ -462,14 +463,42 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	switch_booke_debug_regs(&new->thread);
 #else
+/*
+ * For PPC_BOOK3S_64, we use the hw-breakpoint interfaces that would
+ * schedule DABR
+ */
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
 	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr))
 		set_dabr(new->thread.dabr);
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
 #endif
 
 
 	new_thread = &new->thread;
 	old_thread = &current->thread;
 
+#if defined(CONFIG_PPC_BOOK3E_64)
+	/* XXX Current Book3E code doesn't deal with kernel side DBCR0,
+	 * we always hold the user values, so we set it now.
+	 *
+	 * However, we ensure the kernel MSR:DE is appropriately cleared too
+	 * to avoid spurrious single step exceptions in the kernel.
+	 *
+	 * This will have to change to merge with the ppc32 code at some point,
+	 * but I don't like much what ppc32 is doing today so there's some
+	 * thinking needed there
+	 */
+	if ((new_thread->dbcr0 | old_thread->dbcr0) & DBCR0_IDM) {
+		u32 dbcr0;
+
+		mtmsr(mfmsr() & ~MSR_DE);
+		isync();
+		dbcr0 = mfspr(SPRN_DBCR0);
+		dbcr0 = (dbcr0 & DBCR0_EDM) | new_thread->dbcr0;
+		mtspr(SPRN_DBCR0, dbcr0);
+	}
+#endif /* CONFIG_PPC64_BOOK3E */
+
 #ifdef CONFIG_PPC64
 	/*
 	 * Collect processor utilization data per process
@@ -642,7 +671,11 @@ void flush_thread(void)
 {
 	discard_lazy_cpu_state();
 
+#ifdef CONFIG_HAVE_HW_BREAKPOINTS
+	flush_ptrace_hw_breakpoint(current);
+#else /* CONFIG_HAVE_HW_BREAKPOINTS */
 	set_debug_reg_defaults(&current->thread);
+#endif /* CONFIG_HAVE_HW_BREAKPOINTS */
 }
 
 void
@@ -660,6 +693,9 @@ void prepare_to_copy(struct task_struct *tsk)
 	flush_altivec_to_thread(current);
 	flush_vsx_to_thread(current);
 	flush_spe_to_thread(current);
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	flush_ptrace_hw_breakpoint(tsk);
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
 }
 
 /*
@@ -1263,3 +1299,14 @@ unsigned long randomize_et_dyn(unsigned long base)
 
 	return ret;
 }
+
+#ifdef CONFIG_SMP
+int arch_sd_sibling_asym_packing(void)
+{
+	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+		return SD_ASYM_PACKING;
+	}
+	return 0;
+}
+#endif
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 3b6f8ae9b8c..941ff4dbc56 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -311,6 +311,24 @@ static void __init prom_print_hex(unsigned long val)
 	call_prom("write", 3, 1, _prom->stdout, buf, nibbles);
 }
 
+/* max number of decimal digits in an unsigned long */
+#define UL_DIGITS 21
+static void __init prom_print_dec(unsigned long val)
+{
+	int i, size;
+	char buf[UL_DIGITS+1];
+	struct prom_t *_prom = &RELOC(prom);
+
+	for (i = UL_DIGITS-1; i >= 0;  i--) {
+		buf[i] = (val % 10) + '0';
+		val = val/10;
+		if (val == 0)
+			break;
+	}
+	/* shift stuff down */
+	size = UL_DIGITS - i;
+	call_prom("write", 3, 1, _prom->stdout, buf+i, size);
+}
 
 static void __init prom_printf(const char *format, ...)
 {
@@ -350,6 +368,14 @@ static void __init prom_printf(const char *format, ...)
 			v = va_arg(args, unsigned long);
 			prom_print_hex(v);
 			break;
+		case 'l':
+			++q;
+			if (*q == 'u') { /* '%lu' */
+				++q;
+				v = va_arg(args, unsigned long);
+				prom_print_dec(v);
+			}
+			break;
 		}
 	}
 }
@@ -835,11 +861,11 @@ static int __init prom_count_smt_threads(void)
 		if (plen == PROM_ERROR)
 			break;
 		plen >>= 2;
-		prom_debug("Found 0x%x smt threads per core\n", (unsigned long)plen);
+		prom_debug("Found %lu smt threads per core\n", (unsigned long)plen);
 
 		/* Sanity check */
 		if (plen < 1 || plen > 64) {
-			prom_printf("Threads per core 0x%x out of bounds, assuming 1\n",
+			prom_printf("Threads per core %lu out of bounds, assuming 1\n",
 				    (unsigned long)plen);
 			return 1;
 		}
@@ -869,12 +895,12 @@ static void __init prom_send_capabilities(void)
 		cores = (u32 *)PTRRELOC(&ibm_architecture_vec[IBM_ARCH_VEC_NRCORES_OFFSET]);
 		if (*cores != NR_CPUS) {
 			prom_printf("WARNING ! "
-				    "ibm_architecture_vec structure inconsistent: 0x%x !\n",
+				    "ibm_architecture_vec structure inconsistent: %lu!\n",
 				    *cores);
 		} else {
 			*cores = DIV_ROUND_UP(NR_CPUS, prom_count_smt_threads());
-			prom_printf("Max number of cores passed to firmware: 0x%x\n",
-				    (unsigned long)*cores);
+			prom_printf("Max number of cores passed to firmware: %lu (NR_CPUS = %lu)\n",
+				    *cores, NR_CPUS);
 		}
 
 		/* try calling the ibm,client-architecture-support method */
@@ -1482,7 +1508,7 @@ static void __init prom_hold_cpus(void)
 		reg = -1;
 		prom_getprop(node, "reg", &reg, sizeof(reg));
 
-		prom_debug("cpu hw idx   = 0x%x\n", reg);
+		prom_debug("cpu hw idx   = %lu\n", reg);
 
 		/* Init the acknowledge var which will be reset by
 		 * the secondary cpu when it awakens from its OF
@@ -1492,7 +1518,7 @@ static void __init prom_hold_cpus(void)
 
 		if (reg != _prom->cpu) {
 			/* Primary Thread of non-boot cpu */
-			prom_printf("starting cpu hw idx %x... ", reg);
+			prom_printf("starting cpu hw idx %lu... ", reg);
 			call_prom("start-cpu", 3, 0, node,
 				  secondary_hold, reg);
 
@@ -1507,7 +1533,7 @@ static void __init prom_hold_cpus(void)
 		}
 #ifdef CONFIG_SMP
 		else
-			prom_printf("boot cpu hw idx %x\n", reg);
+			prom_printf("boot cpu hw idx %lu\n", reg);
 #endif /* CONFIG_SMP */
 	}
 
@@ -2420,7 +2446,7 @@ static void __init prom_find_boot_cpu(void)
 	prom_getprop(cpu_pkg, "reg", &getprop_rval, sizeof(getprop_rval));
 	_prom->cpu = getprop_rval;
 
-	prom_debug("Booting CPU hw index = 0x%x\n", _prom->cpu);
+	prom_debug("Booting CPU hw index = %lu\n", _prom->cpu);
 }
 
 static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index 8362620c9e6..88334af038e 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -6,232 +6,11 @@
 #include <linux/module.h>
 #include <linux/ioport.h>
 #include <linux/etherdevice.h>
+#include <linux/of_address.h>
 #include <asm/prom.h>
 #include <asm/pci-bridge.h>
 
-#ifdef DEBUG
-#define DBG(fmt...) do { printk(fmt); } while(0)
-#else
-#define DBG(fmt...) do { } while(0)
-#endif
-
-#ifdef CONFIG_PPC64
-#define PRu64	"%lx"
-#else
-#define PRu64	"%llx"
-#endif
-
-/* Max address size we deal with */
-#define OF_MAX_ADDR_CELLS	4
-#define OF_CHECK_COUNTS(na, ns)	((na) > 0 && (na) <= OF_MAX_ADDR_CELLS && \
-			(ns) > 0)
-
-static struct of_bus *of_match_bus(struct device_node *np);
-static int __of_address_to_resource(struct device_node *dev,
-		const u32 *addrp, u64 size, unsigned int flags,
-		struct resource *r);
-
-
-/* Debug utility */
-#ifdef DEBUG
-static void of_dump_addr(const char *s, const u32 *addr, int na)
-{
-	printk("%s", s);
-	while(na--)
-		printk(" %08x", *(addr++));
-	printk("\n");
-}
-#else
-static void of_dump_addr(const char *s, const u32 *addr, int na) { }
-#endif
-
-
-/* Callbacks for bus specific translators */
-struct of_bus {
-	const char	*name;
-	const char	*addresses;
-	int		(*match)(struct device_node *parent);
-	void		(*count_cells)(struct device_node *child,
-				       int *addrc, int *sizec);
-	u64		(*map)(u32 *addr, const u32 *range,
-				int na, int ns, int pna);
-	int		(*translate)(u32 *addr, u64 offset, int na);
-	unsigned int	(*get_flags)(const u32 *addr);
-};
-
-
-/*
- * Default translator (generic bus)
- */
-
-static void of_bus_default_count_cells(struct device_node *dev,
-				       int *addrc, int *sizec)
-{
-	if (addrc)
-		*addrc = of_n_addr_cells(dev);
-	if (sizec)
-		*sizec = of_n_size_cells(dev);
-}
-
-static u64 of_bus_default_map(u32 *addr, const u32 *range,
-		int na, int ns, int pna)
-{
-	u64 cp, s, da;
-
-	cp = of_read_number(range, na);
-	s  = of_read_number(range + na + pna, ns);
-	da = of_read_number(addr, na);
-
-	DBG("OF: default map, cp="PRu64", s="PRu64", da="PRu64"\n",
-	    cp, s, da);
-
-	if (da < cp || da >= (cp + s))
-		return OF_BAD_ADDR;
-	return da - cp;
-}
-
-static int of_bus_default_translate(u32 *addr, u64 offset, int na)
-{
-	u64 a = of_read_number(addr, na);
-	memset(addr, 0, na * 4);
-	a += offset;
-	if (na > 1)
-		addr[na - 2] = a >> 32;
-	addr[na - 1] = a & 0xffffffffu;
-
-	return 0;
-}
-
-static unsigned int of_bus_default_get_flags(const u32 *addr)
-{
-	return IORESOURCE_MEM;
-}
-
-
 #ifdef CONFIG_PCI
-/*
- * PCI bus specific translator
- */
-
-static int of_bus_pci_match(struct device_node *np)
-{
-	/* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */
-	return !strcmp(np->type, "pci") || !strcmp(np->type, "vci");
-}
-
-static void of_bus_pci_count_cells(struct device_node *np,
-				   int *addrc, int *sizec)
-{
-	if (addrc)
-		*addrc = 3;
-	if (sizec)
-		*sizec = 2;
-}
-
-static unsigned int of_bus_pci_get_flags(const u32 *addr)
-{
-	unsigned int flags = 0;
-	u32 w = addr[0];
-
-	switch((w >> 24) & 0x03) {
-	case 0x01:
-		flags |= IORESOURCE_IO;
-		break;
-	case 0x02: /* 32 bits */
-	case 0x03: /* 64 bits */
-		flags |= IORESOURCE_MEM;
-		break;
-	}
-	if (w & 0x40000000)
-		flags |= IORESOURCE_PREFETCH;
-	return flags;
-}
-
-static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna)
-{
-	u64 cp, s, da;
-	unsigned int af, rf;
-
-	af = of_bus_pci_get_flags(addr);
-	rf = of_bus_pci_get_flags(range);
-
-	/* Check address type match */
-	if ((af ^ rf) & (IORESOURCE_MEM | IORESOURCE_IO))
-		return OF_BAD_ADDR;
-
-	/* Read address values, skipping high cell */
-	cp = of_read_number(range + 1, na - 1);
-	s  = of_read_number(range + na + pna, ns);
-	da = of_read_number(addr + 1, na - 1);
-
-	DBG("OF: PCI map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da);
-
-	if (da < cp || da >= (cp + s))
-		return OF_BAD_ADDR;
-	return da - cp;
-}
-
-static int of_bus_pci_translate(u32 *addr, u64 offset, int na)
-{
-	return of_bus_default_translate(addr + 1, offset, na - 1);
-}
-
-const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size,
-			unsigned int *flags)
-{
-	const u32 *prop;
-	unsigned int psize;
-	struct device_node *parent;
-	struct of_bus *bus;
-	int onesize, i, na, ns;
-
-	/* Get parent & match bus type */
-	parent = of_get_parent(dev);
-	if (parent == NULL)
-		return NULL;
-	bus = of_match_bus(parent);
-	if (strcmp(bus->name, "pci")) {
-		of_node_put(parent);
-		return NULL;
-	}
-	bus->count_cells(dev, &na, &ns);
-	of_node_put(parent);
-	if (!OF_CHECK_COUNTS(na, ns))
-		return NULL;
-
-	/* Get "reg" or "assigned-addresses" property */
-	prop = of_get_property(dev, bus->addresses, &psize);
-	if (prop == NULL)
-		return NULL;
-	psize /= 4;
-
-	onesize = na + ns;
-	for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++)
-		if ((prop[0] & 0xff) == ((bar_no * 4) + PCI_BASE_ADDRESS_0)) {
-			if (size)
-				*size = of_read_number(prop + na, ns);
-			if (flags)
-				*flags = bus->get_flags(prop);
-			return prop;
-		}
-	return NULL;
-}
-EXPORT_SYMBOL(of_get_pci_address);
-
-int of_pci_address_to_resource(struct device_node *dev, int bar,
-			       struct resource *r)
-{
-	const u32	*addrp;
-	u64		size;
-	unsigned int	flags;
-
-	addrp = of_get_pci_address(dev, bar, &size, &flags);
-	if (addrp == NULL)
-		return -EINVAL;
-	return __of_address_to_resource(dev, addrp, size, flags, r);
-}
-EXPORT_SYMBOL_GPL(of_pci_address_to_resource);
-
 int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
 {
 	struct device_node *dn, *ppnode;
@@ -313,345 +92,6 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
 EXPORT_SYMBOL_GPL(of_irq_map_pci);
 #endif /* CONFIG_PCI */
 
-/*
- * ISA bus specific translator
- */
-
-static int of_bus_isa_match(struct device_node *np)
-{
-	return !strcmp(np->name, "isa");
-}
-
-static void of_bus_isa_count_cells(struct device_node *child,
-				   int *addrc, int *sizec)
-{
-	if (addrc)
-		*addrc = 2;
-	if (sizec)
-		*sizec = 1;
-}
-
-static u64 of_bus_isa_map(u32 *addr, const u32 *range, int na, int ns, int pna)
-{
-	u64 cp, s, da;
-
-	/* Check address type match */
-	if ((addr[0] ^ range[0]) & 0x00000001)
-		return OF_BAD_ADDR;
-
-	/* Read address values, skipping high cell */
-	cp = of_read_number(range + 1, na - 1);
-	s  = of_read_number(range + na + pna, ns);
-	da = of_read_number(addr + 1, na - 1);
-
-	DBG("OF: ISA map, cp="PRu64", s="PRu64", da="PRu64"\n", cp, s, da);
-
-	if (da < cp || da >= (cp + s))
-		return OF_BAD_ADDR;
-	return da - cp;
-}
-
-static int of_bus_isa_translate(u32 *addr, u64 offset, int na)
-{
-	return of_bus_default_translate(addr + 1, offset, na - 1);
-}
-
-static unsigned int of_bus_isa_get_flags(const u32 *addr)
-{
-	unsigned int flags = 0;
-	u32 w = addr[0];
-
-	if (w & 1)
-		flags |= IORESOURCE_IO;
-	else
-		flags |= IORESOURCE_MEM;
-	return flags;
-}
-
-
-/*
- * Array of bus specific translators
- */
-
-static struct of_bus of_busses[] = {
-#ifdef CONFIG_PCI
-	/* PCI */
-	{
-		.name = "pci",
-		.addresses = "assigned-addresses",
-		.match = of_bus_pci_match,
-		.count_cells = of_bus_pci_count_cells,
-		.map = of_bus_pci_map,
-		.translate = of_bus_pci_translate,
-		.get_flags = of_bus_pci_get_flags,
-	},
-#endif /* CONFIG_PCI */
-	/* ISA */
-	{
-		.name = "isa",
-		.addresses = "reg",
-		.match = of_bus_isa_match,
-		.count_cells = of_bus_isa_count_cells,
-		.map = of_bus_isa_map,
-		.translate = of_bus_isa_translate,
-		.get_flags = of_bus_isa_get_flags,
-	},
-	/* Default */
-	{
-		.name = "default",
-		.addresses = "reg",
-		.match = NULL,
-		.count_cells = of_bus_default_count_cells,
-		.map = of_bus_default_map,
-		.translate = of_bus_default_translate,
-		.get_flags = of_bus_default_get_flags,
-	},
-};
-
-static struct of_bus *of_match_bus(struct device_node *np)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(of_busses); i ++)
-		if (!of_busses[i].match || of_busses[i].match(np))
-			return &of_busses[i];
-	BUG();
-	return NULL;
-}
-
-static int of_translate_one(struct device_node *parent, struct of_bus *bus,
-			    struct of_bus *pbus, u32 *addr,
-			    int na, int ns, int pna, const char *rprop)
-{
-	const u32 *ranges;
-	unsigned int rlen;
-	int rone;
-	u64 offset = OF_BAD_ADDR;
-
-	/* Normally, an absence of a "ranges" property means we are
-	 * crossing a non-translatable boundary, and thus the addresses
-	 * below the current not cannot be converted to CPU physical ones.
-	 * Unfortunately, while this is very clear in the spec, it's not
-	 * what Apple understood, and they do have things like /uni-n or
-	 * /ht nodes with no "ranges" property and a lot of perfectly
-	 * useable mapped devices below them. Thus we treat the absence of
-	 * "ranges" as equivalent to an empty "ranges" property which means
-	 * a 1:1 translation at that level. It's up to the caller not to try
-	 * to translate addresses that aren't supposed to be translated in
-	 * the first place. --BenH.
-	 */
-	ranges = of_get_property(parent, rprop, &rlen);
-	if (ranges == NULL || rlen == 0) {
-		offset = of_read_number(addr, na);
-		memset(addr, 0, pna * 4);
-		DBG("OF: no ranges, 1:1 translation\n");
-		goto finish;
-	}
-
-	DBG("OF: walking ranges...\n");
-
-	/* Now walk through the ranges */
-	rlen /= 4;
-	rone = na + pna + ns;
-	for (; rlen >= rone; rlen -= rone, ranges += rone) {
-		offset = bus->map(addr, ranges, na, ns, pna);
-		if (offset != OF_BAD_ADDR)
-			break;
-	}
-	if (offset == OF_BAD_ADDR) {
-		DBG("OF: not found !\n");
-		return 1;
-	}
-	memcpy(addr, ranges + na, 4 * pna);
-
- finish:
-	of_dump_addr("OF: parent translation for:", addr, pna);
-	DBG("OF: with offset: "PRu64"\n", offset);
-
-	/* Translate it into parent bus space */
-	return pbus->translate(addr, offset, pna);
-}
-
-
-/*
- * Translate an address from the device-tree into a CPU physical address,
- * this walks up the tree and applies the various bus mappings on the
- * way.
- *
- * Note: We consider that crossing any level with #size-cells == 0 to mean
- * that translation is impossible (that is we are not dealing with a value
- * that can be mapped to a cpu physical address). This is not really specified
- * that way, but this is traditionally the way IBM at least do things
- */
-u64 __of_translate_address(struct device_node *dev, const u32 *in_addr,
-			   const char *rprop)
-{
-	struct device_node *parent = NULL;
-	struct of_bus *bus, *pbus;
-	u32 addr[OF_MAX_ADDR_CELLS];
-	int na, ns, pna, pns;
-	u64 result = OF_BAD_ADDR;
-
-	DBG("OF: ** translation for device %s **\n", dev->full_name);
-
-	/* Increase refcount at current level */
-	of_node_get(dev);
-
-	/* Get parent & match bus type */
-	parent = of_get_parent(dev);
-	if (parent == NULL)
-		goto bail;
-	bus = of_match_bus(parent);
-
-	/* Cound address cells & copy address locally */
-	bus->count_cells(dev, &na, &ns);
-	if (!OF_CHECK_COUNTS(na, ns)) {
-		printk(KERN_ERR "prom_parse: Bad cell count for %s\n",
-		       dev->full_name);
-		goto bail;
-	}
-	memcpy(addr, in_addr, na * 4);
-
-	DBG("OF: bus is %s (na=%d, ns=%d) on %s\n",
-	    bus->name, na, ns, parent->full_name);
-	of_dump_addr("OF: translating address:", addr, na);
-
-	/* Translate */
-	for (;;) {
-		/* Switch to parent bus */
-		of_node_put(dev);
-		dev = parent;
-		parent = of_get_parent(dev);
-
-		/* If root, we have finished */
-		if (parent == NULL) {
-			DBG("OF: reached root node\n");
-			result = of_read_number(addr, na);
-			break;
-		}
-
-		/* Get new parent bus and counts */
-		pbus = of_match_bus(parent);
-		pbus->count_cells(dev, &pna, &pns);
-		if (!OF_CHECK_COUNTS(pna, pns)) {
-			printk(KERN_ERR "prom_parse: Bad cell count for %s\n",
-			       dev->full_name);
-			break;
-		}
-
-		DBG("OF: parent bus is %s (na=%d, ns=%d) on %s\n",
-		    pbus->name, pna, pns, parent->full_name);
-
-		/* Apply bus translation */
-		if (of_translate_one(dev, bus, pbus, addr, na, ns, pna, rprop))
-			break;
-
-		/* Complete the move up one level */
-		na = pna;
-		ns = pns;
-		bus = pbus;
-
-		of_dump_addr("OF: one level translation:", addr, na);
-	}
- bail:
-	of_node_put(parent);
-	of_node_put(dev);
-
-	return result;
-}
-
-u64 of_translate_address(struct device_node *dev, const u32 *in_addr)
-{
-	return __of_translate_address(dev, in_addr, "ranges");
-}
-EXPORT_SYMBOL(of_translate_address);
-
-u64 of_translate_dma_address(struct device_node *dev, const u32 *in_addr)
-{
-	return __of_translate_address(dev, in_addr, "dma-ranges");
-}
-EXPORT_SYMBOL(of_translate_dma_address);
-
-const u32 *of_get_address(struct device_node *dev, int index, u64 *size,
-		    unsigned int *flags)
-{
-	const u32 *prop;
-	unsigned int psize;
-	struct device_node *parent;
-	struct of_bus *bus;
-	int onesize, i, na, ns;
-
-	/* Get parent & match bus type */
-	parent = of_get_parent(dev);
-	if (parent == NULL)
-		return NULL;
-	bus = of_match_bus(parent);
-	bus->count_cells(dev, &na, &ns);
-	of_node_put(parent);
-	if (!OF_CHECK_COUNTS(na, ns))
-		return NULL;
-
-	/* Get "reg" or "assigned-addresses" property */
-	prop = of_get_property(dev, bus->addresses, &psize);
-	if (prop == NULL)
-		return NULL;
-	psize /= 4;
-
-	onesize = na + ns;
-	for (i = 0; psize >= onesize; psize -= onesize, prop += onesize, i++)
-		if (i == index) {
-			if (size)
-				*size = of_read_number(prop + na, ns);
-			if (flags)
-				*flags = bus->get_flags(prop);
-			return prop;
-		}
-	return NULL;
-}
-EXPORT_SYMBOL(of_get_address);
-
-static int __of_address_to_resource(struct device_node *dev, const u32 *addrp,
-				    u64 size, unsigned int flags,
-				    struct resource *r)
-{
-	u64 taddr;
-
-	if ((flags & (IORESOURCE_IO | IORESOURCE_MEM)) == 0)
-		return -EINVAL;
-	taddr = of_translate_address(dev, addrp);
-	if (taddr == OF_BAD_ADDR)
-		return -EINVAL;
-	memset(r, 0, sizeof(struct resource));
-	if (flags & IORESOURCE_IO) {
-		unsigned long port;
-		port = pci_address_to_pio(taddr);
-		if (port == (unsigned long)-1)
-			return -EINVAL;
-		r->start = port;
-		r->end = port + size - 1;
-	} else {
-		r->start = taddr;
-		r->end = taddr + size - 1;
-	}
-	r->flags = flags;
-	r->name = dev->name;
-	return 0;
-}
-
-int of_address_to_resource(struct device_node *dev, int index,
-			   struct resource *r)
-{
-	const u32	*addrp;
-	u64		size;
-	unsigned int	flags;
-
-	addrp = of_get_address(dev, index, &size, &flags);
-	if (addrp == NULL)
-		return -EINVAL;
-	return __of_address_to_resource(dev, addrp, size, flags, r);
-}
-EXPORT_SYMBOL_GPL(of_address_to_resource);
-
 void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 		unsigned long *busno, unsigned long *phys, unsigned long *size)
 {
@@ -678,342 +118,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 	*size = of_read_number(dma_window, cells);
 }
 
-/*
- * Interrupt remapper
- */
-
-static unsigned int of_irq_workarounds;
-static struct device_node *of_irq_dflt_pic;
-
-static struct device_node *of_irq_find_parent(struct device_node *child)
-{
-	struct device_node *p;
-	const phandle *parp;
-
-	if (!of_node_get(child))
-		return NULL;
-
-	do {
-		parp = of_get_property(child, "interrupt-parent", NULL);
-		if (parp == NULL)
-			p = of_get_parent(child);
-		else {
-			if (of_irq_workarounds & OF_IMAP_NO_PHANDLE)
-				p = of_node_get(of_irq_dflt_pic);
-			else
-				p = of_find_node_by_phandle(*parp);
-		}
-		of_node_put(child);
-		child = p;
-	} while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL);
-
-	return p;
-}
-
-/* This doesn't need to be called if you don't have any special workaround
- * flags to pass
- */
-void of_irq_map_init(unsigned int flags)
-{
-	of_irq_workarounds = flags;
-
-	/* OldWorld, don't bother looking at other things */
-	if (flags & OF_IMAP_OLDWORLD_MAC)
-		return;
-
-	/* If we don't have phandles, let's try to locate a default interrupt
-	 * controller (happens when booting with BootX). We do a first match
-	 * here, hopefully, that only ever happens on machines with one
-	 * controller.
-	 */
-	if (flags & OF_IMAP_NO_PHANDLE) {
-		struct device_node *np;
-
-		for_each_node_with_property(np, "interrupt-controller") {
-			/* Skip /chosen/interrupt-controller */
-			if (strcmp(np->name, "chosen") == 0)
-				continue;
-			/* It seems like at least one person on this planet wants
-			 * to use BootX on a machine with an AppleKiwi controller
-			 * which happens to pretend to be an interrupt
-			 * controller too.
-			 */
-			if (strcmp(np->name, "AppleKiwi") == 0)
-				continue;
-			/* I think we found one ! */
-			of_irq_dflt_pic = np;
-			break;
-		}
-	}
-
-}
-
-int of_irq_map_raw(struct device_node *parent, const u32 *intspec, u32 ointsize,
-		const u32 *addr, struct of_irq *out_irq)
-{
-	struct device_node *ipar, *tnode, *old = NULL, *newpar = NULL;
-	const u32 *tmp, *imap, *imask;
-	u32 intsize = 1, addrsize, newintsize = 0, newaddrsize = 0;
-	int imaplen, match, i;
-
-	DBG("of_irq_map_raw: par=%s,intspec=[0x%08x 0x%08x...],ointsize=%d\n",
-	    parent->full_name, intspec[0], intspec[1], ointsize);
-
-	ipar = of_node_get(parent);
-
-	/* First get the #interrupt-cells property of the current cursor
-	 * that tells us how to interpret the passed-in intspec. If there
-	 * is none, we are nice and just walk up the tree
-	 */
-	do {
-		tmp = of_get_property(ipar, "#interrupt-cells", NULL);
-		if (tmp != NULL) {
-			intsize = *tmp;
-			break;
-		}
-		tnode = ipar;
-		ipar = of_irq_find_parent(ipar);
-		of_node_put(tnode);
-	} while (ipar);
-	if (ipar == NULL) {
-		DBG(" -> no parent found !\n");
-		goto fail;
-	}
-
-	DBG("of_irq_map_raw: ipar=%s, size=%d\n", ipar->full_name, intsize);
-
-	if (ointsize != intsize)
-		return -EINVAL;
-
-	/* Look for this #address-cells. We have to implement the old linux
-	 * trick of looking for the parent here as some device-trees rely on it
-	 */
-	old = of_node_get(ipar);
-	do {
-		tmp = of_get_property(old, "#address-cells", NULL);
-		tnode = of_get_parent(old);
-		of_node_put(old);
-		old = tnode;
-	} while(old && tmp == NULL);
-	of_node_put(old);
-	old = NULL;
-	addrsize = (tmp == NULL) ? 2 : *tmp;
-
-	DBG(" -> addrsize=%d\n", addrsize);
-
-	/* Now start the actual "proper" walk of the interrupt tree */
-	while (ipar != NULL) {
-		/* Now check if cursor is an interrupt-controller and if it is
-		 * then we are done
-		 */
-		if (of_get_property(ipar, "interrupt-controller", NULL) !=
-				NULL) {
-			DBG(" -> got it !\n");
-			memcpy(out_irq->specifier, intspec,
-			       intsize * sizeof(u32));
-			out_irq->size = intsize;
-			out_irq->controller = ipar;
-			of_node_put(old);
-			return 0;
-		}
-
-		/* Now look for an interrupt-map */
-		imap = of_get_property(ipar, "interrupt-map", &imaplen);
-		/* No interrupt map, check for an interrupt parent */
-		if (imap == NULL) {
-			DBG(" -> no map, getting parent\n");
-			newpar = of_irq_find_parent(ipar);
-			goto skiplevel;
-		}
-		imaplen /= sizeof(u32);
-
-		/* Look for a mask */
-		imask = of_get_property(ipar, "interrupt-map-mask", NULL);
-
-		/* If we were passed no "reg" property and we attempt to parse
-		 * an interrupt-map, then #address-cells must be 0.
-		 * Fail if it's not.
-		 */
-		if (addr == NULL && addrsize != 0) {
-			DBG(" -> no reg passed in when needed !\n");
-			goto fail;
-		}
-
-		/* Parse interrupt-map */
-		match = 0;
-		while (imaplen > (addrsize + intsize + 1) && !match) {
-			/* Compare specifiers */
-			match = 1;
-			for (i = 0; i < addrsize && match; ++i) {
-				u32 mask = imask ? imask[i] : 0xffffffffu;
-				match = ((addr[i] ^ imap[i]) & mask) == 0;
-			}
-			for (; i < (addrsize + intsize) && match; ++i) {
-				u32 mask = imask ? imask[i] : 0xffffffffu;
-				match =
-				   ((intspec[i-addrsize] ^ imap[i]) & mask) == 0;
-			}
-			imap += addrsize + intsize;
-			imaplen -= addrsize + intsize;
-
-			DBG(" -> match=%d (imaplen=%d)\n", match, imaplen);
-
-			/* Get the interrupt parent */
-			if (of_irq_workarounds & OF_IMAP_NO_PHANDLE)
-				newpar = of_node_get(of_irq_dflt_pic);
-			else
-				newpar = of_find_node_by_phandle((phandle)*imap);
-			imap++;
-			--imaplen;
-
-			/* Check if not found */
-			if (newpar == NULL) {
-				DBG(" -> imap parent not found !\n");
-				goto fail;
-			}
-
-			/* Get #interrupt-cells and #address-cells of new
-			 * parent
-			 */
-			tmp = of_get_property(newpar, "#interrupt-cells", NULL);
-			if (tmp == NULL) {
-				DBG(" -> parent lacks #interrupt-cells !\n");
-				goto fail;
-			}
-			newintsize = *tmp;
-			tmp = of_get_property(newpar, "#address-cells", NULL);
-			newaddrsize = (tmp == NULL) ? 0 : *tmp;
-
-			DBG(" -> newintsize=%d, newaddrsize=%d\n",
-			    newintsize, newaddrsize);
-
-			/* Check for malformed properties */
-			if (imaplen < (newaddrsize + newintsize))
-				goto fail;
-
-			imap += newaddrsize + newintsize;
-			imaplen -= newaddrsize + newintsize;
-
-			DBG(" -> imaplen=%d\n", imaplen);
-		}
-		if (!match)
-			goto fail;
-
-		of_node_put(old);
-		old = of_node_get(newpar);
-		addrsize = newaddrsize;
-		intsize = newintsize;
-		intspec = imap - intsize;
-		addr = intspec - addrsize;
-
-	skiplevel:
-		/* Iterate again with new parent */
-		DBG(" -> new parent: %s\n", newpar ? newpar->full_name : "<>");
-		of_node_put(ipar);
-		ipar = newpar;
-		newpar = NULL;
-	}
- fail:
-	of_node_put(ipar);
-	of_node_put(old);
-	of_node_put(newpar);
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(of_irq_map_raw);
-
-#if defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)
-static int of_irq_map_oldworld(struct device_node *device, int index,
-			       struct of_irq *out_irq)
-{
-	const u32 *ints = NULL;
-	int intlen;
-
-	/*
-	 * Old machines just have a list of interrupt numbers
-	 * and no interrupt-controller nodes. We also have dodgy
-	 * cases where the APPL,interrupts property is completely
-	 * missing behind pci-pci bridges and we have to get it
-	 * from the parent (the bridge itself, as apple just wired
-	 * everything together on these)
-	 */
-	while (device) {
-		ints = of_get_property(device, "AAPL,interrupts", &intlen);
-		if (ints != NULL)
-			break;
-		device = device->parent;
-		if (device && strcmp(device->type, "pci") != 0)
-			break;
-	}
-	if (ints == NULL)
-		return -EINVAL;
-	intlen /= sizeof(u32);
-
-	if (index >= intlen)
-		return -EINVAL;
-
-	out_irq->controller = NULL;
-	out_irq->specifier[0] = ints[index];
-	out_irq->size = 1;
-
-	return 0;
-}
-#else /* defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32) */
-static int of_irq_map_oldworld(struct device_node *device, int index,
-			       struct of_irq *out_irq)
-{
-	return -EINVAL;
-}
-#endif /* !(defined(CONFIG_PPC_PMAC) && defined(CONFIG_PPC32)) */
-
-int of_irq_map_one(struct device_node *device, int index, struct of_irq *out_irq)
-{
-	struct device_node *p;
-	const u32 *intspec, *tmp, *addr;
-	u32 intsize, intlen;
-	int res = -EINVAL;
-
-	DBG("of_irq_map_one: dev=%s, index=%d\n", device->full_name, index);
-
-	/* OldWorld mac stuff is "special", handle out of line */
-	if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)
-		return of_irq_map_oldworld(device, index, out_irq);
-
-	/* Get the interrupts property */
-	intspec = of_get_property(device, "interrupts", &intlen);
-	if (intspec == NULL)
-		return -EINVAL;
-	intlen /= sizeof(u32);
-
-	/* Get the reg property (if any) */
-	addr = of_get_property(device, "reg", NULL);
-
-	/* Look for the interrupt parent. */
-	p = of_irq_find_parent(device);
-	if (p == NULL)
-		return -EINVAL;
-
-	/* Get size of interrupt specifier */
-	tmp = of_get_property(p, "#interrupt-cells", NULL);
-	if (tmp == NULL)
-		goto out;
-	intsize = *tmp;
-
-	DBG(" intsize=%d intlen=%d\n", intsize, intlen);
-
-	/* Check index */
-	if ((index + 1) * intsize > intlen)
-		goto out;
-
-	/* Get new specifier and map it */
-	res = of_irq_map_raw(p, intspec + index * intsize, intsize,
-			     addr, out_irq);
-out:
-	of_node_put(p);
-	return res;
-}
-EXPORT_SYMBOL_GPL(of_irq_map_one);
-
 /**
  * Search the device tree for the best MAC address to use.  'mac-address' is
  * checked first, because that is supposed to contain to "most recent" MAC
@@ -1051,29 +155,3 @@ const void *of_get_mac_address(struct device_node *np)
 	return NULL;
 }
 EXPORT_SYMBOL(of_get_mac_address);
-
-int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
-{
-	int irq = irq_of_parse_and_map(dev, index);
-
-	/* Only dereference the resource if both the
-	 * resource and the irq are valid. */
-	if (r && irq != NO_IRQ) {
-		r->start = r->end = irq;
-		r->flags = IORESOURCE_IRQ;
-	}
-
-	return irq;
-}
-EXPORT_SYMBOL_GPL(of_irq_to_resource);
-
-void __iomem *of_iomap(struct device_node *np, int index)
-{
-	struct resource res;
-
-	if (of_address_to_resource(np, index, &res))
-		return NULL;
-
-	return ioremap(res.start, 1 + res.end - res.start);
-}
-EXPORT_SYMBOL(of_iomap);
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 7a0c0199ea2..11f3cd9c832 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -32,6 +32,8 @@
 #ifdef CONFIG_PPC32
 #include <linux/module.h>
 #endif
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -866,9 +868,34 @@ void user_disable_single_step(struct task_struct *task)
 	clear_tsk_thread_flag(task, TIF_SINGLESTEP);
 }
 
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+void ptrace_triggered(struct perf_event *bp, int nmi,
+		      struct perf_sample_data *data, struct pt_regs *regs)
+{
+	struct perf_event_attr attr;
+
+	/*
+	 * Disable the breakpoint request here since ptrace has defined a
+	 * one-shot behaviour for breakpoint exceptions in PPC64.
+	 * The SIGTRAP signal is generated automatically for us in do_dabr().
+	 * We don't have to do anything about that here
+	 */
+	attr = bp->attr;
+	attr.disabled = true;
+	modify_user_hw_breakpoint(bp, &attr);
+}
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
 int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 			       unsigned long data)
 {
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	int ret;
+	struct thread_struct *thread = &(task->thread);
+	struct perf_event *bp;
+	struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
 	/* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
 	 *  For embedded processors we support one DAC and no IAC's at the
 	 *  moment.
@@ -896,6 +923,43 @@ int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 	/* Ensure breakpoint translation bit is set */
 	if (data && !(data & DABR_TRANSLATION))
 		return -EIO;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	bp = thread->ptrace_bps[0];
+	if ((!data) || !(data & (DABR_DATA_WRITE | DABR_DATA_READ))) {
+		if (bp) {
+			unregister_hw_breakpoint(bp);
+			thread->ptrace_bps[0] = NULL;
+		}
+		return 0;
+	}
+	if (bp) {
+		attr = bp->attr;
+		attr.bp_addr = data & ~HW_BREAKPOINT_ALIGN;
+		arch_bp_generic_fields(data &
+					(DABR_DATA_WRITE | DABR_DATA_READ),
+							&attr.bp_type);
+		ret =  modify_user_hw_breakpoint(bp, &attr);
+		if (ret)
+			return ret;
+		thread->ptrace_bps[0] = bp;
+		thread->dabr = data;
+		return 0;
+	}
+
+	/* Create a new breakpoint request if one doesn't exist already */
+	hw_breakpoint_init(&attr);
+	attr.bp_addr = data & ~HW_BREAKPOINT_ALIGN;
+	arch_bp_generic_fields(data & (DABR_DATA_WRITE | DABR_DATA_READ),
+								&attr.bp_type);
+
+	thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
+							ptrace_triggered, task);
+	if (IS_ERR(bp)) {
+		thread->ptrace_bps[0] = NULL;
+		return PTR_ERR(bp);
+	}
+
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
 
 	/* Move contents to the DABR register */
 	task->thread.dabr = data;
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index d0516dbee76..41048de3c6c 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -47,14 +47,6 @@ struct rtas_t rtas = {
 };
 EXPORT_SYMBOL(rtas);
 
-struct rtas_suspend_me_data {
-	atomic_t working; /* number of cpus accessing this struct */
-	atomic_t done;
-	int token; /* ibm,suspend-me */
-	int error;
-	struct completion *complete; /* wait on this until working == 0 */
-};
-
 DEFINE_SPINLOCK(rtas_data_buf_lock);
 EXPORT_SYMBOL(rtas_data_buf_lock);
 
@@ -714,14 +706,53 @@ void rtas_os_term(char *str)
 
 static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
 #ifdef CONFIG_PPC_PSERIES
-static void rtas_percpu_suspend_me(void *info)
+static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
+{
+	u16 slb_size = mmu_slb_size;
+	int rc = H_MULTI_THREADS_ACTIVE;
+	int cpu;
+
+	slb_set_size(SLB_MIN_SIZE);
+	printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
+
+	while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
+	       !atomic_read(&data->error))
+		rc = rtas_call(data->token, 0, 1, NULL);
+
+	if (rc || atomic_read(&data->error)) {
+		printk(KERN_DEBUG "ibm,suspend-me returned %d\n", rc);
+		slb_set_size(slb_size);
+	}
+
+	if (atomic_read(&data->error))
+		rc = atomic_read(&data->error);
+
+	atomic_set(&data->error, rc);
+
+	if (wake_when_done) {
+		atomic_set(&data->done, 1);
+
+		for_each_online_cpu(cpu)
+			plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
+	}
+
+	if (atomic_dec_return(&data->working) == 0)
+		complete(data->complete);
+
+	return rc;
+}
+
+int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data)
+{
+	atomic_inc(&data->working);
+	return __rtas_suspend_last_cpu(data, 0);
+}
+
+static int __rtas_suspend_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
 {
 	long rc = H_SUCCESS;
 	unsigned long msr_save;
-	u16 slb_size = mmu_slb_size;
 	int cpu;
-	struct rtas_suspend_me_data *data =
-		(struct rtas_suspend_me_data *)info;
 
 	atomic_inc(&data->working);
 
@@ -729,7 +760,7 @@ static void rtas_percpu_suspend_me(void *info)
 	msr_save = mfmsr();
 	mtmsr(msr_save & ~(MSR_EE));
 
-	while (rc == H_SUCCESS && !atomic_read(&data->done))
+	while (rc == H_SUCCESS && !atomic_read(&data->done) && !atomic_read(&data->error))
 		rc = plpar_hcall_norets(H_JOIN);
 
 	mtmsr(msr_save);
@@ -741,33 +772,37 @@ static void rtas_percpu_suspend_me(void *info)
 		/* All other cpus are in H_JOIN, this cpu does
 		 * the suspend.
 		 */
-		slb_set_size(SLB_MIN_SIZE);
-		printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n",
-		       smp_processor_id());
-		data->error = rtas_call(data->token, 0, 1, NULL);
-
-		if (data->error) {
-			printk(KERN_DEBUG "ibm,suspend-me returned %d\n",
-			       data->error);
-			slb_set_size(slb_size);
-		}
+		return __rtas_suspend_last_cpu(data, wake_when_done);
 	} else {
 		printk(KERN_ERR "H_JOIN on cpu %i failed with rc = %ld\n",
 		       smp_processor_id(), rc);
-		data->error = rc;
+		atomic_set(&data->error, rc);
 	}
 
-	atomic_set(&data->done, 1);
+	if (wake_when_done) {
+		atomic_set(&data->done, 1);
 
-	/* This cpu did the suspend or got an error; in either case,
-	 * we need to prod all other other cpus out of join state.
-	 * Extra prods are harmless.
-	 */
-	for_each_online_cpu(cpu)
-		plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
+		/* This cpu did the suspend or got an error; in either case,
+		 * we need to prod all other other cpus out of join state.
+		 * Extra prods are harmless.
+		 */
+		for_each_online_cpu(cpu)
+			plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
+	}
 out:
 	if (atomic_dec_return(&data->working) == 0)
 		complete(data->complete);
+	return rc;
+}
+
+int rtas_suspend_cpu(struct rtas_suspend_me_data *data)
+{
+	return __rtas_suspend_cpu(data, 0);
+}
+
+static void rtas_percpu_suspend_me(void *info)
+{
+	__rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1);
 }
 
 static int rtas_ibm_suspend_me(struct rtas_args *args)
@@ -802,22 +837,22 @@ static int rtas_ibm_suspend_me(struct rtas_args *args)
 
 	atomic_set(&data.working, 0);
 	atomic_set(&data.done, 0);
+	atomic_set(&data.error, 0);
 	data.token = rtas_token("ibm,suspend-me");
-	data.error = 0;
 	data.complete = &done;
 
 	/* Call function on all CPUs.  One of us will make the
 	 * rtas call
 	 */
 	if (on_each_cpu(rtas_percpu_suspend_me, &data, 0))
-		data.error = -EINVAL;
+		atomic_set(&data.error, -EINVAL);
 
 	wait_for_completion(&done);
 
-	if (data.error != 0)
+	if (atomic_read(&data.error) != 0)
 		printk(KERN_ERR "Error doing global join\n");
 
-	return data.error;
+	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
 static int rtas_ibm_suspend_me(struct rtas_args *args)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index b7e6c7e193a..9d4882a4664 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -94,6 +94,12 @@ struct screen_info screen_info = {
 	.orig_video_points = 16
 };
 
+/* Variables required to store legacy IO irq routing */
+int of_i8042_kbd_irq;
+EXPORT_SYMBOL_GPL(of_i8042_kbd_irq);
+int of_i8042_aux_irq;
+EXPORT_SYMBOL_GPL(of_i8042_aux_irq);
+
 #ifdef __DO_IRQ_CANON
 /* XXX should go elsewhere eventually */
 int ppc_do_canonicalize_irqs;
@@ -575,6 +581,15 @@ int check_legacy_ioport(unsigned long base_port)
 			np = of_find_compatible_node(NULL, NULL, "pnpPNP,f03");
 		if (np) {
 			parent = of_get_parent(np);
+
+			of_i8042_kbd_irq = irq_of_parse_and_map(parent, 0);
+			if (!of_i8042_kbd_irq)
+				of_i8042_kbd_irq = 1;
+
+			of_i8042_aux_irq = irq_of_parse_and_map(parent, 1);
+			if (!of_i8042_aux_irq)
+				of_i8042_aux_irq = 12;
+
 			of_node_put(np);
 			np = parent;
 			break;
@@ -701,16 +716,9 @@ static struct notifier_block ppc_dflt_plat_bus_notifier = {
 	.priority = INT_MAX,
 };
 
-static struct notifier_block ppc_dflt_of_bus_notifier = {
-	.notifier_call = ppc_dflt_bus_notify,
-	.priority = INT_MAX,
-};
-
 static int __init setup_bus_notifier(void)
 {
 	bus_register_notifier(&platform_bus_type, &ppc_dflt_plat_bus_notifier);
-	bus_register_notifier(&of_platform_bus_type, &ppc_dflt_of_bus_notifier);
-
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index d135f93cb0f..1bee4b68fa4 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -142,16 +142,6 @@ early_param("smt-enabled", early_smt_enabled);
 #define check_smt_enabled()
 #endif /* CONFIG_SMP */
 
-/* Put the paca pointer into r13 and SPRG_PACA */
-static void __init setup_paca(struct paca_struct *new_paca)
-{
-	local_paca = new_paca;
-	mtspr(SPRN_SPRG_PACA, local_paca);
-#ifdef CONFIG_PPC_BOOK3E
-	mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
-#endif
-}
-
 /*
  * Early initialization entry point. This is called by head.S
  * with MMU translation disabled. We rely on the "feature" of
@@ -600,6 +590,9 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 		return REMOTE_DISTANCE;
 }
 
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
 void __init setup_per_cpu_areas(void)
 {
 	const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
@@ -624,8 +617,10 @@ void __init setup_per_cpu_areas(void)
 		panic("cannot initialize percpu area (err=%d)", rc);
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
-	for_each_possible_cpu(cpu)
-		paca[cpu].data_offset = delta + pcpu_unit_offsets[cpu];
+	for_each_possible_cpu(cpu) {
+                __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+		paca[cpu].data_offset = __per_cpu_offset[cpu];
+	}
 }
 #endif
 
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index a0afb555a7c..7109f5b1baa 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -11,6 +11,7 @@
 
 #include <linux/tracehook.h>
 #include <linux/signal.h>
+#include <asm/hw_breakpoint.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 
@@ -149,6 +150,8 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 	if (current->thread.dabr)
 		set_dabr(current->thread.dabr);
 #endif
+	/* Re-enable the breakpoints for the signal stack */
+	thread_change_pc(current, regs);
 
 	if (is32) {
         	if (ka.sa.sa_flags & SA_SIGINFO)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5c196d1086d..a61b3ddd7bb 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -288,8 +288,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 			max_cpus = NR_CPUS;
 	else
 		max_cpus = 1;
- 
-	smp_space_timers(max_cpus);
 
 	for_each_possible_cpu(cpu)
 		if (cpu != boot_cpuid)
@@ -501,14 +499,6 @@ int __devinit start_secondary(void *unused)
 	current->active_mm = &init_mm;
 
 	smp_store_cpu_info(cpu);
-
-#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
-	/* Clear any pending timer interrupts */
-	mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);
-
-	/* Enable decrementer interrupt */
-	mtspr(SPRN_TCR, TCR_DIE);
-#endif
 	set_dec(tb_ticks_per_jiffy);
 	preempt_disable();
 	cpu_callin_map[cpu] = 1;
diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c
index 6fc6328dc62..0167d53da30 100644
--- a/arch/powerpc/kernel/suspend.c
+++ b/arch/powerpc/kernel/suspend.c
@@ -3,7 +3,7 @@
  *
  * Distribute under GPLv2
  *
- * Copyright (c) 2002 Pavel Machek <pavel@suse.cz>
+ * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
  * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
  */
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 0441bbdadbd..ce53dfa7130 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -149,16 +149,6 @@ unsigned long tb_ticks_per_usec = 100; /* sane default */
 EXPORT_SYMBOL(tb_ticks_per_usec);
 unsigned long tb_ticks_per_sec;
 EXPORT_SYMBOL(tb_ticks_per_sec);	/* for cputime_t conversions */
-u64 tb_to_xs;
-unsigned tb_to_us;
-
-#define TICKLEN_SCALE	NTP_SCALE_SHIFT
-static u64 last_tick_len;	/* units are ns / 2^TICKLEN_SCALE */
-static u64 ticklen_to_xs;	/* 0.64 fraction */
-
-/* If last_tick_len corresponds to about 1/HZ seconds, then
-   last_tick_len << TICKLEN_SHIFT will be about 2^63. */
-#define TICKLEN_SHIFT	(63 - 30 - TICKLEN_SCALE + SHIFT_HZ)
 
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL_GPL(rtc_lock);
@@ -174,7 +164,6 @@ unsigned long ppc_proc_freq;
 EXPORT_SYMBOL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
 
-static u64 tb_last_jiffy __cacheline_aligned_in_smp;
 static DEFINE_PER_CPU(u64, last_jiffy);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
@@ -423,30 +412,6 @@ void udelay(unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
-			       u64 new_tb_to_xs)
-{
-	/*
-	 * tb_update_count is used to allow the userspace gettimeofday code
-	 * to assure itself that it sees a consistent view of the tb_to_xs and
-	 * stamp_xsec variables.  It reads the tb_update_count, then reads
-	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
-	 * the two values of tb_update_count match and are even then the
-	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
-	 * loops back and reads them again until this criteria is met.
-	 * We expect the caller to have done the first increment of
-	 * vdso_data->tb_update_count already.
-	 */
-	vdso_data->tb_orig_stamp = new_tb_stamp;
-	vdso_data->stamp_xsec = new_stamp_xsec;
-	vdso_data->tb_to_xs = new_tb_to_xs;
-	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
-	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
-	vdso_data->stamp_xtime = xtime;
-	smp_wmb();
-	++(vdso_data->tb_update_count);
-}
-
 #ifdef CONFIG_SMP
 unsigned long profile_pc(struct pt_regs *regs)
 {
@@ -470,7 +435,6 @@ EXPORT_SYMBOL(profile_pc);
 
 static int __init iSeries_tb_recal(void)
 {
-	struct div_result divres;
 	unsigned long titan, tb;
 
 	/* Make sure we only run on iSeries */
@@ -501,10 +465,7 @@ static int __init iSeries_tb_recal(void)
 				tb_ticks_per_jiffy = new_tb_ticks_per_jiffy;
 				tb_ticks_per_sec   = new_tb_ticks_per_sec;
 				calc_cputime_factors();
-				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
-				tb_to_xs = divres.result_low;
 				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
-				vdso_data->tb_to_xs = tb_to_xs;
 				setup_cputime_one_jiffy();
 			}
 			else {
@@ -667,27 +628,9 @@ void timer_interrupt(struct pt_regs * regs)
 	trace_timer_interrupt_exit(regs);
 }
 
-void wakeup_decrementer(void)
-{
-	unsigned long ticks;
-
-	/*
-	 * The timebase gets saved on sleep and restored on wakeup,
-	 * so all we need to do is to reset the decrementer.
-	 */
-	ticks = tb_ticks_since(__get_cpu_var(last_jiffy));
-	if (ticks < tb_ticks_per_jiffy)
-		ticks = tb_ticks_per_jiffy - ticks;
-	else
-		ticks = 1;
-	set_dec(ticks);
-}
-
 #ifdef CONFIG_SUSPEND
-void generic_suspend_disable_irqs(void)
+static void generic_suspend_disable_irqs(void)
 {
-	preempt_disable();
-
 	/* Disable the decrementer, so that it doesn't interfere
 	 * with suspending.
 	 */
@@ -697,12 +640,9 @@ void generic_suspend_disable_irqs(void)
 	set_dec(0x7fffffff);
 }
 
-void generic_suspend_enable_irqs(void)
+static void generic_suspend_enable_irqs(void)
 {
-	wakeup_decrementer();
-
 	local_irq_enable();
-	preempt_enable();
 }
 
 /* Overrides the weak version in kernel/power/main.c */
@@ -722,23 +662,6 @@ void arch_suspend_enable_irqs(void)
 }
 #endif
 
-#ifdef CONFIG_SMP
-void __init smp_space_timers(unsigned int max_cpus)
-{
-	int i;
-	u64 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_possible_cpu(i) {
-		if (i == boot_cpuid)
-			continue;
-		per_cpu(last_jiffy, i) = previous_tb;
-	}
-}
-#endif
-
 /*
  * Scheduler clock - returns current time in nanosec units.
  *
@@ -873,10 +796,11 @@ static cycle_t timebase_read(struct clocksource *cs)
 	return (cycle_t)get_tb();
 }
 
-void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
-		     u32 mult)
+void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
+			struct clocksource *clock, u32 mult)
 {
-	u64 t2x, stamp_xsec;
+	u64 new_tb_to_xs, new_stamp_xsec;
+	u32 frac_sec;
 
 	if (clock != &clocksource_timebase)
 		return;
@@ -887,11 +811,35 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock,
 
 	/* XXX this assumes clock->shift == 22 */
 	/* 4611686018 ~= 2^(20+64-22) / 1e9 */
-	t2x = (u64) mult * 4611686018ULL;
-	stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC;
-	do_div(stamp_xsec, 1000000000);
-	stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC;
-	update_gtod(clock->cycle_last, stamp_xsec, t2x);
+	new_tb_to_xs = (u64) mult * 4611686018ULL;
+	new_stamp_xsec = (u64) wall_time->tv_nsec * XSEC_PER_SEC;
+	do_div(new_stamp_xsec, 1000000000);
+	new_stamp_xsec += (u64) wall_time->tv_sec * XSEC_PER_SEC;
+
+	BUG_ON(wall_time->tv_nsec >= NSEC_PER_SEC);
+	/* this is tv_nsec / 1e9 as a 0.32 fraction */
+	frac_sec = ((u64) wall_time->tv_nsec * 18446744073ULL) >> 32;
+
+	/*
+	 * tb_update_count is used to allow the userspace gettimeofday code
+	 * to assure itself that it sees a consistent view of the tb_to_xs and
+	 * stamp_xsec variables.  It reads the tb_update_count, then reads
+	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
+	 * the two values of tb_update_count match and are even then the
+	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
+	 * loops back and reads them again until this criteria is met.
+	 * We expect the caller to have done the first increment of
+	 * vdso_data->tb_update_count already.
+	 */
+	vdso_data->tb_orig_stamp = clock->cycle_last;
+	vdso_data->stamp_xsec = new_stamp_xsec;
+	vdso_data->tb_to_xs = new_tb_to_xs;
+	vdso_data->wtom_clock_sec = wtm->tv_sec;
+	vdso_data->wtom_clock_nsec = wtm->tv_nsec;
+	vdso_data->stamp_xtime = *wall_time;
+	vdso_data->stamp_sec_fraction = frac_sec;
+	smp_wmb();
+	++(vdso_data->tb_update_count);
 }
 
 void update_vsyscall_tz(void)
@@ -1007,15 +955,13 @@ void secondary_cpu_time_init(void)
 /* This function is only called on the boot processor */
 void __init time_init(void)
 {
-	unsigned long flags;
 	struct div_result res;
-	u64 scale, x;
+	u64 scale;
 	unsigned shift;
 
 	if (__USE_RTC()) {
 		/* 601 processor: dec counts down by 128 every 128ns */
 		ppc_tb_freq = 1000000000;
-		tb_last_jiffy = get_rtcl();
 	} else {
 		/* Normal PowerPC with timebase register */
 		ppc_md.calibrate_decr();
@@ -1023,50 +969,15 @@ void __init time_init(void)
 		       ppc_tb_freq / 1000000, ppc_tb_freq % 1000000);
 		printk(KERN_DEBUG "time_init: processor frequency   = %lu.%.6lu MHz\n",
 		       ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
-		tb_last_jiffy = get_tb();
 	}
 
 	tb_ticks_per_jiffy = ppc_tb_freq / HZ;
 	tb_ticks_per_sec = ppc_tb_freq;
 	tb_ticks_per_usec = ppc_tb_freq / 1000000;
-	tb_to_us = mulhwu_scale_factor(ppc_tb_freq, 1000000);
 	calc_cputime_factors();
 	setup_cputime_one_jiffy();
 
 	/*
-	 * Calculate the length of each tick in ns.  It will not be
-	 * exactly 1e9/HZ unless ppc_tb_freq is divisible by HZ.
-	 * We compute 1e9 * tb_ticks_per_jiffy / ppc_tb_freq,
-	 * rounded up.
-	 */
-	x = (u64) NSEC_PER_SEC * tb_ticks_per_jiffy + ppc_tb_freq - 1;
-	do_div(x, ppc_tb_freq);
-	tick_nsec = x;
-	last_tick_len = x << TICKLEN_SCALE;
-
-	/*
-	 * Compute ticklen_to_xs, which is a factor which gets multiplied
-	 * by (last_tick_len << TICKLEN_SHIFT) to get a tb_to_xs value.
-	 * It is computed as:
-	 * ticklen_to_xs = 2^N / (tb_ticks_per_jiffy * 1e9)
-	 * where N = 64 + 20 - TICKLEN_SCALE - TICKLEN_SHIFT
-	 * which turns out to be N = 51 - SHIFT_HZ.
-	 * This gives the result as a 0.64 fixed-point fraction.
-	 * That value is reduced by an offset amounting to 1 xsec per
-	 * 2^31 timebase ticks to avoid problems with time going backwards
-	 * by 1 xsec when we do timer_recalc_offset due to losing the
-	 * fractional xsec.  That offset is equal to ppc_tb_freq/2^51
-	 * since there are 2^20 xsec in a second.
-	 */
-	div128_by_32((1ULL << 51) - ppc_tb_freq, 0,
-		     tb_ticks_per_jiffy << SHIFT_HZ, &res);
-	div128_by_32(res.result_high, res.result_low, NSEC_PER_SEC, &res);
-	ticklen_to_xs = res.result_low;
-
-	/* Compute tb_to_xs from tick_nsec */
-	tb_to_xs = mulhdu(last_tick_len << TICKLEN_SHIFT, ticklen_to_xs);
-
-	/*
 	 * Compute scale factor for sched_clock.
 	 * The calibrate_decr() function has set tb_ticks_per_sec,
 	 * which is the timebase frequency.
@@ -1087,21 +998,14 @@ void __init time_init(void)
 	/* Save the current timebase to pretty up CONFIG_PRINTK_TIME */
 	boot_tb = get_tb_or_rtc();
 
-	write_seqlock_irqsave(&xtime_lock, flags);
-
 	/* If platform provided a timezone (pmac), we correct the time */
         if (timezone_offset) {
 		sys_tz.tz_minuteswest = -timezone_offset / 60;
 		sys_tz.tz_dsttime = 0;
         }
 
-	vdso_data->tb_orig_stamp = tb_last_jiffy;
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
-	vdso_data->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
-	vdso_data->tb_to_xs = tb_to_xs;
-
-	write_sequnlock_irqrestore(&xtime_lock, flags);
 
 	/* Start the decrementer on CPUs that have manual control
 	 * such as BookE
@@ -1195,39 +1099,6 @@ void to_tm(int tim, struct rtc_time * tm)
 	GregorianDay(tm);
 }
 
-/* Auxiliary function to compute scaling factors */
-/* Actually the choice of a timebase running at 1/4 the of the bus
- * frequency giving resolution of a few tens of nanoseconds is quite nice.
- * It makes this computation very precise (27-28 bits typically) which
- * is optimistic considering the stability of most processor clock
- * oscillators and the precision with which the timebase frequency
- * is measured but does not harm.
- */
-unsigned mulhwu_scale_factor(unsigned inscale, unsigned outscale)
-{
-        unsigned mlt=0, tmp, err;
-        /* No concern for performance, it's done once: use a stupid
-         * but safe and compact method to find the multiplier.
-         */
-  
-        for (tmp = 1U<<31; tmp != 0; tmp >>= 1) {
-                if (mulhwu(inscale, mlt|tmp) < outscale)
-			mlt |= tmp;
-        }
-  
-        /* We might still be off by 1 for the best approximation.
-         * A side effect of this is that if outscale is too large
-         * the returned value will be zero.
-         * Many corner cases have been checked and seem to work,
-         * some might have been forgotten in the test however.
-         */
-  
-        err = inscale * (mlt+1);
-        if (err <= inscale/2)
-		mlt++;
-        return mlt;
-}
-
 /*
  * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
  * result.
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 25fc33984c2..a45a63c3a0c 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -55,9 +55,6 @@
 #endif
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
-#ifdef CONFIG_FSL_BOOKE
-#include <asm/dbell.h>
-#endif
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -688,7 +685,7 @@ void RunModeException(struct pt_regs *regs)
 
 void __kprobes single_step_exception(struct pt_regs *regs)
 {
-	regs->msr &= ~(MSR_SE | MSR_BE);  /* Turn off 'trace' bits */
+	clear_single_step(regs);
 
 	if (notify_die(DIE_SSTEP, "single_step", regs, 5,
 					5, SIGTRAP) == NOTIFY_STOP)
@@ -707,10 +704,8 @@ void __kprobes single_step_exception(struct pt_regs *regs)
  */
 static void emulate_single_step(struct pt_regs *regs)
 {
-	if (single_stepping(regs)) {
-		clear_single_step(regs);
-		_exception(SIGTRAP, regs, TRAP_TRACE, 0);
-	}
+	if (single_stepping(regs))
+		single_step_exception(regs);
 }
 
 static inline int __parse_fpscr(unsigned long fpscr)
@@ -1344,24 +1339,6 @@ void vsx_assist_exception(struct pt_regs *regs)
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_FSL_BOOKE
-
-void doorbell_exception(struct pt_regs *regs)
-{
-#ifdef CONFIG_SMP
-	int cpu = smp_processor_id();
-	int msg;
-
-	if (num_online_cpus() < 2)
-		return;
-
-	for (msg = 0; msg < 4; msg++)
-		if (test_and_clear_bit(msg, &dbell_smp_message[cpu]))
-			smp_message_recv(msg);
-#else
-	printk(KERN_WARNING "Received doorbell on non-smp system\n");
-#endif
-}
-
 void CacheLockingException(struct pt_regs *regs, unsigned long address,
 			   unsigned long error_code)
 {
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index ee038d4bf25..4ee09ee2e83 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -19,8 +19,10 @@
 /* Offset for the low 32-bit part of a field of long type */
 #ifdef CONFIG_PPC64
 #define LOPART	4
+#define TSPEC_TV_SEC	TSPC64_TV_SEC+LOPART
 #else
 #define LOPART	0
+#define TSPEC_TV_SEC	TSPC32_TV_SEC
 #endif
 
 	.text
@@ -41,23 +43,11 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	mr	r9, r3			/* datapage ptr in r9 */
 	cmplwi	r10,0			/* check if tv is NULL */
 	beq	3f
-	bl	__do_get_xsec@local	/* get xsec from tb & kernel */
-	bne-	2f			/* out of line -> do syscall */
-
-	/* seconds are xsec >> 20 */
-	rlwinm	r5,r4,12,20,31
-	rlwimi	r5,r3,12,0,19
-	stw	r5,TVAL32_TV_SEC(r10)
-
-	/* get remaining xsec and convert to usec. we scale
-	 * up remaining xsec by 12 bits and get the top 32 bits
-	 * of the multiplication
-	 */
-	rlwinm	r5,r4,12,0,19
-	lis	r6,1000000@h
-	ori	r6,r6,1000000@l
-	mulhwu	r5,r5,r6
-	stw	r5,TVAL32_TV_USEC(r10)
+	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
+	addi	r7,r7,1000000@l		/* so we get microseconds in r4 */
+	bl	__do_get_tspec@local	/* get sec/usec from tb & kernel */
+	stw	r3,TVAL32_TV_SEC(r10)
+	stw	r4,TVAL32_TV_USEC(r10)
 
 3:	cmplwi	r11,0			/* check if tz is NULL */
 	beq	1f
@@ -70,14 +60,6 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	crclr	cr0*4+so
 	li	r3,0
 	blr
-
-2:
-	mtlr	r12
-	mr	r3,r10
-	mr	r4,r11
-	li	r0,__NR_gettimeofday
-	sc
-	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_gettimeofday)
 
@@ -100,7 +82,8 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	mr	r11,r4			/* r11 saves tp */
 	bl	__get_datapage@local	/* get data page */
 	mr	r9,r3			/* datapage ptr in r9 */
-
+	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
+	ori	r7,r7,NSEC_PER_SEC@l
 50:	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
 	bne	cr1,80f			/* not monotonic -> all done */
 
@@ -198,83 +181,12 @@ V_FUNCTION_END(__kernel_clock_getres)
 
 
 /*
- * This is the core of gettimeofday() & friends, it returns the xsec
- * value in r3 & r4 and expects the datapage ptr (non clobbered)
- * in r9. clobbers r0,r4,r5,r6,r7,r8.
- * When returning, r8 contains the counter value that can be reused
- * by the monotonic clock implementation
- */
-__do_get_xsec:
-  .cfi_startproc
-	/* Check for update count & load values. We use the low
-	 * order 32 bits of the update count
-	 */
-1:	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
-	andi.	r0,r8,1			/* pending update ? loop */
-	bne-	1b
-	xor	r0,r8,r8		/* create dependency */
-	add	r9,r9,r0
-
-	/* Load orig stamp (offset to TB) */
-	lwz	r5,CFG_TB_ORIG_STAMP(r9)
-	lwz	r6,(CFG_TB_ORIG_STAMP+4)(r9)
-
-	/* Get a stable TB value */
-2:	mftbu	r3
-	mftbl	r4
-	mftbu	r0
-	cmpl	cr0,r3,r0
-	bne-	2b
-
-	/* Substract tb orig stamp. If the high part is non-zero, we jump to
-	 * the slow path which call the syscall.
-	 * If it's ok, then we have our 32 bits tb_ticks value in r7
-	 */
-	subfc	r7,r6,r4
-	subfe.	r0,r5,r3
-	bne-	3f
-
-	/* Load scale factor & do multiplication */
-	lwz	r5,CFG_TB_TO_XS(r9)	/* load values */
-	lwz	r6,(CFG_TB_TO_XS+4)(r9)
-	mulhwu	r4,r7,r5
-	mulhwu	r6,r7,r6
-	mullw	r0,r7,r5
-	addc	r6,r6,r0
-
-	/* At this point, we have the scaled xsec value in r4 + XER:CA
-	 * we load & add the stamp since epoch
-	 */
-	lwz	r5,CFG_STAMP_XSEC(r9)
-	lwz	r6,(CFG_STAMP_XSEC+4)(r9)
-	adde	r4,r4,r6
-	addze	r3,r5
-
-	/* We now have our result in r3,r4. We create a fake dependency
-	 * on that result and re-check the counter
-	 */
-	or	r6,r4,r3
-	xor	r0,r6,r6
-	add	r9,r9,r0
-	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
-        cmpl    cr0,r8,r0		/* check if updated */
-	bne-	1b
-
-	/* Warning ! The caller expects CR:EQ to be set to indicate a
-	 * successful calculation (so it won't fallback to the syscall
-	 * method). We have overriden that CR bit in the counter check,
-	 * but fortunately, the loop exit condition _is_ CR:EQ set, so
-	 * we can exit safely here. If you change this code, be careful
-	 * of that side effect.
-	 */
-3:	blr
-  .cfi_endproc
-
-/*
- * This is the core of clock_gettime(), it returns the current
- * time in seconds and nanoseconds in r3 and r4.
+ * This is the core of clock_gettime() and gettimeofday(),
+ * it returns the current time in r3 (seconds) and r4.
+ * On entry, r7 gives the resolution of r4, either USEC_PER_SEC
+ * or NSEC_PER_SEC, giving r4 in microseconds or nanoseconds.
  * It expects the datapage ptr in r9 and doesn't clobber it.
- * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7.
+ * It clobbers r0, r5 and r6.
  * On return, r8 contains the counter value that can be reused.
  * This clobbers cr0 but not any other cr field.
  */
@@ -297,70 +209,58 @@ __do_get_tspec:
 2:	mftbu	r3
 	mftbl	r4
 	mftbu	r0
-	cmpl	cr0,r3,r0
+	cmplw	cr0,r3,r0
 	bne-	2b
 
 	/* Subtract tb orig stamp and shift left 12 bits.
 	 */
-	subfc	r7,r6,r4
+	subfc	r4,r6,r4
 	subfe	r0,r5,r3
 	slwi	r0,r0,12
-	rlwimi.	r0,r7,12,20,31
-	slwi	r7,r7,12
+	rlwimi.	r0,r4,12,20,31
+	slwi	r4,r4,12
 
-	/* Load scale factor & do multiplication */
+	/*
+	 * Load scale factor & do multiplication.
+	 * We only use the high 32 bits of the tb_to_xs value.
+	 * Even with a 1GHz timebase clock, the high 32 bits of
+	 * tb_to_xs will be at least 4 million, so the error from
+	 * ignoring the low 32 bits will be no more than 0.25ppm.
+	 * The error will just make the clock run very very slightly
+	 * slow until the next time the kernel updates the VDSO data,
+	 * at which point the clock will catch up to the kernel's value,
+	 * so there is no long-term error accumulation.
+	 */
 	lwz	r5,CFG_TB_TO_XS(r9)	/* load values */
-	lwz	r6,(CFG_TB_TO_XS+4)(r9)
-	mulhwu	r3,r7,r6
-	mullw	r10,r7,r5
-	mulhwu	r4,r7,r5
-	addc	r10,r3,r10
+	mulhwu	r4,r4,r5
 	li	r3,0
 
 	beq+	4f			/* skip high part computation if 0 */
 	mulhwu	r3,r0,r5
-	mullw	r7,r0,r5
-	mulhwu	r5,r0,r6
-	mullw	r6,r0,r6
-	adde	r4,r4,r7
-	addze	r3,r3
+	mullw	r5,r0,r5
 	addc	r4,r4,r5
 	addze	r3,r3
-	addc	r10,r10,r6
-
-4:	addze	r4,r4			/* add in carry */
-	lis	r7,NSEC_PER_SEC@h
-	ori	r7,r7,NSEC_PER_SEC@l
-	mulhwu	r4,r4,r7		/* convert to nanoseconds */
-
-	/* At this point, we have seconds & nanoseconds since the xtime
-	 * stamp in r3+CA and r4.  Load & add the xtime stamp.
+4:
+	/* At this point, we have seconds since the xtime stamp
+	 * as a 32.32 fixed-point number in r3 and r4.
+	 * Load & add the xtime stamp.
 	 */
-#ifdef CONFIG_PPC64
-	lwz	r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9)
-	lwz	r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9)
-#else
-	lwz	r5,STAMP_XTIME+TSPC32_TV_SEC(r9)
-	lwz	r6,STAMP_XTIME+TSPC32_TV_NSEC(r9)
-#endif
-	add	r4,r4,r6
+	lwz	r5,STAMP_XTIME+TSPEC_TV_SEC(r9)
+	lwz	r6,STAMP_SEC_FRAC(r9)
+	addc	r4,r4,r6
 	adde	r3,r3,r5
 
-	/* We now have our result in r3,r4. We create a fake dependency
-	 * on that result and re-check the counter
+	/* We create a fake dependency on the result in r3/r4
+	 * and re-check the counter
 	 */
 	or	r6,r4,r3
 	xor	r0,r6,r6
 	add	r9,r9,r0
 	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
-        cmpl    cr0,r8,r0		/* check if updated */
+        cmplw	cr0,r8,r0		/* check if updated */
 	bne-	1b
 
-	/* check for nanosecond overflow and adjust if necessary */
-	cmpw	r4,r7
-	bltlr				/* all done if no overflow */
-	subf	r4,r7,r4		/* adjust if overflow */
-	addi	r3,r3,1
+	mulhwu	r4,r4,r7		/* convert to micro or nanoseconds */
 
 	blr
   .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 262cd5857a5..e97a9a0dc4a 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -33,18 +33,11 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
 	cmpldi	r11,0			/* check if tv is NULL */
 	beq	2f
-	bl	V_LOCAL_FUNC(__do_get_xsec)	/* get xsec from tb & kernel */
-	lis     r7,15			/* r7 = 1000000 = USEC_PER_SEC */
-	ori     r7,r7,16960
-	rldicl  r5,r4,44,20		/* r5 = sec = xsec / XSEC_PER_SEC */
-	rldicr  r6,r5,20,43		/* r6 = sec * XSEC_PER_SEC */
-	std	r5,TVAL64_TV_SEC(r11)	/* store sec in tv */
-	subf	r0,r6,r4		/* r0 = xsec = (xsec - r6) */
-	mulld   r0,r0,r7		/* usec = (xsec * USEC_PER_SEC) /
-					 * XSEC_PER_SEC
-					 */
-	rldicl  r0,r0,44,20
-	std	r0,TVAL64_TV_USEC(r11)	/* store usec in tv */
+	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
+	addi	r7,r7,1000000@l
+	bl	V_LOCAL_FUNC(__do_get_tspec) /* get sec/us from tb & kernel */
+	std	r4,TVAL64_TV_SEC(r11)	/* store sec in tv */
+	std	r5,TVAL64_TV_USEC(r11)	/* store usec in tv */
 2:	cmpldi	r10,0			/* check if tz is NULL */
 	beq	1f
 	lwz	r4,CFG_TZ_MINUTEWEST(r3)/* fill tz */
@@ -77,6 +70,8 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
   .cfi_register lr,r12
 	mr	r11,r4			/* r11 saves tp */
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
+	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
+	ori	r7,r7,NSEC_PER_SEC@l
 50:	bl	V_LOCAL_FUNC(__do_get_tspec)	/* get time from tb & kernel */
 	bne	cr1,80f			/* if not monotonic, all done */
 
@@ -171,49 +166,12 @@ V_FUNCTION_END(__kernel_clock_getres)
 
 
 /*
- * This is the core of gettimeofday(), it returns the xsec
- * value in r4 and expects the datapage ptr (non clobbered)
- * in r3. clobbers r0,r4,r5,r6,r7,r8
- * When returning, r8 contains the counter value that can be reused
- */
-V_FUNCTION_BEGIN(__do_get_xsec)
-  .cfi_startproc
-	/* check for update count & load values */
-1:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
-	andi.	r0,r8,1			/* pending update ? loop */
-	bne-	1b
-	xor	r0,r8,r8		/* create dependency */
-	add	r3,r3,r0
-
-	/* Get TB & offset it. We use the MFTB macro which will generate
-	 * workaround code for Cell.
-	 */
-	MFTB(r7)
-	ld	r9,CFG_TB_ORIG_STAMP(r3)
-	subf	r7,r9,r7
-
-	/* Scale result */
-	ld	r5,CFG_TB_TO_XS(r3)
-	mulhdu	r7,r7,r5
-
-	/* Add stamp since epoch */
-	ld	r6,CFG_STAMP_XSEC(r3)
-	add	r4,r6,r7
-
-	xor	r0,r4,r4
-	add	r3,r3,r0
-	ld	r0,CFG_TB_UPDATE_COUNT(r3)
-        cmpld   cr0,r0,r8		/* check if updated */
-	bne-	1b
-	blr
-  .cfi_endproc
-V_FUNCTION_END(__do_get_xsec)
-
-/*
- * This is the core of clock_gettime(), it returns the current
- * time in seconds and nanoseconds in r4 and r5.
+ * This is the core of clock_gettime() and gettimeofday(),
+ * it returns the current time in r4 (seconds) and r5.
+ * On entry, r7 gives the resolution of r5, either USEC_PER_SEC
+ * or NSEC_PER_SEC, giving r5 in microseconds or nanoseconds.
  * It expects the datapage ptr in r3 and doesn't clobber it.
- * It clobbers r0 and r6 and returns NSEC_PER_SEC in r7.
+ * It clobbers r0, r6 and r9.
  * On return, r8 contains the counter value that can be reused.
  * This clobbers cr0 but not any other cr field.
  */
@@ -229,18 +187,18 @@ V_FUNCTION_BEGIN(__do_get_tspec)
 	/* Get TB & offset it. We use the MFTB macro which will generate
 	 * workaround code for Cell.
 	 */
-	MFTB(r7)
+	MFTB(r6)
 	ld	r9,CFG_TB_ORIG_STAMP(r3)
-	subf	r7,r9,r7
+	subf	r6,r9,r6
 
 	/* Scale result */
 	ld	r5,CFG_TB_TO_XS(r3)
-	sldi	r7,r7,12		/* compute time since stamp_xtime */
-	mulhdu	r6,r7,r5		/* in units of 2^-32 seconds */
+	sldi	r6,r6,12		/* compute time since stamp_xtime */
+	mulhdu	r6,r6,r5		/* in units of 2^-32 seconds */
 
 	/* Add stamp since epoch */
 	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
-	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+	lwz	r5,STAMP_SEC_FRAC(r3)
 	or	r0,r4,r5
 	or	r0,r0,r6
 	xor	r0,r0,r0
@@ -250,17 +208,11 @@ V_FUNCTION_BEGIN(__do_get_tspec)
 	bne-	1b			/* reload if so */
 
 	/* convert to seconds & nanoseconds and add to stamp */
-	lis	r7,NSEC_PER_SEC@h
-	ori	r7,r7,NSEC_PER_SEC@l
-	mulhwu	r0,r6,r7		/* compute nanoseconds and */
+	add	r6,r6,r5		/* add on fractional seconds of xtime */
+	mulhwu	r5,r6,r7		/* compute micro or nanoseconds and */
 	srdi	r6,r6,32		/* seconds since stamp_xtime */
-	clrldi	r0,r0,32
-	add	r5,r5,r0		/* add nanoseconds together */
-	cmpd	r5,r7			/* overflow? */
+	clrldi	r5,r5,32
 	add	r4,r4,r6
-	bltlr				/* all done if no overflow */
-	subf	r5,r7,r5		/* if overflow, adjust */
-	addi	r4,r4,1
 	blr
   .cfi_endproc
 V_FUNCTION_END(__do_get_tspec)