19 files changed, 205 insertions, 202 deletions

diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index 5c518ad3445..913611105c1 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -64,7 +64,7 @@ _GLOBAL(__setup_cpu_e500v2)
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
 	bl	__setup_e500_ivors
-#ifdef CONFIG_RAPIDIO
+#ifdef CONFIG_FSL_RIO
 	/* Ensure that RFXE is set */
 	mfspr	r3,SPRN_HID1
 	oris	r3,r3,HID1_RFXE@h
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 3d569e2aff1..3d3d416339d 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -163,7 +163,7 @@ static void crash_kexec_prepare_cpus(int cpu)
 }
 
 /* wait for all the CPUs to hit real mode but timeout if they don't come in */
-#ifdef CONFIG_PPC_STD_MMU_64
+#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP)
 static void crash_kexec_wait_realmode(int cpu)
 {
 	unsigned int msecs;
@@ -188,6 +188,8 @@ static void crash_kexec_wait_realmode(int cpu)
 	}
 	mb();
 }
+#else
+static inline void crash_kexec_wait_realmode(int cpu) {}
 #endif
 
 /*
@@ -344,9 +346,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	crash_save_cpu(regs, crashing_cpu);
 	crash_kexec_prepare_cpus(crashing_cpu);
 	cpu_set(crashing_cpu, cpus_in_crash);
-#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP)
 	crash_kexec_wait_realmode(crashing_cpu);
-#endif
 
 	machine_kexec_mask_interrupts();
 
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 0a2af50243c..424afb6b8fb 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -28,9 +28,6 @@
 #define DBG(fmt...)
 #endif
 
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
 #ifndef CONFIG_RELOCATABLE
 void __init reserve_kdump_trampoline(void)
 {
@@ -72,20 +69,6 @@ void __init setup_kdump_trampoline(void)
 }
 #endif /* CONFIG_RELOCATABLE */
 
-/*
- * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
- * is_kdump_kernel() to determine if we are booting after a panic. Hence
- * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
- */
-static int __init parse_elfcorehdr(char *p)
-{
-	if (p)
-		elfcorehdr_addr = memparse(p, &p);
-
-	return 1;
-}
-__setup("elfcorehdr=", parse_elfcorehdr);
-
 static int __init parse_savemaxmem(char *p)
 {
 	if (p)
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index cf02cad62d9..d238c082c3c 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -179,3 +179,21 @@ static int __init dma_init(void)
        return 0;
 }
 fs_initcall(dma_init);
+
+int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+		      void *cpu_addr, dma_addr_t handle, size_t size)
+{
+	unsigned long pfn;
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
+#else
+	pfn = page_to_pfn(virt_to_page(cpu_addr));
+#endif
+	return remap_pfn_range(vma, vma->vm_start,
+			       pfn + vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot);
+}
+EXPORT_SYMBOL_GPL(dma_mmap_coherent);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 8a817995b4c..c532cb2c927 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -977,20 +977,6 @@ _GLOBAL(do_stab_bolted)
 	rfid
 	b	.	/* prevent speculative execution */
 
-/*
- * Space for CPU0's segment table.
- *
- * On iSeries, the hypervisor must fill in at least one entry before
- * we get control (with relocate on).  The address is given to the hv
- * as a page number (see xLparMap below), so this must be at a
- * fixed address (the linker can't compute (u64)&initial_stab >>
- * PAGE_SHIFT).
- */
-	. = STAB0_OFFSET	/* 0x6000 */
-	.globl initial_stab
-initial_stab:
-	.space	4096
-
 #ifdef CONFIG_PPC_PSERIES
 /*
  * Data area reserved for FWNMI option.
@@ -1027,3 +1013,17 @@ xLparMap:
 #ifdef CONFIG_PPC_PSERIES
         . = 0x8000
 #endif /* CONFIG_PPC_PSERIES */
+
+/*
+ * Space for CPU0's segment table.
+ *
+ * On iSeries, the hypervisor must fill in at least one entry before
+ * we get control (with relocate on).  The address is given to the hv
+ * as a page number (see xLparMap above), so this must be at a
+ * fixed address (the linker can't compute (u64)&initial_stab >>
+ * PAGE_SHIFT).
+ */
+	. = STAB0_OFFSET	/* 0x8000 */
+	.globl initial_stab
+initial_stab:
+	.space	4096
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 98c4b29a56f..c5c24beb838 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -890,6 +890,15 @@ __secondary_start:
 	mtspr	SPRN_SRR1,r4
 	SYNC
 	RFI
+
+_GLOBAL(start_secondary_resume)
+	/* Reset stack */
+	rlwinm	r1,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
+	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+	li	r3,0
+	std	r3,0(r1)		/* Zero the stack frame pointer	*/
+	bl	start_secondary
+	b	.
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 782f23df7c8..271140b38b6 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -536,6 +536,13 @@ _GLOBAL(pmac_secondary_start)
 	add	r13,r13,r4		/* for this processor.		*/
 	mtspr	SPRN_SPRG_PACA,r13	/* Save vaddr of paca in an SPRG*/
 
+	/* Mark interrupts soft and hard disabled (they might be enabled
+	 * in the PACA when doing hotplug)
+	 */
+	li	r0,0
+	stb	r0,PACASOFTIRQEN(r13)
+	stb	r0,PACAHARDIRQEN(r13)
+
 	/* Create a temp kernel stack for use before relocation is on.	*/
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index 5328709eeed..ba319547860 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -53,24 +53,3 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	isync
 	b	1b
 
-_GLOBAL(power4_cpu_offline_powersave)
-	/* Go to NAP now */
-	mfmsr	r7
-	rldicl	r0,r7,48,1
-	rotldi	r0,r0,16
-	mtmsrd	r0,1			/* hard-disable interrupts */
-	li	r0,1
-	li	r6,0
-	stb	r0,PACAHARDIRQEN(r13)	/* we'll hard-enable shortly */
-	stb	r6,PACASOFTIRQEN(r13)	/* soft-disable irqs */
-BEGIN_FTR_SECTION
-	DSSALL
-	sync
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	ori	r7,r7,MSR_EE
-	oris	r7,r7,MSR_POW@h
-	sync
-	isync
-	mtmsrd	r7
-	isync
-	blr
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0a5570338b9..f621b7d2d86 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -195,7 +195,7 @@ notrace void arch_local_irq_restore(unsigned long en)
 EXPORT_SYMBOL(arch_local_irq_restore);
 #endif /* CONFIG_PPC64 */
 
-static int show_other_interrupts(struct seq_file *p, int prec)
+int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	int j;
 
@@ -231,65 +231,6 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-int show_interrupts(struct seq_file *p, void *v)
-{
-	unsigned long flags, any_count = 0;
-	int i = *(loff_t *) v, j, prec;
-	struct irqaction *action;
-	struct irq_desc *desc;
-	struct irq_chip *chip;
-
-	if (i > nr_irqs)
-		return 0;
-
-	for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
-		j *= 10;
-
-	if (i == nr_irqs)
-		return show_other_interrupts(p, prec);
-
-	/* print header */
-	if (i == 0) {
-		seq_printf(p, "%*s", prec + 8, "");
-		for_each_online_cpu(j)
-			seq_printf(p, "CPU%-8d", j);
-		seq_putc(p, '\n');
-	}
-
-	desc = irq_to_desc(i);
-	if (!desc)
-		return 0;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if (!action && !any_count)
-		goto out;
-
-	seq_printf(p, "%*d: ", prec, i);
-	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-
-	chip = get_irq_desc_chip(desc);
-	if (chip)
-		seq_printf(p, "  %-16s", chip->name);
-	else
-		seq_printf(p, "  %-16s", "None");
-	seq_printf(p, " %-8s", (desc->status & IRQ_LEVEL) ? "Level" : "Edge");
-
-	if (action) {
-		seq_printf(p, "     %s", action->name);
-		while ((action = action->next) != NULL)
-			seq_printf(p, ", %s", action->name);
-	}
-
-	seq_putc(p, '\n');
-out:
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return 0;
-}
-
 /*
  * /proc/stat helpers
  */
@@ -305,34 +246,37 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-void fixup_irqs(const struct cpumask *map)
+void migrate_irqs(void)
 {
 	struct irq_desc *desc;
 	unsigned int irq;
 	static int warned;
 	cpumask_var_t mask;
+	const struct cpumask *map = cpu_online_mask;
 
 	alloc_cpumask_var(&mask, GFP_KERNEL);
 
 	for_each_irq(irq) {
+		struct irq_data *data;
 		struct irq_chip *chip;
 
 		desc = irq_to_desc(irq);
 		if (!desc)
 			continue;
 
-		if (desc->status & IRQ_PER_CPU)
+		data = irq_desc_get_irq_data(desc);
+		if (irqd_is_per_cpu(data))
 			continue;
 
-		chip = get_irq_desc_chip(desc);
+		chip = irq_data_get_irq_chip(data);
 
-		cpumask_and(mask, desc->irq_data.affinity, map);
+		cpumask_and(mask, data->affinity, map);
 		if (cpumask_any(mask) >= nr_cpu_ids) {
 			printk("Breaking affinity for irq %i\n", irq);
 			cpumask_copy(mask, map);
 		}
 		if (chip->irq_set_affinity)
-			chip->irq_set_affinity(&desc->irq_data, mask, true);
+			chip->irq_set_affinity(data, mask, true);
 		else if (desc->action && !(warned++))
 			printk("Cannot set affinity for irq %i\n", irq);
 	}
@@ -618,7 +562,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node,
 			smp_wmb();
 
 			/* Clear norequest flags */
-			irq_to_desc(i)->status &= ~IRQ_NOREQUEST;
+			irq_clear_status_flags(i, IRQ_NOREQUEST);
 
 			/* Legacy flags are left to default at this point,
 			 * one can then use irq_create_mapping() to
@@ -827,8 +771,8 @@ unsigned int irq_create_of_mapping(struct device_node *controller,
 
 	/* Set type if specified and different than the current one */
 	if (type != IRQ_TYPE_NONE &&
-	    type != (irq_to_desc(virq)->status & IRQF_TRIGGER_MASK))
-		set_irq_type(virq, type);
+	    type != (irqd_get_trigger_type(irq_get_irq_data(virq))))
+		irq_set_irq_type(virq, type);
 	return virq;
 }
 EXPORT_SYMBOL_GPL(irq_create_of_mapping);
@@ -851,7 +795,7 @@ void irq_dispose_mapping(unsigned int virq)
 		return;
 
 	/* remove chip and handler */
-	set_irq_chip_and_handler(virq, NULL, NULL);
+	irq_set_chip_and_handler(virq, NULL, NULL);
 
 	/* Make sure it's completed */
 	synchronize_irq(virq);
@@ -1156,7 +1100,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
 			seq_printf(m, "%5d  ", i);
 			seq_printf(m, "0x%05lx  ", virq_to_hw(i));
 
-			chip = get_irq_desc_chip(desc);
+			chip = irq_desc_get_chip(desc);
 			if (chip && chip->name)
 				p = chip->name;
 			else
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index bd1e1ff17b2..7ee50f0547c 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -31,17 +31,17 @@ void machine_kexec_mask_interrupts(void) {
 		if (!desc)
 			continue;
 
-		chip = get_irq_desc_chip(desc);
+		chip = irq_desc_get_chip(desc);
 		if (!chip)
 			continue;
 
-		if (chip->irq_eoi && desc->status & IRQ_INPROGRESS)
+		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
 			chip->irq_eoi(&desc->irq_data);
 
 		if (chip->irq_mask)
 			chip->irq_mask(&desc->irq_data);
 
-		if (chip->irq_disable && !(desc->status & IRQ_DISABLED))
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
 			chip->irq_disable(&desc->irq_data);
 	}
 }
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index f4adf89d761..10f0aadee95 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -203,7 +203,7 @@ void __init free_unused_pacas(void)
 {
 	int new_size;
 
-	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * num_possible_cpus());
+	new_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
 
 	if (new_size >= paca_size)
 		return;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 3cd85faa8ac..893af2a9cd0 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -261,7 +261,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 
 		virq = irq_create_mapping(NULL, line);
 		if (virq != NO_IRQ)
-			set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
+			irq_set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
 	} else {
 		pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
 			 oirq.size, oirq.specifier[0], oirq.specifier[1],
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 29852688cea..d225d99fe39 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -176,11 +176,14 @@ static void *is_devfn_node(struct device_node *dn, void *data)
  */
 struct device_node *fetch_dev_dn(struct pci_dev *dev)
 {
-	struct device_node *orig_dn = dev->dev.of_node;
+	struct pci_controller *phb = dev->sysdata;
 	struct device_node *dn;
 	unsigned long searchval = (dev->bus->number << 8) | dev->devfn;
 
-	dn = traverse_pci_devices(orig_dn, is_devfn_node, (void *)searchval);
+	if (WARN_ON(!phb))
+		return NULL;
+
+	dn = traverse_pci_devices(phb->dn, is_devfn_node, (void *)searchval);
 	if (dn)
 		dev->dev.of_node = dn;
 	return dn;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8303a6c65ef..f74f355a961 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1218,11 +1218,11 @@ void __ppc64_runlatch_off(void)
 
 static struct kmem_cache *thread_info_cache;
 
-struct thread_info *alloc_thread_info(struct task_struct *tsk)
+struct thread_info *alloc_thread_info_node(struct task_struct *tsk, int node)
 {
 	struct thread_info *ti;
 
-	ti = kmem_cache_alloc(thread_info_cache, GFP_KERNEL);
+	ti = kmem_cache_alloc_node(thread_info_cache, GFP_KERNEL, node);
 	if (unlikely(ti == NULL))
 		return NULL;
 #ifdef CONFIG_DEBUG_STACK_USAGE
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 90653699829..895b082f1e4 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -229,12 +229,16 @@ static int gpr_get(struct task_struct *target, const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   void *kbuf, void __user *ubuf)
 {
-	int ret;
+	int i, ret;
 
 	if (target->thread.regs == NULL)
 		return -EIO;
 
-	CHECK_FULL_REGS(target->thread.regs);
+	if (!FULL_REGS(target->thread.regs)) {
+		/* We have a partial register set.  Fill 14-31 with bogus values */
+		for (i = 14; i < 32; i++)
+			target->thread.regs->gpr[i] = NV_REG_POISON;
+	}
 
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				  target->thread.regs,
@@ -641,11 +645,16 @@ static int gpr32_get(struct task_struct *target,
 	compat_ulong_t *k = kbuf;
 	compat_ulong_t __user *u = ubuf;
 	compat_ulong_t reg;
+	int i;
 
 	if (target->thread.regs == NULL)
 		return -EIO;
 
-	CHECK_FULL_REGS(target->thread.regs);
+	if (!FULL_REGS(target->thread.regs)) {
+		/* We have a partial register set.  Fill 14-31 with bogus values */
+		for (i = 14; i < 32; i++)
+			target->thread.regs->gpr[i] = NV_REG_POISON; 
+	}
 
 	pos /= sizeof(reg);
 	count /= sizeof(reg);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 9d4882a4664..21f30cb6807 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -509,6 +509,9 @@ void __init smp_setup_cpu_maps(void)
 	 */
 	cpu_init_thread_core_maps(nthreads);
 
+	/* Now that possible cpus are set, set nr_cpu_ids for later use */
+	nr_cpu_ids = find_last_bit(cpumask_bits(cpu_possible_mask),NR_CPUS) + 1;
+
 	free_unused_pacas();
 }
 #endif /* CONFIG_SMP */
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 98136050917..cbdbb14be4b 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -57,6 +57,25 @@
 #define DBG(fmt...)
 #endif
 
+
+/* Store all idle threads, this can be reused instead of creating
+* a new thread. Also avoids complicated thread destroy functionality
+* for idle threads.
+*/
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
+ * removed after init for !CONFIG_HOTPLUG_CPU.
+ */
+static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
+#define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
+#define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
+#else
+static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
+#define get_idle_for_cpu(x)      (idle_thread_array[(x)])
+#define set_idle_for_cpu(x, p)   (idle_thread_array[(x)] = (p))
+#endif
+
 struct thread_info *secondary_ti;
 
 DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
@@ -238,23 +257,6 @@ static void __devinit smp_store_cpu_info(int id)
 	per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
 }
 
-static void __init smp_create_idle(unsigned int cpu)
-{
-	struct task_struct *p;
-
-	/* create a process for the processor */
-	p = fork_idle(cpu);
-	if (IS_ERR(p))
-		panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p));
-#ifdef CONFIG_PPC64
-	paca[cpu].__current = p;
-	paca[cpu].kstack = (unsigned long) task_thread_info(p)
-		+ THREAD_SIZE - STACK_FRAME_OVERHEAD;
-#endif
-	current_set[cpu] = task_thread_info(p);
-	task_thread_info(p)->cpu = cpu;
-}
-
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int cpu;
@@ -288,10 +290,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 			max_cpus = NR_CPUS;
 	else
 		max_cpus = 1;
-
-	for_each_possible_cpu(cpu)
-		if (cpu != boot_cpuid)
-			smp_create_idle(cpu);
 }
 
 void __devinit smp_prepare_boot_cpu(void)
@@ -305,7 +303,7 @@ void __devinit smp_prepare_boot_cpu(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 /* State of each CPU during hotplug phases */
-DEFINE_PER_CPU(int, cpu_state) = { 0 };
+static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
 int generic_cpu_disable(void)
 {
@@ -317,30 +315,8 @@ int generic_cpu_disable(void)
 	set_cpu_online(cpu, false);
 #ifdef CONFIG_PPC64
 	vdso_data->processorCount--;
-	fixup_irqs(cpu_online_mask);
-#endif
-	return 0;
-}
-
-int generic_cpu_enable(unsigned int cpu)
-{
-	/* Do the normal bootup if we haven't
-	 * already bootstrapped. */
-	if (system_state != SYSTEM_RUNNING)
-		return -ENOSYS;
-
-	/* get the target out of it's holding state */
-	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
-	smp_wmb();
-
-	while (!cpu_online(cpu))
-		cpu_relax();
-
-#ifdef CONFIG_PPC64
-	fixup_irqs(cpu_online_mask);
-	/* counter the irq disable in fixup_irqs */
-	local_irq_enable();
 #endif
+	migrate_irqs();
 	return 0;
 }
 
@@ -362,37 +338,89 @@ void generic_mach_cpu_die(void)
 	unsigned int cpu;
 
 	local_irq_disable();
+	idle_task_exit();
 	cpu = smp_processor_id();
 	printk(KERN_DEBUG "CPU%d offline\n", cpu);
 	__get_cpu_var(cpu_state) = CPU_DEAD;
 	smp_wmb();
 	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
 		cpu_relax();
-	set_cpu_online(cpu, true);
-	local_irq_enable();
+}
+
+void generic_set_cpu_dead(unsigned int cpu)
+{
+	per_cpu(cpu_state, cpu) = CPU_DEAD;
 }
 #endif
 
-static int __devinit cpu_enable(unsigned int cpu)
+struct create_idle {
+	struct work_struct work;
+	struct task_struct *idle;
+	struct completion done;
+	int cpu;
+};
+
+static void __cpuinit do_fork_idle(struct work_struct *work)
 {
-	if (smp_ops && smp_ops->cpu_enable)
-		return smp_ops->cpu_enable(cpu);
+	struct create_idle *c_idle =
+		container_of(work, struct create_idle, work);
+
+	c_idle->idle = fork_idle(c_idle->cpu);
+	complete(&c_idle->done);
+}
+
+static int __cpuinit create_idle(unsigned int cpu)
+{
+	struct thread_info *ti;
+	struct create_idle c_idle = {
+		.cpu	= cpu,
+		.done	= COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
+	};
+	INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
+
+	c_idle.idle = get_idle_for_cpu(cpu);
+
+	/* We can't use kernel_thread since we must avoid to
+	 * reschedule the child. We use a workqueue because
+	 * we want to fork from a kernel thread, not whatever
+	 * userspace process happens to be trying to online us.
+	 */
+	if (!c_idle.idle) {
+		schedule_work(&c_idle.work);
+		wait_for_completion(&c_idle.done);
+	} else
+		init_idle(c_idle.idle, cpu);
+	if (IS_ERR(c_idle.idle)) {		
+		pr_err("Failed fork for CPU %u: %li", cpu, PTR_ERR(c_idle.idle));
+		return PTR_ERR(c_idle.idle);
+	}
+	ti = task_thread_info(c_idle.idle);
+
+#ifdef CONFIG_PPC64
+	paca[cpu].__current = c_idle.idle;
+	paca[cpu].kstack = (unsigned long)ti + THREAD_SIZE - STACK_FRAME_OVERHEAD;
+#endif
+	ti->cpu = cpu;
+	current_set[cpu] = ti;
 
-	return -ENOSYS;
+	return 0;
 }
 
 int __cpuinit __cpu_up(unsigned int cpu)
 {
-	int c;
+	int rc, c;
 
 	secondary_ti = current_set[cpu];
-	if (!cpu_enable(cpu))
-		return 0;
 
 	if (smp_ops == NULL ||
 	    (smp_ops->cpu_bootable && !smp_ops->cpu_bootable(cpu)))
 		return -EINVAL;
 
+	/* Make sure we have an idle thread */
+	rc = create_idle(cpu);
+	if (rc)
+		return rc;
+
 	/* Make sure callin-map entry is 0 (can be leftover a CPU
 	 * hotplug
 	 */
@@ -502,7 +530,7 @@ static struct device_node *cpu_to_l2cache(int cpu)
 }
 
 /* Activate a secondary processor. */
-int __devinit start_secondary(void *unused)
+void __devinit start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
 	struct device_node *l2_cache;
@@ -523,6 +551,10 @@ int __devinit start_secondary(void *unused)
 
 	secondary_cpu_time_init();
 
+#ifdef CONFIG_PPC64
+	if (system_state == SYSTEM_RUNNING)
+		vdso_data->processorCount++;
+#endif
 	ipi_call_lock();
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
@@ -558,7 +590,8 @@ int __devinit start_secondary(void *unused)
 	local_irq_enable();
 
 	cpu_idle();
-	return 0;
+
+	BUG();
 }
 
 int setup_profiling_timer(unsigned int multiplier)
@@ -585,7 +618,11 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 	free_cpumask_var(old_mask);
 
+	if (smp_ops && smp_ops->bringup_done)
+		smp_ops->bringup_done();
+
 	dump_numa_cpu_topology();
+
 }
 
 int arch_sd_sibling_asym_packing(void)
@@ -660,5 +697,9 @@ void cpu_die(void)
 {
 	if (ppc_md.cpu_die)
 		ppc_md.cpu_die();
+
+	/* If we return, we re-enter start_secondary */
+	start_secondary_resume();
 }
+
 #endif
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 09d31dbf43f..375480c56eb 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -356,7 +356,7 @@ void account_system_vtime(struct task_struct *tsk)
 	}
 	get_paca()->user_time_scaled += user_scaled;
 
-	if (in_irq() || idle_task(smp_processor_id()) != tsk) {
+	if (in_interrupt() || idle_task(smp_processor_id()) != tsk) {
 		account_system_time(tsk, 0, delta, sys_scaled);
 		if (stolen)
 			account_steal_time(stolen);
@@ -577,14 +577,21 @@ void timer_interrupt(struct pt_regs * regs)
 	struct clock_event_device *evt = &decrementer->event;
 	u64 now;
 
+	/* Ensure a positive value is written to the decrementer, or else
+	 * some CPUs will continue to take decrementer exceptions.
+	 */
+	set_dec(DECREMENTER_MAX);
+
+	/* Some implementations of hotplug will get timer interrupts while
+	 * offline, just ignore these
+	 */
+	if (!cpu_online(smp_processor_id()))
+		return;
+
 	trace_timer_interrupt_entry(regs);
 
 	__get_cpu_var(irq_stat).timer_irqs++;
 
-	/* Ensure a positive value is written to the decrementer, or else
-	 * some CPUs will continuue to take decrementer exceptions */
-	set_dec(DECREMENTER_MAX);
-
 #if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index fd8728729ab..142ab1008c3 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -820,17 +820,17 @@ static int __init vdso_init(void)
 }
 arch_initcall(vdso_init);
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return 0;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
 	return 0;
 }
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 	return NULL;
 }