[PATCHES] powerpc: Cleanup and fix CPU hotplug

@@ -362,14 +362,13 @@ 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();
 }
 #endif
 

@@ -867,16 +867,14 @@ static void __devinit smp_core99_setup_cpu(int cpu_nr)
 
 #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32)
 
-int smp_core99_cpu_disable(void)
+static int smp_core99_cpu_disable(void)
 {
-	set_cpu_online(smp_processor_id(), false);
+	int rc = generic_cpu_disable();
+	if (rc)
+		return rc;
 
-	/* XXX reset cpu affinity here */
 	mpic_cpu_set_priority(0xf);
-	asm volatile("mtdec %0" : : "r" (0x7fffffff));
-	mb();
-	udelay(20);
-	asm volatile("mtdec %0" : : "r" (0x7fffffff));
+
 	return 0;
 }
 

@@ -902,12 +900,7 @@ struct smp_ops_t core99_smp_ops = {
 	.give_timebase	= smp_core99_give_timebase,
 	.take_timebase	= smp_core99_take_timebase,
 #if defined(CONFIG_HOTPLUG_CPU)
-# if defined(CONFIG_PPC32)
 	.cpu_disable	= smp_core99_cpu_disable,
-# endif
-# if defined(CONFIG_PPC64)
-	.cpu_disable	= generic_cpu_disable,
-# endif
 	.cpu_die	= generic_cpu_die,
 #endif
 };

@@ -37,7 +37,6 @@ struct smp_ops_t {
 	void  (*setup_cpu)(int nr);
 	void  (*take_timebase)(void);
 	void  (*give_timebase)(void);
-	int   (*cpu_enable)(unsigned int nr);
 	int   (*cpu_disable)(void);
 	void  (*cpu_die)(unsigned int nr);
 	int   (*cpu_bootable)(unsigned int nr);

@@ -350,21 +350,11 @@ void generic_mach_cpu_die(void)
 }
 #endif
 
-static int __devinit cpu_enable(unsigned int cpu)
-{
-	if (smp_ops && smp_ops->cpu_enable)
-		return smp_ops->cpu_enable(cpu);
-
-	return -ENOSYS;
-}
-
 int __cpuinit __cpu_up(unsigned int cpu)
 {
 	int 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)))

@@ -923,8 +923,6 @@ struct smp_ops_t core99_smp_ops = {
 # if defined(CONFIG_PPC64)
 	.cpu_disable	= generic_cpu_disable,
 	.cpu_die	= generic_cpu_die,
-	/* intentionally do *NOT* assign cpu_enable,
-	 * the generic code will use kick_cpu then! */
 # endif
 #endif
 };

@@ -43,7 +43,6 @@ DECLARE_PER_CPU(unsigned int, cpu_pvr);
 #ifdef CONFIG_HOTPLUG_CPU
 extern void fixup_irqs(const struct cpumask *map);
 int generic_cpu_disable(void);
-int generic_cpu_enable(unsigned int cpu);
 void generic_cpu_die(unsigned int cpu);
 void generic_mach_cpu_die(void);
 #endif

@@ -322,28 +322,6 @@ int generic_cpu_disable(void)
 	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
-	return 0;
-}
-
 void generic_cpu_die(unsigned int cpu)
 {
 	int i;

@@ -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 continuue 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);

@@ -33,7 +33,6 @@ extern void pmac_setup_pci_dma(void);
 extern void pmac_check_ht_link(void);
 
 extern void pmac_setup_smp(void);
-extern void pmac32_cpu_die(void);
 extern void low_cpu_die(void) __attribute__((noreturn));
 
 extern int pmac_nvram_init(void);

@@ -650,51 +650,6 @@ static int pmac_pci_probe_mode(struct pci_bus *bus)
 		return PCI_PROBE_NORMAL;
 	return PCI_PROBE_DEVTREE;
 }
-
-#ifdef CONFIG_HOTPLUG_CPU
-/* access per cpu vars from generic smp.c */
-DECLARE_PER_CPU(int, cpu_state);
-
-static void pmac64_cpu_die(void)
-{
-	/*
-	 * turn off as much as possible, we'll be
-	 * kicked out as this will only be invoked
-	 * on core99 platforms for now ...
-	 */
-
-	printk(KERN_INFO "CPU#%d offline\n", smp_processor_id());
-	__get_cpu_var(cpu_state) = CPU_DEAD;
-	smp_wmb();
-
-	/*
-	 * during the path that leads here preemption is disabled,
-	 * reenable it now so that when coming up preempt count is
-	 * zero correctly
-	 */
-	preempt_enable();
-
-	/*
-	 * hard-disable interrupts for the non-NAP case, the NAP code
-	 * needs to re-enable interrupts (but soft-disables them)
-	 */
-	hard_irq_disable();
-
-	while (1) {
-		/* let's not take timer interrupts too often ... */
-		set_dec(0x7fffffff);
-
-		/* should always be true at this point */
-		if (cpu_has_feature(CPU_FTR_CAN_NAP))
-			power4_cpu_offline_powersave();
-		else {
-			HMT_low();
-			HMT_very_low();
-		}
-	}
-}
-#endif /* CONFIG_HOTPLUG_CPU */
-
 #endif /* CONFIG_PPC64 */
 
 define_machine(powermac) {

@@ -726,15 +681,4 @@ define_machine(powermac) {
 	.pcibios_after_init	= pmac_pcibios_after_init,
 	.phys_mem_access_prot	= pci_phys_mem_access_prot,
 #endif
-#ifdef CONFIG_HOTPLUG_CPU
-#ifdef CONFIG_PPC64
-	.cpu_die		= pmac64_cpu_die,
-#endif
-#ifdef CONFIG_PPC32
-	.cpu_die		= pmac32_cpu_die,
-#endif
-#endif
-#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32)
-	.cpu_die		= generic_mach_cpu_die,
-#endif
 };

@@ -865,7 +865,7 @@ static void __devinit smp_core99_setup_cpu(int cpu_nr)
 }
 
 
-#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32)
+#ifdef CONFIG_HOTPLUG_CPU
 
 static int smp_core99_cpu_disable(void)
 {

@@ -878,7 +878,9 @@ static int smp_core99_cpu_disable(void)
 	return 0;
 }
 
-void pmac32_cpu_die(void)
+#ifdef CONFIG_PPC32
+
+static void pmac_cpu_die(void)
 {
 	local_irq_disable();
 	idle_task_exit();

@@ -889,7 +891,52 @@ void pmac32_cpu_die(void)
 	low_cpu_die();
 }
 
-#endif /* CONFIG_HOTPLUG_CPU && CONFIG_PP32 */
+#else /* CONFIG_PPC32 */
+
+static void pmac_cpu_die(void)
+{
+	local_irq_disable();
+	idle_task_exit();
+
+	/*
+	 * turn off as much as possible, we'll be
+	 * kicked out as this will only be invoked
+	 * on core99 platforms for now ...
+	 */
+
+	printk(KERN_INFO "CPU#%d offline\n", smp_processor_id());
+	__get_cpu_var(cpu_state) = CPU_DEAD;
+	smp_wmb();
+
+	/*
+	 * during the path that leads here preemption is disabled,
+	 * reenable it now so that when coming up preempt count is
+	 * zero correctly
+	 */
+	preempt_enable();
+
+	/*
+	 * hard-disable interrupts for the non-NAP case, the NAP code
+	 * needs to re-enable interrupts (but soft-disables them)
+	 */
+	hard_irq_disable();
+
+	while (1) {
+		/* let's not take timer interrupts too often ... */
+		set_dec(0x7fffffff);
+
+		/* should always be true at this point */
+		if (cpu_has_feature(CPU_FTR_CAN_NAP))
+			power4_cpu_offline_powersave();
+		else {
+			HMT_low();
+			HMT_very_low();
+		}
+	}
+}
+
+#endif /* else CONFIG_PPC32 */
+#endif /* CONFIG_HOTPLUG_CPU */
 
 /* Core99 Macs (dual G4s and G5s) */
 struct smp_ops_t core99_smp_ops = {

@@ -933,5 +980,10 @@ void __init pmac_setup_smp(void)
 		smp_ops = &psurge_smp_ops;
 	}
 #endif /* CONFIG_PPC32 */
+
+#ifdef CONFIG_HOTPLUG_CPU
+	ppc_md.cpu_die = pmac_cpu_die;
+#endif
 }
 
+

@@ -45,6 +45,7 @@ extern void fixup_irqs(const struct cpumask *map);
 int generic_cpu_disable(void);
 void generic_cpu_die(unsigned int cpu);
 void generic_mach_cpu_die(void);
+DECLARE_PER_CPU(int, cpu_state);
 #endif
 
 #ifdef CONFIG_PPC64

@@ -880,31 +880,17 @@ int smp_core99_cpu_disable(void)
 	return 0;
 }
 
-static int cpu_dead[NR_CPUS];
-
 void pmac32_cpu_die(void)
 {
 	local_irq_disable();
-	cpu_dead[smp_processor_id()] = 1;
+	idle_task_exit();
+	printk(KERN_DEBUG "CPU%d offline\n", smp_processor_id());
+	__get_cpu_var(cpu_state) = CPU_DEAD;
+	smp_wmb();
 	mb();
 	low_cpu_die();
 }
 
-void smp_core99_cpu_die(unsigned int cpu)
-{
-	int timeout;
-
-	timeout = 1000;
-	while (!cpu_dead[cpu]) {
-		if (--timeout == 0) {
-			printk("CPU %u refused to die!\n", cpu);
-			break;
-		}
-		msleep(1);
-	}
-	cpu_dead[cpu] = 0;
-}
-
 #endif /* CONFIG_HOTPLUG_CPU && CONFIG_PP32 */
 
 /* Core99 Macs (dual G4s and G5s) */

@@ -918,12 +904,11 @@ struct smp_ops_t core99_smp_ops = {
 #if defined(CONFIG_HOTPLUG_CPU)
 # if defined(CONFIG_PPC32)
 	.cpu_disable	= smp_core99_cpu_disable,
-	.cpu_die	= smp_core99_cpu_die,
 # endif
 # if defined(CONFIG_PPC64)
 	.cpu_disable	= generic_cpu_disable,
-	.cpu_die	= generic_cpu_die,
 # endif
+	.cpu_die	= generic_cpu_die,
 #endif
 };
 

@@ -41,7 +41,7 @@ extern void start_secondary_resume(void);
 DECLARE_PER_CPU(unsigned int, cpu_pvr);
 
 #ifdef CONFIG_HOTPLUG_CPU
-extern void fixup_irqs(const struct cpumask *map);
+extern void migrate_irqs(void);
 int generic_cpu_disable(void);
 void generic_cpu_die(unsigned int cpu);
 void generic_mach_cpu_die(void);

@@ -303,12 +303,13 @@ 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);
 

@@ -317,8 +317,8 @@ int generic_cpu_disable(void)
 	set_cpu_online(cpu, false);
 #ifdef CONFIG_PPC64
 	vdso_data->processorCount--;
-	fixup_irqs(cpu_online_mask);
 #endif
+	migrate_irqs();
 	return 0;
 }
 

@@ -36,6 +36,7 @@ extern void cpu_die(void);
 
 extern void smp_send_debugger_break(int cpu);
 extern void smp_message_recv(int);
+extern void start_secondary_resume(void);
 
 DECLARE_PER_CPU(unsigned int, cpu_pvr);
 

@@ -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

@@ -502,7 +502,7 @@ 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;

@@ -558,7 +558,8 @@ int __devinit start_secondary(void *unused)
 	local_irq_enable();
 
 	cpu_idle();
-	return 0;
+
+	BUG();
 }
 
 int setup_profiling_timer(unsigned int multiplier)

@@ -660,5 +661,9 @@ 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

@@ -34,6 +34,4 @@ static inline void set_default_offline_state(int cpu)
 #endif
 
 extern enum cpu_state_vals get_preferred_offline_state(int cpu);
-extern int start_secondary(void);
-extern void start_secondary_resume(void);
 #endif

@@ -45,7 +45,7 @@ extern void migrate_irqs(void);
 int generic_cpu_disable(void);
 void generic_cpu_die(unsigned int cpu);
 void generic_mach_cpu_die(void);
-DECLARE_PER_CPU(int, cpu_state);
+void generic_set_cpu_dead(unsigned int cpu);
 #endif
 
 #ifdef CONFIG_PPC64

@@ -305,7 +305,7 @@ 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)
 {

@@ -348,6 +348,11 @@ void generic_mach_cpu_die(void)
 	while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE)
 		cpu_relax();
 }
+
+void generic_set_cpu_dead(unsigned int cpu)
+{
+	__get_cpu_var(cpu_state) = CPU_DEAD;
+}
 #endif
 
 int __cpuinit __cpu_up(unsigned int cpu)

@@ -920,10 +920,12 @@ static int smp_core99_cpu_disable(void)
 
 static void pmac_cpu_die(void)
 {
+	int cpu = smp_processor_id();
+
 	local_irq_disable();
 	idle_task_exit();
-	printk(KERN_DEBUG "CPU%d offline\n", smp_processor_id());
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	pr_debug("CPU%d offline\n", cpu);
+	generic_set_cpu_dead(cpu);
 	smp_wmb();
 	mb();
 	low_cpu_die();

@@ -933,6 +935,8 @@ static void pmac_cpu_die(void)
 
 static void pmac_cpu_die(void)
 {
+	int cpu = smp_processor_id();
+
 	local_irq_disable();
 	idle_task_exit();
 

@@ -942,8 +946,8 @@ static void pmac_cpu_die(void)
 	 * on core99 platforms for now ...
 	 */
 
-	printk(KERN_INFO "CPU#%d offline\n", smp_processor_id());
-	__get_cpu_var(cpu_state) = CPU_DEAD;
+	printk(KERN_INFO "CPU#%d offline\n", cpu);
+	generic_set_cpu_dead(cpu);
 	smp_wmb();
 
 	/*

@@ -35,6 +35,7 @@ struct smp_ops_t {
 	int   (*probe)(void);
 	void  (*kick_cpu)(int nr);
 	void  (*setup_cpu)(int nr);
+	void  (*bringup_done)(void);
 	void  (*take_timebase)(void);
 	void  (*give_timebase)(void);
 	int   (*cpu_disable)(void);

@@ -553,7 +553,11 @@ 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)

@@ -928,10 +928,6 @@ static void pmac_cpu_die(void)
 		/* should always be true at this point */
 		if (cpu_has_feature(CPU_FTR_CAN_NAP))
 			power4_cpu_offline_powersave();
-		else {
-			HMT_low();
-			HMT_very_low();
-		}
 	}
 }
 

@@ -951,13 +951,6 @@ static void pmac_cpu_die(void)
 	smp_wmb();
 
 	/*
-	 * during the path that leads here preemption is disabled,
-	 * reenable it now so that when coming up preempt count is
-	 * zero correctly
-	 */
-	preempt_enable();
-
-	/*
 	 * Re-enable interrupts. The NAP code needs to enable them
 	 * anyways, do it now so we deal with the case where one already
 	 * happened while soft-disabled.

@@ -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)

@@ -355,9 +353,62 @@ void generic_set_cpu_dead(unsigned int cpu)
 }
 #endif
 
+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)
+{
+	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 0;
+}
+
 int __cpuinit __cpu_up(unsigned int cpu)
 {
-	int c;
+	int rc, c;
 
 	secondary_ti = current_set[cpu];
 

@@ -365,6 +416,11 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	    (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
 	 */

@@ -551,6 +551,10 @@ void __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);

@@ -153,7 +153,7 @@ static struct i2c_adapter *		u3_0;
 static struct i2c_adapter *		u3_1;
 static struct i2c_adapter *		k2;
 static struct i2c_client *		fcu;
-static struct cpu_pid_state		cpu_state[2];
+static struct cpu_pid_state		processor_state[2];
 static struct basckside_pid_params	backside_params;
 static struct backside_pid_state	backside_state;
 static struct drives_pid_state		drives_state;

@@ -664,8 +664,8 @@ static int read_eeprom(int cpu, struct mpu_data *out)
 
 static void fetch_cpu_pumps_minmax(void)
 {
-	struct cpu_pid_state *state0 = &cpu_state[0];
-	struct cpu_pid_state *state1 = &cpu_state[1];
+	struct cpu_pid_state *state0 = &processor_state[0];
+	struct cpu_pid_state *state1 = &processor_state[1];
 	u16 pump_min = 0, pump_max = 0xffff;
 	u16 tmp[4];
 

@@ -717,17 +717,17 @@ static ssize_t show_##name(struct device *dev, struct device_attribute *attr, ch
 	return sprintf(buf, "%d", data);			\
 }
 
-BUILD_SHOW_FUNC_FIX(cpu0_temperature, cpu_state[0].last_temp)
-BUILD_SHOW_FUNC_FIX(cpu0_voltage, cpu_state[0].voltage)
-BUILD_SHOW_FUNC_FIX(cpu0_current, cpu_state[0].current_a)
-BUILD_SHOW_FUNC_INT(cpu0_exhaust_fan_rpm, cpu_state[0].rpm)
-BUILD_SHOW_FUNC_INT(cpu0_intake_fan_rpm, cpu_state[0].intake_rpm)
+BUILD_SHOW_FUNC_FIX(cpu0_temperature, processor_state[0].last_temp)
+BUILD_SHOW_FUNC_FIX(cpu0_voltage, processor_state[0].voltage)
+BUILD_SHOW_FUNC_FIX(cpu0_current, processor_state[0].current_a)
+BUILD_SHOW_FUNC_INT(cpu0_exhaust_fan_rpm, processor_state[0].rpm)
+BUILD_SHOW_FUNC_INT(cpu0_intake_fan_rpm, processor_state[0].intake_rpm)
 
-BUILD_SHOW_FUNC_FIX(cpu1_temperature, cpu_state[1].last_temp)
-BUILD_SHOW_FUNC_FIX(cpu1_voltage, cpu_state[1].voltage)
-BUILD_SHOW_FUNC_FIX(cpu1_current, cpu_state[1].current_a)
-BUILD_SHOW_FUNC_INT(cpu1_exhaust_fan_rpm, cpu_state[1].rpm)
-BUILD_SHOW_FUNC_INT(cpu1_intake_fan_rpm, cpu_state[1].intake_rpm)
+BUILD_SHOW_FUNC_FIX(cpu1_temperature, processor_state[1].last_temp)
+BUILD_SHOW_FUNC_FIX(cpu1_voltage, processor_state[1].voltage)
+BUILD_SHOW_FUNC_FIX(cpu1_current, processor_state[1].current_a)
+BUILD_SHOW_FUNC_INT(cpu1_exhaust_fan_rpm, processor_state[1].rpm)
+BUILD_SHOW_FUNC_INT(cpu1_intake_fan_rpm, processor_state[1].intake_rpm)
 
 BUILD_SHOW_FUNC_FIX(backside_temperature, backside_state.last_temp)
 BUILD_SHOW_FUNC_INT(backside_fan_pwm, backside_state.pwm)

@@ -919,8 +919,8 @@ static void do_cpu_pid(struct cpu_pid_state *state, s32 temp, s32 power)
 
 static void do_monitor_cpu_combined(void)
 {
-	struct cpu_pid_state *state0 = &cpu_state[0];
-	struct cpu_pid_state *state1 = &cpu_state[1];
+	struct cpu_pid_state *state0 = &processor_state[0];
+	struct cpu_pid_state *state1 = &processor_state[1];
 	s32 temp0, power0, temp1, power1;
 	s32 temp_combi, power_combi;
 	int rc, intake, pump;

@@ -1150,7 +1150,7 @@ static void do_monitor_cpu_rack(struct cpu_pid_state *state)
 /*
  * Initialize the state structure for one CPU control loop
  */
-static int init_cpu_state(struct cpu_pid_state *state, int index)
+static int init_processor_state(struct cpu_pid_state *state, int index)
 {
 	int err;
 

@@ -1205,7 +1205,7 @@ static int init_cpu_state(struct cpu_pid_state *state, int index)
 /*
  * Dispose of the state data for one CPU control loop
  */
-static void dispose_cpu_state(struct cpu_pid_state *state)
+static void dispose_processor_state(struct cpu_pid_state *state)
 {
 	if (state->monitor == NULL)
 		return;

@@ -1804,9 +1804,9 @@ static int main_control_loop(void *x)
 		set_pwm_fan(SLOTS_FAN_PWM_INDEX, SLOTS_FAN_DEFAULT_PWM);
 
 	/* Initialize ADCs */
-	initialize_adc(&cpu_state[0]);
-	if (cpu_state[1].monitor != NULL)
-		initialize_adc(&cpu_state[1]);
+	initialize_adc(&processor_state[0]);
+	if (processor_state[1].monitor != NULL)
+		initialize_adc(&processor_state[1]);
 
 	fcu_tickle_ticks = FCU_TICKLE_TICKS;
 

@@ -1833,14 +1833,14 @@ static int main_control_loop(void *x)
 		if (cpu_pid_type == CPU_PID_TYPE_COMBINED)
 			do_monitor_cpu_combined();
 		else if (cpu_pid_type == CPU_PID_TYPE_RACKMAC) {
-			do_monitor_cpu_rack(&cpu_state[0]);
-			if (cpu_state[1].monitor != NULL)
-				do_monitor_cpu_rack(&cpu_state[1]);
+			do_monitor_cpu_rack(&processor_state[0]);
+			if (processor_state[1].monitor != NULL)
+				do_monitor_cpu_rack(&processor_state[1]);
 			// better deal with UP
 		} else {
-			do_monitor_cpu_split(&cpu_state[0]);
-			if (cpu_state[1].monitor != NULL)
-				do_monitor_cpu_split(&cpu_state[1]);
+			do_monitor_cpu_split(&processor_state[0]);
+			if (processor_state[1].monitor != NULL)
+				do_monitor_cpu_split(&processor_state[1]);
 			// better deal with UP
 		}
 		/* Then, the rest */

@@ -1885,8 +1885,8 @@ static int main_control_loop(void *x)
  */
 static void dispose_control_loops(void)
 {
-	dispose_cpu_state(&cpu_state[0]);
-	dispose_cpu_state(&cpu_state[1]);
+	dispose_processor_state(&processor_state[0]);
+	dispose_processor_state(&processor_state[1]);
 	dispose_backside_state(&backside_state);
 	dispose_drives_state(&drives_state);
 	dispose_slots_state(&slots_state);

@@ -1928,12 +1928,12 @@ static int create_control_loops(void)
 	/* Create control loops for everything. If any fail, everything
 	 * fails
 	 */
-	if (init_cpu_state(&cpu_state[0], 0))
+	if (init_processor_state(&processor_state[0], 0))
 		goto fail;
 	if (cpu_pid_type == CPU_PID_TYPE_COMBINED)
 		fetch_cpu_pumps_minmax();
 
-	if (cpu_count > 1 && init_cpu_state(&cpu_state[1], 1))
+	if (cpu_count > 1 && init_processor_state(&processor_state[1], 1))
 		goto fail;
 	if (init_backside_state(&backside_state))
 		goto fail;

@@ -840,30 +840,68 @@ static void __devinit smp_core99_setup_cpu(int cpu_nr)
 
 	/* Setup openpic */
 	mpic_setup_this_cpu();
+}
 
-	if (cpu_nr == 0) {
-#ifdef CONFIG_PPC64
-		extern void g5_phy_disable_cpu1(void);
+#ifdef CONFIG_HOTPLUG_CPU
+static int smp_core99_cpu_notify(struct notifier_block *self,
+				 unsigned long action, void *hcpu)
+{
+	int rc;
 
-		/* Close i2c bus if it was used for tb sync */
+	switch(action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		/* Open i2c bus if it was used for tb sync */
 		if (pmac_tb_clock_chip_host) {
-			pmac_i2c_close(pmac_tb_clock_chip_host);
-			pmac_tb_clock_chip_host	= NULL;
+			rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
+			if (rc) {
+				pr_err("Failed to open i2c bus for time sync\n");
+				return notifier_from_errno(rc);
+			}
 		}
+		break;
+	case CPU_ONLINE:
+	case CPU_UP_CANCELED:
+		/* Close i2c bus if it was used for tb sync */
+		if (pmac_tb_clock_chip_host)
+			pmac_i2c_close(pmac_tb_clock_chip_host);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
 
-		/* If we didn't start the second CPU, we must take
-		 * it off the bus
-		 */
-		if (of_machine_is_compatible("MacRISC4") &&
-		    num_online_cpus() < 2)		
-			g5_phy_disable_cpu1();
-#endif /* CONFIG_PPC64 */
+static struct notifier_block __cpuinitdata smp_core99_cpu_nb = {
+	.notifier_call	= smp_core99_cpu_notify,
+};
+#endif /* CONFIG_HOTPLUG_CPU */
 
-		if (ppc_md.progress)
-			ppc_md.progress("core99_setup_cpu 0 done", 0x349);
+static void __init smp_core99_bringup_done(void)
+{
+#ifdef CONFIG_PPC64
+	extern void g5_phy_disable_cpu1(void);
+
+	/* Close i2c bus if it was used for tb sync */
+	if (pmac_tb_clock_chip_host)
+		pmac_i2c_close(pmac_tb_clock_chip_host);
+
+	/* If we didn't start the second CPU, we must take
+	 * it off the bus.
+	 */
+	if (of_machine_is_compatible("MacRISC4") &&
+	    num_online_cpus() < 2) {
+		set_cpu_present(1, false);
+		g5_phy_disable_cpu1();
 	}
-}
+#endif /* CONFIG_PPC64 */
 
+#ifdef CONFIG_HOTPLUG_CPU
+	register_cpu_notifier(&smp_core99_cpu_nb);
+#endif
+	if (ppc_md.progress)
+		ppc_md.progress("smp_core99_bringup_done", 0x349);
+}
 
 #ifdef CONFIG_HOTPLUG_CPU
 

@@ -940,6 +978,7 @@ static void pmac_cpu_die(void)
 struct smp_ops_t core99_smp_ops = {
 	.message_pass	= smp_mpic_message_pass,
 	.probe		= smp_core99_probe,
+	.bringup_done	= smp_core99_bringup_done,
 	.kick_cpu	= smp_core99_kick_cpu,
 	.setup_cpu	= smp_core99_setup_cpu,
 	.give_timebase	= smp_core99_give_timebase,

@@ -266,7 +266,6 @@ struct machdep_calls {
 
 extern void e500_idle(void);
 extern void power4_idle(void);
-extern void power4_cpu_offline_powersave(void);
 extern void ppc6xx_idle(void);
 extern void book3e_idle(void);
 

@@ -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

@@ -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

@@ -916,18 +916,20 @@ static void pmac_cpu_die(void)
 	preempt_enable();
 
 	/*
-	 * hard-disable interrupts for the non-NAP case, the NAP code
-	 * needs to re-enable interrupts (but soft-disables them)
+	 * Re-enable interrupts. The NAP code needs to enable them
+	 * anyways, do it now so we deal with the case where one already
+	 * happened while soft-disabled.
+	 * We shouldn't get any external interrupts, only decrementer, and the
+	 * decrementer handler is safe for use on offline CPUs
 	 */
-	hard_irq_disable();
+	local_irq_enable();
 
 	while (1) {
 		/* let's not take timer interrupts too often ... */
 		set_dec(0x7fffffff);
 
-		/* should always be true at this point */
-		if (cpu_has_feature(CPU_FTR_CAN_NAP))
-			power4_cpu_offline_powersave();
+		/* Enter NAP mode */
+		power4_idle();
 	}
 }