Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git…

…/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  kdump: Allow shrinking of kdump region to be overridden
  powerpc/pmac/smp: Remove no-longer needed preempt workaround
  powerpc/smp: Increase vdso_data->processorCount, not just decrease it
  powerpc/smp: Create idle threads on demand and properly reset them
  powerpc/smp: Don't expose per-cpu "cpu_state" array
  powerpc/pmac/smp: Fix CPU hotplug crashes on some machines
  powerpc/smp: Add a smp_ops->bringup_up() done callback
  powerpc/pmac: Rename cpu_state in therm_pm72 to avoid collision
  powerpc/pmac/smp: Properly NAP offlined CPU on G5
  powerpc/pmac/smp: Remove HMT changes for PowerMac offline code
  powerpc/pmac/smp: Consolidate 32-bit and 64-bit PowerMac cpu_die in one file
  powerpc/pmac/smp: Fixup smp_core99_cpu_disable() and use it on 64-bit
  powerpc/pmac/smp: Rename fixup_irqs() to migrate_irqs() and use it on ppc32
  powerpc/pmac/smp: Fix 32-bit PowerMac cpu_die
  powerpc/smp: Remove unused smp_ops->cpu_enable()
  powerpc/smp: Remove unused generic_cpu_enable()
  powerpc/smp: Fix generic_mach_cpu_die()
  powerpc/smp: soft-replugged CPUs must go back to start_secondary
  powerpc: Make decrementer interrupt robust against offlined CPUs

arch/powerpc/include/asm/machdep.h

@@ -35,9 +35,9 @@ 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_enable)(unsigned int nr);
 	int   (*cpu_disable)(void);
 	void  (*cpu_die)(unsigned int nr);
 	int   (*cpu_bootable)(unsigned int nr);
@@ -267,7 +267,6 @@ 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);
 

arch/powerpc/include/asm/smp.h

@@ -36,15 +36,16 @@ 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);
 
 #ifdef CONFIG_HOTPLUG_CPU
-extern void fixup_irqs(const struct cpumask *map);
+extern void migrate_irqs(void);
 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);
+void generic_set_cpu_dead(unsigned int cpu);
 #endif
 
 #ifdef CONFIG_PPC64

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

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

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

arch/powerpc/kernel/irq.c

@@ -246,12 +246,13 @@ 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);
 

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

arch/powerpc/kernel/time.c

@@ -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);

arch/powerpc/platforms/powermac/pmac.h

@@ -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);