suspend on G5

@@ -897,7 +897,7 @@ void smp_core99_cpu_die(unsigned int cpu
 	cpu_dead[cpu] = 0;
 }
 
-#endif
+#endif /* CONFIG_HOTPLUG_CPU && CONFIG_PP32 */
 
 /* Core99 Macs (dual G4s and G5s) */
 struct smp_ops_t core99_smp_ops = {

@@ -907,8 +907,16 @@ struct smp_ops_t core99_smp_ops = {
 	.setup_cpu	= smp_core99_setup_cpu,
 	.give_timebase	= smp_core99_give_timebase,
 	.take_timebase	= smp_core99_take_timebase,
-#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32)
+#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,
+	/* intentionally do *NOT* assign cpu_enable,
+	 * the generic code will use kick_cpu then! */
+# endif
 #endif
 };

@@ -425,6 +425,9 @@ static int initializing = 1;
 static int pmac_late_init(void)
 {
 	initializing = 0;
+	/* this is udbg (which is __init) and we can later use it during
+	 * cpu hotplug (in smp_core99_kick_cpu) */
+	ppc_md.progress = NULL;
 	return 0;
 }
 

@@ -651,6 +654,36 @@ static int pmac_pci_probe_mode(struct pc
 		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 pmac_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();
+
+	while (1) {
+		/* let's not take timer interrupts too often ... */
+		set_dec(0x7fffffff);
+		printk("CPU %d dead\n", smp_processor_id());
+
+		power4_idle_irqs_softdisabled();
+	}
+}
+#endif
+
 #endif
 
 define_machine(powermac) {

@@ -689,6 +722,6 @@ define_machine(powermac) {
 	.phys_mem_access_prot	= pci_phys_mem_access_prot,
 #endif
 #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC64)
-	.cpu_die		= generic_mach_cpu_die,
+	.cpu_die		= pmac_cpu_die,
 #endif
 };

@@ -252,6 +252,8 @@ struct machdep_calls {
 
 extern void power4_idle(void);
 extern void ppc6xx_idle(void);
+/* this one is for CPU hotplug (e.g. powermac) */
+extern void power4_idle_irqs_softdisabled(void);
 
 /*
  * ppc_md contains a copy of the machine description structure for the

@@ -354,6 +354,12 @@ static void mpic_startup_ht_interrupt(st
 		tmp |= 0x22;
 	writel(tmp, fixup->base + 4);
 	spin_unlock_irqrestore(&mpic->fixup_lock, flags);
+
+#ifdef CONFIG_PM
+	/* use the lowest bit inverted to the actual HW,
+	 * set if this fixup was enabled, clear otherwise */
+	mpic->save_data[source].fixup_data = tmp | 1;
+#endif
 }
 
 static void mpic_shutdown_ht_interrupt(struct mpic *mpic, unsigned int source,

@@ -375,6 +381,12 @@ static void mpic_shutdown_ht_interrupt(s
 	tmp |= 1;
 	writel(tmp, fixup->base + 4);
 	spin_unlock_irqrestore(&mpic->fixup_lock, flags);
+
+#ifdef CONFIG_PM
+	/* use the lowest bit inverted to the actual HW,
+	 * set if this fixup was enabled, clear otherwise */
+	mpic->save_data[source].fixup_data = tmp & ~1;
+#endif
 }
 
 static void __init mpic_scan_ht_pic(struct mpic *mpic, u8 __iomem *devbase,

@@ -1143,7 +1155,7 @@ void __init mpic_init(struct mpic *mpic)
 	/* Do the HT PIC fixups on U3 broken mpic */
 	DBG("MPIC flags: %x\n", mpic->flags);
 	if ((mpic->flags & MPIC_BROKEN_U3) && (mpic->flags & MPIC_PRIMARY))
- 		mpic_scan_ht_pics(mpic);
+		mpic_scan_ht_pics(mpic);
 
 	for (i = 0; i < mpic->num_sources; i++) {
 		/* start with vector = source number, and masked */

@@ -1167,6 +1179,12 @@ void __init mpic_init(struct mpic *mpic)
 
 	/* Set current processor priority to 0 */
 	mpic_cpu_write(MPIC_INFO(CPU_CURRENT_TASK_PRI), 0);
+
+#ifdef CONFIG_PM
+	/* allocate memory to save mpic state */
+	mpic->save_data = alloc_bootmem(mpic->num_sources * sizeof(struct mpic_irq_save));
+	BUG_ON(mpic->save_data == NULL);
+#endif
 }
 
 void __init mpic_set_clk_ratio(struct mpic *mpic, u32 clock_ratio)

@@ -1417,3 +1435,79 @@ void __devinit smp_mpic_setup_cpu(int cp
 	mpic_setup_this_cpu();
 }
 #endif /* CONFIG_SMP */
+
+#ifdef CONFIG_PM
+static int mpic_suspend(struct sys_device *dev, pm_message_t state)
+{
+	struct mpic *mpic = container_of(dev, struct mpic, sysdev);
+	int i;
+
+	for (i = 0; i < mpic->num_sources; i++) {
+		mpic->save_data[i].vecprio =
+			mpic_irq_read(i, MPIC_INFO(IRQ_VECTOR_PRI));
+		mpic->save_data[i].dest =
+			mpic_irq_read(i, MPIC_INFO(IRQ_DESTINATION));
+	}
+
+	return 0;
+}
+
+static int mpic_resume(struct sys_device *dev)
+{
+	struct mpic *mpic = container_of(dev, struct mpic, sysdev);
+	int i;
+
+	for (i = 0; i < mpic->num_sources; i++) {
+		mpic_irq_write(i, MPIC_INFO(IRQ_VECTOR_PRI),
+			       mpic->save_data[i].vecprio);
+		mpic_irq_write(i, MPIC_INFO(IRQ_DESTINATION),
+			       mpic->save_data[i].dest);
+
+#ifdef CONFIG_MPIC_BROKEN_U3
+	{
+		struct mpic_irq_fixup *fixup = &mpic->fixups[i];
+
+		if (fixup->base) {
+			/* we use the lowest bit in an inverted meaning */
+			if ((mpic->save_data[i].fixup_data & 1) == 0)
+				continue;
+
+			/* Enable and configure */
+			writeb(0x10 + 2 * fixup->index, fixup->base + 2);
+
+			writel(mpic->save_data[i].fixup_data & ~1,
+			       fixup->base + 4);
+		}
+	}
+#endif
+	} /* end for loop */
+
+	return 0;
+}
+#endif
+
+static struct sysdev_class mpic_sysclass = {
+#ifdef CONFIG_PM
+	.resume = mpic_resume,
+	.suspend = mpic_suspend,
+#endif
+	set_kset_name("mpic"),
+};
+
+static int mpic_init_sys(void)
+{
+	struct mpic *mpic = mpics;
+	int error, id = 0;
+
+	error = sysdev_class_register(&mpic_sysclass);
+
+	while (mpic && !error) {
+		mpic->sysdev.cls = &mpic_sysclass;
+		mpic->sysdev.id = id++;
+		error = sysdev_register(&mpic->sysdev);
+		mpic = mpic->next;
+	}
+	return error;
+}
+
+device_initcall(mpic_init_sys);

@@ -3,6 +3,7 @@
 #ifdef __KERNEL__
 
 #include <linux/irq.h>
+#include <linux/sysdev.h>
 #include <asm/dcr.h>
 
 /*

@@ -228,6 +229,14 @@ struct mpic_reg_bank {
 #endif /* CONFIG_PPC_DCR */
 };
 
+struct mpic_irq_save {
+	u32		vecprio,
+			dest;
+#ifdef CONFIG_MPIC_BROKEN_U3
+	u32		fixup_data;
+#endif
+};
+
 /* The instance data of a given MPIC */
 struct mpic
 {

@@ -294,6 +303,12 @@ struct mpic
 
 	/* link */
 	struct mpic		*next;
+
+	struct sys_device	sysdev;
+
+#ifdef CONFIG_PM
+	struct mpic_irq_save	*save_data;
+#endif
 };
 
 /*

@@ -36,6 +36,7 @@
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/vmalloc.h>
+#include <linux/suspend.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>

@@ -54,6 +55,9 @@ static unsigned long dart_tablesize;
 
 /* Virtual base address of the DART table */
 static u32 *dart_vbase;
+#ifdef CONFIG_PM
+static u32 *dart_copy;
+#endif
 
 /* Mapped base address for the dart */
 static unsigned int __iomem *dart;

@@ -346,6 +350,48 @@ void iommu_init_early_dart(void)
 	pci_dma_ops = &dma_direct_ops;
 }
 
+#ifdef CONFIG_PM
+static void iommu_dart_save(void)
+{
+	memcpy(dart_copy, dart_vbase, 2*1024*1024);
+}
+
+static void iommu_dart_restore(void)
+{
+	memcpy(dart_vbase, dart_copy, 2*1024*1024);
+	dart_tlb_invalidate_all();
+}
+
+static int __init iommu_init_late_dart(void)
+{
+	unsigned long tbasepfn;
+	struct page *p;
+
+	/* if no dart table exists then we won't need to save it
+	 * and the area has also not been reserved */
+	if (!dart_tablebase)
+		return 0;
+
+	tbasepfn = __pa(dart_tablebase) >> PAGE_SHIFT;
+	register_nosave_region_late(tbasepfn,
+				    tbasepfn + ((1<<24) >> PAGE_SHIFT));
+
+	/* For suspend we need to copy the dart contents because
+	 * it is not part of the regular mapping (see above) and
+	 * thus not saved automatically. The memory for this copy
+	 * must be allocated early because we need 2 MB. */
+	p = alloc_pages(GFP_KERNEL, 21 - PAGE_SHIFT);
+	BUG_ON(!p);
+	dart_copy = page_address(p);
+
+	ppc_md.iommu_save = iommu_dart_save;
+	ppc_md.iommu_restore = iommu_dart_restore;
+
+	return 0;
+}
+
+late_initcall(iommu_init_late_dart);
+#endif
 
 void __init alloc_dart_table(void)
 {

@@ -26,6 +26,7 @@
 #include <linux/spinlock.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <asm/machdep.h>
 #include <asm/types.h>
 #include <asm/bitops.h>
 

@@ -109,6 +110,19 @@ static inline void pci_iommu_init(void) 
 #endif
 
 extern void alloc_dart_table(void);
+#if defined(CONFIG_PPC64) && defined(CONFIG_PM)
+static inline void iommu_save(void)
+{
+	if (ppc_md.iommu_save)
+		ppc_md.iommu_save();
+}
+
+static inline void iommu_restore(void)
+{
+	if (ppc_md.iommu_restore)
+		ppc_md.iommu_restore();
+}
+#endif
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_IOMMU_H */

@@ -91,6 +91,11 @@ struct machdep_calls {
 	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
 				   unsigned long flags);
 	void		(*iounmap)(volatile void __iomem *token);
+
+#ifdef CONFIG_PM
+	void		(*iommu_save)(void);
+	void		(*iommu_restore)(void);
+#endif
 #endif /* CONFIG_PPC64 */
 
 	int		(*probe)(void);

@@ -31,6 +31,7 @@
 #include <linux/highmem.h>
 #include <linux/initrd.h>
 #include <linux/pagemap.h>
+#include <linux/suspend.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>

@@ -280,6 +281,28 @@ void __init do_init_bootmem(void)
 	init_bootmem_done = 1;
 }
 
+/* mark pages that don't exist as nosave */
+static int __init mark_nonram_nosave(void)
+{
+	unsigned long lmb_next_region_start_pfn,
+		      lmb_region_max_pfn;
+	int i;
+
+	for (i = 0; i < lmb.memory.cnt - 1; i++) {
+		lmb_region_max_pfn =
+			(lmb.memory.region[i].base >> PAGE_SHIFT) +
+			(lmb.memory.region[i].size >> PAGE_SHIFT);
+		lmb_next_region_start_pfn =
+			lmb.memory.region[i+1].base >> PAGE_SHIFT;
+
+		if (lmb_region_max_pfn < lmb_next_region_start_pfn)
+			register_nosave_region(lmb_region_max_pfn,
+					       lmb_next_region_start_pfn);
+	}
+
+	return 0;
+}
+
 /*
  * paging_init() sets up the page tables - in fact we've already done this.
  */

@@ -311,6 +334,8 @@ void __init paging_init(void)
 	max_zone_pfns[ZONE_DMA] = top_of_ram >> PAGE_SHIFT;
 #endif
 	free_area_init_nodes(max_zone_pfns);
+
+	mark_nonram_nosave();
 }
 #endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 

@@ -357,13 +357,13 @@ static unsigned int g5_cpufreq_get_speed
 
 static int g5_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	if (policy->cpu != 0)
-		return -ENODEV;
-
 	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	policy->cur = g5_cpu_freqs[g5_query_freq()].frequency;
-	policy->cpus = cpu_possible_map;
+	/* secondary CPUs are tied to the primary one by the
+	 * cpufreq core if in the secondary policy we tell it that
+	 * it actually must be one policy together with all others. */
+	policy->cpus = cpu_online_map;
 	cpufreq_frequency_table_get_attr(g5_cpu_freqs, policy->cpu);
 
 	return cpufreq_frequency_table_cpuinfo(policy,

@@ -1,7 +1,7 @@
 #ifndef _LINUX_SWSUSP_H
 #define _LINUX_SWSUSP_H
 
-#if defined(CONFIG_X86) || defined(CONFIG_FRV) || defined(CONFIG_PPC32)
+#if defined(CONFIG_X86) || defined(CONFIG_FRV) || defined(CONFIG_PPC32) || defined(CONFIG_PPC64)
 #include <asm/suspend.h>
 #endif
 #include <linux/swap.h>

@@ -0,0 +1,24 @@
+/*
+ * PowerPC 64-bit swsusp implementation
+ *
+ * Copyright 2006 Johannes Berg <[email protected]>
+ *
+ * GPLv2
+ */
+
+#include <asm/system.h>
+#include <asm/iommu.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+void do_after_copyback(void)
+{
+	iommu_restore();
+	touch_softlockup_watchdog();
+	mb();
+}
+
+void _iommu_save(void)
+{
+	iommu_save();
+}

@@ -21,12 +21,12 @@
 #include <linux/types.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/suspend.h>
 #ifdef CONFIG_PPC64
 #include <linux/time.h>
 #include <linux/hardirq.h>
 #else
 #include <linux/ptrace.h>
-#include <linux/suspend.h>
 #endif
 
 #include <asm/io.h>

@@ -257,11 +257,11 @@ int main(void)
 	DEFINE(CPU_SPEC_SETUP, offsetof(struct cpu_spec, cpu_setup));
 	DEFINE(CPU_SPEC_RESTORE, offsetof(struct cpu_spec, cpu_restore));
 
-#ifndef CONFIG_PPC64
 	DEFINE(pbe_address, offsetof(struct pbe, address));
 	DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
 	DEFINE(pbe_next, offsetof(struct pbe, next));
 
+#ifndef CONFIG_PPC64
 	DEFINE(TASK_SIZE, TASK_SIZE);
 	DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28);
 #endif /* ! CONFIG_PPC64 */

@@ -33,8 +33,11 @@
 #include <asm/smp.h>
 
 #ifdef CONFIG_HOTPLUG_CPU
+/* this is used for software suspend, and that shuts down
+ * CPUs even while the system is still booting... */
 #define cpu_should_die()	(cpu_is_offline(smp_processor_id()) && \
-				 system_state == SYSTEM_RUNNING)
+				   (system_state == SYSTEM_RUNNING     \
+				 || system_state == SYSTEM_BOOTING))
 #else
 #define cpu_should_die()	0
 #endif

@@ -32,6 +32,11 @@ void save_processor_state(void)
 #ifdef CONFIG_SPE
 	enable_kernel_spe();
 #endif
+
+#ifdef CONFIG_PPC64
+	hard_irq_disable();
+#endif
+
 }
 
 void restore_processor_state(void)

@@ -39,4 +44,8 @@ void restore_processor_state(void)
 #ifdef CONFIG_PPC32
 	set_context(current->active_mm->context.id, current->active_mm->pgd);
 #endif
+
+#ifdef CONFIG_PPC64
+	hard_irq_enable();
+#endif
 }