Merge branch 'syscore' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6

* 'syscore' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6:
  Introduce ARCH_NO_SYSDEV_OPS config option (v2)
  cpufreq: Use syscore_ops for boot CPU suspend/resume (v2)
  KVM: Use syscore_ops instead of sysdev class and sysdev
  PCI / Intel IOMMU: Use syscore_ops instead of sysdev class and sysdev
  timekeeping: Use syscore_ops instead of sysdev class and sysdev
  x86: Use syscore_ops instead of sysdev classes and sysdevs

arch/x86/Kconfig

@@ -71,6 +71,7 @@ config X86
 	select GENERIC_IRQ_SHOW
 	select IRQ_FORCED_THREADING
 	select USE_GENERIC_SMP_HELPERS if SMP
+	select ARCH_NO_SYSDEV_OPS
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)

arch/x86/kernel/amd_iommu_init.c

@@ -21,7 +21,7 @@
 #include <linux/acpi.h>
 #include <linux/list.h>
 #include <linux/slab.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/interrupt.h>
 #include <linux/msi.h>
 #include <asm/pci-direct.h>
@@ -1260,7 +1260,7 @@ static void disable_iommus(void)
  * disable suspend until real resume implemented
  */
 
-static int amd_iommu_resume(struct sys_device *dev)
+static void amd_iommu_resume(void)
 {
 	struct amd_iommu *iommu;
 
@@ -1276,11 +1276,9 @@ static int amd_iommu_resume(struct sys_device *dev)
 	 */
 	amd_iommu_flush_all_devices();
 	amd_iommu_flush_all_domains();
-
-	return 0;
 }
 
-static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
+static int amd_iommu_suspend(void)
 {
 	/* disable IOMMUs to go out of the way for BIOS */
 	disable_iommus();
@@ -1288,17 +1286,11 @@ static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static struct sysdev_class amd_iommu_sysdev_class = {
-	.name = "amd_iommu",
+static struct syscore_ops amd_iommu_syscore_ops = {
 	.suspend = amd_iommu_suspend,
 	.resume = amd_iommu_resume,
 };
 
-static struct sys_device device_amd_iommu = {
-	.id = 0,
-	.cls = &amd_iommu_sysdev_class,
-};
-
 /*
  * This is the core init function for AMD IOMMU hardware in the system.
  * This function is called from the generic x86 DMA layer initialization
@@ -1415,14 +1407,6 @@ static int __init amd_iommu_init(void)
 		goto free;
 	}
 
-	ret = sysdev_class_register(&amd_iommu_sysdev_class);
-	if (ret)
-		goto free;
-
-	ret = sysdev_register(&device_amd_iommu);
-	if (ret)
-		goto free;
-
 	ret = amd_iommu_init_devices();
 	if (ret)
 		goto free;
@@ -1441,6 +1425,8 @@ static int __init amd_iommu_init(void)
 
 	amd_iommu_init_notifier();
 
+	register_syscore_ops(&amd_iommu_syscore_ops);
+
 	if (iommu_pass_through)
 		goto out;
 

arch/x86/kernel/apic/apic.c

@@ -24,7 +24,7 @@
 #include <linux/ftrace.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/delay.h>
 #include <linux/timex.h>
 #include <linux/dmar.h>
@@ -2046,7 +2046,7 @@ static struct {
 	unsigned int apic_thmr;
 } apic_pm_state;
 
-static int lapic_suspend(struct sys_device *dev, pm_message_t state)
+static int lapic_suspend(void)
 {
 	unsigned long flags;
 	int maxlvt;
@@ -2084,23 +2084,21 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int lapic_resume(struct sys_device *dev)
+static void lapic_resume(void)
 {
 	unsigned int l, h;
 	unsigned long flags;
-	int maxlvt;
-	int ret = 0;
+	int maxlvt, ret;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
 	if (!apic_pm_state.active)
-		return 0;
+		return;
 
 	local_irq_save(flags);
 	if (intr_remapping_enabled) {
 		ioapic_entries = alloc_ioapic_entries();
 		if (!ioapic_entries) {
 			WARN(1, "Alloc ioapic_entries in lapic resume failed.");
-			ret = -ENOMEM;
 			goto restore;
 		}
 
@@ -2162,8 +2160,6 @@ static int lapic_resume(struct sys_device *dev)
 	}
 restore:
 	local_irq_restore(flags);
-
-	return ret;
 }
 
 /*
@@ -2171,17 +2167,11 @@ static int lapic_resume(struct sys_device *dev)
  * are needed on every CPU up until machine_halt/restart/poweroff.
  */
 
-static struct sysdev_class lapic_sysclass = {
-	.name		= "lapic",
+static struct syscore_ops lapic_syscore_ops = {
 	.resume		= lapic_resume,
 	.suspend	= lapic_suspend,
 };
 
-static struct sys_device device_lapic = {
-	.id	= 0,
-	.cls	= &lapic_sysclass,
-};
-
 static void __cpuinit apic_pm_activate(void)
 {
 	apic_pm_state.active = 1;
@@ -2189,16 +2179,11 @@ static void __cpuinit apic_pm_activate(void)
 
 static int __init init_lapic_sysfs(void)
 {
-	int error;
-
-	if (!cpu_has_apic)
-		return 0;
 	/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
+	if (cpu_has_apic)
+		register_syscore_ops(&lapic_syscore_ops);
 
-	error = sysdev_class_register(&lapic_sysclass);
-	if (!error)
-		error = sysdev_register(&device_lapic);
-	return error;
+	return 0;
 }
 
 /* local apic needs to resume before other devices access its registers. */

arch/x86/kernel/apic/io_apic.c

@@ -30,7 +30,7 @@
 #include <linux/compiler.h>
 #include <linux/acpi.h>
 #include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/msi.h>
 #include <linux/htirq.h>
 #include <linux/freezer.h>
@@ -2918,89 +2918,84 @@ static int __init io_apic_bug_finalize(void)
 
 late_initcall(io_apic_bug_finalize);
 
-struct sysfs_ioapic_data {
-	struct sys_device dev;
-	struct IO_APIC_route_entry entry[0];
-};
-static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
+static struct IO_APIC_route_entry *ioapic_saved_data[MAX_IO_APICS];
 
-static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
+static void suspend_ioapic(int ioapic_id)
 {
-	struct IO_APIC_route_entry *entry;
-	struct sysfs_ioapic_data *data;
+	struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
 	int i;
 
-	data = container_of(dev, struct sysfs_ioapic_data, dev);
-	entry = data->entry;
-	for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ )
-		*entry = ioapic_read_entry(dev->id, i);
+	if (!saved_data)
+		return;
+
+	for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+		saved_data[i] = ioapic_read_entry(ioapic_id, i);
+}
+
+static int ioapic_suspend(void)
+{
+	int ioapic_id;
+
+	for (ioapic_id = 0; ioapic_id < nr_ioapics; ioapic_id++)
+		suspend_ioapic(ioapic_id);
 
 	return 0;
 }
 
-static int ioapic_resume(struct sys_device *dev)
+static void resume_ioapic(int ioapic_id)
 {
-	struct IO_APIC_route_entry *entry;
-	struct sysfs_ioapic_data *data;
+	struct IO_APIC_route_entry *saved_data = ioapic_saved_data[ioapic_id];
 	unsigned long flags;
 	union IO_APIC_reg_00 reg_00;
 	int i;
 
-	data = container_of(dev, struct sysfs_ioapic_data, dev);
-	entry = data->entry;
+	if (!saved_data)
+		return;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	reg_00.raw = io_apic_read(dev->id, 0);
-	if (reg_00.bits.ID != mp_ioapics[dev->id].apicid) {
-		reg_00.bits.ID = mp_ioapics[dev->id].apicid;
-		io_apic_write(dev->id, 0, reg_00.raw);
+	reg_00.raw = io_apic_read(ioapic_id, 0);
+	if (reg_00.bits.ID != mp_ioapics[ioapic_id].apicid) {
+		reg_00.bits.ID = mp_ioapics[ioapic_id].apicid;
+		io_apic_write(ioapic_id, 0, reg_00.raw);
 	}
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-	for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
-		ioapic_write_entry(dev->id, i, entry[i]);
+	for (i = 0; i < nr_ioapic_registers[ioapic_id]; i++)
+		ioapic_write_entry(ioapic_id, i, saved_data[i]);
+}
 
-	return 0;
+static void ioapic_resume(void)
+{
+	int ioapic_id;
+
+	for (ioapic_id = nr_ioapics - 1; ioapic_id >= 0; ioapic_id--)
+		resume_ioapic(ioapic_id);
 }
 
-static struct sysdev_class ioapic_sysdev_class = {
-	.name = "ioapic",
+static struct syscore_ops ioapic_syscore_ops = {
 	.suspend = ioapic_suspend,
 	.resume = ioapic_resume,
 };
 
-static int __init ioapic_init_sysfs(void)
+static int __init ioapic_init_ops(void)
 {
-	struct sys_device * dev;
-	int i, size, error;
+	int i;
 
-	error = sysdev_class_register(&ioapic_sysdev_class);
-	if (error)
-		return error;
+	for (i = 0; i < nr_ioapics; i++) {
+		unsigned int size;
 
-	for (i = 0; i < nr_ioapics; i++ ) {
-		size = sizeof(struct sys_device) + nr_ioapic_registers[i]
+		size = nr_ioapic_registers[i]
 			* sizeof(struct IO_APIC_route_entry);
-		mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
-		if (!mp_ioapic_data[i]) {
-			printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
-			continue;
-		}
-		dev = &mp_ioapic_data[i]->dev;
-		dev->id = i;
-		dev->cls = &ioapic_sysdev_class;
-		error = sysdev_register(dev);
-		if (error) {
-			kfree(mp_ioapic_data[i]);
-			mp_ioapic_data[i] = NULL;
-			printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
-			continue;
-		}
+		ioapic_saved_data[i] = kzalloc(size, GFP_KERNEL);
+		if (!ioapic_saved_data[i])
+			pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
 	}
 
+	register_syscore_ops(&ioapic_syscore_ops);
+
 	return 0;
 }
 
-device_initcall(ioapic_init_sysfs);
+device_initcall(ioapic_init_ops);
 
 /*
  * Dynamic irq allocate and deallocation

arch/x86/kernel/cpu/mcheck/mce.c

@@ -21,6 +21,7 @@
 #include <linux/percpu.h>
 #include <linux/string.h>
 #include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/delay.h>
 #include <linux/ctype.h>
 #include <linux/sched.h>
@@ -1749,14 +1750,14 @@ static int mce_disable_error_reporting(void)
 	return 0;
 }
 
-static int mce_suspend(struct sys_device *dev, pm_message_t state)
+static int mce_suspend(void)
 {
 	return mce_disable_error_reporting();
 }
 
-static int mce_shutdown(struct sys_device *dev)
+static void mce_shutdown(void)
 {
-	return mce_disable_error_reporting();
+	mce_disable_error_reporting();
 }
 
 /*
@@ -1764,14 +1765,18 @@ static int mce_shutdown(struct sys_device *dev)
  * Only one CPU is active at this time, the others get re-added later using
  * CPU hotplug:
  */
-static int mce_resume(struct sys_device *dev)
+static void mce_resume(void)
 {
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
-
-	return 0;
 }
 
+static struct syscore_ops mce_syscore_ops = {
+	.suspend	= mce_suspend,
+	.shutdown	= mce_shutdown,
+	.resume		= mce_resume,
+};
+
 static void mce_cpu_restart(void *data)
 {
 	del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1808,9 +1813,6 @@ static void mce_enable_ce(void *all)
 }
 
 static struct sysdev_class mce_sysclass = {
-	.suspend	= mce_suspend,
-	.shutdown	= mce_shutdown,
-	.resume		= mce_resume,
 	.name		= "machinecheck",
 };
 
@@ -2139,6 +2141,7 @@ static __init int mcheck_init_device(void)
 			return err;
 	}
 
+	register_syscore_ops(&mce_syscore_ops);
 	register_hotcpu_notifier(&mce_cpu_notifier);
 	misc_register(&mce_log_device);
 

arch/x86/kernel/cpu/mtrr/main.c

@@ -45,6 +45,7 @@
 #include <linux/cpu.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/processor.h>
 #include <asm/e820.h>
@@ -630,7 +631,7 @@ struct mtrr_value {
 
 static struct mtrr_value mtrr_value[MTRR_MAX_VAR_RANGES];
 
-static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
+static int mtrr_save(void)
 {
 	int i;
 
@@ -642,7 +643,7 @@ static int mtrr_save(struct sys_device *sysdev, pm_message_t state)
 	return 0;
 }
 
-static int mtrr_restore(struct sys_device *sysdev)
+static void mtrr_restore(void)
 {
 	int i;
 
@@ -653,12 +654,11 @@ static int mtrr_restore(struct sys_device *sysdev)
 				    mtrr_value[i].ltype);
 		}
 	}
-	return 0;
 }
 
 
 
-static struct sysdev_driver mtrr_sysdev_driver = {
+static struct syscore_ops mtrr_syscore_ops = {
 	.suspend	= mtrr_save,
 	.resume		= mtrr_restore,
 };
@@ -839,7 +839,7 @@ static int __init mtrr_init_finialize(void)
 	 * TBD: is there any system with such CPU which supports
 	 * suspend/resume? If no, we should remove the code.
 	 */
-	sysdev_driver_register(&cpu_sysdev_class, &mtrr_sysdev_driver);
+	register_syscore_ops(&mtrr_syscore_ops);
 
 	return 0;
 }

arch/x86/kernel/i8237.c

@@ -10,7 +10,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/dma.h>
 
@@ -21,7 +21,7 @@
  * in asm/dma.h.
  */
 
-static int i8237A_resume(struct sys_device *dev)
+static void i8237A_resume(void)
 {
 	unsigned long flags;
 	int i;
@@ -41,31 +41,15 @@ static int i8237A_resume(struct sys_device *dev)
 	enable_dma(4);
 
 	release_dma_lock(flags);
-
-	return 0;
 }
 
-static int i8237A_suspend(struct sys_device *dev, pm_message_t state)
-{
-	return 0;
-}
-
-static struct sysdev_class i8237_sysdev_class = {
-	.name		= "i8237",
-	.suspend	= i8237A_suspend,
+static struct syscore_ops i8237_syscore_ops = {
 	.resume		= i8237A_resume,
 };
 
-static struct sys_device device_i8237A = {
-	.id		= 0,
-	.cls		= &i8237_sysdev_class,
-};
-
-static int __init i8237A_init_sysfs(void)
+static int __init i8237A_init_ops(void)
 {
-	int error = sysdev_class_register(&i8237_sysdev_class);
-	if (!error)
-		error = sysdev_register(&device_i8237A);
-	return error;
+	register_syscore_ops(&i8237_syscore_ops);
+	return 0;
 }
-device_initcall(i8237A_init_sysfs);
+device_initcall(i8237A_init_ops);

arch/x86/kernel/i8259.c

@@ -8,7 +8,7 @@
 #include <linux/random.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/bitops.h>
 #include <linux/acpi.h>
 #include <linux/io.h>
@@ -245,20 +245,19 @@ static void save_ELCR(char *trigger)
 	trigger[1] = inb(0x4d1) & 0xDE;
 }
 
-static int i8259A_resume(struct sys_device *dev)
+static void i8259A_resume(void)
 {
 	init_8259A(i8259A_auto_eoi);
 	restore_ELCR(irq_trigger);
-	return 0;
 }
 
-static int i8259A_suspend(struct sys_device *dev, pm_message_t state)
+static int i8259A_suspend(void)
 {
 	save_ELCR(irq_trigger);
 	return 0;
 }
 
-static int i8259A_shutdown(struct sys_device *dev)
+static void i8259A_shutdown(void)
 {
 	/* Put the i8259A into a quiescent state that
 	 * the kernel initialization code can get it
@@ -266,21 +265,14 @@ static int i8259A_shutdown(struct sys_device *dev)
 	 */
 	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
 	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-1 */
-	return 0;
 }
 
-static struct sysdev_class i8259_sysdev_class = {
-	.name = "i8259",
+static struct syscore_ops i8259_syscore_ops = {
 	.suspend = i8259A_suspend,
 	.resume = i8259A_resume,
 	.shutdown = i8259A_shutdown,
 };
 
-static struct sys_device device_i8259A = {
-	.id	= 0,
-	.cls	= &i8259_sysdev_class,
-};
-
 static void mask_8259A(void)
 {
 	unsigned long flags;
@@ -399,17 +391,12 @@ struct legacy_pic default_legacy_pic = {
 
 struct legacy_pic *legacy_pic = &default_legacy_pic;
 
-static int __init i8259A_init_sysfs(void)
+static int __init i8259A_init_ops(void)
 {
-	int error;
-
-	if (legacy_pic != &default_legacy_pic)
-		return 0;
+	if (legacy_pic == &default_legacy_pic)
+		register_syscore_ops(&i8259_syscore_ops);
 
-	error = sysdev_class_register(&i8259_sysdev_class);
-	if (!error)
-		error = sysdev_register(&device_i8259A);
-	return error;
+	return 0;
 }
 
-device_initcall(i8259A_init_sysfs);
+device_initcall(i8259A_init_ops);

arch/x86/kernel/microcode_core.c

@@ -82,6 +82,7 @@
 #include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/microcode.h>
 #include <asm/processor.h>
@@ -438,33 +439,25 @@ static int mc_sysdev_remove(struct sys_device *sys_dev)
 	return 0;
 }
 
-static int mc_sysdev_resume(struct sys_device *dev)
+static struct sysdev_driver mc_sysdev_driver = {
+	.add			= mc_sysdev_add,
+	.remove			= mc_sysdev_remove,
+};
+
+/**
+ * mc_bp_resume - Update boot CPU microcode during resume.
+ */
+static void mc_bp_resume(void)
 {
-	int cpu = dev->id;
+	int cpu = smp_processor_id();
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
-	if (!cpu_online(cpu))
-		return 0;
-
-	/*
-	 * All non-bootup cpus are still disabled,
-	 * so only CPU 0 will apply ucode here.
-	 *
-	 * Moreover, there can be no concurrent
-	 * updates from any other places at this point.
-	 */
-	WARN_ON(cpu != 0);
-
 	if (uci->valid && uci->mc)
 		microcode_ops->apply_microcode(cpu);
-
-	return 0;
 }
 
-static struct sysdev_driver mc_sysdev_driver = {
-	.add			= mc_sysdev_add,
-	.remove			= mc_sysdev_remove,
-	.resume			= mc_sysdev_resume,
+static struct syscore_ops mc_syscore_ops = {
+	.resume			= mc_bp_resume,
 };
 
 static __cpuinit int
@@ -542,6 +535,7 @@ static int __init microcode_init(void)
 	if (error)
 		return error;
 
+	register_syscore_ops(&mc_syscore_ops);
 	register_hotcpu_notifier(&mc_cpu_notifier);
 
 	pr_info("Microcode Update Driver: v" MICROCODE_VERSION

arch/x86/kernel/pci-gart_64.c

@@ -27,7 +27,7 @@
 #include <linux/kdebug.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/io.h>
 #include <linux/gfp.h>
 #include <asm/atomic.h>
@@ -589,7 +589,7 @@ void set_up_gart_resume(u32 aper_order, u32 aper_alloc)
 	aperture_alloc = aper_alloc;
 }
 
-static void gart_fixup_northbridges(struct sys_device *dev)
+static void gart_fixup_northbridges(void)
 {
 	int i;
 
@@ -613,33 +613,20 @@ static void gart_fixup_northbridges(struct sys_device *dev)
 	}
 }
 
-static int gart_resume(struct sys_device *dev)
+static void gart_resume(void)
 {
 	pr_info("PCI-DMA: Resuming GART IOMMU\n");
 
-	gart_fixup_northbridges(dev);
+	gart_fixup_northbridges();
 
 	enable_gart_translations();
-
-	return 0;
 }
 
-static int gart_suspend(struct sys_device *dev, pm_message_t state)
-{
-	return 0;
-}
-
-static struct sysdev_class gart_sysdev_class = {
-	.name		= "gart",
-	.suspend	= gart_suspend,
+static struct syscore_ops gart_syscore_ops = {
 	.resume		= gart_resume,
 
 };
 
-static struct sys_device device_gart = {
-	.cls		= &gart_sysdev_class,
-};
-
 /*
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
@@ -650,7 +637,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
 	unsigned aper_base, new_aper_base;
 	struct pci_dev *dev;
 	void *gatt;
-	int i, error;
+	int i;
 
 	pr_info("PCI-DMA: Disabling AGP.\n");
 
@@ -685,12 +672,7 @@ static __init int init_amd_gatt(struct agp_kern_info *info)
 
 	agp_gatt_table = gatt;
 
-	error = sysdev_class_register(&gart_sysdev_class);
-	if (!error)
-		error = sysdev_register(&device_gart);
-	if (error)
-		panic("Could not register gart_sysdev -- "
-		      "would corrupt data on next suspend");
+	register_syscore_ops(&gart_syscore_ops);
 
 	flush_gart();
 

arch/x86/oprofile/nmi_int.c

@@ -15,7 +15,7 @@
 #include <linux/notifier.h>
 #include <linux/smp.h>
 #include <linux/oprofile.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/slab.h>
 #include <linux/moduleparam.h>
 #include <linux/kdebug.h>
@@ -536,7 +536,7 @@ static void nmi_shutdown(void)
 
 #ifdef CONFIG_PM
 
-static int nmi_suspend(struct sys_device *dev, pm_message_t state)
+static int nmi_suspend(void)
 {
 	/* Only one CPU left, just stop that one */
 	if (nmi_enabled == 1)
@@ -544,49 +544,31 @@ static int nmi_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int nmi_resume(struct sys_device *dev)
+static void nmi_resume(void)
 {
 	if (nmi_enabled == 1)
 		nmi_cpu_start(NULL);
-	return 0;
 }
 
-static struct sysdev_class oprofile_sysclass = {
-	.name		= "oprofile",
+static struct syscore_ops oprofile_syscore_ops = {
 	.resume		= nmi_resume,
 	.suspend	= nmi_suspend,
 };
 
-static struct sys_device device_oprofile = {
-	.id	= 0,
-	.cls	= &oprofile_sysclass,
-};
-
-static int __init init_sysfs(void)
+static void __init init_suspend_resume(void)
 {
-	int error;
-
-	error = sysdev_class_register(&oprofile_sysclass);
-	if (error)
-		return error;
-
-	error = sysdev_register(&device_oprofile);
-	if (error)
-		sysdev_class_unregister(&oprofile_sysclass);
-
-	return error;
+	register_syscore_ops(&oprofile_syscore_ops);
 }
 
-static void exit_sysfs(void)
+static void exit_suspend_resume(void)
 {
-	sysdev_unregister(&device_oprofile);
-	sysdev_class_unregister(&oprofile_sysclass);
+	unregister_syscore_ops(&oprofile_syscore_ops);
 }
 
 #else
 
-static inline int  init_sysfs(void) { return 0; }
-static inline void exit_sysfs(void) { }
+static inline void init_suspend_resume(void) { }
+static inline void exit_suspend_resume(void) { }
 
 #endif /* CONFIG_PM */
 
@@ -789,9 +771,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 
 	mux_init(ops);
 
-	ret = init_sysfs();
-	if (ret)
-		return ret;
+	init_suspend_resume();
 
 	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
 	return 0;
@@ -799,5 +779,5 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 
 void op_nmi_exit(void)
 {
-	exit_sysfs();
+	exit_suspend_resume();
 }

drivers/base/Kconfig

@@ -168,4 +168,11 @@ config SYS_HYPERVISOR
 	bool
 	default n
 
+config ARCH_NO_SYSDEV_OPS
+	bool
+	---help---
+	  To be selected by architectures that don't use sysdev class or
+	  sysdev driver power management (suspend/resume) and shutdown
+	  operations.
+
 endmenu

drivers/base/sys.c

@@ -329,7 +329,7 @@ void sysdev_unregister(struct sys_device *sysdev)
 }
 
 
-
+#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
 /**
  *	sysdev_shutdown - Shut down all system devices.
  *
@@ -524,6 +524,7 @@ int sysdev_resume(void)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sysdev_resume);
+#endif /* CONFIG_ARCH_NO_SYSDEV_OPS */
 
 int __init system_bus_init(void)
 {

drivers/cpufreq/cpufreq.c

@@ -28,6 +28,7 @@
 #include <linux/cpu.h>
 #include <linux/completion.h>
 #include <linux/mutex.h>
+#include <linux/syscore_ops.h>
 
 #include <trace/events/power.h>
 
@@ -1340,35 +1341,31 @@ unsigned int cpufreq_get(unsigned int cpu)
 }
 EXPORT_SYMBOL(cpufreq_get);
 
+static struct sysdev_driver cpufreq_sysdev_driver = {
+	.add		= cpufreq_add_dev,
+	.remove		= cpufreq_remove_dev,
+};
+
 
 /**
- *	cpufreq_suspend - let the low level driver prepare for suspend
+ * cpufreq_bp_suspend - Prepare the boot CPU for system suspend.
+ *
+ * This function is only executed for the boot processor.  The other CPUs
+ * have been put offline by means of CPU hotplug.
  */
-
-static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg)
+static int cpufreq_bp_suspend(void)
 {
 	int ret = 0;
 
-	int cpu = sysdev->id;
+	int cpu = smp_processor_id();
 	struct cpufreq_policy *cpu_policy;
 
 	dprintk("suspending cpu %u\n", cpu);
 
-	if (!cpu_online(cpu))
-		return 0;
-
-	/* we may be lax here as interrupts are off. Nonetheless
-	 * we need to grab the correct cpu policy, as to check
-	 * whether we really run on this CPU.
-	 */
-
+	/* If there's no policy for the boot CPU, we have nothing to do. */
 	cpu_policy = cpufreq_cpu_get(cpu);
 	if (!cpu_policy)
-		return -EINVAL;
-
-	/* only handle each CPU group once */
-	if (unlikely(cpu_policy->cpu != cpu))
-		goto out;
+		return 0;
 
 	if (cpufreq_driver->suspend) {
 		ret = cpufreq_driver->suspend(cpu_policy);
@@ -1377,13 +1374,12 @@ static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg)
 					"step on CPU %u\n", cpu_policy->cpu);
 	}
 
-out:
 	cpufreq_cpu_put(cpu_policy);
 	return ret;
 }
 
 /**
- *	cpufreq_resume -  restore proper CPU frequency handling after resume
+ * cpufreq_bp_resume - Restore proper frequency handling of the boot CPU.
  *
  *	1.) resume CPUfreq hardware support (cpufreq_driver->resume())
  *	2.) schedule call cpufreq_update_policy() ASAP as interrupts are
@@ -1391,31 +1387,23 @@ static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg)
  *	    what we believe it to be. This is a bit later than when it
  *	    should be, but nonethteless it's better than calling
  *	    cpufreq_driver->get() here which might re-enable interrupts...
+ *
+ * This function is only executed for the boot CPU.  The other CPUs have not
+ * been turned on yet.
  */
-static int cpufreq_resume(struct sys_device *sysdev)
+static void cpufreq_bp_resume(void)
 {
 	int ret = 0;
 
-	int cpu = sysdev->id;
+	int cpu = smp_processor_id();
 	struct cpufreq_policy *cpu_policy;
 
 	dprintk("resuming cpu %u\n", cpu);
 
-	if (!cpu_online(cpu))
-		return 0;
-
-	/* we may be lax here as interrupts are off. Nonetheless
-	 * we need to grab the correct cpu policy, as to check
-	 * whether we really run on this CPU.
-	 */
-
+	/* If there's no policy for the boot CPU, we have nothing to do. */
 	cpu_policy = cpufreq_cpu_get(cpu);
 	if (!cpu_policy)
-		return -EINVAL;
-
-	/* only handle each CPU group once */
-	if (unlikely(cpu_policy->cpu != cpu))
-		goto fail;
+		return;
 
 	if (cpufreq_driver->resume) {
 		ret = cpufreq_driver->resume(cpu_policy);
@@ -1430,14 +1418,11 @@ static int cpufreq_resume(struct sys_device *sysdev)
 
 fail:
 	cpufreq_cpu_put(cpu_policy);
-	return ret;
 }
 
-static struct sysdev_driver cpufreq_sysdev_driver = {
-	.add		= cpufreq_add_dev,
-	.remove		= cpufreq_remove_dev,
-	.suspend	= cpufreq_suspend,
-	.resume		= cpufreq_resume,
+static struct syscore_ops cpufreq_syscore_ops = {
+	.suspend	= cpufreq_bp_suspend,
+	.resume		= cpufreq_bp_resume,
 };
 
 
@@ -2002,6 +1987,7 @@ static int __init cpufreq_core_init(void)
 	cpufreq_global_kobject = kobject_create_and_add("cpufreq",
 						&cpu_sysdev_class.kset.kobj);
 	BUG_ON(!cpufreq_global_kobject);
+	register_syscore_ops(&cpufreq_syscore_ops);
 
 	return 0;
 }

drivers/pci/intel-iommu.c

@@ -36,7 +36,7 @@
 #include <linux/iova.h>
 #include <linux/iommu.h>
 #include <linux/intel-iommu.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/tboot.h>
 #include <linux/dmi.h>
 #include <asm/cacheflush.h>
@@ -3135,7 +3135,7 @@ static void iommu_flush_all(void)
 	}
 }
 
-static int iommu_suspend(struct sys_device *dev, pm_message_t state)
+static int iommu_suspend(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu = NULL;
@@ -3175,7 +3175,7 @@ static int iommu_suspend(struct sys_device *dev, pm_message_t state)
 	return -ENOMEM;
 }
 
-static int iommu_resume(struct sys_device *dev)
+static void iommu_resume(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu = NULL;
@@ -3183,7 +3183,7 @@ static int iommu_resume(struct sys_device *dev)
 
 	if (init_iommu_hw()) {
 		WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
-		return -EIO;
+		return;
 	}
 
 	for_each_active_iommu(iommu, drhd) {
@@ -3204,40 +3204,20 @@ static int iommu_resume(struct sys_device *dev)
 
 	for_each_active_iommu(iommu, drhd)
 		kfree(iommu->iommu_state);
-
-	return 0;
 }
 
-static struct sysdev_class iommu_sysclass = {
-	.name		= "iommu",
+static struct syscore_ops iommu_syscore_ops = {
 	.resume		= iommu_resume,
 	.suspend	= iommu_suspend,
 };
 
-static struct sys_device device_iommu = {
-	.cls	= &iommu_sysclass,
-};
-
-static int __init init_iommu_sysfs(void)
+static void __init init_iommu_pm_ops(void)
 {
-	int error;
-
-	error = sysdev_class_register(&iommu_sysclass);
-	if (error)
-		return error;
-
-	error = sysdev_register(&device_iommu);
-	if (error)
-		sysdev_class_unregister(&iommu_sysclass);
-
-	return error;
+	register_syscore_ops(&iommu_syscore_ops);
 }
 
 #else
-static int __init init_iommu_sysfs(void)
-{
-	return 0;
-}
+static inline int init_iommu_pm_ops(void) { }
 #endif	/* CONFIG_PM */
 
 /*
@@ -3320,7 +3300,7 @@ int __init intel_iommu_init(void)
 #endif
 	dma_ops = &intel_dma_ops;
 
-	init_iommu_sysfs();
+	init_iommu_pm_ops();
 
 	register_iommu(&intel_iommu_ops);
 

include/linux/device.h

@@ -633,8 +633,12 @@ static inline int devtmpfs_mount(const char *mountpoint) { return 0; }
 /* drivers/base/power/shutdown.c */
 extern void device_shutdown(void);
 
+#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
 /* drivers/base/sys.c */
 extern void sysdev_shutdown(void);
+#else
+static inline void sysdev_shutdown(void) { }
+#endif
 
 /* debugging and troubleshooting/diagnostic helpers. */
 extern const char *dev_driver_string(const struct device *dev);

include/linux/pm.h

@@ -529,13 +529,19 @@ struct dev_power_domain {
  */
 
 #ifdef CONFIG_PM_SLEEP
-extern void device_pm_lock(void);
+#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
+extern int sysdev_suspend(pm_message_t state);
 extern int sysdev_resume(void);
+#else
+static inline int sysdev_suspend(pm_message_t state) { return 0; }
+static inline int sysdev_resume(void) { return 0; }
+#endif
+
+extern void device_pm_lock(void);
 extern void dpm_resume_noirq(pm_message_t state);
 extern void dpm_resume_end(pm_message_t state);
 
 extern void device_pm_unlock(void);
-extern int sysdev_suspend(pm_message_t state);
 extern int dpm_suspend_noirq(pm_message_t state);
 extern int dpm_suspend_start(pm_message_t state);
 

include/linux/sysdev.h

@@ -33,12 +33,13 @@ struct sysdev_class {
 	const char *name;
 	struct list_head	drivers;
 	struct sysdev_class_attribute **attrs;
-
+	struct kset		kset;
+#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
 	/* Default operations for these types of devices */
 	int	(*shutdown)(struct sys_device *);
 	int	(*suspend)(struct sys_device *, pm_message_t state);
 	int	(*resume)(struct sys_device *);
-	struct kset		kset;
+#endif
 };
 
 struct sysdev_class_attribute {
@@ -76,9 +77,11 @@ struct sysdev_driver {
 	struct list_head	entry;
 	int	(*add)(struct sys_device *);
 	int	(*remove)(struct sys_device *);
+#ifndef CONFIG_ARCH_NO_SYSDEV_OPS
 	int	(*shutdown)(struct sys_device *);
 	int	(*suspend)(struct sys_device *, pm_message_t state);
 	int	(*resume)(struct sys_device *);
+#endif
 };
 
 

kernel/time/timekeeping.c

@@ -14,7 +14,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
 #include <linux/time.h>
@@ -597,13 +597,12 @@ static struct timespec timekeeping_suspend_time;
 
 /**
  * timekeeping_resume - Resumes the generic timekeeping subsystem.
- * @dev:	unused
  *
  * This is for the generic clocksource timekeeping.
  * xtime/wall_to_monotonic/jiffies/etc are
  * still managed by arch specific suspend/resume code.
  */
-static int timekeeping_resume(struct sys_device *dev)
+static void timekeeping_resume(void)
 {
 	unsigned long flags;
 	struct timespec ts;
@@ -632,11 +631,9 @@ static int timekeeping_resume(struct sys_device *dev)
 
 	/* Resume hrtimers */
 	hres_timers_resume();
-
-	return 0;
 }
 
-static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
+static int timekeeping_suspend(void)
 {
 	unsigned long flags;
 
@@ -654,26 +651,18 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
 }
 
 /* sysfs resume/suspend bits for timekeeping */
-static struct sysdev_class timekeeping_sysclass = {
-	.name		= "timekeeping",
+static struct syscore_ops timekeeping_syscore_ops = {
 	.resume		= timekeeping_resume,
 	.suspend	= timekeeping_suspend,
 };
 
-static struct sys_device device_timer = {
-	.id		= 0,
-	.cls		= &timekeeping_sysclass,
-};
-
-static int __init timekeeping_init_device(void)
+static int __init timekeeping_init_ops(void)
 {
-	int error = sysdev_class_register(&timekeeping_sysclass);
-	if (!error)
-		error = sysdev_register(&device_timer);
-	return error;
+	register_syscore_ops(&timekeeping_syscore_ops);
+	return 0;
 }
 
-device_initcall(timekeeping_init_device);
+device_initcall(timekeeping_init_ops);
 
 /*
  * If the error is already larger, we look ahead even further

virt/kvm/kvm_main.c

@@ -30,7 +30,7 @@
 #include <linux/debugfs.h>
 #include <linux/highmem.h>
 #include <linux/file.h>
-#include <linux/sysdev.h>
+#include <linux/syscore_ops.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/cpumask.h>
@@ -2446,33 +2446,26 @@ static void kvm_exit_debug(void)
 	debugfs_remove(kvm_debugfs_dir);
 }
 
-static int kvm_suspend(struct sys_device *dev, pm_message_t state)
+static int kvm_suspend(void)
 {
 	if (kvm_usage_count)
 		hardware_disable_nolock(NULL);
 	return 0;
 }
 
-static int kvm_resume(struct sys_device *dev)
+static void kvm_resume(void)
 {
 	if (kvm_usage_count) {
 		WARN_ON(raw_spin_is_locked(&kvm_lock));
 		hardware_enable_nolock(NULL);
 	}
-	return 0;
 }
 
-static struct sysdev_class kvm_sysdev_class = {
-	.name = "kvm",
+static struct syscore_ops kvm_syscore_ops = {
 	.suspend = kvm_suspend,
 	.resume = kvm_resume,
 };
 
-static struct sys_device kvm_sysdev = {
-	.id = 0,
-	.cls = &kvm_sysdev_class,
-};
-
 struct page *bad_page;
 pfn_t bad_pfn;
 
@@ -2556,14 +2549,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		goto out_free_2;
 	register_reboot_notifier(&kvm_reboot_notifier);
 
-	r = sysdev_class_register(&kvm_sysdev_class);
-	if (r)
-		goto out_free_3;
-
-	r = sysdev_register(&kvm_sysdev);
-	if (r)
-		goto out_free_4;
-
 	/* A kmem cache lets us meet the alignment requirements of fx_save. */
 	if (!vcpu_align)
 		vcpu_align = __alignof__(struct kvm_vcpu);
@@ -2571,7 +2556,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 					   0, NULL);
 	if (!kvm_vcpu_cache) {
 		r = -ENOMEM;
-		goto out_free_5;
+		goto out_free_3;
 	}
 
 	r = kvm_async_pf_init();
@@ -2588,6 +2573,8 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		goto out_unreg;
 	}
 
+	register_syscore_ops(&kvm_syscore_ops);
+
 	kvm_preempt_ops.sched_in = kvm_sched_in;
 	kvm_preempt_ops.sched_out = kvm_sched_out;
 
@@ -2599,10 +2586,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	kvm_async_pf_deinit();
 out_free:
 	kmem_cache_destroy(kvm_vcpu_cache);
-out_free_5:
-	sysdev_unregister(&kvm_sysdev);
-out_free_4:
-	sysdev_class_unregister(&kvm_sysdev_class);
 out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
@@ -2630,8 +2613,7 @@ void kvm_exit(void)
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
 	kvm_async_pf_deinit();
-	sysdev_unregister(&kvm_sysdev);
-	sysdev_class_unregister(&kvm_sysdev_class);
+	unregister_syscore_ops(&kvm_syscore_ops);
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
 	on_each_cpu(hardware_disable_nolock, NULL, 1);