Merge commit 'v3.3-rc1' into stable/for-linus-fixes-3.3

* commit 'v3.3-rc1': (9775 commits)
  Linux 3.3-rc1
  x86, syscall: Need __ARCH_WANT_SYS_IPC for 32 bits
  qnx4: don't leak ->BitMap on late failure exits
  qnx4: reduce the insane nesting in qnx4_checkroot()
  qnx4: di_fname is an array, for crying out loud...
  KEYS: Permit key_serial() to be called with a const key pointer
  keys: fix user_defined key sparse messages
  ima: fix cred sparse warning
  uml: fix compile for x86-64
  MPILIB: Add a missing ENOMEM check
  tpm: fix (ACPI S3) suspend regression
  nvme: fix merge error due to change of 'make_request_fn' fn type
  xen: using EXPORT_SYMBOL requires including export.h
  gpio: tps65910: Use correct offset for gpio initialization
  acpi/apei/einj: Add extensions to EINJ from rev 5.0 of acpi spec
  intel_idle: Split up and provide per CPU initialization func
  ACPI processor: Remove unneeded variable passed by acpi_processor_hotadd_init V2
  tg3: Fix single-vector MSI-X code
  openvswitch: Fix multipart datapath dumps.
  ipv6: fix per device IP snmp counters
  ...

6 files changed, 215 insertions, 149 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 319882ef848d..fc4beb393577 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/fs.h>
+#include <linux/preempt.h>
 #include <linux/smp.h>
 #include <linux/notifier.h>
 #include <linux/kdebug.h>
@@ -92,6 +93,18 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 	return NMI_HANDLED;
 }
 
+static void mce_irq_ipi(void *info)
+{
+	int cpu = smp_processor_id();
+	struct mce *m = &__get_cpu_var(injectm);
+
+	if (cpumask_test_cpu(cpu, mce_inject_cpumask) &&
+			m->inject_flags & MCJ_EXCEPTION) {
+		cpumask_clear_cpu(cpu, mce_inject_cpumask);
+		raise_exception(m, NULL);
+	}
+}
+
 /* Inject mce on current CPU */
 static int raise_local(void)
 {
@@ -139,9 +152,10 @@ static void raise_mce(struct mce *m)
 		return;
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	if (m->inject_flags & MCJ_NMI_BROADCAST) {
+	if (m->inject_flags & (MCJ_IRQ_BRAODCAST | MCJ_NMI_BROADCAST)) {
 		unsigned long start;
 		int cpu;
+
 		get_online_cpus();
 		cpumask_copy(mce_inject_cpumask, cpu_online_mask);
 		cpumask_clear_cpu(get_cpu(), mce_inject_cpumask);
@@ -151,13 +165,25 @@ static void raise_mce(struct mce *m)
 			    MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM)
 				cpumask_clear_cpu(cpu, mce_inject_cpumask);
 		}
-		if (!cpumask_empty(mce_inject_cpumask))
-			apic->send_IPI_mask(mce_inject_cpumask, NMI_VECTOR);
+		if (!cpumask_empty(mce_inject_cpumask)) {
+			if (m->inject_flags & MCJ_IRQ_BRAODCAST) {
+				/*
+				 * don't wait because mce_irq_ipi is necessary
+				 * to be sync with following raise_local
+				 */
+				preempt_disable();
+				smp_call_function_many(mce_inject_cpumask,
+					mce_irq_ipi, NULL, 0);
+				preempt_enable();
+			} else if (m->inject_flags & MCJ_NMI_BROADCAST)
+				apic->send_IPI_mask(mce_inject_cpumask,
+						NMI_VECTOR);
+		}
 		start = jiffies;
 		while (!cpumask_empty(mce_inject_cpumask)) {
 			if (!time_before(jiffies, start + 2*HZ)) {
 				printk(KERN_ERR
-				"Timeout waiting for mce inject NMI %lx\n",
+				"Timeout waiting for mce inject %lx\n",
 					*cpumask_bits(mce_inject_cpumask));
 				break;
 			}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index fefcc69ee8b5..ed44c8a65858 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -1,4 +1,4 @@
-#include <linux/sysdev.h>
+#include <linux/device.h>
 #include <asm/mce.h>
 
 enum severity_level {
@@ -17,7 +17,7 @@ enum severity_level {
 struct mce_bank {
 	u64			ctl;			/* subevents to enable */
 	unsigned char init;				/* initialise bank? */
-	struct sysdev_attribute attr;			/* sysdev attribute */
+	struct device_attribute attr;			/* device attribute */
 	char			attrname[ATTR_LEN];	/* attribute name */
 };
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 2af127d4c3d1..5a11ae2e9e91 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -19,7 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/string.h>
-#include <linux/sysdev.h>
+#include <linux/device.h>
 #include <linux/syscore_ops.h>
 #include <linux/delay.h>
 #include <linux/ctype.h>
@@ -95,13 +95,6 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
-/*
- * CPU/chipset specific EDAC code can register a notifier call here to print
- * MCE errors in a human-readable form.
- */
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
-EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
-
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
@@ -109,6 +102,12 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 
 static DEFINE_PER_CPU(struct work_struct, mce_work);
 
+/*
+ * CPU/chipset specific EDAC code can register a notifier call here to print
+ * MCE errors in a human-readable form.
+ */
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+
 /* Do initial initialization of a struct mce */
 void mce_setup(struct mce *m)
 {
@@ -119,9 +118,7 @@ void mce_setup(struct mce *m)
 	m->time = get_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
 	m->cpuid = cpuid_eax(1);
-#ifdef CONFIG_SMP
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
-#endif
 	m->apicid = cpu_data(m->extcpu).initial_apicid;
 	rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap);
 }
@@ -190,6 +187,57 @@ void mce_log(struct mce *mce)
 	set_bit(0, &mce_need_notify);
 }
 
+static void drain_mcelog_buffer(void)
+{
+	unsigned int next, i, prev = 0;
+
+	next = rcu_dereference_check_mce(mcelog.next);
+
+	do {
+		struct mce *m;
+
+		/* drain what was logged during boot */
+		for (i = prev; i < next; i++) {
+			unsigned long start = jiffies;
+			unsigned retries = 1;
+
+			m = &mcelog.entry[i];
+
+			while (!m->finished) {
+				if (time_after_eq(jiffies, start + 2*retries))
+					retries++;
+
+				cpu_relax();
+
+				if (!m->finished && retries >= 4) {
+					pr_err("MCE: skipping error being logged currently!\n");
+					break;
+				}
+			}
+			smp_rmb();
+			atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
+		}
+
+		memset(mcelog.entry + prev, 0, (next - prev) * sizeof(*m));
+		prev = next;
+		next = cmpxchg(&mcelog.next, prev, 0);
+	} while (next != prev);
+}
+
+
+void mce_register_decode_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+	drain_mcelog_buffer();
+}
+EXPORT_SYMBOL_GPL(mce_register_decode_chain);
+
+void mce_unregister_decode_chain(struct notifier_block *nb)
+{
+	atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+}
+EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
+
 static void print_mce(struct mce *m)
 {
 	int ret = 0;
@@ -1770,7 +1818,7 @@ static struct syscore_ops mce_syscore_ops = {
 };
 
 /*
- * mce_sysdev: Sysfs support
+ * mce_device: Sysfs support
  */
 
 static void mce_cpu_restart(void *data)
@@ -1806,27 +1854,28 @@ static void mce_enable_ce(void *all)
 		__mcheck_cpu_init_timer();
 }
 
-static struct sysdev_class mce_sysdev_class = {
+static struct bus_type mce_subsys = {
 	.name		= "machinecheck",
+	.dev_name	= "machinecheck",
 };
 
-DEFINE_PER_CPU(struct sys_device, mce_sysdev);
+struct device *mce_device[CONFIG_NR_CPUS];
 
 __cpuinitdata
 void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
-static inline struct mce_bank *attr_to_bank(struct sysdev_attribute *attr)
+static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
 {
 	return container_of(attr, struct mce_bank, attr);
 }
 
-static ssize_t show_bank(struct sys_device *s, struct sysdev_attribute *attr,
+static ssize_t show_bank(struct device *s, struct device_attribute *attr,
 			 char *buf)
 {
 	return sprintf(buf, "%llx\n", attr_to_bank(attr)->ctl);
 }
 
-static ssize_t set_bank(struct sys_device *s, struct sysdev_attribute *attr,
+static ssize_t set_bank(struct device *s, struct device_attribute *attr,
 			const char *buf, size_t size)
 {
 	u64 new;
@@ -1841,14 +1890,14 @@ static ssize_t set_bank(struct sys_device *s, struct sysdev_attribute *attr,
 }
 
 static ssize_t
-show_trigger(struct sys_device *s, struct sysdev_attribute *attr, char *buf)
+show_trigger(struct device *s, struct device_attribute *attr, char *buf)
 {
 	strcpy(buf, mce_helper);
 	strcat(buf, "\n");
 	return strlen(mce_helper) + 1;
 }
 
-static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
+static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
 				const char *buf, size_t siz)
 {
 	char *p;
@@ -1863,8 +1912,8 @@ static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
 	return strlen(mce_helper) + !!p;
 }
 
-static ssize_t set_ignore_ce(struct sys_device *s,
-			     struct sysdev_attribute *attr,
+static ssize_t set_ignore_ce(struct device *s,
+			     struct device_attribute *attr,
 			     const char *buf, size_t size)
 {
 	u64 new;
@@ -1887,8 +1936,8 @@ static ssize_t set_ignore_ce(struct sys_device *s,
 	return size;
 }
 
-static ssize_t set_cmci_disabled(struct sys_device *s,
-				 struct sysdev_attribute *attr,
+static ssize_t set_cmci_disabled(struct device *s,
+				 struct device_attribute *attr,
 				 const char *buf, size_t size)
 {
 	u64 new;
@@ -1910,108 +1959,117 @@ static ssize_t set_cmci_disabled(struct sys_device *s,
 	return size;
 }
 
-static ssize_t store_int_with_restart(struct sys_device *s,
-				      struct sysdev_attribute *attr,
+static ssize_t store_int_with_restart(struct device *s,
+				      struct device_attribute *attr,
 				      const char *buf, size_t size)
 {
-	ssize_t ret = sysdev_store_int(s, attr, buf, size);
+	ssize_t ret = device_store_int(s, attr, buf, size);
 	mce_restart();
 	return ret;
 }
 
-static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger);
-static SYSDEV_INT_ATTR(tolerant, 0644, tolerant);
-static SYSDEV_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
-static SYSDEV_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);
+static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
+static DEVICE_INT_ATTR(tolerant, 0644, tolerant);
+static DEVICE_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
+static DEVICE_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);
 
-static struct sysdev_ext_attribute attr_check_interval = {
-	_SYSDEV_ATTR(check_interval, 0644, sysdev_show_int,
-		     store_int_with_restart),
+static struct dev_ext_attribute dev_attr_check_interval = {
+	__ATTR(check_interval, 0644, device_show_int, store_int_with_restart),
 	&check_interval
 };
 
-static struct sysdev_ext_attribute attr_ignore_ce = {
-	_SYSDEV_ATTR(ignore_ce, 0644, sysdev_show_int, set_ignore_ce),
+static struct dev_ext_attribute dev_attr_ignore_ce = {
+	__ATTR(ignore_ce, 0644, device_show_int, set_ignore_ce),
 	&mce_ignore_ce
 };
 
-static struct sysdev_ext_attribute attr_cmci_disabled = {
-	_SYSDEV_ATTR(cmci_disabled, 0644, sysdev_show_int, set_cmci_disabled),
+static struct dev_ext_attribute dev_attr_cmci_disabled = {
+	__ATTR(cmci_disabled, 0644, device_show_int, set_cmci_disabled),
 	&mce_cmci_disabled
 };
 
-static struct sysdev_attribute *mce_sysdev_attrs[] = {
-	&attr_tolerant.attr,
-	&attr_check_interval.attr,
-	&attr_trigger,
-	&attr_monarch_timeout.attr,
-	&attr_dont_log_ce.attr,
-	&attr_ignore_ce.attr,
-	&attr_cmci_disabled.attr,
+static struct device_attribute *mce_device_attrs[] = {
+	&dev_attr_tolerant.attr,
+	&dev_attr_check_interval.attr,
+	&dev_attr_trigger,
+	&dev_attr_monarch_timeout.attr,
+	&dev_attr_dont_log_ce.attr,
+	&dev_attr_ignore_ce.attr,
+	&dev_attr_cmci_disabled.attr,
 	NULL
 };
 
-static cpumask_var_t mce_sysdev_initialized;
+static cpumask_var_t mce_device_initialized;
+
+static void mce_device_release(struct device *dev)
+{
+	kfree(dev);
+}
 
-/* Per cpu sysdev init. All of the cpus still share the same ctrl bank: */
-static __cpuinit int mce_sysdev_create(unsigned int cpu)
+/* Per cpu device init. All of the cpus still share the same ctrl bank: */
+static __cpuinit int mce_device_create(unsigned int cpu)
 {
-	struct sys_device *sysdev = &per_cpu(mce_sysdev, cpu);
+	struct device *dev;
 	int err;
 	int i, j;
 
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
-	memset(&sysdev->kobj, 0, sizeof(struct kobject));
-	sysdev->id  = cpu;
-	sysdev->cls = &mce_sysdev_class;
+	dev = kzalloc(sizeof *dev, GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+	dev->id  = cpu;
+	dev->bus = &mce_subsys;
+	dev->release = &mce_device_release;
 
-	err = sysdev_register(sysdev);
+	err = device_register(dev);
 	if (err)
 		return err;
 
-	for (i = 0; mce_sysdev_attrs[i]; i++) {
-		err = sysdev_create_file(sysdev, mce_sysdev_attrs[i]);
+	for (i = 0; mce_device_attrs[i]; i++) {
+		err = device_create_file(dev, mce_device_attrs[i]);
 		if (err)
 			goto error;
 	}
 	for (j = 0; j < banks; j++) {
-		err = sysdev_create_file(sysdev, &mce_banks[j].attr);
+		err = device_create_file(dev, &mce_banks[j].attr);
 		if (err)
 			goto error2;
 	}
-	cpumask_set_cpu(cpu, mce_sysdev_initialized);
+	cpumask_set_cpu(cpu, mce_device_initialized);
+	mce_device[cpu] = dev;
 
 	return 0;
 error2:
 	while (--j >= 0)
-		sysdev_remove_file(sysdev, &mce_banks[j].attr);
+		device_remove_file(dev, &mce_banks[j].attr);
 error:
 	while (--i >= 0)
-		sysdev_remove_file(sysdev, mce_sysdev_attrs[i]);
+		device_remove_file(dev, mce_device_attrs[i]);
 
-	sysdev_unregister(sysdev);
+	device_unregister(dev);
 
 	return err;
 }
 
-static __cpuinit void mce_sysdev_remove(unsigned int cpu)
+static __cpuinit void mce_device_remove(unsigned int cpu)
 {
-	struct sys_device *sysdev = &per_cpu(mce_sysdev, cpu);
+	struct device *dev = mce_device[cpu];
 	int i;
 
-	if (!cpumask_test_cpu(cpu, mce_sysdev_initialized))
+	if (!cpumask_test_cpu(cpu, mce_device_initialized))
 		return;
 
-	for (i = 0; mce_sysdev_attrs[i]; i++)
-		sysdev_remove_file(sysdev, mce_sysdev_attrs[i]);
+	for (i = 0; mce_device_attrs[i]; i++)
+		device_remove_file(dev, mce_device_attrs[i]);
 
 	for (i = 0; i < banks; i++)
-		sysdev_remove_file(sysdev, &mce_banks[i].attr);
+		device_remove_file(dev, &mce_banks[i].attr);
 
-	sysdev_unregister(sysdev);
-	cpumask_clear_cpu(cpu, mce_sysdev_initialized);
+	device_unregister(dev);
+	cpumask_clear_cpu(cpu, mce_device_initialized);
+	mce_device[cpu] = NULL;
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
@@ -2061,7 +2119,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		mce_sysdev_create(cpu);
+		mce_device_create(cpu);
 		if (threshold_cpu_callback)
 			threshold_cpu_callback(action, cpu);
 		break;
@@ -2069,7 +2127,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	case CPU_DEAD_FROZEN:
 		if (threshold_cpu_callback)
 			threshold_cpu_callback(action, cpu);
-		mce_sysdev_remove(cpu);
+		mce_device_remove(cpu);
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
@@ -2103,7 +2161,7 @@ static __init void mce_init_banks(void)
 
 	for (i = 0; i < banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
-		struct sysdev_attribute *a = &b->attr;
+		struct device_attribute *a = &b->attr;
 
 		sysfs_attr_init(&a->attr);
 		a->attr.name	= b->attrname;
@@ -2123,16 +2181,16 @@ static __init int mcheck_init_device(void)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
-	zalloc_cpumask_var(&mce_sysdev_initialized, GFP_KERNEL);
+	zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
 
 	mce_init_banks();
 
-	err = sysdev_class_register(&mce_sysdev_class);
+	err = subsys_system_register(&mce_subsys, NULL);
 	if (err)
 		return err;
 
 	for_each_online_cpu(i) {
-		err = mce_sysdev_create(i);
+		err = mce_device_create(i);
 		if (err)
 			return err;
 	}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index f5474218cffe..786e76a86322 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -17,7 +17,6 @@
 #include <linux/notifier.h>
 #include <linux/kobject.h>
 #include <linux/percpu.h>
-#include <linux/sysdev.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sysfs.h>
@@ -64,11 +63,9 @@ struct threshold_bank {
 };
 static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
 
-#ifdef CONFIG_SMP
 static unsigned char shared_bank[NR_BANKS] = {
 	0, 0, 0, 0, 1
 };
-#endif
 
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
@@ -202,10 +199,9 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 
 			if (!block)
 				per_cpu(bank_map, cpu) |= (1 << bank);
-#ifdef CONFIG_SMP
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
-#endif
+
 			offset = setup_APIC_mce(offset,
 						(high & MASK_LVTOFF_HI) >> 20);
 
@@ -527,11 +523,11 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 {
 	int i, err = 0;
 	struct threshold_bank *b = NULL;
+	struct device *dev = mce_device[cpu];
 	char name[32];
 
 	sprintf(name, "threshold_bank%i", bank);
 
-#ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
 		i = cpumask_first(cpu_llc_shared_mask(cpu));
 
@@ -548,8 +544,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (!b)
 			goto out;
 
-		err = sysfs_create_link(&per_cpu(mce_sysdev, cpu).kobj,
-					b->kobj, name);
+		err = sysfs_create_link(&dev->kobj, b->kobj, name);
 		if (err)
 			goto out;
 
@@ -558,7 +553,6 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 		goto out;
 	}
-#endif
 
 	b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL);
 	if (!b) {
@@ -571,7 +565,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		goto out;
 	}
 
-	b->kobj = kobject_create_and_add(name, &per_cpu(mce_sysdev, cpu).kobj);
+	b->kobj = kobject_create_and_add(name, &dev->kobj);
 	if (!b->kobj)
 		goto out_free;
 
@@ -591,8 +585,9 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (i == cpu)
 			continue;
 
-		err = sysfs_create_link(&per_cpu(mce_sysdev, i).kobj,
-					b->kobj, name);
+		dev = mce_device[i];
+		if (dev)
+			err = sysfs_create_link(&dev->kobj,b->kobj, name);
 		if (err)
 			goto out;
 
@@ -655,6 +650,7 @@ static void deallocate_threshold_block(unsigned int cpu,
 static void threshold_remove_bank(unsigned int cpu, int bank)
 {
 	struct threshold_bank *b;
+	struct device *dev;
 	char name[32];
 	int i = 0;
 
@@ -669,7 +665,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
 #ifdef CONFIG_SMP
 	/* sibling symlink */
 	if (shared_bank[bank] && b->blocks->cpu != cpu) {
-		sysfs_remove_link(&per_cpu(mce_sysdev, cpu).kobj, name);
+		sysfs_remove_link(&mce_device[cpu]->kobj, name);
 		per_cpu(threshold_banks, cpu)[bank] = NULL;
 
 		return;
@@ -681,7 +677,9 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
 		if (i == cpu)
 			continue;
 
-		sysfs_remove_link(&per_cpu(mce_sysdev, i).kobj, name);
+		dev = mce_device[i];
+		if (dev)
+			sysfs_remove_link(&dev->kobj, name);
 		per_cpu(threshold_banks, i)[bank] = NULL;
 	}
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 787e06c84ea6..67bb17a37a0a 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -19,7 +19,6 @@
 #include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/export.h>
-#include <linux/sysdev.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/smp.h>
@@ -69,16 +68,16 @@ static atomic_t therm_throt_en	= ATOMIC_INIT(0);
 static u32 lvtthmr_init __read_mostly;
 
 #ifdef CONFIG_SYSFS
-#define define_therm_throt_sysdev_one_ro(_name)				\
-	static SYSDEV_ATTR(_name, 0444,					\
-			   therm_throt_sysdev_show_##_name,		\
+#define define_therm_throt_device_one_ro(_name)				\
+	static DEVICE_ATTR(_name, 0444,					\
+			   therm_throt_device_show_##_name,		\
 				   NULL)				\
 
-#define define_therm_throt_sysdev_show_func(event, name)		\
+#define define_therm_throt_device_show_func(event, name)		\
 									\
-static ssize_t therm_throt_sysdev_show_##event##_##name(		\
-			struct sys_device *dev,				\
-			struct sysdev_attribute *attr,			\
+static ssize_t therm_throt_device_show_##event##_##name(		\
+			struct device *dev,				\
+			struct device_attribute *attr,			\
 			char *buf)					\
 {									\
 	unsigned int cpu = dev->id;					\
@@ -95,20 +94,20 @@ static ssize_t therm_throt_sysdev_show_##event##_##name(		\
 	return ret;							\
 }
 
-define_therm_throt_sysdev_show_func(core_throttle, count);
-define_therm_throt_sysdev_one_ro(core_throttle_count);
+define_therm_throt_device_show_func(core_throttle, count);
+define_therm_throt_device_one_ro(core_throttle_count);
 
-define_therm_throt_sysdev_show_func(core_power_limit, count);
-define_therm_throt_sysdev_one_ro(core_power_limit_count);
+define_therm_throt_device_show_func(core_power_limit, count);
+define_therm_throt_device_one_ro(core_power_limit_count);
 
-define_therm_throt_sysdev_show_func(package_throttle, count);
-define_therm_throt_sysdev_one_ro(package_throttle_count);
+define_therm_throt_device_show_func(package_throttle, count);
+define_therm_throt_device_one_ro(package_throttle_count);
 
-define_therm_throt_sysdev_show_func(package_power_limit, count);
-define_therm_throt_sysdev_one_ro(package_power_limit_count);
+define_therm_throt_device_show_func(package_power_limit, count);
+define_therm_throt_device_one_ro(package_power_limit_count);
 
 static struct attribute *thermal_throttle_attrs[] = {
-	&attr_core_throttle_count.attr,
+	&dev_attr_core_throttle_count.attr,
 	NULL
 };
 
@@ -223,36 +222,36 @@ static int thresh_event_valid(int event)
 
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
-static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
+static __cpuinit int thermal_throttle_add_dev(struct device *dev,
 				unsigned int cpu)
 {
 	int err;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group);
+	err = sysfs_create_group(&dev->kobj, &thermal_attr_group);
 	if (err)
 		return err;
 
 	if (cpu_has(c, X86_FEATURE_PLN))
-		err = sysfs_add_file_to_group(&sys_dev->kobj,
-					      &attr_core_power_limit_count.attr,
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_core_power_limit_count.attr,
 					      thermal_attr_group.name);
 	if (cpu_has(c, X86_FEATURE_PTS)) {
-		err = sysfs_add_file_to_group(&sys_dev->kobj,
-					      &attr_package_throttle_count.attr,
+		err = sysfs_add_file_to_group(&dev->kobj,
+					      &dev_attr_package_throttle_count.attr,
 					      thermal_attr_group.name);
 		if (cpu_has(c, X86_FEATURE_PLN))
-			err = sysfs_add_file_to_group(&sys_dev->kobj,
-					&attr_package_power_limit_count.attr,
+			err = sysfs_add_file_to_group(&dev->kobj,
+					&dev_attr_package_power_limit_count.attr,
 					thermal_attr_group.name);
 	}
 
 	return err;
 }
 
-static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
+static __cpuinit void thermal_throttle_remove_dev(struct device *dev)
 {
-	sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group);
+	sysfs_remove_group(&dev->kobj, &thermal_attr_group);
 }
 
 /* Mutex protecting device creation against CPU hotplug: */
@@ -265,16 +264,16 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
 			      void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
-	struct sys_device *sys_dev;
+	struct device *dev;
 	int err = 0;
 
-	sys_dev = get_cpu_sysdev(cpu);
+	dev = get_cpu_device(cpu);
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
 		mutex_lock(&therm_cpu_lock);
-		err = thermal_throttle_add_dev(sys_dev, cpu);
+		err = thermal_throttle_add_dev(dev, cpu);
 		mutex_unlock(&therm_cpu_lock);
 		WARN_ON(err);
 		break;
@@ -283,7 +282,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		mutex_lock(&therm_cpu_lock);
-		thermal_throttle_remove_dev(sys_dev);
+		thermal_throttle_remove_dev(dev);
 		mutex_unlock(&therm_cpu_lock);
 		break;
 	}
@@ -310,7 +309,7 @@ static __init int thermal_throttle_init_device(void)
 #endif
 	/* connect live CPUs to sysfs */
 	for_each_online_cpu(cpu) {
-		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu), cpu);
+		err = thermal_throttle_add_dev(get_cpu_device(cpu), cpu);
 		WARN_ON(err);
 	}
 #ifdef CONFIG_HOTPLUG_CPU
@@ -323,17 +322,6 @@ device_initcall(thermal_throttle_init_device);
 
 #endif /* CONFIG_SYSFS */
 
-/*
- * Set up the most two significant bit to notify mce log that this thermal
- * event type.
- * This is a temp solution. May be changed in the future with mce log
- * infrasture.
- */
-#define CORE_THROTTLED		(0)
-#define CORE_POWER_LIMIT	((__u64)1 << 62)
-#define PACKAGE_THROTTLED	((__u64)2 << 62)
-#define PACKAGE_POWER_LIMIT	((__u64)3 << 62)
-
 static void notify_thresholds(__u64 msr_val)
 {
 	/* check whether the interrupt handler is defined;
@@ -363,27 +351,23 @@ static void intel_thermal_interrupt(void)
 	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
 				THERMAL_THROTTLING_EVENT,
 				CORE_LEVEL) != 0)
-		mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
+		mce_log_therm_throt_event(msr_val);
 
 	if (this_cpu_has(X86_FEATURE_PLN))
-		if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
+		therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
-					CORE_LEVEL) != 0)
-			mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
+					CORE_LEVEL);
 
 	if (this_cpu_has(X86_FEATURE_PTS)) {
 		rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
-		if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
+		therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
 					THERMAL_THROTTLING_EVENT,
-					PACKAGE_LEVEL) != 0)
-			mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
+					PACKAGE_LEVEL);
 		if (this_cpu_has(X86_FEATURE_PLN))
-			if (therm_throt_process(msr_val &
+			therm_throt_process(msr_val &
 					PACKAGE_THERM_STATUS_POWER_LIMIT,
 					POWER_LIMIT_EVENT,
-					PACKAGE_LEVEL) != 0)
-				mce_log_therm_throt_event(PACKAGE_POWER_LIMIT
-							  | msr_val);
+					PACKAGE_LEVEL);
 	}
 }
 
@@ -397,8 +381,8 @@ static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
 
 asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
 {
-	exit_idle();
 	irq_enter();
+	exit_idle();
 	inc_irq_stat(irq_thermal_count);
 	smp_thermal_vector();
 	irq_exit();
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index d746df2909c9..aa578cadb940 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -19,8 +19,8 @@ void (*mce_threshold_vector)(void) = default_threshold_interrupt;
 
 asmlinkage void smp_threshold_interrupt(void)
 {
-	exit_idle();
 	irq_enter();
+	exit_idle();
 	inc_irq_stat(irq_threshold_count);
 	mce_threshold_vector();
 	irq_exit();