17 files changed, 151 insertions, 49 deletions

diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index f35eb45d6576..c4191b3b7056 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -26,11 +26,11 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
-void *
+void __iomem *
 iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
 
 void
-iounmap_atomic(void *kvaddr, enum km_type type);
+iounmap_atomic(void __iomem *kvaddr, enum km_type type);
 
 int
 iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 404a880ea325..d395540ff894 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -27,6 +27,9 @@ extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
 					    int node);
 extern struct pci_bus *pci_scan_bus_with_sysdata(int busno);
 
+#ifdef CONFIG_PCI
+
+#ifdef CONFIG_PCI_DOMAINS
 static inline int pci_domain_nr(struct pci_bus *bus)
 {
 	struct pci_sysdata *sd = bus->sysdata;
@@ -37,13 +40,12 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 {
 	return pci_domain_nr(bus);
 }
-
+#endif
 
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
    or architectures with incomplete PCI setup by the loader */
 
-#ifdef CONFIG_PCI
 extern unsigned int pcibios_assign_all_busses(void);
 extern int pci_legacy_init(void);
 # ifdef CONFIG_ACPI
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index c0427295e8f5..1ca132fc0d03 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -59,5 +59,7 @@ extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 
 extern int notsc_setup(char *);
+extern void save_sched_clock_state(void);
+extern void restore_sched_clock_state(void);
 
 #endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 224392d8fe8c..5e975298fa81 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -530,7 +530,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		err = -ENOMEM;
 		goto out;
 	}
-	if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
 		kfree(b);
 		err = -ENOMEM;
 		goto out;
@@ -543,7 +543,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, c->llc_shared_map);
+	cpumask_set_cpu(cpu, b->cpus);
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index c2a8b26d4fea..d9368eeda309 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -202,10 +202,11 @@ static int therm_throt_process(bool new_event, int event, int level)
 
 #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 sys_device *sys_dev,
+				unsigned int cpu)
 {
 	int err;
-	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
 	err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group);
 	if (err)
@@ -251,7 +252,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
 		mutex_lock(&therm_cpu_lock);
-		err = thermal_throttle_add_dev(sys_dev);
+		err = thermal_throttle_add_dev(sys_dev, cpu);
 		mutex_unlock(&therm_cpu_lock);
 		WARN_ON(err);
 		break;
@@ -287,7 +288,7 @@ 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));
+		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu), cpu);
 		WARN_ON(err);
 	}
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index f2da20fda02d..3efdf2870a35 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1154,7 +1154,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		/*
 		 * event overflow
 		 */
-		handled		= 1;
+		handled++;
 		data.period	= event->hw.last_period;
 
 		if (!x86_perf_event_set_period(event))
@@ -1200,12 +1200,20 @@ void perf_events_lapic_init(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
+struct pmu_nmi_state {
+	unsigned int	marked;
+	int		handled;
+};
+
+static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
+
 static int __kprobes
 perf_event_nmi_handler(struct notifier_block *self,
 			 unsigned long cmd, void *__args)
 {
 	struct die_args *args = __args;
-	struct pt_regs *regs;
+	unsigned int this_nmi;
+	int handled;
 
 	if (!atomic_read(&active_events))
 		return NOTIFY_DONE;
@@ -1214,22 +1222,47 @@ perf_event_nmi_handler(struct notifier_block *self,
 	case DIE_NMI:
 	case DIE_NMI_IPI:
 		break;
-
+	case DIE_NMIUNKNOWN:
+		this_nmi = percpu_read(irq_stat.__nmi_count);
+		if (this_nmi != __get_cpu_var(pmu_nmi).marked)
+			/* let the kernel handle the unknown nmi */
+			return NOTIFY_DONE;
+		/*
+		 * This one is a PMU back-to-back nmi. Two events
+		 * trigger 'simultaneously' raising two back-to-back
+		 * NMIs. If the first NMI handles both, the latter
+		 * will be empty and daze the CPU. So, we drop it to
+		 * avoid false-positive 'unknown nmi' messages.
+		 */
+		return NOTIFY_STOP;
 	default:
 		return NOTIFY_DONE;
 	}
 
-	regs = args->regs;
-
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	/*
-	 * Can't rely on the handled return value to say it was our NMI, two
-	 * events could trigger 'simultaneously' raising two back-to-back NMIs.
-	 *
-	 * If the first NMI handles both, the latter will be empty and daze
-	 * the CPU.
-	 */
-	x86_pmu.handle_irq(regs);
+
+	handled = x86_pmu.handle_irq(args->regs);
+	if (!handled)
+		return NOTIFY_DONE;
+
+	this_nmi = percpu_read(irq_stat.__nmi_count);
+	if ((handled > 1) ||
+		/* the next nmi could be a back-to-back nmi */
+	    ((__get_cpu_var(pmu_nmi).marked == this_nmi) &&
+	     (__get_cpu_var(pmu_nmi).handled > 1))) {
+		/*
+		 * We could have two subsequent back-to-back nmis: The
+		 * first handles more than one counter, the 2nd
+		 * handles only one counter and the 3rd handles no
+		 * counter.
+		 *
+		 * This is the 2nd nmi because the previous was
+		 * handling more than one counter. We will mark the
+		 * next (3rd) and then drop it if unhandled.
+		 */
+		__get_cpu_var(pmu_nmi).marked	= this_nmi + 1;
+		__get_cpu_var(pmu_nmi).handled	= handled;
+	}
 
 	return NOTIFY_STOP;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index d8d86d014008..ee05c90012d2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -712,7 +712,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
 	int bit, loops;
-	u64 ack, status;
+	u64 status;
+	int handled = 0;
 
 	perf_sample_data_init(&data, 0);
 
@@ -728,6 +729,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	loops = 0;
 again:
+	intel_pmu_ack_status(status);
 	if (++loops > 100) {
 		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
 		perf_event_print_debug();
@@ -736,19 +738,22 @@ again:
 	}
 
 	inc_irq_stat(apic_perf_irqs);
-	ack = status;
 
 	intel_pmu_lbr_read();
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
-	if (__test_and_clear_bit(62, (unsigned long *)&status))
+	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+		handled++;
 		x86_pmu.drain_pebs(regs);
+	}
 
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
 
+		handled++;
+
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
@@ -761,8 +766,6 @@ again:
 			x86_pmu_stop(event);
 	}
 
-	intel_pmu_ack_status(ack);
-
 	/*
 	 * Repeat if there is more work to be done:
 	 */
@@ -772,7 +775,7 @@ again:
 
 done:
 	intel_pmu_enable_all(0);
-	return 1;
+	return handled;
 }
 
 static struct event_constraint *
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index febb12cea795..b560db3305be 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -497,6 +497,8 @@ static int p4_hw_config(struct perf_event *event)
 		event->hw.config |= event->attr.config &
 			(p4_config_pack_escr(P4_ESCR_MASK_HT) |
 			 p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED));
+
+		event->hw.config &= ~P4_CCCR_FORCE_OVF;
 	}
 
 	rc = x86_setup_perfctr(event);
@@ -690,7 +692,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 		inc_irq_stat(apic_perf_irqs);
 	}
 
-	return handled > 0;
+	return handled;
 }
 
 /*
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 1f11f5ce668f..a46cb3522c0c 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -40,6 +40,7 @@
 
 static unsigned int		mxcsr_feature_mask __read_mostly = 0xffffffffu;
 unsigned int xstate_size;
+EXPORT_SYMBOL_GPL(xstate_size);
 unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
 static struct i387_fxsave_struct fx_scratch __cpuinitdata;
 
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index a874495b3673..e2a595257390 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -45,8 +45,7 @@ void __init setup_trampoline_page_table(void)
 	/* Copy kernel address range */
 	clone_pgd_range(trampoline_pg_dir + KERNEL_PGD_BOUNDARY,
 			swapper_pg_dir + KERNEL_PGD_BOUNDARY,
-			min_t(unsigned long, KERNEL_PGD_PTRS,
-			      KERNEL_PGD_BOUNDARY));
+			KERNEL_PGD_PTRS);
 
 	/* Initialize low mappings */
 	clone_pgd_range(trampoline_pg_dir,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ce8e50239332..d632934cb638 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -626,6 +626,44 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 	local_irq_restore(flags);
 }
 
+static unsigned long long cyc2ns_suspend;
+
+void save_sched_clock_state(void)
+{
+	if (!sched_clock_stable)
+		return;
+
+	cyc2ns_suspend = sched_clock();
+}
+
+/*
+ * Even on processors with invariant TSC, TSC gets reset in some the
+ * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to
+ * arbitrary value (still sync'd across cpu's) during resume from such sleep
+ * states. To cope up with this, recompute the cyc2ns_offset for each cpu so
+ * that sched_clock() continues from the point where it was left off during
+ * suspend.
+ */
+void restore_sched_clock_state(void)
+{
+	unsigned long long offset;
+	unsigned long flags;
+	int cpu;
+
+	if (!sched_clock_stable)
+		return;
+
+	local_irq_save(flags);
+
+	get_cpu_var(cyc2ns_offset) = 0;
+	offset = cyc2ns_suspend - sched_clock();
+
+	for_each_possible_cpu(cpu)
+		per_cpu(cyc2ns_offset, cpu) = offset;
+
+	local_irq_restore(flags);
+}
+
 #ifdef CONFIG_CPU_FREQ
 
 /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 0fd6378981f4..ddeb2314b522 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -697,6 +697,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	pit->wq = create_singlethread_workqueue("kvm-pit-wq");
 	if (!pit->wq) {
 		mutex_unlock(&pit->pit_state.lock);
+		kvm_free_irq_source_id(kvm, pit->irq_source_id);
 		kfree(pit);
 		return NULL;
 	}
@@ -742,7 +743,7 @@ fail:
 	kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
 	kvm_unregister_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
 	kvm_free_irq_source_id(kvm, pit->irq_source_id);
-
+	destroy_workqueue(pit->wq);
 	kfree(pit);
 	return NULL;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 25f19078b321..3a09c625d526 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2387,7 +2387,7 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 	if (cpu_has_xsave)
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->xsave,
-			sizeof(struct xsave_struct));
+			xstate_size);
 	else {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->fxsave,
@@ -2405,7 +2405,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 
 	if (cpu_has_xsave)
 		memcpy(&vcpu->arch.guest_fpu.state->xsave,
-			guest_xsave->region, sizeof(struct xsave_struct));
+			guest_xsave->region, xstate_size);
 	else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 84e236ce76ba..72fc70cf6184 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -74,7 +74,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 /*
  * Map 'pfn' using fixed map 'type' and protections 'prot'
  */
-void *
+void __iomem *
 iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 {
 	/*
@@ -86,12 +86,12 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 	if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
 		prot = PAGE_KERNEL_UC_MINUS;
 
-	return kmap_atomic_prot_pfn(pfn, type, prot);
+	return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, type, prot);
 }
 EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
 
 void
-iounmap_atomic(void *kvaddr, enum km_type type)
+iounmap_atomic(void __iomem *kvaddr, enum km_type type)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index f6b48f6c5951..cfe4faabb0f6 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -568,8 +568,13 @@ static int __init init_sysfs(void)
 	int error;
 
 	error = sysdev_class_register(&oprofile_sysclass);
-	if (!error)
-		error = sysdev_register(&device_oprofile);
+	if (error)
+		return error;
+
+	error = sysdev_register(&device_oprofile);
+	if (error)
+		sysdev_class_unregister(&oprofile_sysclass);
+
 	return error;
 }
 
@@ -580,8 +585,10 @@ static void exit_sysfs(void)
 }
 
 #else
-#define init_sysfs() do { } while (0)
-#define exit_sysfs() do { } while (0)
+
+static inline int  init_sysfs(void) { return 0; }
+static inline void exit_sysfs(void) { }
+
 #endif /* CONFIG_PM */
 
 static int __init p4_init(char **cpu_type)
@@ -695,6 +702,8 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	char *cpu_type = NULL;
 	int ret = 0;
 
+	using_nmi = 0;
+
 	if (!cpu_has_apic)
 		return -ENODEV;
 
@@ -774,7 +783,10 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 
 	mux_init(ops);
 
-	init_sysfs();
+	ret = init_sysfs();
+	if (ret)
+		return ret;
+
 	using_nmi = 1;
 	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
 	return 0;
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index e7e8c5f54956..87bb35e34ef1 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -113,6 +113,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 void save_processor_state(void)
 {
 	__save_processor_state(&saved_context);
+	save_sched_clock_state();
 }
 #ifdef CONFIG_X86_32
 EXPORT_SYMBOL(save_processor_state);
@@ -229,6 +230,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 void restore_processor_state(void)
 {
 	__restore_processor_state(&saved_context);
+	restore_sched_clock_state();
 }
 #ifdef CONFIG_X86_32
 EXPORT_SYMBOL(restore_processor_state);
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 554c002a1e1a..0f456386cce5 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -72,13 +72,17 @@ void __init xen_unplug_emulated_devices(void)
 {
 	int r;
 
+	/* user explicitly requested no unplug */
+	if (xen_emul_unplug & XEN_UNPLUG_NEVER)
+		return;
 	/* check the version of the xen platform PCI device */
 	r = check_platform_magic();
 	/* If the version matches enable the Xen platform PCI driver.
-	 * Also enable the Xen platform PCI driver if the version is really old
-	 * and the user told us to ignore it. */
+	 * Also enable the Xen platform PCI driver if the host does
+	 * not support the unplug protocol (XEN_PLATFORM_ERR_MAGIC)
+	 * but the user told us that unplugging is unnecessary. */
 	if (r && !(r == XEN_PLATFORM_ERR_MAGIC &&
-			(xen_emul_unplug & XEN_UNPLUG_IGNORE)))
+			(xen_emul_unplug & XEN_UNPLUG_UNNECESSARY)))
 		return;
 	/* Set the default value of xen_emul_unplug depending on whether or
 	 * not the Xen PV frontends and the Xen platform PCI driver have
@@ -99,7 +103,7 @@ void __init xen_unplug_emulated_devices(void)
 		}
 	}
 	/* Now unplug the emulated devices */
-	if (!(xen_emul_unplug & XEN_UNPLUG_IGNORE))
+	if (!(xen_emul_unplug & XEN_UNPLUG_UNNECESSARY))
 		outw(xen_emul_unplug, XEN_IOPORT_UNPLUG);
 	xen_platform_pci_unplug = xen_emul_unplug;
 }
@@ -125,8 +129,10 @@ static int __init parse_xen_emul_unplug(char *arg)
 			xen_emul_unplug |= XEN_UNPLUG_AUX_IDE_DISKS;
 		else if (!strncmp(p, "nics", l))
 			xen_emul_unplug |= XEN_UNPLUG_ALL_NICS;
-		else if (!strncmp(p, "ignore", l))
-			xen_emul_unplug |= XEN_UNPLUG_IGNORE;
+		else if (!strncmp(p, "unnecessary", l))
+			xen_emul_unplug |= XEN_UNPLUG_UNNECESSARY;
+		else if (!strncmp(p, "never", l))
+			xen_emul_unplug |= XEN_UNPLUG_NEVER;
 		else
 			printk(KERN_WARNING "unrecognised option '%s' "
 				 "in parameter 'xen_emul_unplug'\n", p);