Merge branch 'for-2.6.34' into for-2.6.35

27 files changed, 284 insertions, 515 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a54d714545f..0061ea26306 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -490,6 +490,7 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
  *  ACPI based hotplug support for CPU
  */
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
+#include <acpi/processor.h>
 
 static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
@@ -567,6 +568,8 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
 		goto free_new_map;
 	}
 
+	acpi_processor_set_pdc(handle);
+
 	cpu = cpumask_first(new_map);
 	acpi_map_cpu2node(handle, cpu, physid);
 
@@ -1293,23 +1296,6 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d)
 }
 
 /*
- * Limit ACPI to CPU enumeration for HT
- */
-static int __init force_acpi_ht(const struct dmi_system_id *d)
-{
-	if (!acpi_force) {
-		printk(KERN_NOTICE "%s detected: force use of acpi=ht\n",
-		       d->ident);
-		disable_acpi();
-		acpi_ht = 1;
-	} else {
-		printk(KERN_NOTICE
-		       "Warning: acpi=force overrules DMI blacklist: acpi=ht\n");
-	}
-	return 0;
-}
-
-/*
  * Force ignoring BIOS IRQ0 pin2 override
  */
 static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
@@ -1345,82 +1331,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
 	 },
 
 	/*
-	 * Boxes that need acpi=ht
-	 */
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "FSC Primergy T850",
-	 .matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "PRIMERGY T850"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "HP VISUALIZE NT Workstation",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "Hewlett-Packard"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "HP VISUALIZE NT Workstation"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "Compaq Workstation W8000",
-	 .matches = {
-		     DMI_MATCH(DMI_SYS_VENDOR, "Compaq"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "Workstation W8000"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "ASUS CUR-DLS",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
-		     DMI_MATCH(DMI_BOARD_NAME, "CUR-DLS"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "ABIT i440BX-W83977",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "ABIT <http://www.abit.com>"),
-		     DMI_MATCH(DMI_BOARD_NAME, "i440BX-W83977 (BP6)"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "IBM Bladecenter",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
-		     DMI_MATCH(DMI_BOARD_NAME, "IBM eServer BladeCenter HS20"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "IBM eServer xSeries 360",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
-		     DMI_MATCH(DMI_BOARD_NAME, "eServer xSeries 360"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "IBM eserver xSeries 330",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
-		     DMI_MATCH(DMI_BOARD_NAME, "eserver xSeries 330"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
-	 .ident = "IBM eserver xSeries 440",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
-		     DMI_MATCH(DMI_PRODUCT_NAME, "eserver xSeries 440"),
-		     },
-	 },
-
-	/*
 	 * Boxes that need ACPI PCI IRQ routing disabled
 	 */
 	{
@@ -1652,8 +1562,10 @@ static int __init parse_acpi(char *arg)
 	}
 	/* Limit ACPI just to boot-time to enable HT */
 	else if (strcmp(arg, "ht") == 0) {
-		if (!acpi_force)
+		if (!acpi_force) {
+			printk(KERN_WARNING "acpi=ht will be removed in Linux-2.6.35\n");
 			disable_acpi();
+		}
 		acpi_ht = 1;
 	}
 	/* acpi=rsdt use RSDT instead of XSDT */
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index f147a95fd84..3704997e8b2 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -31,7 +31,6 @@
 #include <asm/x86_init.h>
 
 int gart_iommu_aperture;
-EXPORT_SYMBOL_GPL(gart_iommu_aperture);
 int gart_iommu_aperture_disabled __initdata;
 int gart_iommu_aperture_allowed __initdata;
 
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index e3c3d820c32..09d3b17ce0c 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -223,7 +223,7 @@ struct apic apic_flat =  {
 };
 
 /*
- * Physflat mode is used when there are more than 8 CPUs on a AMD system.
+ * Physflat mode is used when there are more than 8 CPUs on a system.
  * We cannot use logical delivery in this case because the mask
  * overflows, so use physical mode.
  */
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 3740c8a4eae..49dbeaef2a2 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -120,11 +120,9 @@ EXPORT_SYMBOL_GPL(uv_possible_blades);
 unsigned long sn_rtc_cycles_per_second;
 EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
-
 static const struct cpumask *uv_target_cpus(void)
 {
-	return cpumask_of(0);
+	return cpu_online_mask;
 }
 
 static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 879666f4d87..7e1cca13af3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -70,7 +70,8 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		sched_clock_stable = 1;
+		if (!check_tsc_unstable())
+			sched_clock_stable = 1;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 28cba46bf32..3ab9c886b61 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -46,6 +46,13 @@
 
 #include "mce-internal.h"
 
+static DEFINE_MUTEX(mce_read_mutex);
+
+#define rcu_dereference_check_mce(p) \
+	rcu_dereference_check((p), \
+			      rcu_read_lock_sched_held() || \
+			      lockdep_is_held(&mce_read_mutex))
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
 
@@ -158,7 +165,7 @@ void mce_log(struct mce *mce)
 	mce->finished = 0;
 	wmb();
 	for (;;) {
-		entry = rcu_dereference(mcelog.next);
+		entry = rcu_dereference_check_mce(mcelog.next);
 		for (;;) {
 			/*
 			 * When the buffer fills up discard new entries.
@@ -1485,8 +1492,6 @@ static void collect_tscs(void *data)
 	rdtscll(cpu_tsc[smp_processor_id()]);
 }
 
-static DEFINE_MUTEX(mce_read_mutex);
-
 static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
 			loff_t *off)
 {
@@ -1500,7 +1505,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
 		return -ENOMEM;
 
 	mutex_lock(&mce_read_mutex);
-	next = rcu_dereference(mcelog.next);
+	next = rcu_dereference_check_mce(mcelog.next);
 
 	/* Only supports full reads right now */
 	if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) {
@@ -1565,7 +1570,7 @@ timeout:
 static unsigned int mce_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &mce_wait, wait);
-	if (rcu_dereference(mcelog.next))
+	if (rcu_dereference_check_mce(mcelog.next))
 		return POLLIN | POLLRDNORM;
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 7c785634af2..d15df6e49bf 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -95,7 +95,7 @@ static void cmci_discover(int banks, int boot)
 
 		/* Already owned by someone else? */
 		if (val & CMCI_EN) {
-			if (test_and_clear_bit(i, owned) || boot)
+			if (test_and_clear_bit(i, owned) && !boot)
 				print_update("SHD", &hdr, i);
 			__clear_bit(i, __get_cpu_var(mce_poll_banks));
 			continue;
@@ -107,7 +107,7 @@ static void cmci_discover(int banks, int boot)
 
 		/* Did the enable bit stick? -- the bank supports CMCI */
 		if (val & CMCI_EN) {
-			if (!test_and_set_bit(i, owned) || boot)
+			if (!test_and_set_bit(i, owned) && !boot)
 				print_update("CMCI", &hdr, i);
 			__clear_bit(i, __get_cpu_var(mce_poll_banks));
 		} else {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b1fbdeecf6c..60398a0d947 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -73,10 +73,10 @@ struct debug_store {
 struct event_constraint {
 	union {
 		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
-		u64		idxmsk64[1];
+		u64		idxmsk64;
 	};
-	int	code;
-	int	cmask;
+	u64	code;
+	u64	cmask;
 	int	weight;
 };
 
@@ -103,7 +103,7 @@ struct cpu_hw_events {
 };
 
 #define __EVENT_CONSTRAINT(c, n, m, w) {\
-	{ .idxmsk64[0] = (n) },		\
+	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
 	.cmask = (m),			\
 	.weight = (w),			\
@@ -116,7 +116,7 @@ struct cpu_hw_events {
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVTSEL_MASK)
 
 #define FIXED_EVENT_CONSTRAINT(c, n)	\
-	EVENT_CONSTRAINT(c, n, INTEL_ARCH_FIXED_MASK)
+	EVENT_CONSTRAINT(c, (1ULL << (32+n)), INTEL_ARCH_FIXED_MASK)
 
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
@@ -133,8 +133,8 @@ struct x86_pmu {
 	int		(*handle_irq)(struct pt_regs *);
 	void		(*disable_all)(void);
 	void		(*enable_all)(void);
-	void		(*enable)(struct hw_perf_event *, int);
-	void		(*disable)(struct hw_perf_event *, int);
+	void		(*enable)(struct perf_event *);
+	void		(*disable)(struct perf_event *);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	u64		(*event_map)(int);
@@ -157,6 +157,11 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
+
+	void		(*cpu_prepare)(int cpu);
+	void		(*cpu_starting)(int cpu);
+	void		(*cpu_dying)(int cpu);
+	void		(*cpu_dead)(int cpu);
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -165,8 +170,7 @@ static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
 };
 
-static int x86_perf_event_set_period(struct perf_event *event,
-			     struct hw_perf_event *hwc, int idx);
+static int x86_perf_event_set_period(struct perf_event *event);
 
 /*
  * Generalized hw caching related hw_event table, filled
@@ -189,11 +193,12 @@ static u64 __read_mostly hw_cache_event_ids
  * Returns the delta events processed.
  */
 static u64
-x86_perf_event_update(struct perf_event *event,
-			struct hw_perf_event *hwc, int idx)
+x86_perf_event_update(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.event_bits;
 	u64 prev_raw_count, new_raw_count;
+	int idx = hwc->idx;
 	s64 delta;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
@@ -293,7 +298,7 @@ static inline bool bts_available(void)
 	return x86_pmu.enable_bts != NULL;
 }
 
-static inline void init_debug_store_on_cpu(int cpu)
+static void init_debug_store_on_cpu(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
 
@@ -305,7 +310,7 @@ static inline void init_debug_store_on_cpu(int cpu)
 		     (u32)((u64)(unsigned long)ds >> 32));
 }
 
-static inline void fini_debug_store_on_cpu(int cpu)
+static void fini_debug_store_on_cpu(int cpu)
 {
 	if (!per_cpu(cpu_hw_events, cpu).ds)
 		return;
@@ -503,6 +508,9 @@ static int __hw_perf_event_init(struct perf_event *event)
 	 */
 	if (attr->type == PERF_TYPE_RAW) {
 		hwc->config |= x86_pmu.raw_event(attr->config);
+		if ((hwc->config & ARCH_PERFMON_EVENTSEL_ANY) &&
+		    perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
+			return -EACCES;
 		return 0;
 	}
 
@@ -553,9 +561,9 @@ static void x86_pmu_disable_all(void)
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 		rdmsrl(x86_pmu.eventsel + idx, val);
-		if (!(val & ARCH_PERFMON_EVENTSEL0_ENABLE))
+		if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
 			continue;
-		val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(x86_pmu.eventsel + idx, val);
 	}
 }
@@ -590,7 +598,7 @@ static void x86_pmu_enable_all(void)
 			continue;
 
 		val = event->hw.config;
-		val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 		wrmsrl(x86_pmu.eventsel + idx, val);
 	}
 }
@@ -612,8 +620,8 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 
 	for (i = 0; i < n; i++) {
-		constraints[i] =
-		  x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+		c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
+		constraints[i] = c;
 	}
 
 	/*
@@ -635,7 +643,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		if (test_bit(hwc->idx, used_mask))
 			break;
 
-		set_bit(hwc->idx, used_mask);
+		__set_bit(hwc->idx, used_mask);
 		if (assign)
 			assign[i] = hwc->idx;
 	}
@@ -684,7 +692,7 @@ static int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			if (j == X86_PMC_IDX_MAX)
 				break;
 
-			set_bit(j, used_mask);
+			__set_bit(j, used_mask);
 
 			if (assign)
 				assign[i] = j;
@@ -777,6 +785,7 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc,
 		hwc->last_tag == cpuc->tags[i];
 }
 
+static int x86_pmu_start(struct perf_event *event);
 static void x86_pmu_stop(struct perf_event *event);
 
 void hw_perf_enable(void)
@@ -793,6 +802,7 @@ void hw_perf_enable(void)
 		return;
 
 	if (cpuc->n_added) {
+		int n_running = cpuc->n_events - cpuc->n_added;
 		/*
 		 * apply assignment obtained either from
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
@@ -800,8 +810,7 @@ void hw_perf_enable(void)
 		 * step1: save events moving to new counters
 		 * step2: reprogram moved events into new counters
 		 */
-		for (i = 0; i < cpuc->n_events; i++) {
-
+		for (i = 0; i < n_running; i++) {
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
 
@@ -816,29 +825,18 @@ void hw_perf_enable(void)
 				continue;
 
 			x86_pmu_stop(event);
-
-			hwc->idx = -1;
 		}
 
 		for (i = 0; i < cpuc->n_events; i++) {
-
 			event = cpuc->event_list[i];
 			hwc = &event->hw;
 
-			if (hwc->idx == -1) {
+			if (!match_prev_assignment(hwc, cpuc, i))
 				x86_assign_hw_event(event, cpuc, i);
-				x86_perf_event_set_period(event, hwc, hwc->idx);
-			}
-			/*
-			 * need to mark as active because x86_pmu_disable()
-			 * clear active_mask and events[] yet it preserves
-			 * idx
-			 */
-			set_bit(hwc->idx, cpuc->active_mask);
-			cpuc->events[hwc->idx] = event;
+			else if (i < n_running)
+				continue;
 
-			x86_pmu.enable(hwc, hwc->idx);
-			perf_event_update_userpage(event);
+			x86_pmu_start(event);
 		}
 		cpuc->n_added = 0;
 		perf_events_lapic_init();
@@ -850,15 +848,16 @@ void hw_perf_enable(void)
 	x86_pmu.enable_all();
 }
 
-static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc)
 {
-	(void)checking_wrmsrl(hwc->config_base + idx,
-			      hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx,
+			      hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
-static inline void x86_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+static inline void x86_pmu_disable_event(struct perf_event *event)
 {
-	(void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
+	struct hw_perf_event *hwc = &event->hw;
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, hwc->config);
 }
 
 static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
@@ -868,12 +867,12 @@ static DEFINE_PER_CPU(u64 [X86_PMC_IDX_MAX], pmc_prev_left);
  * To be called with the event disabled in hw:
  */
 static int
-x86_perf_event_set_period(struct perf_event *event,
-			     struct hw_perf_event *hwc, int idx)
+x86_perf_event_set_period(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	s64 left = atomic64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
-	int err, ret = 0;
+	int err, ret = 0, idx = hwc->idx;
 
 	if (idx == X86_PMC_IDX_FIXED_BTS)
 		return 0;
@@ -919,11 +918,11 @@ x86_perf_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static void x86_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void x86_pmu_enable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	if (cpuc->enabled)
-		__x86_pmu_enable_event(hwc, idx);
+		__x86_pmu_enable_event(&event->hw);
 }
 
 /*
@@ -959,34 +958,32 @@ static int x86_pmu_enable(struct perf_event *event)
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->n_events = n;
-	cpuc->n_added  = n - n0;
+	cpuc->n_added += n - n0;
 
 	return 0;
 }
 
 static int x86_pmu_start(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx = event->hw.idx;
 
-	if (hwc->idx == -1)
+	if (idx == -1)
 		return -EAGAIN;
 
-	x86_perf_event_set_period(event, hwc, hwc->idx);
-	x86_pmu.enable(hwc, hwc->idx);
+	x86_perf_event_set_period(event);
+	cpuc->events[idx] = event;
+	__set_bit(idx, cpuc->active_mask);
+	x86_pmu.enable(event);
+	perf_event_update_userpage(event);
 
 	return 0;
 }
 
 static void x86_pmu_unthrottle(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (WARN_ON_ONCE(hwc->idx >= X86_PMC_IDX_MAX ||
-				cpuc->events[hwc->idx] != event))
-		return;
-
-	x86_pmu.enable(hwc, hwc->idx);
+	int ret = x86_pmu_start(event);
+	WARN_ON_ONCE(ret);
 }
 
 void perf_event_print_debug(void)
@@ -1046,18 +1043,16 @@ static void x86_pmu_stop(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
-	/*
-	 * Must be done before we disable, otherwise the nmi handler
-	 * could reenable again:
-	 */
-	clear_bit(idx, cpuc->active_mask);
-	x86_pmu.disable(hwc, idx);
+	if (!__test_and_clear_bit(idx, cpuc->active_mask))
+		return;
+
+	x86_pmu.disable(event);
 
 	/*
 	 * Drain the remaining delta count out of a event
 	 * that we are disabling:
 	 */
-	x86_perf_event_update(event, hwc, idx);
+	x86_perf_event_update(event);
 
 	cpuc->events[idx] = NULL;
 }
@@ -1094,8 +1089,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 	int idx, handled = 0;
 	u64 val;
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
@@ -1106,7 +1100,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		event = cpuc->events[idx];
 		hwc = &event->hw;
 
-		val = x86_perf_event_update(event, hwc, idx);
+		val = x86_perf_event_update(event);
 		if (val & (1ULL << (x86_pmu.event_bits - 1)))
 			continue;
 
@@ -1116,11 +1110,11 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		handled		= 1;
 		data.period	= event->hw.last_period;
 
-		if (!x86_perf_event_set_period(event, hwc, idx))
+		if (!x86_perf_event_set_period(event))
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu.disable(hwc, idx);
+			x86_pmu_stop(event);
 	}
 
 	if (handled)
@@ -1307,7 +1301,7 @@ int hw_perf_group_sched_in(struct perf_event *leader,
 	memcpy(cpuc->assign, assign, n0*sizeof(int));
 
 	cpuc->n_events  = n0;
-	cpuc->n_added   = n1;
+	cpuc->n_added  += n1;
 	ctx->nr_active += n1;
 
 	/*
@@ -1335,6 +1329,39 @@ undo:
 #include "perf_event_p6.c"
 #include "perf_event_intel.c"
 
+static int __cpuinit
+x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		if (x86_pmu.cpu_prepare)
+			x86_pmu.cpu_prepare(cpu);
+		break;
+
+	case CPU_STARTING:
+		if (x86_pmu.cpu_starting)
+			x86_pmu.cpu_starting(cpu);
+		break;
+
+	case CPU_DYING:
+		if (x86_pmu.cpu_dying)
+			x86_pmu.cpu_dying(cpu);
+		break;
+
+	case CPU_DEAD:
+		if (x86_pmu.cpu_dead)
+			x86_pmu.cpu_dead(cpu);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
 static void __init pmu_check_apic(void)
 {
 	if (cpu_has_apic)
@@ -1347,6 +1374,7 @@ static void __init pmu_check_apic(void)
 
 void __init init_hw_perf_events(void)
 {
+	struct event_constraint *c;
 	int err;
 
 	pr_info("Performance Events: ");
@@ -1395,6 +1423,16 @@ void __init init_hw_perf_events(void)
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_events) - 1,
 				   0, x86_pmu.num_events);
 
+	if (x86_pmu.event_constraints) {
+		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			if (c->cmask != INTEL_ARCH_FIXED_MASK)
+				continue;
+
+			c->idxmsk64 |= (1ULL << x86_pmu.num_events) - 1;
+			c->weight += x86_pmu.num_events;
+		}
+	}
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.event_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_events);
@@ -1402,11 +1440,13 @@ void __init init_hw_perf_events(void)
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_events_fixed);
 	pr_info("... event mask:             %016Lx\n", perf_event_mask);
+
+	perf_cpu_notifier(x86_pmu_notifier);
 }
 
 static inline void x86_pmu_read(struct perf_event *event)
 {
-	x86_perf_event_update(event, &event->hw, event->hw.idx);
+	x86_perf_event_update(event);
 }
 
 static const struct pmu pmu = {
@@ -1662,28 +1702,16 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-void hw_perf_event_setup_online(int cpu)
+#ifdef CONFIG_EVENT_TRACING
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
-	init_debug_store_on_cpu(cpu);
-
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		amd_pmu_cpu_online(cpu);
-		break;
-	default:
-		return;
-	}
-}
-
-void hw_perf_event_setup_offline(int cpu)
-{
-	init_debug_store_on_cpu(cpu);
-
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		amd_pmu_cpu_offline(cpu);
-		break;
-	default:
-		return;
-	}
+	regs->ip = ip;
+	/*
+	 * perf_arch_fetch_caller_regs adds another call, we need to increment
+	 * the skip level
+	 */
+	regs->bp = rewind_frame_pointer(skip + 1);
+	regs->cs = __KERNEL_CS;
+	local_save_flags(regs->flags);
 }
+#endif
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 8f3dbfda3c4..573458f1caf 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -271,28 +271,6 @@ done:
 	return &emptyconstraint;
 }
 
-static __initconst struct x86_pmu amd_pmu = {
-	.name			= "AMD",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= x86_pmu_enable_all,
-	.enable			= x86_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
-	.eventsel		= MSR_K7_EVNTSEL0,
-	.perfctr		= MSR_K7_PERFCTR0,
-	.event_map		= amd_pmu_event_map,
-	.raw_event		= amd_pmu_raw_event,
-	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_events		= 4,
-	.event_bits		= 48,
-	.event_mask		= (1ULL << 48) - 1,
-	.apic			= 1,
-	/* use highest bit to detect overflow */
-	.max_period		= (1ULL << 47) - 1,
-	.get_event_constraints	= amd_get_event_constraints,
-	.put_event_constraints	= amd_put_event_constraints
-};
-
 static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 {
 	struct amd_nb *nb;
@@ -309,7 +287,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	 * initialize all possible NB constraints
 	 */
 	for (i = 0; i < x86_pmu.num_events; i++) {
-		set_bit(i, nb->event_constraints[i].idxmsk);
+		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
 	return nb;
@@ -378,6 +356,31 @@ static void amd_pmu_cpu_offline(int cpu)
 	raw_spin_unlock(&amd_nb_lock);
 }
 
+static __initconst struct x86_pmu amd_pmu = {
+	.name			= "AMD",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= x86_pmu_disable_all,
+	.enable_all		= x86_pmu_enable_all,
+	.enable			= x86_pmu_enable_event,
+	.disable		= x86_pmu_disable_event,
+	.eventsel		= MSR_K7_EVNTSEL0,
+	.perfctr		= MSR_K7_PERFCTR0,
+	.event_map		= amd_pmu_event_map,
+	.raw_event		= amd_pmu_raw_event,
+	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
+	.num_events		= 4,
+	.event_bits		= 48,
+	.event_mask		= (1ULL << 48) - 1,
+	.apic			= 1,
+	/* use highest bit to detect overflow */
+	.max_period		= (1ULL << 47) - 1,
+	.get_event_constraints	= amd_get_event_constraints,
+	.put_event_constraints	= amd_put_event_constraints,
+
+	.cpu_prepare		= amd_pmu_cpu_online,
+	.cpu_dead		= amd_pmu_cpu_offline,
+};
+
 static __init int amd_pmu_init(void)
 {
 	/* Performance-monitoring supported from K7 and later: */
@@ -390,11 +393,6 @@ static __init int amd_pmu_init(void)
 	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
 	       sizeof(hw_cache_event_ids));
 
-	/*
-	 * explicitly initialize the boot cpu, other cpus will get
-	 * the cpu hotplug callbacks from smp_init()
-	 */
-	amd_pmu_cpu_online(smp_processor_id());
 	return 0;
 }
 
@@ -405,12 +403,4 @@ static int amd_pmu_init(void)
 	return 0;
 }
 
-static void amd_pmu_cpu_online(int cpu)
-{
-}
-
-static void amd_pmu_cpu_offline(int cpu)
-{
-}
-
 #endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 977e7544738..84bfde64a33 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1,7 +1,7 @@
 #ifdef CONFIG_CPU_SUP_INTEL
 
 /*
- * Intel PerfMon