Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (35 commits)
  perf: Fix unexported generic perf_arch_fetch_caller_regs
  perf record: Don't try to find buildids in a zero sized file
  perf: export perf_trace_regs and perf_arch_fetch_caller_regs
  perf, x86: Fix hw_perf_enable() event assignment
  perf, ppc: Fix compile error due to new cpu notifiers
  perf: Make the install relative to DESTDIR if specified
  kprobes: Calculate the index correctly when freeing the out-of-line execution slot
  perf tools: Fix sparse CPU numbering related bugs
  perf_event: Fix oops triggered by cpu offline/online
  perf: Drop the obsolete profile naming for trace events
  perf: Take a hot regs snapshot for trace events
  perf: Introduce new perf_fetch_caller_regs() for hot regs snapshot
  perf/x86-64: Use frame pointer to walk on irq and process stacks
  lockdep: Move lock events under lockdep recursion protection
  perf report: Print the map table just after samples for which no map was found
  perf report: Add multiple event support
  perf session: Change perf_session post processing functions to take histogram tree
  perf session: Add storage for seperating event types in report
  perf session: Change add_hist_entry to take the tree root instead of session
  perf record: Add ID and to recorded event data when recording multiple events
  ...

6 files changed, 176 insertions, 155 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 42aafd11e170..60398a0d947c 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -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;
@@ -638,7 +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;
 	}
@@ -687,7 +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;
@@ -780,6 +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)
@@ -796,6 +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()
@@ -803,8 +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;
 
@@ -819,29 +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();
@@ -853,15 +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,
+	(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);
@@ -871,12 +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;
@@ -922,11 +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);
 }
 
 /*
@@ -962,34 +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)
@@ -1049,18 +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;
 }
@@ -1108,7 +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;
 
@@ -1118,11 +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)
@@ -1309,7 +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;
 
 	/*
@@ -1337,6 +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)
@@ -1415,11 +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 = {
@@ -1675,28 +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 8f3dbfda3c4f..573458f1caf2 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 44b60c852107..84bfde64a337 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -548,9 +548,9 @@ static inline void intel_pmu_ack_status(u64 ack)
 }
 
 static inline void
-intel_pmu_disable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 {
-	int idx = __idx - X86_PMC_IDX_FIXED;
+	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
 	mask = 0xfULL << (idx * 4);
@@ -621,26 +621,28 @@ static void intel_pmu_drain_bts_buffer(void)
 }
 
 static inline void
-intel_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+intel_pmu_disable_event(struct perf_event *event)
 {
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
 		return;
 	}
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_disable_fixed(hwc, idx);
+		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
-	x86_pmu_disable_event(hwc, idx);
+	x86_pmu_disable_event(event);
 }
 
 static inline void
-intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
+intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 {
-	int idx = __idx - X86_PMC_IDX_FIXED;
+	int idx = hwc->idx - X86_PMC_IDX_FIXED;
 	u64 ctrl_val, bits, mask;
 	int err;
 
@@ -670,9 +672,11 @@ intel_pmu_enable_fixed(struct hw_perf_event *hwc, int __idx)
 	err = checking_wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void intel_pmu_enable_event(struct perf_event *event)
 {
-	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		if (!__get_cpu_var(cpu_hw_events).enabled)
 			return;
 
@@ -681,11 +685,11 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
 	}
 
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc, idx);
+		intel_pmu_enable_fixed(hwc);
 		return;
 	}
 
-	__x86_pmu_enable_event(hwc, idx);
+	__x86_pmu_enable_event(hwc);
 }
 
 /*
@@ -694,14 +698,8 @@ static void intel_pmu_enable_event(struct hw_perf_event *hwc, int idx)
  */
 static int intel_pmu_save_and_restart(struct perf_event *event)
 {
-	struct hw_perf_event *hwc = &event->hw;
-	int idx = hwc->idx;
-	int ret;
-
-	x86_perf_event_update(event, hwc, idx);
-	ret = x86_perf_event_set_period(event, hwc, idx);
-
-	return ret;
+	x86_perf_event_update(event);
+	return x86_perf_event_set_period(event);
 }
 
 static void intel_pmu_reset(void)
@@ -745,11 +743,11 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = &__get_cpu_var(cpu_hw_events);
 
-	perf_disable();
+	intel_pmu_disable_all();
 	intel_pmu_drain_bts_buffer();
 	status = intel_pmu_get_status();
 	if (!status) {
-		perf_enable();
+		intel_pmu_enable_all();
 		return 0;
 	}
 
@@ -759,8 +757,7 @@ again:
 		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
 		perf_event_print_debug();
 		intel_pmu_reset();
-		perf_enable();
-		return 1;
+		goto done;
 	}
 
 	inc_irq_stat(apic_perf_irqs);
@@ -768,7 +765,6 @@ again:
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
 
-		clear_bit(bit, (unsigned long *) &status);
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
@@ -778,7 +774,7 @@ again:
 		data.period = event->hw.last_period;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			intel_pmu_disable_event(&event->hw, bit);
+			x86_pmu_stop(event);
 	}
 
 	intel_pmu_ack_status(ack);
@@ -790,8 +786,8 @@ again:
 	if (status)
 		goto again;
 
-	perf_enable();
-
+done:
+	intel_pmu_enable_all();
 	return 1;
 }
 
@@ -870,7 +866,10 @@ static __initconst struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.enable_bts		= intel_pmu_enable_bts,
 	.disable_bts		= intel_pmu_disable_bts,
-	.get_event_constraints	= intel_get_event_constraints
+	.get_event_constraints	= intel_get_event_constraints,
+
+	.cpu_starting		= init_debug_store_on_cpu,
+	.cpu_dying		= fini_debug_store_on_cpu,
 };
 
 static __init int intel_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index a4e67b99d91c..a330485d14da 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -77,27 +77,29 @@ static void p6_pmu_enable_all(void)
 }
 
 static inline void
-p6_pmu_disable_event(struct hw_perf_event *hwc, int idx)
+p6_pmu_disable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	u64 val = P6_NOP_EVENT;
 
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
-static void p6_pmu_enable_event(struct hw_perf_event *hwc, int idx)
+static void p6_pmu_enable_event(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
 	u64 val;
 
 	val = hwc->config;
 	if (cpuc->enabled)
 		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
 
-	(void)checking_wrmsrl(hwc->config_base + idx, val);
+	(void)checking_wrmsrl(hwc->config_base + hwc->idx, val);
 }
 
 static __initconst struct x86_pmu p6_pmu = {
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 4fd1420faffa..29e5f7c845b2 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,4 +29,19 @@ struct stack_frame {
 	struct stack_frame *next_frame;
 	unsigned long return_address;
 };
+
+static inline unsigned long rewind_frame_pointer(int n)
+{
+	struct stack_frame *frame;
+
+	get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+	while (n--)
+		frame = frame->next_frame;
 #endif
+
+	return (unsigned long)frame;
+}
+
+#endif /* DUMPSTACK_H */
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index d5e2a2ebb627..272c9f1f05f3 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -208,7 +208,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
 				if (ops->stack(data, "IRQ") < 0)
 					break;
-				bp = print_context_stack(tinfo, stack, bp,
+				bp = ops->walk_stack(tinfo, stack, bp,
 					ops, data, irq_stack_end, &graph);
 				/*
 				 * We link to the next stack (which would be
@@ -229,7 +229,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	/*
 	 * This handles the process stack:
 	 */
-	bp = print_context_stack(tinfo, stack, bp, ops, data, NULL, &graph);
+	bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
 	put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);