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

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (163 commits)
  tracing: Fix compile issue for trace_sched_wakeup.c
  [S390] hardirq: remove pointless header file includes
  [IA64] Move local_softirq_pending() definition
  perf, powerpc: Fix power_pmu_event_init to not use event->ctx
  ftrace: Remove recursion between recordmcount and scripts/mod/empty
  jump_label: Add COND_STMT(), reducer wrappery
  perf: Optimize sw events
  perf: Use jump_labels to optimize the scheduler hooks
  jump_label: Add atomic_t interface
  jump_label: Use more consistent naming
  perf, hw_breakpoint: Fix crash in hw_breakpoint creation
  perf: Find task before event alloc
  perf: Fix task refcount bugs
  perf: Fix group moving
  irq_work: Add generic hardirq context callbacks
  perf_events: Fix transaction recovery in group_sched_in()
  perf_events: Fix bogus AMD64 generic TLB events
  perf_events: Fix bogus context time tracking
  tracing: Remove parent recording in latency tracer graph options
  tracing: Use one prologue for the preempt irqs off tracer function tracers
  ...

6 files changed, 240 insertions, 205 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 631e5a0fb6a..4b1e521d966 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -138,6 +138,7 @@ config PPC
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS if PPC64
 	select GENERIC_ATOMIC64 if PPC32
+	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 1ff6662f7fa..9b287fdd8ea 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -129,7 +129,7 @@ struct paca_struct {
 	u8 soft_enabled;		/* irq soft-enable flag */
 	u8 hard_enabled;		/* set if irqs are enabled in MSR */
 	u8 io_sync;			/* writel() needs spin_unlock sync */
-	u8 perf_event_pending;		/* PM interrupt while soft-disabled */
+	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
 
 	/* Stuff for accurate time accounting */
 	u64 user_time;			/* accumulated usermode TB ticks */
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index 95ad9dad298..d05ae4204bb 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -23,18 +23,6 @@
 #include "ppc32.h"
 #endif
 
-/*
- * Store another value in a callchain_entry.
- */
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-	unsigned int nr = entry->nr;
-
-	if (nr < PERF_MAX_STACK_DEPTH) {
-		entry->ip[nr] = ip;
-		entry->nr = nr + 1;
-	}
-}
 
 /*
  * Is sp valid as the address of the next kernel stack frame after prev_sp?
@@ -58,8 +46,8 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 	return 0;
 }
 
-static void perf_callchain_kernel(struct pt_regs *regs,
-				  struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -69,8 +57,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_KERNEL);
-	callchain_store(entry, regs->nip);
+	perf_callchain_store(entry, regs->nip);
 
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return;
@@ -89,7 +76,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			next_ip = regs->nip;
 			lr = regs->link;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_KERNEL);
+			perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
 
 		} else {
 			if (level == 0)
@@ -111,7 +98,7 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 			++level;
 		}
 
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		if (!valid_next_sp(next_sp, sp))
 			return;
 		sp = next_sp;
@@ -233,8 +220,8 @@ static int sane_signal_64_frame(unsigned long sp)
 		puc == (unsigned long) &sf->uc;
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned long sp, next_sp;
 	unsigned long next_ip;
@@ -246,8 +233,7 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, next_ip);
 
 	for (;;) {
 		fp = (unsigned long __user *) sp;
@@ -276,14 +262,14 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 			    read_user_stack_64(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
@@ -315,8 +301,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	return __get_user_inatomic(*ret, ptr);
 }
 
-static inline void perf_callchain_user_64(struct pt_regs *regs,
-					  struct perf_callchain_entry *entry)
+static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
+					  struct pt_regs *regs)
 {
 }
 
@@ -435,8 +421,8 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp,
 	return mctx->mc_gregs;
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-				   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+				   struct pt_regs *regs)
 {
 	unsigned int sp, next_sp;
 	unsigned int next_ip;
@@ -447,8 +433,7 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 	next_ip = regs->nip;
 	lr = regs->link;
 	sp = regs->gpr[1];
-	callchain_store(entry, PERF_CONTEXT_USER);
-	callchain_store(entry, next_ip);
+	perf_callchain_store(entry, next_ip);
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		fp = (unsigned int __user *) (unsigned long) sp;
@@ -470,45 +455,24 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 			    read_user_stack_32(&uregs[PT_R1], &sp))
 				return;
 			level = 0;
-			callchain_store(entry, PERF_CONTEXT_USER);
-			callchain_store(entry, next_ip);
+			perf_callchain_store(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
 			continue;
 		}
 
 		if (level == 0)
 			next_ip = lr;
-		callchain_store(entry, next_ip);
+		perf_callchain_store(entry, next_ip);
 		++level;
 		sp = next_sp;
 	}
 }
 
-/*
- * Since we can't get PMU interrupts inside a PMU interrupt handler,
- * we don't need separate irq and nmi entries here.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-	struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
-
-	entry->nr = 0;
-
-	if (!user_mode(regs)) {
-		perf_callchain_kernel(regs, entry);
-		if (current->mm)
-			regs = task_pt_regs(current);
-		else
-			regs = NULL;
-	}
-
-	if (regs) {
-		if (current_is_64bit())
-			perf_callchain_user_64(regs, entry);
-		else
-			perf_callchain_user_32(regs, entry);
-	}
-
-	return entry;
+	if (current_is_64bit())
+		perf_callchain_user_64(entry, regs);
+	else
+		perf_callchain_user_32(entry, regs);
 }
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index d301a30445e..3129c855933 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -402,6 +402,9 @@ static void power_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	if (!event->hw.idx)
 		return;
 	/*
@@ -517,7 +520,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0)
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void power_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -565,7 +568,7 @@ void hw_perf_disable(void)
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void power_pmu_enable(struct pmu *pmu)
 {
 	struct perf_event *event;
 	struct cpu_hw_events *cpuhw;
@@ -672,6 +675,8 @@ void hw_perf_enable(void)
 		}
 		local64_set(&event->hw.prev_count, val);
 		event->hw.idx = idx;
+		if (event->hw.state & PERF_HES_STOPPED)
+			val = 0;
 		write_pmc(idx, val);
 		perf_event_update_userpage(event);
 	}
@@ -727,7 +732,7 @@ static int collect_events(struct perf_event *group, int max_count,
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
  */
-static int power_pmu_enable(struct perf_event *event)
+static int power_pmu_add(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -735,7 +740,7 @@ static int power_pmu_enable(struct perf_event *event)
 	int ret = -EAGAIN;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	/*
 	 * Add the event to the list (if there is room)
@@ -749,6 +754,9 @@ static int power_pmu_enable(struct perf_event *event)
 	cpuhw->events[n0] = event->hw.config;
 	cpuhw->flags[n0] = event->hw.event_base;
 
+	if (!(ef_flags & PERF_EF_START))
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
@@ -769,7 +777,7 @@ nocheck:
 
 	ret = 0;
  out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }
@@ -777,14 +785,14 @@ nocheck:
 /*
  * Remove a event from the PMU.
  */
-static void power_pmu_disable(struct perf_event *event)
+static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
 	struct cpu_hw_events *cpuhw;
 	long i;
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	power_pmu_read(event);
 
@@ -821,34 +829,60 @@ static void power_pmu_disable(struct perf_event *event)
 		cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
 	}
 
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
 /*
- * Re-enable interrupts on a event after they were throttled
- * because they were coming too fast.
+ * POWER-PMU does not support disabling individual counters, hence
+ * program their cycle counter to their max value and ignore the interrupts.
  */
-static void power_pmu_unthrottle(struct perf_event *event)
+
+static void power_pmu_start(struct perf_event *event, int ef_flags)
+{
+	unsigned long flags;
+	s64 left;
+
+	if (!event->hw.idx || !event->hw.sample_period)
+		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
+
+static void power_pmu_stop(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
 	unsigned long flags;
 
 	if (!event->hw.idx || !event->hw.sample_period)
 		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
+
 	power_pmu_read(event);
-	left = event->hw.sample_period;
-	event->hw.last_period = left;
-	val = 0;
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	write_pmc(event->hw.idx, 0);
+
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
@@ -857,10 +891,11 @@ static void power_pmu_unthrottle(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-void power_pmu_start_txn(const struct pmu *pmu)
+void power_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 	cpuhw->n_txn_start = cpuhw->n_events;
 }
@@ -870,11 +905,12 @@ void power_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-void power_pmu_cancel_txn(const struct pmu *pmu)
+void power_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 }
 
 /*
@@ -882,7 +918,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-int power_pmu_commit_txn(const struct pmu *pmu)
+int power_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	long i, n;
@@ -901,19 +937,10 @@ int power_pmu_commit_txn(const struct pmu *pmu)
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
-struct pmu power_pmu = {
-	.enable		= power_pmu_enable,
-	.disable	= power_pmu_disable,
-	.read		= power_pmu_read,
-	.unthrottle	= power_pmu_unthrottle,
-	.start_txn	= power_pmu_start_txn,
-	.cancel_txn	= power_pmu_cancel_txn,
-	.commit_txn	= power_pmu_commit_txn,
-};
-
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
@@ -1014,7 +1041,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp)
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int power_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	unsigned long flags;
@@ -1026,25 +1053,27 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	struct cpu_hw_events *cpuhw;
 
 	if (!ppmu)
-		return ERR_PTR(-ENXIO);
+		return -ENOENT;
+
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 	case PERF_TYPE_RAW:
 		ev = event->attr.config;
 		break;
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
+
 	event->hw.config_base = ev;
 	event->hw.idx = 0;
 
@@ -1063,7 +1092,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	 * XXX we should check if the task is an idle task.
 	 */
 	flags = 0;
-	if (event->ctx->task)
+	if (event->attach_state & PERF_ATTACH_TASK)
 		flags |= PPMU_ONLY_COUNT_RUN;
 
 	/*
@@ -1081,7 +1110,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 			 */
 			ev = normal_pmc_alternative(ev, flags);
 			if (!ev)
-				return ERR_PTR(-EINVAL);
+				return -EINVAL;
 		}
 	}
 
@@ -1095,19 +1124,19 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		n = collect_events(event->group_leader, ppmu->n_counter - 1,
 				   ctrs, events, cflags);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 	events[n] = ev;
 	ctrs[n] = event;
 	cflags[n] = flags;
 	if (check_excludes(ctrs, cflags, n, 1))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	cpuhw = &get_cpu_var(cpu_hw_events);
 	err = power_check_constraints(cpuhw, events, cflags, n + 1);
 	put_cpu_var(cpu_hw_events);
 	if (err)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	event->hw.config = events[n];
 	event->hw.event_base = cflags[n];
@@ -1132,11 +1161,23 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
-		return ERR_PTR(err);
-	return &power_pmu;
+	return err;
 }
 
+struct pmu power_pmu = {
+	.pmu_enable	= power_pmu_enable,
+	.pmu_disable	= power_pmu_disable,
+	.event_init	= power_pmu_event_init,
+	.add		= power_pmu_add,
+	.del		= power_pmu_del,
+	.start		= power_pmu_start,
+	.stop		= power_pmu_stop,
+	.read		= power_pmu_read,
+	.start_txn	= power_pmu_start_txn,
+	.cancel_txn	= power_pmu_cancel_txn,
+	.commit_txn	= power_pmu_commit_txn,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -1149,6 +1190,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -1171,6 +1217,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -1183,23 +1234,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR)
 			perf_get_data_addr(regs, &data.addr);
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
-			/*
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
+		if (perf_event_overflow(event, nmi, &data, regs))
+			power_pmu_stop(event, 0);
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 /*
@@ -1342,6 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu)
 		freeze_events_kernel = MMCR0_FCHV;
 #endif /* CONFIG_PPC64 */
 
+	perf_pmu_register(&power_pmu);
 	perf_cpu_notifier(power_pmu_notifier);
 
 	return 0;
diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c
index 1ba45471ae4..7ecca59ddf7 100644
--- a/arch/powerpc/kernel/perf_event_fsl_emb.c
+++ b/arch/powerpc/kernel/perf_event_fsl_emb.c
@@ -156,6 +156,9 @@ static void fsl_emb_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
 
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
 	/*
 	 * Performance monitor interrupts come even when interrupts
 	 * are soft-disabled, as long as interrupts are hard-enabled.
@@ -177,7 +180,7 @@ static void fsl_emb_pmu_read(struct perf_event *event)
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void fsl_emb_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -216,7 +219,7 @@ void hw_perf_disable(void)
  * If we were previously disabled and events were added, then
  * put the new config on the PMU.
  */
-void hw_perf_enable(void)
+static void fsl_emb_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;
@@ -262,8 +265,8 @@ static int collect_events(struct perf_event *group, int max_count,
 	return n;
 }
 
-/* perf must be disabled, context locked on entry */
-static int fsl_emb_pmu_enable(struct perf_event *event)
+/* context locked on entry */
+static int fsl_emb_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int ret = -EAGAIN;
@@ -271,6 +274,7 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 	u64 val;
 	int i;
 
+	perf_pmu_disable(event->pmu);
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)
@@ -301,6 +305,12 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 			val = 0x80000000L - left;
 	}
 	local64_set(&event->hw.prev_count, val);
+
+	if (!(flags & PERF_EF_START)) {
+		event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+		val = 0;
+	}
+
 	write_pmc(i, val);
 	perf_event_update_userpage(event);
 
@@ -310,15 +320,17 @@ static int fsl_emb_pmu_enable(struct perf_event *event)
 	ret = 0;
  out:
 	put_cpu_var(cpu_hw_events);
+	perf_pmu_enable(event->pmu);
 	return ret;
 }
 
-/* perf must be disabled, context locked on entry */
-static void fsl_emb_pmu_disable(struct perf_event *event)
+/* context locked on entry */
+static void fsl_emb_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuhw;
 	int i = event->hw.idx;
 
+	perf_pmu_disable(event->pmu);
 	if (i < 0)
 		goto out;
 
@@ -346,44 +358,57 @@ static void fsl_emb_pmu_disable(struct perf_event *event)
 	cpuhw->n_events--;
 
  out:
+	perf_pmu_enable(event->pmu);
 	put_cpu_var(cpu_hw_events);
 }
 
-/*
- * Re-enable interrupts on a event after they were throttled
- * because they were coming too fast.
- *
- * Context is locked on entry, but perf is not disabled.
- */
-static void fsl_emb_pmu_unthrottle(struct perf_event *event)
+static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags)
 {
-	s64 val, left;
 	unsigned long flags;
+	s64 left;
 
 	if (event->hw.idx < 0 || !event->hw.sample_period)
 		return;
+
+	if (!(event->hw.state & PERF_HES_STOPPED))
+		return;
+
+	if (ef_flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
 	local_irq_save(flags);
-	perf_disable();
-	fsl_emb_pmu_read(event);
-	left = event->hw.sample_period;
-	event->hw.last_period = left;
-	val = 0;
-	if (left < 0x80000000L)
-		val = 0x80000000L - left;
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = 0;
+	left = local64_read(&event->hw.period_left);
+	write_pmc(event->hw.idx, left);
+
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 
-static struct pmu fsl_emb_pmu = {
-	.enable		= fsl_emb_pmu_enable,
-	.disable	= fsl_emb_pmu_disable,
-	.read		= fsl_emb_pmu_read,
-	.unthrottle	= fsl_emb_pmu_unthrottle,
-};
+static void fsl_emb_pmu_stop(struct perf_event *event, int ef_flags)
+{
+	unsigned long flags;
+
+	if (event->hw.idx < 0 || !event->hw.sample_period)
+		return;
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	local_irq_save(flags);
+	perf_pmu_disable(event->pmu);
+
+	fsl_emb_pmu_read(event);
+	event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	write_pmc(event->hw.idx, 0);
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	local_irq_restore(flags);
+}
 
 /*
  * Release the PMU if this is the last perf_event.
@@ -428,7 +453,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp)
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int fsl_emb_pmu_event_init(struct perf_event *event)
 {
 	u64 ev;
 	struct perf_event *events[MAX_HWEVENTS];
@@ -441,14 +466,14 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	case PERF_TYPE_HARDWARE:
 		ev = event->attr.config;
 		if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0)
-			return ERR_PTR(-EOPNOTSUPP);
+			return -EOPNOTSUPP;
 		ev = ppmu->generic_events[ev];
 		break;
 
 	case PERF_TYPE_HW_CACHE:
 		err = hw_perf_cache_event(event->attr.config, &ev);
 		if (err)
-			return ERR_PTR(err);
+			return err;
 		break;
 
 	case PERF_TYPE_RAW:
@@ -456,12 +481,12 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		break;
 
 	default:
-		return ERR_PTR(-EINVAL);
+		return -ENOENT;
 	}
 
 	event->hw.config = ppmu->xlate_event(ev);
 	if (!(event->hw.config & FSL_EMB_EVENT_VALID))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	/*
 	 * If this is in a group, check if it can go on with all the
@@ -473,7 +498,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		n = collect_events(event->group_leader,
 		                   ppmu->n_counter - 1, events);
 		if (n < 0)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) {
@@ -484,7 +509,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 		}
 
 		if (num_restricted >= ppmu->n_restricted)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	event->hw.idx = -1;
@@ -497,7 +522,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	if (event->attr.exclude_kernel)
 		event->hw.config_base |= PMLCA_FCS;
 	if (event->attr.exclude_idle)
-		return ERR_PTR(-ENOTSUPP);
+		return -ENOTSUPP;
 
 	event->hw.last_period = event->hw.sample_period;
 	local64_set(&event->hw.period_left, event->hw.last_period);
@@ -523,11 +548,20 @@ const struct pmu *hw_perf_event_init(struct perf_event *event)
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
-		return ERR_PTR(err);
-	return &fsl_emb_pmu;
+	return err;
 }
 
+static struct pmu fsl_emb_pmu = {
+	.pmu_enable	= fsl_emb_pmu_enable,
+	.pmu_disable	= fsl_emb_pmu_disable,
+	.event_init	= fsl_emb_pmu_event_init,
+	.add		= fsl_emb_pmu_add,
+	.del		= fsl_emb_pmu_del,
+	.start		= fsl_emb_pmu_start,
+	.stop		= fsl_emb_pmu_stop,
+	.read		= fsl_emb_pmu_read,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled
@@ -540,6 +574,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	s64 prev, delta, left;
 	int record = 0;
 
+	if (event->hw.state & PERF_HES_STOPPED) {
+		write_pmc(event->hw.idx, 0);
+		return;
+	}
+
 	/* we don't have to worry about interrupts here */
 	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
@@ -562,6 +601,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			val = 0x80000000LL - left;
 	}
 
+	write_pmc(event->hw.idx, val);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
+	perf_event_update_userpage(event);
+
 	/*
 	 * Finally record data if requested.
 	 */
@@ -571,23 +615,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 		perf_sample_data_init(&data, 0);
 		data.period = event->hw.last_period;
 
-		if (perf_event_overflow(event, nmi, &data, regs)) {
-			/*
-			 * Interrupts are coming too fast - throttle them
-			 * by setting the event to 0, so it will be
-			 * at least 2^30 cycles until the next interrupt
-			 * (assuming each event counts at most 2 counts
-			 * per cycle).
-			 */
-			val = 0;
-			left = ~0ULL >> 1;
-		}
+		if (perf_event_overflow(event, nmi, &data, regs))
+			fsl_emb_pmu_stop(event, 0);
 	}
-
-	write_pmc(event->hw.idx, val);
-	local64_set(&event->hw.prev_count, val);
-	local64_set(&event->hw.period_left, left);
-	perf_event_update_userpage(event);
 }
 
 static void perf_event_interrupt(struct pt_regs *regs)
@@ -651,5 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	perf_pmu_register(&fsl_emb_pmu);
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 8533b3b83f5..54888eb10c3 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -53,7 +53,7 @@
 #include <linux/posix-timers.h>
 #include <linux/irq.h>
 #include <linux/delay.h>
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <asm/trace.h>
 
 #include <asm/io.h>
@@ -493,60 +493,60 @@ void __init iSeries_time_init_early(void)
 }
 #endif /* CONFIG_PPC_ISERIES */
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_IRQ_WORK
 
 /*
  * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable...
  */
 #ifdef CONFIG_PPC64
-static inline unsigned long test_perf_event_pending(void)
+static inline unsigned long test_irq_work_pending(void)
 {
 	unsigned long x;
 
 	asm volatile("lbz %0,%1(13)"
 		: "=r" (x)
-		: "i" (offsetof(struct paca_struct, perf_event_pending)));
+		: "i" (offsetof(struct paca_struct, irq_work_pending)));
 	return x;
 }
 
-static inline void set_perf_event_pending_flag(void)
+static inline void set_irq_work_pending_flag(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (1),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
-static inline void clear_perf_event_pending(void)
+static inline void clear_irq_work_pending(void)
 {
 	asm volatile("stb %0,%1(13)" : :
 		"r" (0),
-		"i" (offsetof(struct paca_struct, perf_event_pending)));
+		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
 #else /* 32-bit */
 
-DEFINE_PER_CPU(u8, perf_event_pending);
+DEFINE_PER_CPU(u8, irq_work_pending);
 
-#define set_perf_event_pending_flag()	__get_cpu_var(perf_event_pending) = 1
-#define test_perf_event_pending()	__get_cpu_var(perf_event_pending)
-#define clear_perf_event_pending()	__get_cpu_var(perf_event_pending) = 0
+#define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1
+#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)
+#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0
 
 #endif /* 32 vs 64 bit */
 
-void set_perf_event_pending(void)
+void set_irq_work_pending(void)
 {
 	preempt_disable();
-	set_perf_event_pending_flag();
+	set_irq_work_pending_flag();
 	set_dec(1);
 	preempt_enable();
 }
 
-#else  /* CONFIG_PERF_EVENTS */
+#else  /* CONFIG_IRQ_WORK */
 
-#define test_perf_event_pending()	0
-#define clear_perf_event_pending()
+#define test_irq_work_pending()	0
+#define clear_irq_work_pending()
 
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_IRQ_WORK */
 
 /*
  * For iSeries shared processors, we have to let the hypervisor
@@ -587,9 +587,9 @@ void timer_interrupt(struct pt_regs * regs)
 
 	calculate_steal_time();
 
-	if (test_perf_event_pending()) {
-		clear_perf_event_pending();
-		perf_event_do_pending();
+	if (test_irq_work_pending()) {
+		clear_irq_work_pending();
+		irq_work_run();
 	}
 
 #ifdef CONFIG_PPC_ISERIES