perf pmu interface changes -v3

Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel.c
===================================================================
@@ -504,7 +504,7 @@ static void intel_pmu_nhm_enable_all(int
 		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x4300B1);
 		wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x4300B5);
 
-		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
+		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x7);
 		wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
 
 		for (i = 0; i < 3; i++) {

Index: linux-2.6/arch/sparc/kernel/perf_event.c
===================================================================
@@ -657,6 +657,7 @@ static u64 maybe_change_configuration(st
 		cpuc->current_idx[i] = idx;
 
 		enc = perf_event_get_enc(cpuc->events[i]);
+		pcr &= ~mask_for_index(idx);
 		pcr |= event_encoding(enc, idx);
 	}
 out:

Index: linux-2.6/kernel/perf_event.c
===================================================================
@@ -5743,15 +5743,15 @@ perf_cpu_notify(struct notifier_block *s
 {
 	unsigned int cpu = (long)hcpu;
 
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
+	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 		perf_event_exit_cpu(cpu);
 		break;
 

Index: linux-2.6/arch/powerpc/kernel/perf_event_fsl_emb.c
===================================================================
@@ -566,9 +566,9 @@ static void record_and_restart(struct pe
 	 * Finally record data if requested.
 	 */
 	if (record) {
-		struct perf_sample_data data = {
-			.period	= event->hw.last_period,
-		};
+		struct perf_sample_data data;
+
+		perf_sample_data_init(&data, 0);
 
 		if (perf_event_overflow(event, nmi, &data, regs)) {
 			/*

Index: linux-2.6/arch/powerpc/kernel/perf_event_fsl_emb.c
===================================================================
@@ -162,15 +162,15 @@ static void fsl_emb_pmu_read(struct perf
 	 * Therefore we treat them like NMIs.
 	 */
 	do {
-		prev = atomic64_read(&event->hw.prev_count);
+		prev = local64_read(&event->hw.prev_count);
 		barrier();
 		val = read_pmc(event->hw.idx);
-	} while (atomic64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
+	} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
 
 	/* The counters are only 32 bits wide */
 	delta = (val - prev) & 0xfffffffful;
-	atomic64_add(delta, &event->count);
-	atomic64_sub(delta, &event->hw.period_left);
+	local64_add(delta, &event->count);
+	local64_sub(delta, &event->hw.period_left);
 }
 
 /*

@@ -296,11 +296,11 @@ static int fsl_emb_pmu_enable(struct per
 
 	val = 0;
 	if (event->hw.sample_period) {
-		s64 left = atomic64_read(&event->hw.period_left);
+		s64 left = local64_read(&event->hw.period_left);
 		if (left < 0x80000000L)
 			val = 0x80000000L - left;
 	}
-	atomic64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.prev_count, val);
 	write_pmc(i, val);
 	perf_event_update_userpage(event);
 

@@ -371,8 +371,8 @@ static void fsl_emb_pmu_unthrottle(struc
 	if (left < 0x80000000L)
 		val = 0x80000000L - left;
 	write_pmc(event->hw.idx, val);
-	atomic64_set(&event->hw.prev_count, val);
-	atomic64_set(&event->hw.period_left, left);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
 	perf_event_update_userpage(event);
 	perf_enable();
 	local_irq_restore(flags);

@@ -500,7 +500,7 @@ const struct pmu *hw_perf_event_init(str
 		return ERR_PTR(-ENOTSUPP);
 
 	event->hw.last_period = event->hw.sample_period;
-	atomic64_set(&event->hw.period_left, event->hw.last_period);
+	local64_set(&event->hw.period_left, event->hw.last_period);
 
 	/*
 	 * See if we need to reserve the PMU.

@@ -541,16 +541,16 @@ static void record_and_restart(struct pe
 	int record = 0;
 
 	/* we don't have to worry about interrupts here */
-	prev = atomic64_read(&event->hw.prev_count);
+	prev = local64_read(&event->hw.prev_count);
 	delta = (val - prev) & 0xfffffffful;
-	atomic64_add(delta, &event->count);
+	local64_add(delta, &event->count);
 
 	/*
 	 * See if the total period for this event has expired,
 	 * and update for the next period.
 	 */
 	val = 0;
-	left = atomic64_read(&event->hw.period_left) - delta;
+	left = local64_read(&event->hw.period_left) - delta;
 	if (period) {
 		if (left <= 0) {
 			left += period;

@@ -584,8 +584,8 @@ static void record_and_restart(struct pe
 	}
 
 	write_pmc(event->hw.idx, val);
-	atomic64_set(&event->hw.prev_count, val);
-	atomic64_set(&event->hw.period_left, left);
+	local64_set(&event->hw.prev_count, val);
+	local64_set(&event->hw.period_left, left);
 	perf_event_update_userpage(event);
 }
 

Index: linux-2.6/arch/arm/kernel/perf_event.c
===================================================================
@@ -491,7 +491,7 @@ __hw_perf_event_init(struct perf_event *
 	return err;
 }
 
-const struct pmu *
+struct pmu *
 hw_perf_event_init(struct perf_event *event)
 {
 	int err = 0;

Index: linux-2.6/arch/powerpc/kernel/perf_event.c
===================================================================
@@ -854,7 +854,7 @@ static void power_pmu_unthrottle(struct 
  * 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);
 

@@ -867,7 +867,7 @@ void power_pmu_start_txn(const struct pm
  * 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);
 

@@ -879,7 +879,7 @@ void power_pmu_cancel_txn(const struct p
  * 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;

@@ -1011,7 +1011,7 @@ static int hw_perf_cache_event(u64 confi
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+struct pmu *hw_perf_event_init(struct perf_event *event)
 {
 	u64 ev;
 	unsigned long flags;

Index: linux-2.6/arch/powerpc/kernel/perf_event_fsl_emb.c
===================================================================
@@ -428,7 +428,7 @@ static int hw_perf_cache_event(u64 confi
 	return 0;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+struct pmu *hw_perf_event_init(struct perf_event *event)
 {
 	u64 ev;
 	struct perf_event *events[MAX_HWEVENTS];

Index: linux-2.6/arch/sh/kernel/perf_event.c
===================================================================
@@ -257,13 +257,13 @@ static void sh_pmu_read(struct perf_even
 	sh_perf_event_update(event, &event->hw, event->hw.idx);
 }
 
-static const struct pmu pmu = {
+static struct pmu pmu = {
 	.enable		= sh_pmu_enable,
 	.disable	= sh_pmu_disable,
 	.read		= sh_pmu_read,
 };
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+struct pmu *hw_perf_event_init(struct perf_event *event)
 {
 	int err = __hw_perf_event_init(event);
 	if (unlikely(err)) {

Index: linux-2.6/arch/sparc/kernel/perf_event.c
===================================================================
@@ -1098,7 +1098,7 @@ static int __hw_perf_event_init(struct p
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void sparc_pmu_start_txn(const struct pmu *pmu)
+static void sparc_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 

@@ -1110,7 +1110,7 @@ static void sparc_pmu_start_txn(const st
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void sparc_pmu_cancel_txn(const struct pmu *pmu)
+static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 

@@ -1122,7 +1122,7 @@ static void sparc_pmu_cancel_txn(const s
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int sparc_pmu_commit_txn(const struct pmu *pmu)
+static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int n;

@@ -1141,7 +1141,7 @@ static int sparc_pmu_commit_txn(const st
 	return 0;
 }
 
-static const struct pmu pmu = {
+static struct pmu pmu = {
 	.enable		= sparc_pmu_enable,
 	.disable	= sparc_pmu_disable,
 	.read		= sparc_pmu_read,

@@ -1151,7 +1151,7 @@ static const struct pmu pmu = {
 	.commit_txn	= sparc_pmu_commit_txn,
 };
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+struct pmu *hw_perf_event_init(struct perf_event *event)
 {
 	int err = __hw_perf_event_init(event);
 

Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
===================================================================
@@ -618,7 +618,7 @@ static void x86_pmu_enable_all(int added
 	}
 }
 
-static const struct pmu pmu;
+static struct pmu pmu;
 
 static inline int is_x86_event(struct perf_event *event)
 {

@@ -1394,7 +1394,7 @@ static inline void x86_pmu_read(struct p
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void x86_pmu_start_txn(const struct pmu *pmu)
+static void x86_pmu_start_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 

@@ -1407,7 +1407,7 @@ static void x86_pmu_start_txn(const stru
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void x86_pmu_cancel_txn(const struct pmu *pmu)
+static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 

@@ -1424,7 +1424,7 @@ static void x86_pmu_cancel_txn(const str
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int x86_pmu_commit_txn(const struct pmu *pmu)
+static int x86_pmu_commit_txn(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int assign[X86_PMC_IDX_MAX];

@@ -1450,7 +1450,7 @@ static int x86_pmu_commit_txn(const stru
 	return 0;
 }
 
-static const struct pmu pmu = {
+static struct pmu pmu = {
 	.enable		= x86_pmu_enable,
 	.disable	= x86_pmu_disable,
 	.start		= x86_pmu_start,

@@ -1536,9 +1536,9 @@ out:
 	return ret;
 }
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+struct pmu *hw_perf_event_init(struct perf_event *event)
 {
-	const struct pmu *tmp;
+	struct pmu *tmp;
 	int err;
 
 	err = __hw_perf_event_init(event);

Index: linux-2.6/include/linux/perf_event.h
===================================================================
@@ -576,19 +576,19 @@ struct pmu {
 	 * Start the transaction, after this ->enable() doesn't need
 	 * to do schedulability tests.
 	 */
-	void (*start_txn)	(const struct pmu *pmu);
+	void (*start_txn)	(struct pmu *pmu);
 	/*
 	 * If ->start_txn() disabled the ->enable() schedulability test
 	 * then ->commit_txn() is required to perform one. On success
 	 * the transaction is closed. On error the transaction is kept
 	 * open until ->cancel_txn() is called.
 	 */
-	int  (*commit_txn)	(const struct pmu *pmu);
+	int  (*commit_txn)	(struct pmu *pmu);
 	/*
 	 * Will cancel the transaction, assumes ->disable() is called for
 	 * each successfull ->enable() during the transaction.
 	 */
-	void (*cancel_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(struct pmu *pmu);
 };
 
 /**

@@ -667,7 +667,7 @@ struct perf_event {
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
-	const struct pmu		*pmu;
+	struct pmu		*pmu;
 
 	enum perf_event_active_state	state;
 	unsigned int			attach_state;

@@ -845,7 +845,7 @@ struct perf_output_handle {
  */
 extern int perf_max_events;
 
-extern const struct pmu *hw_perf_event_init(struct perf_event *event);
+extern struct pmu *hw_perf_event_init(struct perf_event *event);
 
 extern void perf_event_task_sched_in(struct task_struct *task);
 extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);

Index: linux-2.6/kernel/perf_event.c
===================================================================
@@ -75,7 +75,7 @@ static DEFINE_SPINLOCK(perf_resource_loc
 /*
  * Architecture provided APIs - weak aliases:
  */
-extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
+extern __weak struct pmu *hw_perf_event_init(struct perf_event *event)
 {
 	return NULL;
 }

@@ -673,7 +673,7 @@ group_sched_in(struct perf_event *group_
 	       struct perf_event_context *ctx)
 {
 	struct perf_event *event, *partial_group = NULL;
-	const struct pmu *pmu = group_event->pmu;
+	struct pmu *pmu = group_event->pmu;
 	bool txn = false;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)

@@ -4291,7 +4291,7 @@ static int perf_swevent_int(struct perf_
 	return 0;
 }
 
-static const struct pmu perf_ops_generic = {
+static struct pmu perf_ops_generic = {
 	.enable		= perf_swevent_enable,
 	.disable	= perf_swevent_disable,
 	.start		= perf_swevent_int,

@@ -4404,7 +4404,7 @@ static void cpu_clock_perf_event_read(st
 	cpu_clock_perf_event_update(event);
 }
 
-static const struct pmu perf_ops_cpu_clock = {
+static struct pmu perf_ops_cpu_clock = {
 	.enable		= cpu_clock_perf_event_enable,
 	.disable	= cpu_clock_perf_event_disable,
 	.read		= cpu_clock_perf_event_read,

@@ -4461,7 +4461,7 @@ static void task_clock_perf_event_read(s
 	task_clock_perf_event_update(event, time);
 }
 
-static const struct pmu perf_ops_task_clock = {
+static struct pmu perf_ops_task_clock = {
 	.enable		= task_clock_perf_event_enable,
 	.disable	= task_clock_perf_event_disable,
 	.read		= task_clock_perf_event_read,

@@ -4575,7 +4575,7 @@ static int swevent_hlist_get(struct perf
 
 #ifdef CONFIG_EVENT_TRACING
 
-static const struct pmu perf_ops_tracepoint = {
+static struct pmu perf_ops_tracepoint = {
 	.enable		= perf_trace_enable,
 	.disable	= perf_trace_disable,
 	.start		= perf_swevent_int,

@@ -4639,7 +4639,7 @@ static void tp_perf_event_destroy(struct
 	perf_trace_destroy(event);
 }
 
-static const struct pmu *tp_perf_event_init(struct perf_event *event)
+static struct pmu *tp_perf_event_init(struct perf_event *event)
 {
 	int err;
 

@@ -4686,7 +4686,7 @@ static void perf_event_free_filter(struc
 
 #else
 
-static const struct pmu *tp_perf_event_init(struct perf_event *event)
+static struct pmu *tp_perf_event_init(struct perf_event *event)
 {
 	return NULL;
 }

@@ -4708,7 +4708,7 @@ static void bp_perf_event_destroy(struct
 	release_bp_slot(event);
 }
 
-static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+static struct pmu *bp_perf_event_init(struct perf_event *bp)
 {
 	int err;
 

@@ -4732,7 +4732,7 @@ void perf_bp_event(struct perf_event *bp
 		perf_swevent_add(bp, 1, 1, &sample, regs);
 }
 #else
-static const struct pmu *bp_perf_event_init(struct perf_event *bp)
+static struct pmu *bp_perf_event_init(struct perf_event *bp)
 {
 	return NULL;
 }

@@ -4754,9 +4754,9 @@ static void sw_perf_event_destroy(struct
 	swevent_hlist_put(event);
 }
 
-static const struct pmu *sw_perf_event_init(struct perf_event *event)
+static struct pmu *sw_perf_event_init(struct perf_event *event)
 {
-	const struct pmu *pmu = NULL;
+	struct pmu *pmu = NULL;
 	u64 event_id = event->attr.config;
 
 	/*

@@ -4818,7 +4818,7 @@ perf_event_alloc(struct perf_event_attr 
 		   perf_overflow_handler_t overflow_handler,
 		   gfp_t gfpflags)
 {
-	const struct pmu *pmu;
+	struct pmu *pmu;
 	struct perf_event *event;
 	struct hw_perf_event *hwc;
 	long err;

Index: linux-2.6/arch/arm/kernel/perf_event.c
===================================================================
@@ -306,12 +306,7 @@ out:
 	return err;
 }
 
-static struct pmu pmu = {
-	.enable	    = armpmu_enable,
-	.disable    = armpmu_disable,
-	.unthrottle = armpmu_unthrottle,
-	.read	    = armpmu_read,
-};
+static struct pmu pmu;
 
 static int
 validate_event(struct cpu_hw_events *cpuc,

@@ -491,20 +486,29 @@ __hw_perf_event_init(struct perf_event *
 	return err;
 }
 
-struct pmu *
-hw_perf_event_init(struct perf_event *event)
+static int armpmu_event_init(struct perf_event *event)
 {
 	int err = 0;
 
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (!armpmu)
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 
 	event->destroy = hw_perf_event_destroy;
 
 	if (!atomic_inc_not_zero(&active_events)) {
 		if (atomic_read(&active_events) > perf_max_events) {
 			atomic_dec(&active_events);
-			return ERR_PTR(-ENOSPC);
+			return -ENOSPC;
 		}
 
 		mutex_lock(&pmu_reserve_mutex);

@@ -518,15 +522,23 @@ hw_perf_event_init(struct perf_event *ev
 	}
 
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
 	err = __hw_perf_event_init(event);
 	if (err)
 		hw_perf_event_destroy(event);
 
-	return err ? ERR_PTR(err) : &pmu;
+	return err;
 }
 
+static struct pmu pmu = {
+	.event_init = armpmu_event_init,
+	.enable	    = armpmu_enable,
+	.disable    = armpmu_disable,
+	.unthrottle = armpmu_unthrottle,
+	.read	    = armpmu_read,
+};
+
 void
 hw_perf_enable(void)
 {

@@ -2994,6 +3006,8 @@ init_hw_perf_events(void)
 		perf_max_events = -1;
 	}
 
+	perf_pmu_register(&pmu);
+
 	return 0;
 }
 arch_initcall(init_hw_perf_events);

115 lines not on this page · raw message

Index: linux-2.6/arch/powerpc/kernel/perf_event_fsl_emb.c
===================================================================
@@ -378,13 +378,6 @@ static void fsl_emb_pmu_unthrottle(struc
 	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,
-};
-
 /*
  * Release the PMU if this is the last perf_event.
  */

@@ -428,7 +421,7 @@ static int hw_perf_cache_event(u64 confi
 	return 0;
 }
 
-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 +434,14 @@ struct pmu *hw_perf_event_init(struct pe
 	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 +449,12 @@ struct pmu *hw_perf_event_init(struct pe
 		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 +466,7 @@ struct pmu *hw_perf_event_init(struct pe
 		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 +477,7 @@ struct pmu *hw_perf_event_init(struct pe
 		}
 
 		if (num_restricted >= ppmu->n_restricted)
-			return ERR_PTR(-EINVAL);
+			return -EINVAL;
 	}
 
 	event->hw.idx = -1;

@@ -497,7 +490,7 @@ struct pmu *hw_perf_event_init(struct pe
 	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 +516,17 @@ struct pmu *hw_perf_event_init(struct pe
 	}
 	event->destroy = hw_perf_event_destroy;
 
-	if (err)
-		return ERR_PTR(err);
-	return &fsl_emb_pmu;
+	return err;
 }
 
+static struct pmu fsl_emb_pmu = {
+	.event_init	= fsl_emb_pmu_event_init,
+	.enable		= fsl_emb_pmu_enable,
+	.disable	= fsl_emb_pmu_disable,
+	.read		= fsl_emb_pmu_read,
+	.unthrottle	= fsl_emb_pmu_unthrottle,
+};
+
 /*
  * A counter has overflowed; update its count and record
  * things if requested.  Note that interrupts are hard-disabled

@@ -650,5 +649,7 @@ int register_fsl_emb_pmu(struct fsl_emb_
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
+	perf_pmu_register(&fsl_emb_pmu);
+
 	return 0;
 }

Index: linux-2.6/arch/sh/kernel/perf_event.c
===================================================================
@@ -257,26 +257,38 @@ static void sh_pmu_read(struct perf_even
 	sh_perf_event_update(event, &event->hw, event->hw.idx);
 }
 
-static struct pmu pmu = {
-	.enable		= sh_pmu_enable,
-	.disable	= sh_pmu_disable,
-	.read		= sh_pmu_read,
-};
-
-struct pmu *hw_perf_event_init(struct perf_event *event)
+static int sh_pmu_event_init(struct perf_event *event)
 {
-	int err = __hw_perf_event_init(event);
+	int err;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HW_CACHE:
+	case PERF_TYPE_HARDWARE:
+		err = __hw_perf_event_init(event);
+		break;
+
+	default:
+		return -ENOENT;
+	}
+
 	if (unlikely(err)) {
 		if (event->destroy)
 			event->destroy(event);
-		return ERR_PTR(err);
 	}
 
-	return &pmu;
+	return err;
 }
 
+static struct pmu pmu = {
+	.event_init	= sh_pmu_event_init,
+	.enable		= sh_pmu_enable,
+	.disable	= sh_pmu_disable,
+	.read		= sh_pmu_read,
+};
+
 static void sh_pmu_setup(int cpu)
-{
+
 	struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
 
 	memset(cpuhw, 0, sizeof(struct cpu_hw_events));

@@ -325,6 +337,7 @@ int __cpuinit register_sh_pmu(struct sh_
 
 	WARN_ON(pmu->num_events > MAX_HWEVENTS);
 
+	perf_pmu_register(&pmu);
 	perf_cpu_notifier(sh_pmu_notifier);
 	return 0;
 }

Index: linux-2.6/arch/sparc/kernel/perf_event.c
===================================================================
@@ -1025,7 +1025,7 @@ out:
 	return ret;
 }
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int sparc_pmu_event_init(struct perf_event *event)
 {
 	struct perf_event_attr *attr = &event->attr;
 	struct perf_event *evts[MAX_HWEVENTS];

@@ -1038,17 +1038,27 @@ static int __hw_perf_event_init(struct p
 	if (atomic_read(&nmi_active) < 0)
 		return -ENODEV;
 
-	if (attr->type == PERF_TYPE_HARDWARE) {
+	switch (attr->type) {
+	case PERF_TYPE_HARDWARE:
 		if (attr->config >= sparc_pmu->max_events)
 			return -EINVAL;
 		pmap = sparc_pmu->event_map(attr->config);
-	} else if (attr->type == PERF_TYPE_HW_CACHE) {
+		break;
+
+	case PERF_TYPE_HW_CACHE:
 		pmap = sparc_map_cache_event(attr->config);
 		if (IS_ERR(pmap))
 			return PTR_ERR(pmap);
-	} else
+		break;
+
+	case PERF_TYPE_RAW:
 		return -EOPNOTSUPP;
 
+	default:
+		return -ENOENT;
+
+	}
+
 	/* We save the enable bits in the config_base.  */
 	hwc->config_base = sparc_pmu->irq_bit;
 	if (!attr->exclude_user)

@@ -1143,6 +1153,7 @@ static int sparc_pmu_commit_txn(struct p
 }
 
 static struct pmu pmu = {
+	.event_init	= sparc_pmu_event_init,
 	.enable		= sparc_pmu_enable,
 	.disable	= sparc_pmu_disable,
 	.read		= sparc_pmu_read,

@@ -1152,15 +1163,6 @@ static struct pmu pmu = {
 	.commit_txn	= sparc_pmu_commit_txn,
 };
 
-struct pmu *hw_perf_event_init(struct perf_event *event)
-{
-	int err = __hw_perf_event_init(event);
-
-	if (err)
-		return ERR_PTR(err);
-	return &pmu;
-}
-
 void perf_event_print_debug(void)
 {
 	unsigned long flags;

@@ -1280,6 +1282,7 @@ void __init init_hw_perf_events(void)
 	/* All sparc64 PMUs currently have 2 events.  */
 	perf_max_events = 2;
 
+	perf_pmu_register(&pmu);
 	register_die_notifier(&perf_event_nmi_notifier);
 }
 

83 lines not on this page · raw message

Index: linux-2.6/include/linux/perf_event.h
===================================================================
@@ -561,6 +561,13 @@ struct perf_event;
  * struct pmu - generic performance monitoring unit
  */
 struct pmu {
+	struct list_head		entry;
+
+	/*
+	 * Should return -ENOENT when the @event doesn't match this pmu
+	 */
+	int (*event_init)		(struct perf_event *event);
+
 	int (*enable)			(struct perf_event *event);
 	void (*disable)			(struct perf_event *event);
 	int (*start)			(struct perf_event *event);

@@ -847,7 +854,8 @@ struct perf_output_handle {
  */
 extern int perf_max_events;
 
-extern struct pmu *hw_perf_event_init(struct perf_event *event);
+extern int perf_pmu_register(struct pmu *pmu);
+extern void perf_pmu_unregister(struct pmu *pmu);
 
 extern void perf_event_task_sched_in(struct task_struct *task);
 extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);

Index: linux-2.6/kernel/hw_breakpoint.c
===================================================================
@@ -553,6 +553,34 @@ static struct notifier_block hw_breakpoi
 	.priority = 0x7fffffff
 };
 
+static void bp_perf_event_destroy(struct perf_event *event)
+{
+	release_bp_slot(event);
+}
+
+static int hw_breakpoint_event_init(struct perf_event *bp)
+{
+	int err;
+
+	if (bp->attr.type != PERF_TYPE_BREAKPOINT)
+		return -ENOENT;
+
+	err = register_perf_hw_breakpoint(bp);
+	if (err)
+		return err;
+
+	bp->destroy = bp_perf_event_destroy;
+
+	return 0;
+}
+
+static struct pmu perf_breakpoint = {
+	.event_init	= hw_breakpoint_event_init,
+	.enable		= arch_install_hw_breakpoint,
+	.disable	= arch_uninstall_hw_breakpoint,
+	.read		= hw_breakpoint_pmu_read,
+};
+
 static int __init init_hw_breakpoint(void)
 {
 	unsigned int **task_bp_pinned;

@@ -574,6 +602,8 @@ static int __init init_hw_breakpoint(voi
 
 	constraints_initialized = 1;
 
+	perf_pmu_register(&perf_breakpoint);
+
 	return register_die_notifier(&hw_breakpoint_exceptions_nb);
 
  err_alloc:

@@ -589,8 +619,3 @@ static int __init init_hw_breakpoint(voi
 core_initcall(init_hw_breakpoint);
 
 
-struct pmu perf_ops_bp = {
-	.enable		= arch_install_hw_breakpoint,
-	.disable	= arch_uninstall_hw_breakpoint,
-	.read		= hw_breakpoint_pmu_read,
-};

700 lines not on this page · raw message

Index: linux-2.6/kernel/perf_event.c
===================================================================
@@ -147,7 +147,7 @@ perf_lock_task_context(struct task_struc
 	struct perf_event_context *ctx;
 
 	rcu_read_lock();
- retry:
+retry:
 	ctx = rcu_dereference(task->perf_event_ctxp);
 	if (ctx) {
 		/*

@@ -601,7 +601,7 @@ void perf_event_disable(struct perf_even
 		return;
 	}
 
- retry:
+retry:
 	task_oncpu_function_call(task, __perf_event_disable, event);
 
 	raw_spin_lock_irq(&ctx->lock);

@@ -831,7 +831,7 @@ static void __perf_install_in_context(vo
 	if (!err && !ctx->task && cpuctx->max_pertask)
 		cpuctx->max_pertask--;
 
- unlock:
+unlock:
 	perf_enable();
 
 	raw_spin_unlock(&ctx->lock);

@@ -904,10 +904,12 @@ static void __perf_event_mark_enabled(st
 
 	event->state = PERF_EVENT_STATE_INACTIVE;
 	event->tstamp_enabled = ctx->time - event->total_time_enabled;
-	list_for_each_entry(sub, &event->sibling_list, group_entry)
-		if (sub->state >= PERF_EVENT_STATE_INACTIVE)
+	list_for_each_entry(sub, &event->sibling_list, group_entry) {
+		if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
 			sub->tstamp_enabled =
 				ctx->time - sub->total_time_enabled;
+		}
+	}
 }
 
 /*

@@ -973,7 +975,7 @@ static void __perf_event_enable(void *in
 		}
 	}
 
- unlock:
+unlock:
 	raw_spin_unlock(&ctx->lock);
 }
 

@@ -1014,7 +1016,7 @@ void perf_event_enable(struct perf_event
 	if (event->state == PERF_EVENT_STATE_ERROR)
 		event->state = PERF_EVENT_STATE_OFF;
 
- retry:
+retry:
 	raw_spin_unlock_irq(&ctx->lock);
 	task_oncpu_function_call(task, __perf_event_enable, event);
 

@@ -1034,7 +1036,7 @@ void perf_event_enable(struct perf_event
 	if (event->state == PERF_EVENT_STATE_OFF)
 		__perf_event_mark_enabled(event, ctx);
 
- out:
+out:
 	raw_spin_unlock_irq(&ctx->lock);
 }
 

@@ -1074,17 +1076,19 @@ static void ctx_sched_out(struct perf_ev
 	if (!ctx->nr_active)
 		goto out_enable;
 
-	if (event_type & EVENT_PINNED)
+	if (event_type & EVENT_PINNED) {
 		list_for_each_entry(event, &ctx->pinned_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
+	}
 
-	if (event_type & EVENT_FLEXIBLE)
+	if (event_type & EVENT_FLEXIBLE) {
 		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
+	}
 
  out_enable:
 	perf_enable();
- out:
+out:
 	raw_spin_unlock(&ctx->lock);
 }
 

@@ -1323,9 +1327,10 @@ ctx_flexible_sched_in(struct perf_event_
 		if (event->cpu != -1 && event->cpu != smp_processor_id())
 			continue;
 
-		if (group_can_go_on(event, cpuctx, can_add_hw))
+		if (group_can_go_on(event, cpuctx, can_add_hw)) {
 			if (group_sched_in(event, cpuctx, ctx))
 				can_add_hw = 0;
+		}
 	}
 }
 

@@ -1355,7 +1360,7 @@ ctx_sched_in(struct perf_event_context *
 		ctx_flexible_sched_in(ctx, cpuctx);
 
 	perf_enable();
- out:
+out:
 	raw_spin_unlock(&ctx->lock);
 }
 

@@ -1696,7 +1701,7 @@ static void perf_event_enable_on_exec(st
 	raw_spin_unlock(&ctx->lock);
 
 	perf_event_task_sched_in(task);
- out:
+out:
 	local_irq_restore(flags);
 }
 

@@ -1825,7 +1830,7 @@ static struct perf_event_context *find_g
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto errout;
 
- retry:
+retry:
 	ctx = perf_lock_task_context(task, &flags);
 	if (ctx) {
 		unclone_ctx(ctx);

@@ -1853,7 +1858,7 @@ static struct perf_event_context *find_g
 	put_task_struct(task);
 	return ctx;
 
- errout:
+errout:
 	put_task_struct(task);
 	return ERR_PTR(err);
 }

@@ -3044,7 +3049,7 @@ again:
 	if (handle->wakeup != local_read(&buffer->wakeup))
 		perf_output_wakeup(handle);
 
- out:
+out:
 	preempt_enable();
 }
 

@@ -4352,7 +4357,7 @@ static int swevent_hlist_get_cpu(struct 
 		rcu_assign_pointer(cpuctx->swevent_hlist, hlist);
 	}
 	cpuctx->hlist_refcount++;
- exit:
+exit:
 	mutex_unlock(&cpuctx->hlist_mutex);
 
 	return err;

@@ -4377,7 +4382,7 @@ static int swevent_hlist_get(struct perf
 	put_online_cpus();
 
 	return 0;
- fail:
+fail:
 	for_each_possible_cpu(cpu) {
 		if (cpu == failed_cpu)
 			break;

Index: linux-2.6/include/linux/perf_event.h
===================================================================
@@ -562,26 +562,26 @@ struct pmu {
 	struct list_head		entry;
 
 	/*
-	 * Should return -ENOENT when the @event doesn't match this pmu
+	 * Should return -ENOENT when the @event doesn't match this PMU.
 	 */
 	int (*event_init)		(struct perf_event *event);
 
-	int (*enable)			(struct perf_event *event);
+	int  (*enable)			(struct perf_event *event);
 	void (*disable)			(struct perf_event *event);
-	int (*start)			(struct perf_event *event);
+	int  (*start)			(struct perf_event *event);
 	void (*stop)			(struct perf_event *event);
 	void (*read)			(struct perf_event *event);
 	void (*unthrottle)		(struct perf_event *event);
 
 	/*
-	 * Group events scheduling is treated as a transaction, add group
-	 * events as a whole and perform one schedulability test. If the test
-	 * fails, roll back the whole group
+	 * Group events scheduling is treated as a transaction, add
+	 * group events as a whole and perform one schedulability test.
+	 * If the test fails, roll back the whole group
 	 */
 
 	/*
-	 * Start the transaction, after this ->enable() doesn't need
-	 * to do schedulability tests.
+	 * Start the transaction, after this ->enable() doesn't need to
+	 * do schedulability tests.
 	 */
 	void (*start_txn)	(struct pmu *pmu);
 	/*

@@ -592,8 +592,8 @@ struct pmu {
 	 */
 	int  (*commit_txn)	(struct pmu *pmu);
 	/*
-	 * Will cancel the transaction, assumes ->disable() is called for
-	 * each successfull ->enable() during the transaction.
+	 * Will cancel the transaction, assumes ->disable() is called
+	 * for each successfull ->enable() during the transaction.
 	 */
 	void (*cancel_txn)	(struct pmu *pmu);
 };

Index: linux-2.6/kernel/perf_event.c
===================================================================
@@ -460,11 +460,6 @@ static void __perf_event_remove_from_con
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * events on a global level.
-	 */
-	perf_disable();
 
 	event_sched_out(event, cpuctx, ctx);
 

@@ -480,7 +475,6 @@ static void __perf_event_remove_from_con
 			    perf_max_events - perf_reserved_percpu);
 	}
 
-	perf_enable();
 	raw_spin_unlock(&ctx->lock);
 }
 

@@ -785,12 +779,6 @@ static void __perf_install_in_context(vo
 	ctx->is_active = 1;
 	update_context_time(ctx);
 
-	/*
-	 * Protect the list operation against NMI by disabling the
-	 * events on a global level. NOP for non NMI based events.
-	 */
-	perf_disable();
-
 	add_event_to_ctx(event, ctx);
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())

@@ -832,8 +820,6 @@ static void __perf_install_in_context(vo
 		cpuctx->max_pertask--;
 
 unlock:
-	perf_enable();
-
 	raw_spin_unlock(&ctx->lock);
 }
 

@@ -954,12 +940,10 @@ static void __perf_event_enable(void *in
 	if (!group_can_go_on(event, cpuctx, 1)) {
 		err = -EEXIST;
 	} else {
-		perf_disable();
 		if (event == leader)
 			err = group_sched_in(event, cpuctx, ctx);
 		else
 			err = event_sched_in(event, cpuctx, ctx);
-		perf_enable();
 	}
 
 	if (err) {

@@ -1072,9 +1056,8 @@ static void ctx_sched_out(struct perf_ev
 		goto out;
 	update_context_time(ctx);
 
-	perf_disable();
 	if (!ctx->nr_active)
-		goto out_enable;
+		goto out;
 
 	if (event_type & EVENT_PINNED) {
 		list_for_each_entry(event, &ctx->pinned_groups, group_entry)

@@ -1085,9 +1068,6 @@ static void ctx_sched_out(struct perf_ev
 		list_for_each_entry(event, &ctx->flexible_groups, group_entry)
 			group_sched_out(event, cpuctx, ctx);
 	}
-
- out_enable:
-	perf_enable();
 out:
 	raw_spin_unlock(&ctx->lock);
 }

@@ -1346,8 +1326,6 @@ ctx_sched_in(struct perf_event_context *
 
 	ctx->timestamp = perf_clock();
 
-	perf_disable();
-
 	/*
 	 * First go through the list and put on any pinned groups
 	 * in order to give them the best chance of going on.

@@ -1359,7 +1337,6 @@ ctx_sched_in(struct perf_event_context *
 	if (event_type & EVENT_FLEXIBLE)
 		ctx_flexible_sched_in(ctx, cpuctx);
 
-	perf_enable();
 out:
 	raw_spin_unlock(&ctx->lock);
 }

@@ -1407,8 +1384,6 @@ void perf_event_task_sched_in(struct tas
 	if (cpuctx->task_ctx == ctx)
 		return;
 
-	perf_disable();
-
 	/*
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,

@@ -1421,8 +1396,6 @@ void perf_event_task_sched_in(struct tas
 	ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
 
 	cpuctx->task_ctx = ctx;
-
-	perf_enable();
 }
 
 #define MAX_INTERRUPTS (~0ULL)

@@ -1537,11 +1510,9 @@ static void perf_adjust_period(struct pe
 	hwc->sample_period = sample_period;
 
 	if (local64_read(&hwc->period_left) > 8*sample_period) {
-		perf_disable();
 		perf_event_stop(event);
 		local64_set(&hwc->period_left, 0);
 		perf_event_start(event);
-		perf_enable();
 	}
 }
 

@@ -1570,15 +1541,12 @@ static void perf_ctx_adjust_freq(struct 
 		 */
 		if (interrupts == MAX_INTERRUPTS) {
 			perf_log_throttle(event, 1);
-			perf_disable();
 			event->pmu->unthrottle(event);
-			perf_enable();
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
 			continue;
 
-		perf_disable();
 		event->pmu->read(event);
 		now = local64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;

@@ -1586,7 +1554,6 @@ static void perf_ctx_adjust_freq(struct 
 
 		if (delta > 0)
 			perf_adjust_period(event, TICK_NSEC, delta);
-		perf_enable();
 	}
 	raw_spin_unlock(&ctx->lock);
 }

@@ -1629,7 +1596,6 @@ void perf_event_task_tick(struct task_st
 	if (!rotate)
 		return;
 
-	perf_disable();
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_out(ctx, EVENT_FLEXIBLE);

@@ -1641,7 +1607,6 @@ void perf_event_task_tick(struct task_st
 	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_in(curr, EVENT_FLEXIBLE);
-	perf_enable();
 }
 
 static int event_enable_on_exec(struct perf_event *event,

Index: linux-2.6/arch/powerpc/kernel/perf_event_fsl_emb.c
===================================================================
@@ -262,7 +262,7 @@ static int collect_events(struct perf_ev
 	return n;
 }
 
-/* perf must be disabled, context locked on entry */
+/* context locked on entry */
 static int fsl_emb_pmu_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuhw;

@@ -271,6 +271,7 @@ static int fsl_emb_pmu_enable(struct per
 	u64 val;
 	int i;
 
+	perf_disable();
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)

@@ -310,15 +311,17 @@ static int fsl_emb_pmu_enable(struct per
 	ret = 0;
  out:
 	put_cpu_var(cpu_hw_events);
+	perf_enable();
 	return ret;
 }
 
-/* perf must be disabled, context locked on entry */
+/* context locked on entry */
 static void fsl_emb_pmu_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuhw;
 	int i = event->hw.idx;
 
+	perf_disable();
 	if (i < 0)
 		goto out;
 

@@ -346,6 +349,7 @@ static void fsl_emb_pmu_disable(struct p
 	cpuhw->n_events--;
 
  out:
+	perf_enable();
 	put_cpu_var(cpu_hw_events);
 }
 

Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
===================================================================
@@ -969,10 +969,11 @@ static int x86_pmu_enable(struct perf_ev
 
 	hwc = &event->hw;
 
+	perf_disable();
 	n0 = cpuc->n_events;
-	n = collect_events(cpuc, event, false);
-	if (n < 0)
-		return n;
+	ret = n = collect_events(cpuc, event, false);
+	if (ret < 0)
+		goto out;
 
 	/*
 	 * If group events scheduling transaction was started,

@@ -980,23 +981,26 @@ static int x86_pmu_enable(struct perf_ev
 	 * at commit time(->commit_txn) as a whole
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
-		goto out;
+		goto done_collect;
 
 	ret = x86_pmu.schedule_events(cpuc, n, assign);
 	if (ret)
-		return ret;
+		goto out;
 	/*
 	 * copy new assignment, now we know it is possible
 	 * will be used by hw_perf_enable()
 	 */
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
-out:
+done_collect:
 	cpuc->n_events = n;
 	cpuc->n_added += n - n0;
 	cpuc->n_txn += n - n0;
 
-	return 0;
+	ret = 0;
+out:
+	perf_enable();
+	return ret;
 }
 
 static int x86_pmu_start(struct perf_event *event)

@@ -1399,6 +1403,7 @@ static void x86_pmu_start_txn(struct pmu
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
+	perf_disable();
 	cpuc->group_flag |= PERF_EVENT_TXN;
 	cpuc->n_txn = 0;
 }

@@ -1418,6 +1423,7 @@ static void x86_pmu_cancel_txn(struct pm
 	 */
 	cpuc->n_added -= cpuc->n_txn;
 	cpuc->n_events -= cpuc->n_txn;
+	perf_enable();
 }
 
 /*

@@ -1447,7 +1453,7 @@ static int x86_pmu_commit_txn(struct pmu
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
-
+	perf_enable();
 	return 0;
 }
 

Index: linux-2.6/arch/powerpc/kernel/perf_event.c
===================================================================
@@ -858,6 +858,7 @@ void power_pmu_start_txn(struct pmu *pmu
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_disable();
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 	cpuhw->n_txn_start = cpuhw->n_events;
 }

@@ -872,6 +873,7 @@ void power_pmu_cancel_txn(struct pmu *pm
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_enable();
 }
 
 /*

@@ -898,6 +900,7 @@ int power_pmu_commit_txn(struct pmu *pmu
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_enable();
 	return 0;
 }
 

Index: linux-2.6/arch/sparc/kernel/perf_event.c
===================================================================
@@ -1112,6 +1112,7 @@ static void sparc_pmu_start_txn(struct p
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+	perf_disable();
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 

@@ -1125,6 +1126,7 @@ static void sparc_pmu_cancel_txn(struct 
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
+	perf_enable();
 }
 
 /*

@@ -1148,6 +1150,7 @@ static int sparc_pmu_commit_txn(struct p
 		return -EAGAIN;
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
+	perf_enable();
 	return 0;
 }
 

Index: linux-2.6/arch/arm/kernel/perf_event.c
===================================================================
@@ -531,16 +531,7 @@ static int armpmu_event_init(struct perf
 	return err;
 }
 
-static struct pmu pmu = {
-	.event_init = armpmu_event_init,
-	.enable	    = armpmu_enable,
-	.disable    = armpmu_disable,
-	.unthrottle = armpmu_unthrottle,
-	.read	    = armpmu_read,
-};
-
-void
-hw_perf_enable(void)
+static void armpmu_pmu_enable(struct pmu *pmu)
 {
 	/* Enable all of the perf events on hardware. */
 	int idx;

@@ -561,13 +552,22 @@ hw_perf_enable(void)
 	armpmu->start();
 }
 
-void
-hw_perf_disable(void)
+static void armpmu_pmu_disable(struct pmu *pmu)
 {
 	if (armpmu)
 		armpmu->stop();
 }
 
+static struct pmu pmu = {
+	.pmu_enable = armpmu_pmu_enable,
+	.pmu_disable= armpmu_pmu_disable,
+	.event_init = armpmu_event_init,
+	.enable	    = armpmu_enable,
+	.disable    = armpmu_disable,
+	.unthrottle = armpmu_unthrottle,
+	.read	    = armpmu_read,
+};
+
 /*
  * ARMv6 Performance counter handling code.
  *

Index: linux-2.6/arch/powerpc/kernel/perf_event.c
===================================================================
@@ -517,7 +517,7 @@ static void write_mmcr0(struct cpu_hw_ev
  * Disable all events to prevent PMU interrupts and to allow
  * events to be added or removed.
  */
-void hw_perf_disable(void)
+static void powerpc_pmu_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;

@@ -565,7 +565,7 @@ 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 powerpc_pmu_pmu_enable(struct pmu *pmu)
 {
 	struct perf_event *event;
 	struct cpu_hw_events *cpuhw;

@@ -735,7 +735,7 @@ static int power_pmu_enable(struct perf_
 	int ret = -EAGAIN;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	/*
 	 * Add the event to the list (if there is room)

@@ -769,7 +769,7 @@ nocheck:
 
 	ret = 0;
  out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }

@@ -784,7 +784,7 @@ static void power_pmu_disable(struct per
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	power_pmu_read(event);
 

@@ -818,7 +818,7 @@ static void power_pmu_disable(struct per
 		cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE);
 	}
 
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 

@@ -834,7 +834,7 @@ static void power_pmu_unthrottle(struct 
 	if (!event->hw.idx || !event->hw.sample_period)
 		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;

@@ -845,7 +845,7 @@ static void power_pmu_unthrottle(struct 
 	local64_set(&event->hw.prev_count, val);
 	local64_set(&event->hw.period_left, left);
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 

@@ -858,7 +858,7 @@ void power_pmu_start_txn(struct pmu *pmu
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
-	perf_disable();
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 	cpuhw->n_txn_start = cpuhw->n_events;
 }

@@ -873,7 +873,7 @@ void power_pmu_cancel_txn(struct pmu *pm
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
-	perf_enable();
+	perf_pmu_enable(pmu);
 }
 
 /*

@@ -900,7 +900,7 @@ int power_pmu_commit_txn(struct pmu *pmu
 		cpuhw->event[i]->hw.config = cpuhw->events[i];
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
-	perf_enable();
+	perf_pmu_enable(pmu);
 	return 0;
 }
 

@@ -1128,7 +1128,9 @@ static int power_pmu_event_init(struct p
 }
 
 struct pmu power_pmu = {
-	.event_init	= power_pmu_event_init,
+	.pmu_enable	= power_pmu_pmu_enable,
+	.pmu_disable	= power_pmu_pmu_disable,
+	.event_init	= pmwer_pmu_event_init,
 	.enable		= power_pmu_enable,
 	.disable	= power_pmu_disable,
 	.read		= power_pmu_read,

Index: linux-2.6/arch/powerpc/kernel/perf_event_fsl_emb.c
===================================================================
@@ -177,7 +177,7 @@ static void fsl_emb_pmu_read(struct perf
  * 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_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;

@@ -216,7 +216,7 @@ 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_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuhw;
 	unsigned long flags;

@@ -271,7 +271,7 @@ static int fsl_emb_pmu_enable(struct per
 	u64 val;
 	int i;
 
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 	cpuhw = &get_cpu_var(cpu_hw_events);
 
 	if (event->hw.config & FSL_EMB_EVENT_RESTRICTED)

@@ -311,7 +311,7 @@ static int fsl_emb_pmu_enable(struct per
 	ret = 0;
  out:
 	put_cpu_var(cpu_hw_events);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	return ret;
 }
 

@@ -321,7 +321,7 @@ static void fsl_emb_pmu_disable(struct p
 	struct cpu_hw_events *cpuhw;
 	int i = event->hw.idx;
 
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 	if (i < 0)
 		goto out;
 

@@ -349,7 +349,7 @@ static void fsl_emb_pmu_disable(struct p
 	cpuhw->n_events--;
 
  out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	put_cpu_var(cpu_hw_events);
 }
 

@@ -367,7 +367,7 @@ static void fsl_emb_pmu_unthrottle(struc
 	if (event->hw.idx < 0 || !event->hw.sample_period)
 		return;
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 	fsl_emb_pmu_read(event);
 	left = event->hw.sample_period;
 	event->hw.last_period = left;

@@ -378,7 +378,7 @@ static void fsl_emb_pmu_unthrottle(struc
 	local64_set(&event->hw.prev_count, val);
 	local64_set(&event->hw.period_left, left);
 	perf_event_update_userpage(event);
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 

@@ -524,6 +524,8 @@ static int fsl_emb_pmu_event_init(struct
 }
 
 static struct pmu fsl_emb_pmu = {
+	.pmu_enable	= fsl_emb_pmu_pmu_enable,
+	.pmu_disable	= fsl_emb_pmu_pmu_disable,
 	.event_init	= fsl_emb_pmu_event_init,
 	.enable		= fsl_emb_pmu_enable,
 	.disable	= fsl_emb_pmu_disable,

Index: linux-2.6/arch/sh/kernel/perf_event.c
===================================================================
@@ -268,7 +268,25 @@ static in sh_pmu_event_init(struct perf_
 	return err;
 }
 
+static void sh_pmu_pmu_enable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->enable_all();
+}
+
+static void sh_pmu_pmu_disable(struct pmu *pmu)
+{
+	if (!sh_pmu_initialized())
+		return;
+
+	sh_pmu->disable_all();
+}
+
 static struct pmu pmu = {
+	.pmu_enable	= sh_pmu_pmu_enable,
+	.pmu_disable	= sh_pmu_pmu_disable,
 	.event_init	= sh_pmu_event_init,
 	.enable		= sh_pmu_enable,
 	.disable	= sh_pmu_disable,

@@ -299,22 +317,6 @@ sh_pmu_notifier(struct notifier_block *s
 	return NOTIFY_OK;
 }
 
-void hw_perf_enable(void)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->enable_all();
-}
-
-void hw_perf_disable(void)
-{
-	if (!sh_pmu_initialized())
-		return;
-
-	sh_pmu->disable_all();
-}
-
 int __cpuinit register_sh_pmu(struct sh_pmu *pmu)
 {
 	if (sh_pmu)

Index: linux-2.6/arch/sparc/kernel/perf_event.c
===================================================================
@@ -664,7 +664,7 @@ out:
 	return pcr;
 }
 
-void hw_perf_enable(void)
+static void sparc_pmu_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 pcr;

@@ -691,7 +691,7 @@ void hw_perf_enable(void)
 	pcr_ops->write(cpuc->pcr);
 }
 
-void hw_perf_disable(void)
+static void sparc_pmu_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	u64 val;

@@ -718,7 +718,7 @@ static void sparc_pmu_disable(struct per
 	int i;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event[i]) {

@@ -748,7 +748,7 @@ static void sparc_pmu_disable(struct per
 		}
 	}
 
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 }
 

@@ -991,7 +991,7 @@ static int sparc_pmu_enable(struct perf_
 	unsigned long flags;
 
 	local_irq_save(flags);
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 
 	n0 = cpuc->n_events;
 	if (n0 >= perf_max_events)

@@ -1020,7 +1020,7 @@ nocheck:
 
 	ret = 0;
 out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
 }

@@ -1113,7 +1113,7 @@ static void sparc_pmu_start_txn(struct p
 {
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
-	perf_disable();
+	perf_pmu_disable(pmu);
 	cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 

@@ -1127,7 +1127,7 @@ static void sparc_pmu_cancel_txn(struct 
 	struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
 	cpuhw->group_flag &= ~PERF_EVENT_TXN;
-	perf_enable();
+	perf_pmu_enable(pmu);
 }
 
 /*

@@ -1151,11 +1151,13 @@ static int sparc_pmu_commit_txn(struct p
 		return -EAGAIN;
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
-	perf_enable();
+	perf_pmu_enable(pmu);
 	return 0;
 }
 
 static struct pmu pmu = {
+	.pmu_enable	= sparc_pmu_pmu_enable,
+	.pmu_disable	= sparc_pmu_pmu_disable,
 	.event_init	= sparc_pmu_event_init,
 	.enable		= sparc_pmu_enable,
 	.disable	= sparc_pmu_disable,

Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
===================================================================
@@ -583,7 +583,7 @@ static void x86_pmu_disable_all(void)
 	}
 }
 
-void hw_perf_disable(void)
+static void x86_pmu_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 

@@ -803,7 +803,7 @@ static inline int match_prev_assignment(
 static int x86_pmu_start(struct perf_event *event);
 static void x86_pmu_stop(struct perf_event *event);
 
-void hw_perf_enable(void)
+static void x86_pmu_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;

@@ -969,7 +969,7 @@ static int x86_pmu_enable(struct perf_ev
 
 	hwc = &event->hw;
 
-	perf_disable();
+	perf_pmu_disable(event->pmu);
 	n0 = cpuc->n_events;
 	ret = n = collect_events(cpuc, event, false);
 	if (ret < 0)

@@ -999,7 +999,7 @@ done_collect:
 
 	ret = 0;
 out:
-	perf_enable();
+	perf_pmu_enable(event->pmu);
 	return ret;
 }
 

@@ -1403,7 +1403,7 @@ static void x86_pmu_start_txn(struct pmu
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
-	perf_disable();
+	perf_pmu_disable(pmu);
 	cpuc->group_flag |= PERF_EVENT_TXN;
 	cpuc->n_txn = 0;
 }

@@ -1423,7 +1423,7 @@ static void x86_pmu_cancel_txn(struct pm
 	 */
 	cpuc->n_added -= cpuc->n_txn;
 	cpuc->n_events -= cpuc->n_txn;
-	perf_enable();
+	perf_pmu_enable(pmu);
 }
 
 /*

@@ -1453,7 +1453,7 @@ static int x86_pmu_commit_txn(struct pmu
 	memcpy(cpuc->assign, assign, n*sizeof(int));
 
 	cpuc->group_flag &= ~PERF_EVENT_TXN;
-	perf_enable();
+	perf_pmu_enable(pmu);
 	return 0;
 }
 

@@ -1572,6 +1572,8 @@ int x86_pmu_event_init(struct perf_event
 }
 
 static struct pmu pmu = {
+	.pmu_enable	= x86_pmu_pmu_enable,
+	.pmu_disable	= x86_pmu_pmu_disable,
 	.event_init	= x86_pmu_event_init,
 	.enable		= x86_pmu_enable,
 	.disable	= x86_pmu_disable,

Index: linux-2.6/include/linux/perf_event.h
===================================================================
@@ -563,6 +563,11 @@ struct perf_event;
 struct pmu {
 	struct list_head		entry;
 
+	int				*pmu_disable_count;
+
+	void (*pmu_enable)		(struct pmu *pmu);
+	void (*pmu_disable)		(struct pmu *pmu);
+
 	/*
 	 * Should return -ENOENT when the @event doesn't match this PMU.
 	 */

@@ -866,10 +871,8 @@ extern void perf_event_free_task(struct 
 extern void set_perf_event_pending(void);
 extern void perf_event_do_pending(void);
 extern void perf_event_print_debug(void);
-extern void __perf_disable(void);
-extern bool __perf_enable(void);
-extern void perf_disable(void);
-extern void perf_enable(void);
+extern void perf_pmu_disable(struct pmu *pmu);
+extern void perf_pmu_enable(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern void perf_event_update_userpage(struct perf_event *event);

@@ -1040,8 +1043,6 @@ static inline void perf_event_exit_task(
 static inline void perf_event_free_task(struct task_struct *task)	{ }
 static inline void perf_event_do_pending(void)				{ }
 static inline void perf_event_print_debug(void)				{ }
-static inline void perf_disable(void)					{ }
-static inline void perf_enable(void)					{ }
 static inline int perf_event_task_disable(void)				{ return -EINVAL; }
 static inline int perf_event_task_enable(void)				{ return -EINVAL; }
 

Index: linux-2.6/kernel/perf_event.c
===================================================================
@@ -71,23 +71,20 @@ static atomic64_t perf_event_id;
  */
 static DEFINE_SPINLOCK(perf_resource_lock);
 
-void __weak hw_perf_disable(void)		{ barrier(); }
-void __weak hw_perf_enable(void)		{ barrier(); }
-
 void __weak perf_event_print_debug(void)	{ }
 
-static DEFINE_PER_CPU(int, perf_disable_count);
-
-void perf_disable(void)
+void perf_pmu_disable(struct pmu *pmu)
 {
-	if (!__get_cpu_var(perf_disable_count)++)
-		hw_perf_disable();
+	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	if (!(*count)++)
+		pmu->pmu_disable(pmu);
 }
 
-void perf_enable(void)
+void perf_pmu_enable(struct pmu *pmu)
 {
-	if (!--__get_cpu_var(perf_disable_count))
-		hw_perf_enable();
+	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+	if (!--(*count))
+		pmu->pmu_enable(pmu);
 }
 
 static void get_ctx(struct perf_event_context *ctx)

@@ -4760,16 +4757,25 @@ static struct srcu_struct pmus_srcu;
 
 int perf_pmu_register(struct pmu *pmu)
 {
+	int ret;
+
 	mutex_lock(&pmus_lock);
+	ret = -ENOMEM;
+	pmu->pmu_disable_count = alloc_percpu(int);
+	if (!pmu->pmu_disable_count)
+		goto unlock;
 	list_add_rcu(&pmu->entry, &pmus);
+	ret = 0;
+unlock:
 	mutex_unlock(&pmus_lock);
 
-	return 0;
+	return ret;
 }
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
 	mutex_lock(&pmus_lock);
+	free_percpu(pmu->pmu_disable_count);
 	list_del_rcu(&pmu->entry);
 	mutex_unlock(&pmus_lock);
 

Index: linux-2.6/kernel/perf_event.c
===================================================================
@@ -656,21 +656,14 @@ group_sched_in(struct perf_event *group_
 {
 	struct perf_event *event, *partial_group = NULL;
 	struct pmu *pmu = group_event->pmu;
-	bool txn = false;
 
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
-	/* Check if group transaction availabe */
-	if (pmu->start_txn)
-		txn = true;
-
-	if (txn)
-		pmu->start_txn(pmu);
+	pmu->start_txn(pmu);
 
 	if (event_sched_in(group_event, cpuctx, ctx)) {
-		if (txn)
-			pmu->cancel_txn(pmu);
+		pmu->cancel_txn(pmu);
 		return -EAGAIN;
 	}
 

@@ -684,7 +677,7 @@ group_sched_in(struct perf_event *group_
 		}
 	}
 
-	if (!txn || !pmu->commit_txn(pmu))
+	if (!pmu->commit_txn(pmu))
 		return 0;
 
 group_error:

@@ -699,8 +692,7 @@ group_error:
 	}
 	event_sched_out(group_event, cpuctx, ctx);
 
-	if (txn)
-		pmu->cancel_txn(pmu);
+	pmu->cancel_txn(pmu);
 
 	return -EAGAIN;
 }

@@ -4755,6 +4747,31 @@ static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
 static struct srcu_struct pmus_srcu;
 
+static void perf_pmu_nop_void(struct pmu *pmu)
+{
+}
+
+static int perf_pmu_nop_int(struct pmu *pmu)
+{
+	return 0;
+}
+
+static void perf_pmu_start_txn(struct pmu *pmu)
+{
+	perf_pmu_disable(pmu);
+}
+
+static int perf_pmu_commit_txn(struct pmu *pmu)
+{
+	perf_pmu_enable(pmu);
+	return 0;
+}
+
+static void perf_pmu_cancel_txn(struct pmu *pmu)
+{
+	perf_pmu_enable(pmu);
+}
+
 int perf_pmu_register(struct pmu *pmu)
 {
 	int ret;

@@ -4764,6 +4781,29 @@ int perf_pmu_register(struct pmu *pmu)
 	pmu->pmu_disable_count = alloc_percpu(int);
 	if (!pmu->pmu_disable_count)
 		goto unlock;
+
+	if (!pmu->start_txn) {
+		if (pmu->pmu_enable) {
+			/*
+			 * If we have pmu_enable/pmu_disable calls, install
+			 * transaction stubs that use that to try and batch
+			 * hardware accesses.
+			 */
+			pmu->start_txn  = perf_pmu_start_txn;
+			pmu->commit_txn = perf_pmu_commit_txn;
+			pmu->cancel_txn = perf_pmu_cancel_txn;
+		} else {
+			pmu->start_txn  = perf_pmu_nop_void;
+			pmu->commit_txn = perf_pmu_nop_int;
+			pmu->cancel_txn = perf_pmu_nop_void;
+		}
+	}
+
+	if (!pmu->pmu_enable) {
+		pmu->pmu_enable  = perf_pmu_nop_void;
+		pmu->pmu_disable = perf_pmu_nop_void;
+	}
+
 	list_add_rcu(&pmu->entry, &pmus);
 	ret = 0;
 unlock:

Index: linux-2.6/include/linux/perf_event.h
===================================================================
@@ -565,8 +565,8 @@ struct pmu {
 
 	int				*pmu_disable_count;
 
-	void (*pmu_enable)		(struct pmu *pmu);
-	void (*pmu_disable)		(struct pmu *pmu);
+	void (*pmu_enable)		(struct pmu *pmu); /* optional */
+	void (*pmu_disable)		(struct pmu *pmu); /* optional */
 
 	/*
 	 * Should return -ENOENT when the @event doesn't match this PMU.

@@ -590,19 +590,19 @@ struct pmu {
 	 * Start the transaction, after this ->enable() doesn't need to
 	 * do schedulability tests.
 	 */
-	void (*start_txn)	(struct pmu *pmu);
+	void (*start_txn)	(struct pmu *pmu); /* optional */
 	/*
 	 * If ->start_txn() disabled the ->enable() schedulability test
 	 * then ->commit_txn() is required to perform one. On success
 	 * the transaction is closed. On error the transaction is kept
 	 * open until ->cancel_txn() is called.
 	 */
-	int  (*commit_txn)	(struct pmu *pmu);
+	int  (*commit_txn)	(struct pmu *pmu); /* optional */
 	/*
 	 * Will cancel the transaction, assumes ->disable() is called
 	 * for each successfull ->enable() during the transaction.
 	 */
-	void (*cancel_txn)	(struct pmu *pmu);
+	void (*cancel_txn)	(struct pmu *pmu); /* optional */
 };
 
 /**

Index: linux-2.6/include/linux/perf_event.h
===================================================================
@@ -529,7 +529,6 @@ struct hw_perf_event {
 			int		last_cpu;
 		};
 		struct { /* software */
-			s64		remaining;
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT

Index: linux-2.6/kernel/perf_event.c
===================================================================
@@ -4590,14 +4590,13 @@ static void perf_swevent_start_hrtimer(s
 	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hwc->hrtimer.function = perf_swevent_hrtimer;
 	if (hwc->sample_period) {
-		u64 period;
+		s64 period = local64_read(&hwc->period_left);
 
-		if (hwc->remaining) {
-			if (hwc->remaining < 0)
+		if (period) {
+			if (period < 0)
 				period = 10000;
-			else
-				period = hwc->remaining;
-			hwc->remaining = 0;
+
+			local64_set(&hwc->period_left, 0);
 		} else {
 			period = max_t(u64, 10000, hwc->sample_period);
 		}

@@ -4613,7 +4612,7 @@ static void perf_swevent_cancel_hrtimer(
 
 	if (hwc->sample_period) {
 		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
-		hwc->remaining = ktime_to_ns(remaining);
+		local64_set(&hwc->period_left, ktime_to_ns(remaining));
 
 		hrtimer_cancel(&hwc->hrtimer);
 	}

Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
===================================================================
@@ -583,7 +583,7 @@ static void x86_pmu_disable_all(void)
 	}
 }
 
-static void x86_pmu_pmu_disable(struct pmu *pmu)
+static void x86_pmu_disable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 

@@ -800,10 +800,10 @@ static inline int match_prev_assignment(
 		hwc->last_tag == cpuc->tags[i];
 }
 
-static int x86_pmu_start(struct perf_event *event);
-static void x86_pmu_stop(struct perf_event *event);
+static void x86_pmu_start(struct perf_event *event, int flags);
+static void x86_pmu_stop(struct perf_event *event, int flags);
 
-static void x86_pmu_pmu_enable(struct pmu *pmu)
+static void x86_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct perf_event *event;

@@ -839,7 +839,14 @@ static void x86_pmu_pmu_enable(struct pm
 			    match_prev_assignment(hwc, cpuc, i))
 				continue;
 
-			x86_pmu_stop(event);
+			/*
+			 * Ensure we don't accidentally enable a stopped
+			 * counter simply because we rescheduled.
+			 */
+			if (hwc->state & PERF_HES_STOPPED)
+				hwc->state |= PERF_HES_ARCH;
+
+			x86_pmu_stop(event, PERF_EF_UPDATE);
 		}
 
 		for (i = 0; i < cpuc->n_events; i++) {

@@ -851,7 +858,10 @@ static void x86_pmu_pmu_enable(struct pm
 			else if (i < n_running)
 				continue;
 
-			x86_pmu_start(event);
+			if (hwc->state & PERF_HES_ARCH)
+				continue;
+
+			x86_pmu_start(event, PERF_EF_RELOAD);
 		}
 		cpuc->n_added = 0;
 		perf_events_lapic_init();

@@ -952,15 +962,12 @@ static void x86_pmu_enable_event(struct 
 }
 
 /*
- * activate a single event
+ * Add a single event to the PMU.
  *
  * The event is added to the group of enabled events
  * but only if it can be scehduled with existing events.
- *
- * Called with PMU disabled. If successful and return value 1,
- * then guaranteed to call perf_enable() and hw_perf_enable()
  */
-static int x86_pmu_enable(struct perf_event *event)
+static int x86_pmu_add(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc;

@@ -975,10 +982,14 @@ static int x86_pmu_enable(struct perf_ev
 	if (ret < 0)
 		goto out;
 
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
+
 	/*
 	 * If group events scheduling transaction was started,
 	 * skip the schedulability test here, it will be peformed
-	 * at commit time(->commit_txn) as a whole
+	 * at commit time (->commit_txn) as a whole
 	 */
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		goto done_collect;

@@ -1003,27 +1014,28 @@ out:
 	return ret;
 }
 
-static int x86_pmu_start(struct perf_event *event)
+static void x86_pmu_start(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int idx = event->hw.idx;
 
-	if (idx == -1)
-		return -EAGAIN;
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	if (WARN_ON_ONCE(idx == -1))
+		return;
+
+	if (flags & PERF_EF_RELOAD) {
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+		x86_perf_event_set_period(event);
+	}
+
+	event->hw.state = 0;
 
-	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)
-{
-	int ret = x86_pmu_start(event);
-	WARN_ON_ONCE(ret);
 }
 
 void perf_event_print_debug(void)

@@ -1080,27 +1092,29 @@ void perf_event_print_debug(void)
 	local_irq_restore(flags);
 }
 
-static void x86_pmu_stop(struct perf_event *event)
+static void x86_pmu_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	int idx = 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);
+	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+		x86_pmu.disable(event);
+		cpuc->events[hwc->idx] = NULL;
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+	}
 
-	cpuc->events[idx] = NULL;
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		x86_perf_event_update(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
 }
 
-static void x86_pmu_disable(struct perf_event *event)
+static void x86_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	int i;

@@ -1113,7 +1127,7 @@ static void x86_pmu_disable(struct perf_
 	if (cpuc->group_flag & PERF_EVENT_TXN)
 		return;
 
-	x86_pmu_stop(event);
+	x86_pmu_stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {

@@ -1165,7 +1179,7 @@ static int x86_pmu_handle_irq(struct pt_
 			continue;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	if (handled)

@@ -1572,15 +1586,17 @@ int x86_pmu_event_init(struct perf_event
 }
 
 static struct pmu pmu = {
-	.pmu_enable	= x86_pmu_pmu_enable,
-	.pmu_disable	= x86_pmu_pmu_disable,
+	.pmu_enable	= x86_pmu_enable,
+	.pmu_disable	= x86_pmu_disable,
+
 	.event_init	= x86_pmu_event_init,
-	.enable		= x86_pmu_enable,
-	.disable	= x86_pmu_disable,
+
+	.add		= x86_pmu_add,
+	.del		= x86_pmu_del,
 	.start		= x86_pmu_start,
 	.stop		= x86_pmu_stop,
 	.read		= x86_pmu_read,
-	.unthrottle	= x86_pmu_unthrottle,
+
 	.start_txn	= x86_pmu_start_txn,
 	.cancel_txn	= x86_pmu_cancel_txn,
 	.commit_txn	= x86_pmu_commit_txn,

301 lines not on this page · raw message

Index: linux-2.6/kernel/trace/trace_event_perf.c
===================================================================
@@ -99,7 +99,7 @@ int perf_trace_init(struct perf_event *p
 	return ret;
 }
 
-int perf_trace_enable(struct perf_event *p_event)
+int perf_trace_add(struct perf_event *p_event, int flags)
 {
 	struct ftrace_event_call *tp_event = p_event->tp_event;
 	struct hlist_head *list;

@@ -108,13 +108,16 @@ int perf_trace_enable(struct perf_event 
 	if (WARN_ON_ONCE(!list))
 		return -EINVAL;
 
+	if (!(flags & PERF_EF_START))
+		p_event->hw.state = PERF_HES_STOPPED;
+
 	list = this_cpu_ptr(list);
 	hlist_add_head_rcu(&p_event->hlist_entry, list);
 
 	return 0;
 }
 
-void perf_trace_disable(struct perf_event *p_event)
+void perf_trace_del(struct perf_event *p_event, int flags)
 {
 	hlist_del_rcu(&p_event->hlist_entry);
 }

137 lines not on this page · raw message

153 lines not on this page · raw message

190 lines not on this page · raw message

186 lines not on this page · raw message

184 lines not on this page · raw message

Index: linux-2.6/include/linux/ftrace_event.h
===================================================================
@@ -248,8 +248,8 @@ DECLARE_PER_CPU(struct pt_regs, perf_tra
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
-extern int  perf_trace_enable(struct perf_event *event);
-extern void perf_trace_disable(struct perf_event *event);
+extern int  perf_trace_add(struct perf_event *event, int flags);
+extern void perf_trace_del(struct perf_event *event, int flags);
 extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);

102 lines not on this page · raw message

Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel.c
===================================================================
@@ -713,7 +713,7 @@ again:
 		data.period = event->hw.last_period;
 
 		if (perf_event_overflow(event, 1, &data, regs))
-			x86_pmu_stop(event);
+			x86_pmu_stop(event, 0);
 	}
 
 	intel_pmu_ack_status(ack);

Index: linux-2.6/arch/x86/kernel/cpu/perf_event_intel_ds.c
===================================================================
@@ -491,7 +491,7 @@ static void __intel_pmu_pebs_event(struc
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
 	if (perf_event_overflow(event, 1, &data, &regs))
-		x86_pmu_stop(event);
+		x86_pmu_stop(event, 0);
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)

Index: linux-2.6/kernel/hw_breakpoint.c
===================================================================
@@ -574,10 +574,35 @@ static int hw_breakpoint_event_init(stru
 	return 0;
 }
 
+static int hw_breakpoint_add(struct perf_event *bp, int flags)
+{
+	if (!(flags & PERF_EF_START))
+		bp->hw.state = PERF_HES_STOPPED;
+
+	return arch_install_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_del(struct perf_event *bp, int flags)
+{
+	arch_uninstall_hw_breakpoint(bp);
+}
+
+static void hw_breakpoint_start(struct perf_event *bp, int flags)
+{
+	bp->hw.state = 0;
+}
+
+static void hw_breakpoint_stop(struct perf_event *bp, int flags)
+{
+	bp->hw.state = PERF_HES_STOPPED;
+}
+
 static struct pmu perf_breakpoint = {
 	.event_init	= hw_breakpoint_event_init,
-	.enable		= arch_install_hw_breakpoint,
-	.disable	= arch_uninstall_hw_breakpoint,
+	.add		= hw_breakpoint_add,
+	.del		= hw_breakpoint_del,
+	.start		= hw_breakpoint_start,
+	.stop		= hw_breakpoint_stop,
 	.read		= hw_breakpoint_pmu_read,
 };
 

index c440ae1..a946a77 100644
@@ -304,6 +304,8 @@ armpmu_add(struct perf_event *event, int flags)
        int idx;
        int err = 0;
 
+       perf_pmu_disable(event->pmu);
+
        /* If we don't have a space for the counter then finish early.

Index: linux-2.6/arch/arm/kernel/perf_event.c
===================================================================
@@ -304,6 +304,8 @@ armpmu_add(struct perf_event *event, int
 	int idx;
 	int err = 0;
 
+	perf_pmu_disable(event->pmu);
+
 	/* If we don't have a space for the counter then finish early. */
 	idx = armpmu->get_event_idx(cpuc, hwc);
 	if (idx < 0) {

@@ -328,6 +330,7 @@ armpmu_add(struct perf_event *event, int
 	perf_event_update_userpage(event);
 
 out:
+	perf_pmu_enable(event->pmu);
 	return err;
 }
 

Index: linux-2.6/arch/sh/kernel/perf_event.c
===================================================================
@@ -256,11 +256,14 @@ static int sh_pmu_add(struct perf_event 
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	int ret = -EAGAIN;
+
+	perf_pmu_disable(event->pmu);
 
 	if (__test_and_set_bit(idx, cpuc->used_mask)) {
 		idx = find_first_zero_bit(cpuc->used_mask, sh_pmu->num_events);
 		if (idx == sh_pmu->num_events)
-			return -EAGAIN;
+			goto ret;
 
 		__set_bit(idx, cpuc->used_mask);
 		hwc->idx = idx;

@@ -273,8 +276,11 @@ static int sh_pmu_add(struct perf_event 
 		sh_pmu_start(event, PERF_EF_RELOAD);
 
 	perf_event_update_userpage(event);
+	ret = 0;
 
-	return 0;
+out:
+	perf_pmu_enable(event->pmu);
+	return ret;
 }
 
 static void sh_pmu_read(struct perf_event *event)