MIPS, Perf-events: Work with the new PMU interface

This is the MIPS part of the following commits by Peter Zijlstra:

- a4eaf7f1
    perf: Rework the PMU methods

    Replace pmu::{enable,disable,start,stop,unthrottle} with
    pmu::{add,del,start,stop}, all of which take a flags argument.

    The new interface extends the capability to stop a counter while
    keeping it scheduled on the PMU. We replace the throttled state with
    the generic stopped state.

    This also allows us to efficiently stop/start counters over certain
    code paths (like IRQ handlers).

    It also allows scheduling a counter without it starting, allowing for
    a generic frozen state (useful for rotating stopped counters).

    The stopped state is implemented in two different ways, depending on
    how the architecture implemented the throttled state:

     1) We disable the counter:
        a) the pmu has per-counter enable bits, we flip that
        b) we program a NOP event, preserving the counter state

     2) We store the counter state and ignore all read/overflow events

For MIPSXX, the stopped state is implemented in the way of 1.b as above.

- 33696fc0
    perf: Per PMU disable

    Changes perf_disable() into perf_pmu_disable().

- 24cd7f54
    perf: Reduce perf_disable() usage

    Since the current perf_disable() usage is only an optimization,
    remove it for now. This eases the removal of the __weak
    hw_perf_enable() interface.

- b0a873eb
    perf: Register PMU implementations

    Simple registration interface for struct pmu, this provides the
    infrastructure for removing all the weak functions.

- 51b0fe39
    perf: Deconstify struct pmu

    sed -ie 's/const struct pmu\>/struct pmu/g' `git grep -l "const struct pmu\>"`
Reported-by: Wu Zhangjin <wuzhangjin@gmail.com>
Acked-by: David Daney <ddaney@caviumnetworks.com>
Signed-off-by: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
To: a.p.zijlstra@chello.nl
To: fweisbec@gmail.com
To: will.deacon@arm.com
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: wuzhangjin@gmail.com
Cc: paulus@samba.org
Cc: mingo@elte.hu
Cc: acme@redhat.com
Cc: dengcheng.zhu@gmail.com
Cc: matt@console-pimps.org
Cc: sshtylyov@mvista.com
Cc: ddaney@caviumnetworks.com
Patchwork: http://patchwork.linux-mips.org/patch/2012/Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/kernel/perf_event.c

@@ -161,41 +161,6 @@ mipspmu_event_set_period(struct perf_event *event,
 	return ret;
 }
 
-static int mipspmu_enable(struct perf_event *event)
-{
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	int idx;
-	int err = 0;
-
-	/* To look for a free counter for this event. */
-	idx = mipspmu->alloc_counter(cpuc, hwc);
-	if (idx < 0) {
-		err = idx;
-		goto out;
-	}
-
-	/*
-	 * If there is an event in the counter we are going to use then
-	 * make sure it is disabled.
-	 */
-	event->hw.idx = idx;
-	mipspmu->disable_event(idx);
-	cpuc->events[idx] = event;
-
-	/* Set the period for the event. */
-	mipspmu_event_set_period(event, hwc, idx);
-
-	/* Enable the event. */
-	mipspmu->enable_event(hwc, idx);
-
-	/* Propagate our changes to the userspace mapping. */
-	perf_event_update_userpage(event);
-
-out:
-	return err;
-}
-
 static void mipspmu_event_update(struct perf_event *event,
 			struct hw_perf_event *hwc,
 			int idx)
@@ -231,32 +196,90 @@ static void mipspmu_event_update(struct perf_event *event,
 	return;
 }
 
-static void mipspmu_disable(struct perf_event *event)
+static void mipspmu_start(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 (!mipspmu)
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
 
-	WARN_ON(idx < 0 || idx >= mipspmu->num_counters);
+	hwc->state = 0;
 
-	/* We are working on a local event. */
-	mipspmu->disable_event(idx);
+	/* Set the period for the event. */
+	mipspmu_event_set_period(event, hwc, hwc->idx);
+
+	/* Enable the event. */
+	mipspmu->enable_event(hwc, hwc->idx);
+}
+
+static void mipspmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!mipspmu)
+		return;
 
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		/* We are working on a local event. */
+		mipspmu->disable_event(hwc->idx);
 		barrier();
+		mipspmu_event_update(event, hwc, hwc->idx);
+		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	}
+}
 
-	mipspmu_event_update(event, hwc, idx);
-	cpuc->events[idx] = NULL;
-	clear_bit(idx, cpuc->used_mask);
+static int mipspmu_add(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;
+	int err = 0;
+
+	perf_pmu_disable(event->pmu);
+
+	/* To look for a free counter for this event. */
+	idx = mipspmu->alloc_counter(cpuc, hwc);
+	if (idx < 0) {
+		err = idx;
+		goto out;
+	}
+
+	/*
+	 * If there is an event in the counter we are going to use then
+	 * make sure it is disabled.
+	 */
+	event->hw.idx = idx;
+	mipspmu->disable_event(idx);
+	cpuc->events[idx] = event;
 
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	if (flags & PERF_EF_START)
+		mipspmu_start(event, PERF_EF_RELOAD);
+
+	/* Propagate our changes to the userspace mapping. */
 	perf_event_update_userpage(event);
+
+out:
+	perf_pmu_enable(event->pmu);
+	return err;
 }
 
-static void mipspmu_unthrottle(struct perf_event *event)
+static void mipspmu_del(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;
 
-	mipspmu->enable_event(hwc, hwc->idx);
+	WARN_ON(idx < 0 || idx >= mipspmu->num_counters);
+
+	mipspmu_stop(event, PERF_EF_UPDATE);
+	cpuc->events[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+
+	perf_event_update_userpage(event);
 }
 
 static void mipspmu_read(struct perf_event *event)
@@ -270,12 +293,17 @@ static void mipspmu_read(struct perf_event *event)
 	mipspmu_event_update(event, hwc, hwc->idx);
 }
 
-static struct pmu pmu = {
-	.enable		= mipspmu_enable,
-	.disable	= mipspmu_disable,
-	.unthrottle	= mipspmu_unthrottle,
-	.read		= mipspmu_read,
-};
+static void mipspmu_enable(struct pmu *pmu)
+{
+	if (mipspmu)
+		mipspmu->start();
+}
+
+static void mipspmu_disable(struct pmu *pmu)
+{
+	if (mipspmu)
+		mipspmu->stop();
+}
 
 static atomic_t active_events = ATOMIC_INIT(0);
 static DEFINE_MUTEX(pmu_reserve_mutex);
@@ -318,6 +346,82 @@ static void mipspmu_free_irq(void)
 		perf_irq = save_perf_irq;
 }
 
+/*
+ * mipsxx/rm9000/loongson2 have different performance counters, they have
+ * specific low-level init routines.
+ */
+static void reset_counters(void *arg);
+static int __hw_perf_event_init(struct perf_event *event);
+
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+	if (atomic_dec_and_mutex_lock(&active_events,
+				&pmu_reserve_mutex)) {
+		/*
+		 * We must not call the destroy function with interrupts
+		 * disabled.
+		 */
+		on_each_cpu(reset_counters,
+			(void *)(long)mipspmu->num_counters, 1);
+		mipspmu_free_irq();
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+}
+
+static int mipspmu_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 (!mipspmu || event->cpu >= nr_cpumask_bits ||
+		(event->cpu >= 0 && !cpu_online(event->cpu)))
+		return -ENODEV;
+
+	if (!atomic_inc_not_zero(&active_events)) {
+		if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
+			atomic_dec(&active_events);
+			return -ENOSPC;
+		}
+
+		mutex_lock(&pmu_reserve_mutex);
+		if (atomic_read(&active_events) == 0)
+			err = mipspmu_get_irq();
+
+		if (!err)
+			atomic_inc(&active_events);
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+
+	if (err)
+		return err;
+
+	err = __hw_perf_event_init(event);
+	if (err)
+		hw_perf_event_destroy(event);
+
+	return err;
+}
+
+static struct pmu pmu = {
+	.pmu_enable	= mipspmu_enable,
+	.pmu_disable	= mipspmu_disable,
+	.event_init	= mipspmu_event_init,
+	.add		= mipspmu_add,
+	.del		= mipspmu_del,
+	.start		= mipspmu_start,
+	.stop		= mipspmu_stop,
+	.read		= mipspmu_read,
+};
+
 static inline unsigned int
 mipspmu_perf_event_encode(const struct mips_perf_event *pev)
 {
@@ -409,73 +513,6 @@ static int validate_group(struct perf_event *event)
 	return 0;
 }
 
-/*
- * mipsxx/rm9000/loongson2 have different performance counters, they have
- * specific low-level init routines.
- */
-static void reset_counters(void *arg);
-static int __hw_perf_event_init(struct perf_event *event);
-
-static void hw_perf_event_destroy(struct perf_event *event)
-{
-	if (atomic_dec_and_mutex_lock(&active_events,
-				&pmu_reserve_mutex)) {
-		/*
-		 * We must not call the destroy function with interrupts
-		 * disabled.
-		 */
-		on_each_cpu(reset_counters,
-			(void *)(long)mipspmu->num_counters, 1);
-		mipspmu_free_irq();
-		mutex_unlock(&pmu_reserve_mutex);
-	}
-}
-
-const struct pmu *hw_perf_event_init(struct perf_event *event)
-{
-	int err = 0;
-
-	if (!mipspmu || event->cpu >= nr_cpumask_bits ||
-		(event->cpu >= 0 && !cpu_online(event->cpu)))
-		return ERR_PTR(-ENODEV);
-
-	if (!atomic_inc_not_zero(&active_events)) {
-		if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
-			atomic_dec(&active_events);
-			return ERR_PTR(-ENOSPC);
-		}
-
-		mutex_lock(&pmu_reserve_mutex);
-		if (atomic_read(&active_events) == 0)
-			err = mipspmu_get_irq();
-
-		if (!err)
-			atomic_inc(&active_events);
-		mutex_unlock(&pmu_reserve_mutex);
-	}
-
-	if (err)
-		return ERR_PTR(err);
-
-	err = __hw_perf_event_init(event);
-	if (err)
-		hw_perf_event_destroy(event);
-
-	return err ? ERR_PTR(err) : &pmu;
-}
-
-void hw_perf_enable(void)
-{
-	if (mipspmu)
-		mipspmu->start();
-}
-
-void hw_perf_disable(void)
-{
-	if (mipspmu)
-		mipspmu->stop();
-}
-
 /* This is needed by specific irq handlers in perf_event_*.c */
 static void
 handle_associated_event(struct cpu_hw_events *cpuc,

arch/mips/kernel/perf_event_mipsxx.c

@@ -1045,6 +1045,8 @@ init_hw_perf_events(void)
 			"CPU, irq %d%s\n", mipspmu->name, counters, irq,
 			irq < 0 ? " (share with timer interrupt)" : "");
 
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+
 	return 0;
 }
 early_initcall(init_hw_perf_events);