[PATCH v5 05/11] arm-cci PMU: Delay counter writes to pmu_enable

[Suzuki K. Poulose]

Delay setting the event periods for enabled events to pmu::pmu_enable().
We mark the event.hw->state PERF_HES_ARCH for the events that we know
have their counts recorded and have been started. Since we reprogram the
counters every time before count, we can set the counters for all the
event counters which are !STOPPED && ARCH.

Grouping the writes to counters can ammortise the cost of the operation
on PMUs where it is expensive (e.g, CCI-500).

Cc: Mark Rutland <mark.rutland at arm.com>
Cc: Punit Agrawal <punit.agrawal at arm.com>
Cc: Peter Zijlstra <peterz at infradead.org>
Signed-off-by: Suzuki K. Poulose <suzuki.poulose at arm.com>
---
 drivers/bus/arm-cci.c |   42 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/arm-cci.c b/drivers/bus/arm-cci.c
index 0189f3a..c768ee4 100644
--- a/drivers/bus/arm-cci.c
+++ b/drivers/bus/arm-cci.c
@@ -916,6 +916,40 @@ static void hw_perf_event_destroy(struct perf_event *event)
 	}
 }
 
+/*
+ * Program the CCI PMU counters which have PERF_HES_ARCH set
+ * with the event period and mark them ready before we enable
+ * PMU.
+ */
+void cci_pmu_update_counters(struct cci_pmu *cci_pmu)
+{
+	int i;
+	unsigned long mask[BITS_TO_LONGS(cci_pmu->num_cntrs)];
+
+	memset(mask, 0, BITS_TO_LONGS(cci_pmu->num_cntrs) * sizeof(unsigned long));
+
+	for_each_set_bit(i, cci_pmu->hw_events.used_mask, cci_pmu->num_cntrs) {
+		struct hw_perf_event *hwe;
+
+		if (!cci_pmu->hw_events.events[i]) {
+			WARN_ON(1);
+			continue;
+		}
+
+		hwe = &cci_pmu->hw_events.events[i]->hw;
+		/* Leave the events which are not counting */
+		if (hwe->state & PERF_HES_STOPPED)
+			continue;
+		if (hwe->state & PERF_HES_ARCH) {
+			set_bit(i, mask);
+			hwe->state &= ~PERF_HES_ARCH;
+			local64_set(&hwe->prev_count, CCI_CNTR_PERIOD);
+		}
+	}
+
+	pmu_write_counters(cci_pmu, mask, CCI_CNTR_PERIOD);
+}
+
 static void cci_pmu_enable(struct pmu *pmu)
 {
 	struct cci_pmu *cci_pmu = to_cci_pmu(pmu);
@@ -927,6 +961,7 @@ static void cci_pmu_enable(struct pmu *pmu)
 		return;
 
 	raw_spin_lock_irqsave(&hw_events->pmu_lock, flags);
+	cci_pmu_update_counters(cci_pmu);
 	__cci_pmu_enable();
 	raw_spin_unlock_irqrestore(&hw_events->pmu_lock, flags);
 
@@ -980,8 +1015,11 @@ static void cci_pmu_start(struct perf_event *event, int pmu_flags)
 	/* Configure the counter unless you are counting a fixed event */
 	if (!pmu_fixed_hw_idx(cci_pmu, idx))
 		pmu_set_event(cci_pmu, idx, hwc->config_base);
-
-	pmu_event_set_period(event);
+	/*
+	 * Mark this counter, so that we can program the
+	 * counter with the event_period. see cci_pmu_enable()
+	 */
+	hwc->state = PERF_HES_ARCH;
 	pmu_enable_counter(cci_pmu, idx);
 
 	raw_spin_unlock_irqrestore(&hw_events->pmu_lock, flags);
-- 
1.7.9.5