Merge branch 'for-next/perf' into for-next/core

* for-next/perf:
  drivers/perf: hisi: Update HiSilicon PMU maintainers
  arm_pmu: acpi: Add a representative platform device for TRBE
  arm_pmu: acpi: Refactor arm_spe_acpi_register_device()
  hw_breakpoint: fix single-stepping when using bpf_overflow_handler
  perf/imx_ddr: don't enable counter0 if none of 4 counters are used
  perf/imx_ddr: speed up overflow frequency of cycle
  drivers/perf: hisi: Schedule perf session according to locality
  perf/arm-dmc620: Fix dmc620_pmu_irqs_lock/cpu_hotplug_lock circular lock dependency
  perf/smmuv3: Add MODULE_ALIAS for module auto loading
  perf/smmuv3: Enable HiSilicon Erratum 162001900 quirk for HIP08/09
  perf: pmuv3: Remove comments from armv8pmu_[enable|disable]_event()
  perf/arm-cmn: Add CMN-700 r3 support
  perf/arm-cmn: Refactor HN-F event selector macros
  perf/arm-cmn: Remove spurious event aliases
  drivers/perf: Explicitly include correct DT includes
  perf: pmuv3: Add Cortex A520, A715, A720, X3 and X4 PMUs
  dt-bindings: arm: pmu: Add Cortex A520, A715, A720, X3, and X4
  perf/smmuv3: Remove build dependency on ACPI
  perf: xgene_pmu: Convert to devm_platform_ioremap_resource()
  driver/perf: Add identifier sysfs file for Yitian 710 DDR

1 files changed, 31 insertions, 17 deletions

diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 5222ba1e79d0..92611c98120f 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -10,10 +10,9 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/perf_event.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 
 #define COUNTER_CNTL		0x0
@@ -28,6 +27,8 @@
 #define CNTL_CLEAR_MASK		0xFFFFFFFD
 #define CNTL_OVER_MASK		0xFFFFFFFE
 
+#define CNTL_CP_SHIFT		16
+#define CNTL_CP_MASK		(0xFF << CNTL_CP_SHIFT)
 #define CNTL_CSV_SHIFT		24
 #define CNTL_CSV_MASK		(0xFFU << CNTL_CSV_SHIFT)
 
@@ -35,6 +36,8 @@
 #define EVENT_CYCLES_COUNTER	0
 #define NUM_COUNTERS		4
 
+/* For removing bias if cycle counter CNTL.CP is set to 0xf0 */
+#define CYCLES_COUNTER_MASK	0x0FFFFFFF
 #define AXI_MASKING_REVERT	0xffff0000	/* AXI_MASKING(MSB 16bits) + AXI_ID(LSB 16bits) */
 
 #define to_ddr_pmu(p)		container_of(p, struct ddr_pmu, pmu)
@@ -101,6 +104,7 @@ struct ddr_pmu {
 	const struct fsl_ddr_devtype_data *devtype_data;
 	int irq;
 	int id;
+	int active_counter;
 };
 
 static ssize_t ddr_perf_identifier_show(struct device *dev,
@@ -427,6 +431,17 @@ static void ddr_perf_counter_enable(struct ddr_pmu *pmu, int config,
 		writel(0, pmu->base + reg);
 		val = CNTL_EN | CNTL_CLEAR;
 		val |= FIELD_PREP(CNTL_CSV_MASK, config);
+
+		/*
+		 * On i.MX8MP we need to bias the cycle counter to overflow more often.
+		 * We do this by initializing bits [23:16] of the counter value via the
+		 * COUNTER_CTRL Counter Parameter (CP) field.
+		 */
+		if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED) {
+			if (counter == EVENT_CYCLES_COUNTER)
+				val |= FIELD_PREP(CNTL_CP_MASK, 0xf0);
+		}
+
 		writel(val, pmu->base + reg);
 	} else {
 		/* Disable counter */
@@ -466,6 +481,12 @@ static void ddr_perf_event_update(struct perf_event *event)
 	int ret;
 
 	new_raw_count = ddr_perf_read_counter(pmu, counter);
+	/* Remove the bias applied in ddr_perf_counter_enable(). */
+	if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED) {
+		if (counter == EVENT_CYCLES_COUNTER)
+			new_raw_count &= CYCLES_COUNTER_MASK;
+	}
+
 	local64_add(new_raw_count, &event->count);
 
 	/*
@@ -495,6 +516,10 @@ static void ddr_perf_event_start(struct perf_event *event, int flags)
 
 	ddr_perf_counter_enable(pmu, event->attr.config, counter, true);
 
+	if (!pmu->active_counter++)
+		ddr_perf_counter_enable(pmu, EVENT_CYCLES_ID,
+			EVENT_CYCLES_COUNTER, true);
+
 	hwc->state = 0;
 }
 
@@ -548,6 +573,10 @@ static void ddr_perf_event_stop(struct perf_event *event, int flags)
 	ddr_perf_counter_enable(pmu, event->attr.config, counter, false);
 	ddr_perf_event_update(event);
 
+	if (!--pmu->active_counter)
+		ddr_perf_counter_enable(pmu, EVENT_CYCLES_ID,
+			EVENT_CYCLES_COUNTER, false);
+
 	hwc->state |= PERF_HES_STOPPED;
 }
 
@@ -565,25 +594,10 @@ static void ddr_perf_event_del(struct perf_event *event, int flags)
 
 static void ddr_perf_pmu_enable(struct pmu *pmu)
 {
-	struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu);
-
-	/* enable cycle counter if cycle is not active event list */
-	if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL)
-		ddr_perf_counter_enable(ddr_pmu,
-				      EVENT_CYCLES_ID,
-				      EVENT_CYCLES_COUNTER,
-				      true);
 }
 
 static void ddr_perf_pmu_disable(struct pmu *pmu)
 {
-	struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu);
-
-	if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL)
-		ddr_perf_counter_enable(ddr_pmu,
-				      EVENT_CYCLES_ID,
-				      EVENT_CYCLES_COUNTER,
-				      false);
 }
 
 static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base,