drivers/perf: hisi: Update DDRC PMU for programmable counter

DDRC PMU's events are useful for performance profiling, but the events
are limited and counter is fixed. On HiSilicon Hip09 platform, PMU
counters are the programmable and more events are supported. Let's
add the DDRC PMU v2 driver.

Bandwidth events are exposed directly in driver and some more events
will listed in JSON file later.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Co-developed-by: Qi Liu <liuqi115@huawei.com>
Signed-off-by: Qi Liu <liuqi115@huawei.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Link: https://lore.kernel.org/r/1615186237-22263-7-git-send-email-zhangshaokun@hisilicon.com
Signed-off-by: Will Deacon <will@kernel.org>

2 files changed, 196 insertions, 13 deletions

diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
index 38a0622372c5..7c8a4bc21db4 100644
--- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c
@@ -18,7 +18,7 @@
 
 #include "hisi_uncore_pmu.h"
 
-/* DDRC register definition */
+/* DDRC register definition in v1 */
 #define DDRC_PERF_CTRL		0x010
 #define DDRC_FLUX_WR		0x380
 #define DDRC_FLUX_RD		0x384
@@ -34,13 +34,24 @@
 #define DDRC_INT_CLEAR		0x6d0
 #define DDRC_VERSION		0x710
 
+/* DDRC register definition in v2 */
+#define DDRC_V2_INT_MASK	0x528
+#define DDRC_V2_INT_STATUS	0x52c
+#define DDRC_V2_INT_CLEAR	0x530
+#define DDRC_V2_EVENT_CNT	0xe00
+#define DDRC_V2_EVENT_CTRL	0xe70
+#define DDRC_V2_EVENT_TYPE	0xe74
+#define DDRC_V2_PERF_CTRL	0xeA0
+
 /* DDRC has 8-counters */
 #define DDRC_NR_COUNTERS	0x8
 #define DDRC_V1_PERF_CTRL_EN	0x2
+#define DDRC_V2_PERF_CTRL_EN	0x1
 #define DDRC_V1_NR_EVENTS	0x7
+#define DDRC_V2_NR_EVENTS	0x90
 
 /*
- * For DDRC PMU, there are eight-events and every event has been mapped
+ * For PMU v1, there are eight-events and every event has been mapped
  * to fixed-purpose counters which register offset is not consistent.
  * Therefore there is no write event type and we assume that event
  * code (0 to 7) is equal to counter index in PMU driver.
@@ -62,6 +73,11 @@ static u32 hisi_ddrc_pmu_v1_get_counter_offset(int cntr_idx)
 	return ddrc_reg_off[cntr_idx];
 }
 
+static u32 hisi_ddrc_pmu_v2_get_counter_offset(int cntr_idx)
+{
+	return DDRC_V2_EVENT_CNT + cntr_idx * 8;
+}
+
 static u64 hisi_ddrc_pmu_v1_read_counter(struct hisi_pmu *ddrc_pmu,
 				      struct hw_perf_event *hwc)
 {
@@ -76,13 +92,34 @@ static void hisi_ddrc_pmu_v1_write_counter(struct hisi_pmu *ddrc_pmu,
 	       ddrc_pmu->base + hisi_ddrc_pmu_v1_get_counter_offset(hwc->idx));
 }
 
+static u64 hisi_ddrc_pmu_v2_read_counter(struct hisi_pmu *ddrc_pmu,
+					 struct hw_perf_event *hwc)
+{
+	return readq(ddrc_pmu->base +
+		     hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx));
+}
+
+static void hisi_ddrc_pmu_v2_write_counter(struct hisi_pmu *ddrc_pmu,
+					   struct hw_perf_event *hwc, u64 val)
+{
+	writeq(val,
+	       ddrc_pmu->base + hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx));
+}
+
 /*
- * For DDRC PMU, event has been mapped to fixed-purpose counter by hardware,
- * so there is no need to write event type.
+ * For DDRC PMU v1, event has been mapped to fixed-purpose counter by hardware,
+ * so there is no need to write event type, while it is programmable counter in
+ * PMU v2.
  */
 static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx,
 				       u32 type)
 {
+	u32 offset;
+
+	if (hha_pmu->identifier >= HISI_PMU_V2) {
+		offset = DDRC_V2_EVENT_TYPE + 4 * idx;
+		writel(type, hha_pmu->base + offset);
+	}
 }
 
 static void hisi_ddrc_pmu_v1_start_counters(struct hisi_pmu *ddrc_pmu)
@@ -143,6 +180,49 @@ static int hisi_ddrc_pmu_v1_get_event_idx(struct perf_event *event)
 	return idx;
 }
 
+static int hisi_ddrc_pmu_v2_get_event_idx(struct perf_event *event)
+{
+	return hisi_uncore_pmu_get_event_idx(event);
+}
+
+static void hisi_ddrc_pmu_v2_start_counters(struct hisi_pmu *ddrc_pmu)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+	val |= DDRC_V2_PERF_CTRL_EN;
+	writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_stop_counters(struct hisi_pmu *ddrc_pmu)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+	val &= ~DDRC_V2_PERF_CTRL_EN;
+	writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_enable_counter(struct hisi_pmu *ddrc_pmu,
+					    struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+	val |= 1 << hwc->idx;
+	writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_disable_counter(struct hisi_pmu *ddrc_pmu,
+					     struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+	val &= ~(1 << hwc->idx);
+	writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+}
+
 static void hisi_ddrc_pmu_v1_enable_counter_int(struct hisi_pmu *ddrc_pmu,
 						struct hw_perf_event *hwc)
 {
@@ -150,7 +230,7 @@ static void hisi_ddrc_pmu_v1_enable_counter_int(struct hisi_pmu *ddrc_pmu,
 
 	/* Write 0 to enable interrupt */
 	val = readl(ddrc_pmu->base + DDRC_INT_MASK);
-	val &= ~(1 << GET_DDRC_EVENTID(hwc));
+	val &= ~(1 << hwc->idx);
 	writel(val, ddrc_pmu->base + DDRC_INT_MASK);
 }
 
@@ -161,10 +241,30 @@ static void hisi_ddrc_pmu_v1_disable_counter_int(struct hisi_pmu *ddrc_pmu,
 
 	/* Write 1 to mask interrupt */
 	val = readl(ddrc_pmu->base + DDRC_INT_MASK);
-	val |= (1 << GET_DDRC_EVENTID(hwc));
+	val |= 1 << hwc->idx;
 	writel(val, ddrc_pmu->base + DDRC_INT_MASK);
 }
 
+static void hisi_ddrc_pmu_v2_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+						struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK);
+	val &= ~(1 << hwc->idx);
+	writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK);
+}
+
+static void hisi_ddrc_pmu_v2_disable_counter_int(struct hisi_pmu *ddrc_pmu,
+						struct hw_perf_event *hwc)
+{
+	u32 val;
+
+	val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK);
+	val |= 1 << hwc->idx;
+	writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK);
+}
+
 static u32 hisi_ddrc_pmu_v1_get_int_status(struct hisi_pmu *ddrc_pmu)
 {
 	return readl(ddrc_pmu->base + DDRC_INT_STATUS);
@@ -176,9 +276,21 @@ static void hisi_ddrc_pmu_v1_clear_int_status(struct hisi_pmu *ddrc_pmu,
 	writel(1 << idx, ddrc_pmu->base + DDRC_INT_CLEAR);
 }
 
+static u32 hisi_ddrc_pmu_v2_get_int_status(struct hisi_pmu *ddrc_pmu)
+{
+	return readl(ddrc_pmu->base + DDRC_V2_INT_STATUS);
+}
+
+static void hisi_ddrc_pmu_v2_clear_int_status(struct hisi_pmu *ddrc_pmu,
+					      int idx)
+{
+	writel(1 << idx, ddrc_pmu->base + DDRC_V2_INT_CLEAR);
+}
+
 static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = {
 	{ "HISI0233", },
-	{},
+	{ "HISI0234", },
+	{}
 };
 MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match);
 
@@ -210,6 +322,13 @@ static int hisi_ddrc_pmu_init_data(struct platform_device *pdev,
 	}
 
 	ddrc_pmu->identifier = readl(ddrc_pmu->base + DDRC_VERSION);
+	if (ddrc_pmu->identifier >= HISI_PMU_V2) {
+		if (device_property_read_u32(&pdev->dev, "hisilicon,sub-id",
+					     &ddrc_pmu->sub_id)) {
+			dev_err(&pdev->dev, "Can not read sub-id!\n");
+			return -EINVAL;
+		}
+	}
 
 	return 0;
 }
@@ -224,6 +343,16 @@ static const struct attribute_group hisi_ddrc_pmu_v1_format_group = {
 	.attrs = hisi_ddrc_pmu_v1_format_attr,
 };
 
+static struct attribute *hisi_ddrc_pmu_v2_format_attr[] = {
+	HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+	NULL
+};
+
+static const struct attribute_group hisi_ddrc_pmu_v2_format_group = {
+	.name = "format",
+	.attrs = hisi_ddrc_pmu_v2_format_attr,
+};
+
 static struct attribute *hisi_ddrc_pmu_v1_events_attr[] = {
 	HISI_PMU_EVENT_ATTR(flux_wr,		0x00),
 	HISI_PMU_EVENT_ATTR(flux_rd,		0x01),
@@ -241,6 +370,18 @@ static const struct attribute_group hisi_ddrc_pmu_v1_events_group = {
 	.attrs = hisi_ddrc_pmu_v1_events_attr,
 };
 
+static struct attribute *hisi_ddrc_pmu_v2_events_attr[] = {
+	HISI_PMU_EVENT_ATTR(cycles,		0x00),
+	HISI_PMU_EVENT_ATTR(flux_wr,		0x83),
+	HISI_PMU_EVENT_ATTR(flux_rd,		0x84),
+	NULL
+};
+
+static const struct attribute_group hisi_ddrc_pmu_v2_events_group = {
+	.name = "events",
+	.attrs = hisi_ddrc_pmu_v2_events_attr,
+};
+
 static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
 
 static struct attribute *hisi_ddrc_pmu_cpumask_attrs[] = {
@@ -272,6 +413,14 @@ static const struct attribute_group *hisi_ddrc_pmu_v1_attr_groups[] = {
 	NULL,
 };
 
+static const struct attribute_group *hisi_ddrc_pmu_v2_attr_groups[] = {
+	&hisi_ddrc_pmu_v2_format_group,
+	&hisi_ddrc_pmu_v2_events_group,
+	&hisi_ddrc_pmu_cpumask_attr_group,
+	&hisi_ddrc_pmu_identifier_group,
+	NULL
+};
+
 static const struct hisi_uncore_ops hisi_uncore_ddrc_v1_ops = {
 	.write_evtype           = hisi_ddrc_pmu_write_evtype,
 	.get_event_idx		= hisi_ddrc_pmu_v1_get_event_idx,
@@ -287,6 +436,21 @@ static const struct hisi_uncore_ops hisi_uncore_ddrc_v1_ops = {
 	.clear_int_status	= hisi_ddrc_pmu_v1_clear_int_status,
 };
 
+static const struct hisi_uncore_ops hisi_uncore_ddrc_v2_ops = {
+	.write_evtype           = hisi_ddrc_pmu_write_evtype,
+	.get_event_idx		= hisi_ddrc_pmu_v2_get_event_idx,
+	.start_counters		= hisi_ddrc_pmu_v2_start_counters,
+	.stop_counters		= hisi_ddrc_pmu_v2_stop_counters,
+	.enable_counter		= hisi_ddrc_pmu_v2_enable_counter,
+	.disable_counter	= hisi_ddrc_pmu_v2_disable_counter,
+	.enable_counter_int	= hisi_ddrc_pmu_v2_enable_counter_int,
+	.disable_counter_int	= hisi_ddrc_pmu_v2_disable_counter_int,
+	.write_counter		= hisi_ddrc_pmu_v2_write_counter,
+	.read_counter		= hisi_ddrc_pmu_v2_read_counter,
+	.get_int_status		= hisi_ddrc_pmu_v2_get_int_status,
+	.clear_int_status	= hisi_ddrc_pmu_v2_clear_int_status,
+};
+
 static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev,
 				   struct hisi_pmu *ddrc_pmu)
 {
@@ -300,12 +464,21 @@ static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
+	if (ddrc_pmu->identifier >= HISI_PMU_V2) {
+		ddrc_pmu->counter_bits = 48;
+		ddrc_pmu->check_event = DDRC_V2_NR_EVENTS;
+		ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v2_attr_groups;
+		ddrc_pmu->ops = &hisi_uncore_ddrc_v2_ops;
+	} else {
+		ddrc_pmu->counter_bits = 32;
+		ddrc_pmu->check_event = DDRC_V1_NR_EVENTS;
+		ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v1_attr_groups;
+		ddrc_pmu->ops = &hisi_uncore_ddrc_v1_ops;
+	}
+
 	ddrc_pmu->num_counters = DDRC_NR_COUNTERS;
-	ddrc_pmu->counter_bits = 32;
-	ddrc_pmu->ops = &hisi_uncore_ddrc_v1_ops;
 	ddrc_pmu->dev = &pdev->dev;
 	ddrc_pmu->on_cpu = -1;
-	ddrc_pmu->check_event = DDRC_V1_NR_EVENTS;
 
 	return 0;
 }
@@ -333,8 +506,16 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_ddrc%u",
-			      ddrc_pmu->sccl_id, ddrc_pmu->index_id);
+	if (ddrc_pmu->identifier >= HISI_PMU_V2)
+		name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+				      "hisi_sccl%u_ddrc%u_%u",
+				      ddrc_pmu->sccl_id, ddrc_pmu->index_id,
+				      ddrc_pmu->sub_id);
+	else
+		name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+				      "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id,
+				      ddrc_pmu->index_id);
+
 	ddrc_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
@@ -347,7 +528,7 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev)
 		.start		= hisi_uncore_pmu_start,
 		.stop		= hisi_uncore_pmu_stop,
 		.read		= hisi_uncore_pmu_read,
-		.attr_groups	= hisi_ddrc_pmu_v1_attr_groups,
+		.attr_groups	= ddrc_pmu->pmu_events.attr_groups,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h
index 1591dbc6a119..ea9d89bbc1ea 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.h
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h
@@ -85,6 +85,8 @@ struct hisi_pmu {
 	void __iomem *base;
 	/* the ID of the PMU modules */
 	u32 index_id;
+	/* For DDRC PMU v2: each DDRC has more than one DMC */
+	u32 sub_id;
 	int num_counters;
 	int counter_bits;
 	/* check event code range */