Received-SPF: pass (google.com: domain of linux-kernel+bounces-120423-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Gowthami Thiagarajan <gthiagarajan@marvell.com>
To: <will@kernel.org>, <mark.rutland@arm.com>,
        <linux-arm-kernel@lists.infradead.org>, <linux-kernel@vger.kernel.org>
CC: <sgoutham@marvell.com>, <bbhushan2@marvell.com>, <gcherian@marvell.com>,
        Gowthami Thiagarajan <gthiagarajan@marvell.com>
Subject: [RESEND PATCH v4 3/3] perf/marvell : Odyssey LLC-TAD performance monitor
Date: Wed, 27 Mar 2024 12:48:32 +0530
Message-ID: <20240327071832.1556576-4-gthiagarajan@marvell.com>
In-Reply-To: <20240327071832.1556576-1-gthiagarajan@marvell.com>
References: <20240327071832.1556576-1-gthiagarajan@marvell.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain

Each TAD provides eight 64-bit counters for monitoring
cache behavior.The driver always configures the same counter for
all the TADs. The user would end up effectively reserving one of
eight counters in every TAD to look across all TADs.
The occurrences of events are aggregated and presented to the user
at the end of running the workload. The driver does not provide a
way for the user to partition TADs so that different TADs are used for
different applications.

The performance events reflect various internal or interface activities.
By combining the values from multiple performance counters, cache
performance can be measured in terms such as: cache miss rate, cache
allocations, interface retry rate, internal resource occupancy, etc.

Each supported counter's event and formatting information is exposed
to sysfs at /sys/devices/tad/. Use perf tool stat command to measure
the pmu events. For instance:

perf stat -e tad_hit_ltg,tad_hit_dtg <workload>

Signed-off-by: Gowthami Thiagarajan <gthiagarajan@marvell.com>
---
 drivers/perf/marvell_cn10k_tad_pmu.c | 62 ++++++++++++++++++++++++++--
 1 file changed, 59 insertions(+), 3 deletions(-)

diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c
index fec8e82edb95..df6569f7a06f 100644
--- a/drivers/perf/marvell_cn10k_tad_pmu.c
+++ b/drivers/perf/marvell_cn10k_tad_pmu.c
@@ -37,6 +37,15 @@ struct tad_pmu {
 	DECLARE_BITMAP(counters_map, TAD_MAX_COUNTERS);
 };
 
+enum mrvl_tad_pmu_version {
+	TAD_PMU_V1 = 1,
+	TAD_PMU_V2,
+};
+
+struct tad_pmu_data {
+	int id;
+};
+
 static int tad_pmu_cpuhp_state;
 
 static void tad_pmu_event_counter_read(struct perf_event *event)
@@ -214,6 +223,24 @@ static const struct attribute_group tad_pmu_events_attr_group = {
 	.attrs = tad_pmu_event_attrs,
 };
 
+static struct attribute *ody_tad_pmu_event_attrs[] = {
+	TAD_PMU_EVENT_ATTR(tad_req_msh_in_exlmn, 0x3),
+	TAD_PMU_EVENT_ATTR(tad_alloc_dtg, 0x1a),
+	TAD_PMU_EVENT_ATTR(tad_alloc_ltg, 0x1b),
+	TAD_PMU_EVENT_ATTR(tad_alloc_any, 0x1c),
+	TAD_PMU_EVENT_ATTR(tad_hit_dtg, 0x1d),
+	TAD_PMU_EVENT_ATTR(tad_hit_ltg, 0x1e),
+	TAD_PMU_EVENT_ATTR(tad_hit_any, 0x1f),
+	TAD_PMU_EVENT_ATTR(tad_tag_rd, 0x20),
+	TAD_PMU_EVENT_ATTR(tad_tot_cycle, 0xFF),
+	NULL
+};
+
+static const struct attribute_group ody_tad_pmu_events_attr_group = {
+	.name = "events",
+	.attrs = ody_tad_pmu_event_attrs,
+};
+
 PMU_FORMAT_ATTR(event, "config:0-7");
 
 static struct attribute *tad_pmu_format_attrs[] = {
@@ -252,8 +279,16 @@ static const struct attribute_group *tad_pmu_attr_groups[] = {
 	NULL
 };
 
+static const struct attribute_group *ody_tad_pmu_attr_groups[] = {
+	&ody_tad_pmu_events_attr_group,
+	&tad_pmu_format_attr_group,
+	&tad_pmu_cpumask_attr_group,
+	NULL
+};
+
 static int tad_pmu_probe(struct platform_device *pdev)
 {
+	const struct tad_pmu_data *dev_data;
 	struct device *dev = &pdev->dev;
 	struct tad_region *regions;
 	struct tad_pmu *tad_pmu;
@@ -261,6 +296,7 @@ static int tad_pmu_probe(struct platform_device *pdev)
 	u32 tad_pmu_page_size;
 	u32 tad_page_size;
 	u32 tad_cnt;
+	int version;
 	int i, ret;
 	char *name;
 
@@ -270,6 +306,13 @@ static int tad_pmu_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, tad_pmu);
 
+	dev_data = device_get_match_data(&pdev->dev);
+	if (!dev_data) {
+		dev_err(&pdev->dev, "Error: No device match data found\n");
+		return -ENODEV;
+	}
+	version = dev_data->id;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "Mem resource not found\n");
@@ -319,7 +362,6 @@ static int tad_pmu_probe(struct platform_device *pdev)
 	tad_pmu->pmu = (struct pmu) {
 
 		.module		= THIS_MODULE,
-		.attr_groups	= tad_pmu_attr_groups,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE |
 				  PERF_PMU_CAP_NO_INTERRUPT,
 		.task_ctx_nr	= perf_invalid_context,
@@ -332,6 +374,11 @@ static int tad_pmu_probe(struct platform_device *pdev)
 		.read		= tad_pmu_event_counter_read,
 	};
 
+	if (version == TAD_PMU_V1)
+		tad_pmu->pmu.attr_groups = tad_pmu_attr_groups;
+	else
+		tad_pmu->pmu.attr_groups = ody_tad_pmu_attr_groups;
+
 	tad_pmu->cpu = raw_smp_processor_id();
 
 	/* Register pmu instance for cpu hotplug */
@@ -362,16 +409,25 @@ static int tad_pmu_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct tad_pmu_data tad_pmu_data = {
+	.id   = TAD_PMU_V1,
+};
+
+static const struct tad_pmu_data tad_pmu_v2_data = {
+	.id   = TAD_PMU_V2,
+};
+
 #ifdef CONFIG_OF
 static const struct of_device_id tad_pmu_of_match[] = {
-	{ .compatible = "marvell,cn10k-tad-pmu", },
+	{ .compatible = "marvell,cn10k-tad-pmu", .data = &tad_pmu_data },
 	{},
 };
 #endif
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id tad_pmu_acpi_match[] = {
-	{"MRVL000B", 0},
+	{"MRVL000B", (kernel_ulong_t)&tad_pmu_data},
+	{"MRVL000D", (kernel_ulong_t)&tad_pmu_v2_data},
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, tad_pmu_acpi_match);
-- 
2.25.1