@@ -15,6 +15,7 @@ Performance monitor support
qcom_l3_pmu
starfive_starlink_pmu
mrvl-odyssey-ddr-pmu
+ mrvl-odyssey-tad-pmu
arm-ccn
arm-cmn
arm-ni
new file mode 100644
@@ -0,0 +1,37 @@
+====================================================================
+Marvell Odyssey LLC-TAD Performance Monitoring Unit (PMU UNCORE)
+====================================================================
+
+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.
+
+The PMU driver exposes the available events and format options under sysfs::
+
+ /sys/bus/event_source/devices/tad/events/
+ /sys/bus/event_source/devices/tad/format/
+
+Examples::
+
+ $ perf list | grep tad
+ tad/tad_alloc_any/ [Kernel PMU event]
+ tad/tad_alloc_dtg/ [Kernel PMU event]
+ tad/tad_alloc_ltg/ [Kernel PMU event]
+ tad/tad_hit_any/ [Kernel PMU event]
+ tad/tad_hit_dtg/ [Kernel PMU event]
+ tad/tad_hit_ltg/ [Kernel PMU event]
+ tad/tad_req_msh_in_exlmn/ [Kernel PMU event]
+ tad/tad_tag_rd/ [Kernel PMU event]
+ tad/tad_tot_cycle/ [Kernel PMU event]
+
+ $ perf stat -e tad_alloc_dtg,tad_alloc_ltg,tad_alloc_any,tad_hit_dtg,tad_hit_ltg,tad_hit_any,tad_tag_rd <workload>
@@ -39,6 +39,7 @@ struct tad_pmu {
enum mrvl_tad_pmu_version {
TAD_PMU_V1 = 1,
+ TAD_PMU_V2,
};
struct tad_pmu_data {
@@ -222,6 +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[] = {
@@ -260,6 +279,13 @@ 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;
@@ -350,6 +376,8 @@ static int tad_pmu_probe(struct platform_device *pdev)
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();
@@ -385,6 +413,12 @@ static const struct tad_pmu_data tad_pmu_data = {
};
#endif
+#ifdef CONFIG_ACPI
+static const struct tad_pmu_data tad_pmu_v2_data = {
+ .id = TAD_PMU_V2,
+};
+#endif
+
#ifdef CONFIG_OF
static const struct of_device_id tad_pmu_of_match[] = {
{ .compatible = "marvell,cn10k-tad-pmu", .data = &tad_pmu_data },
@@ -395,6 +429,7 @@ static const struct of_device_id tad_pmu_of_match[] = {
#ifdef CONFIG_ACPI
static const struct acpi_device_id tad_pmu_acpi_match[] = {
{"MRVL000B", (kernel_ulong_t)&tad_pmu_data},
+ {"MRVL000D", (kernel_ulong_t)&tad_pmu_v2_data},
{},
};
MODULE_DEVICE_TABLE(acpi, tad_pmu_acpi_match);
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> --- Documentation/admin-guide/perf/index.rst | 1 + .../admin-guide/perf/mrvl-odyssey-tad-pmu.rst | 37 +++++++++++++++++++ drivers/perf/marvell_cn10k_tad_pmu.c | 35 ++++++++++++++++++ 3 files changed, 73 insertions(+) create mode 100644 Documentation/admin-guide/perf/mrvl-odyssey-tad-pmu.rst