[PATCH 1/2] perf: uncore: Adding documentation for ThunderX2 pmu uncore driver

[Ganapatrao Kulkarni]

Documentation for the UNCORE PMUs on Cavium's ThunderX2 SoC.
The SoC has PMU support in its L3 cache controller (L3C) and in the
DDR4 Memory Controller (DMC).

Signed-off-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@xxxxxxxxxx>
---
 Documentation/perf/thunderx2-pmu.txt | 60 ++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100644 Documentation/perf/thunderx2-pmu.txt

diff --git a/Documentation/perf/thunderx2-pmu.txt b/Documentation/perf/thunderx2-pmu.txt
new file mode 100644
index 0000000..eb8df9a
--- /dev/null
+++ b/Documentation/perf/thunderx2-pmu.txt
@@ -0,0 +1,60 @@
+
+Cavium ThunderX2 SoC Performance Monitoring Unit (PMU UNCORE)
+=============================================================
+
+ThunderX2 SoC PMU consists of independent system wide PMUs such as
+Level 3 Cache(L3C) and DDR4 Memory Controller(DMC).
+
+DMC: There are 8 independent PMUs to capture performance events corresponding
+to 8 channels of DDR4 Memory Controller. Each PMU supports upto 4 counters.
+
+L3C: There are 16 independent PMUs to capture events corresponding to 16 tiles
+of L3 cache. Each PMU supports up to 4 counters.
+
+PMU UNCORE (perf) driver
+-----------------------
+
+The thunderx2-pmu driver registers several perf PMUs for DMC and L3C devices.
+Each of the PMU provides description of its available events
+and configuration options in sysfs.
+	see /sys/devices/uncore_<l3c_X/dmc_S_X/.
+
+S is socket id and X represents channel number.
+There are 8 supported channels for DMC and 16 for L3C.
+Each channel supports up to 4 counters, which can be measured
+simultaneously without event muxing for each channel.
+
+The "format" directory describes format of the config (event ID).
+The "events" directory provides configuration templates for all
+supported event types that can be used with perf tool.
+
+For example, "uncore_dmc_0_0/cnt_cycles/" is an
+equivalent of "uncore_dmc_0_0/config=0x1/".
+
+
+Each perf driver also provides a "cpumask" sysfs attribute, which contains a
+single CPU ID of the processor which will be used to handle all the PMU events.
+It will be the first online CPU of the node of PMU device.
+
+Example for perf tool use:
+
+perf stat -a -e \
+	uncore_dmc_0_0/cnt_cycles/,\
+	uncore_dmc_0_1/cnt_cycles/,\
+	uncore_dmc_0_2/cnt_cycles/,\
+	uncore_dmc_0_3/cnt_cycles/,\
+	uncore_dmc_0_4/cnt_cycles/,\
+	uncore_dmc_0_5/cnt_cycles/,\
+	uncore_dmc_0_6/cnt_cycles/,\
+	uncore_dmc_0_7/cnt_cycles/ \
+	sleep 1
+
+perf stat -a -e \
+	uncore_dmc_0_0/cnt_cycles/,\
+	uncore_dmc_0_0/data_txfered/,\
+	uncore_dmc_0_0/txn_cycles/,\
+	uncore_dmc_0_0/cancelled_read_txn/ \
+	sleep 1
+
+The driver does not support sampling, therefore "perf record" will
+not work. Per-task (without "-a") perf sessions are not supported.
-- 
1.8.1.4