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 | 66 ++++++++++++++++++++++++++++++++++++ 1 file changed, 66 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..7d89935 --- /dev/null +++ b/Documentation/perf/thunderx2-pmu.txt @@ -0,0 +1,66 @@ + +Cavium ThunderX2 SoC Performance Monitoring Unit (PMU UNCORE) +========================================================================== + +ThunderX2 SoC PMU consists of independent system wide per Socket PMUs such +as Level 3 Cache(L3C) and DDR4 Memory Controller(DMC). + +It has 8 independent DMC PMUs to capture performance events corresponding +to 8 channels of DDR4 Memory Controller. There are 16 independent L3C PMUs +to capture events corresponding to 16 tiles of L3 cache. Each PMU supports +up to 4 counters. + +Counters are independently programmable and can be started and stopped +individually. Each counter can be set to sample specific perf events. +Counters are 32 bit and do not support overflow interrupt; they are +sampled at every 2 seconds. The Counters register access are multiplexed +across channels of DMC and L3C. The muxing(select channel) is done through +write to a Secure register using smcc calls. + +PMU UNCORE (perf) driver: + +The thunderx2-pmu driver registers several perf PMUs for DMC and L3C devices. +Each of the PMUs provides description of its available events +and configuration options in sysfs. + see /sys/devices/uncore_<l3c_S_X/dmc_S_X/> + +S is socket id and X represents channel number. +Each PMU can be used to sample up to 4 events simultaneously. + +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 is likely to be used to handle all the +PMU events. It will be the first online CPU from the NUMA 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/cancelled_read_txns/,\ +uncore_dmc_0_0/cnt_cycles/,\ +uncore_dmc_0_0/consumed_read_txns/,\ +uncore_dmc_0_0/data_transfers/ sleep 1 + +perf stat -a -e \ +uncore_l3c_0_0/l3_retry/,\ +uncore_l3c_0_0/read_hit/,\ +uncore_l3c_0_0/read_request/,\ +uncore_l3c_0_0/inv_request/ sleep 1 + +The driver does not support sampling, therefore "perf record" will +not work. Per-task (without "-a") perf sessions are not supported. -- 2.9.4 -- To unsubscribe from this list: send the line "unsubscribe linux-doc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
