@@ -7,6 +7,7 @@ TARGETS += cgroup
TARGETS += clone3
TARGETS += core
TARGETS += cpufreq
+TARGETS += cpuidle
TARGETS += cpu-hotplug
TARGETS += drivers/dma-buf
TARGETS += efivarfs
new file mode 100644
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+all:
+
+TEST_PROGS := cpuidle.sh
+
+include ../lib.mk
\ No newline at end of file
new file mode 100755
@@ -0,0 +1,323 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+LOG=cpuidle.log
+MODULE=/lib/modules/$(uname -r)/kernel/drivers/cpuidle/test-cpuidle_latency.ko
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+SMT=$(lscpu | grep "Thread(s) per core" | awk '{print $4}')
+RUN_TIMER_TEST=0
+
+helpme()
+{
+ printf "Usage: $0 [-h] [-todg args]
+ [-h <help>]
+ [-i <run timer tests>]
+ [-m <location of the module>]
+ [-o <location of the output>]
+ [-v <verbose>]
+ \n"
+ exit 2
+}
+
+parse_arguments()
+{
+ while getopts ht:m:o:vt:it: arg
+ do
+ case $arg in
+ h) # --help
+ helpme
+ ;;
+ i) # run timer tests
+ RUN_TIMER_TEST=1
+ ;;
+ m) # --mod-file
+ MODULE=$OPTARG
+ ;;
+ o) # output log files
+ LOG=$OPTARG
+ ;;
+ v) # Verbose mode
+ SMT=1
+ ;;
+ \?)
+ helpme
+ ;;
+ esac
+ done
+}
+
+ins_mod()
+{
+ debugfs_file=/sys/kernel/debug/latency_test/ipi_latency_ns
+ # Check if the module is already loaded
+ if [ -f "$debugfs_file" ]; then
+ printf "Module already loaded\n\n"
+ return 0
+ fi
+ # Try to load the module
+ if [ ! -f "$MODULE" ]; then
+ printf "$MODULE module does not exist. Exitting\n"
+ exit $ksft_skip
+ fi
+ printf "Inserting $MODULE module\n\n"
+ insmod $MODULE
+ if [ $? != 0 ]; then
+ printf "Insmod $MODULE failed\n"
+ exit $ksft_skip
+ fi
+}
+
+compute_average()
+{
+ arr=("$@")
+ sum=0
+ size=${#arr[@]}
+ if [ $size == 0 ]; then
+ avg=0
+ return 1
+ fi
+ for i in "${arr[@]}"
+ do
+ sum=$((sum + i))
+ done
+ avg=$((sum/size))
+}
+
+# Disable all stop states
+disable_idle()
+{
+ for ((cpu=0; cpu<NUM_CPUS; cpu++))
+ do
+ local cpu_status=$(cpu_is_online $cpu)
+ if [ $cpu_status == 0 ]; then
+ continue
+ fi
+ for ((state=0; state<NUM_STATES; state++))
+ do
+ echo 1 > /sys/devices/system/cpu/cpu$cpu/cpuidle/state$state/disable
+ done
+ done
+}
+
+# Perform operation on each CPU for the given state
+# $1 - Operation: enable (0) / disable (1)
+# $2 - State to enable
+op_state()
+{
+ for ((cpu=0; cpu<NUM_CPUS; cpu++))
+ do
+ local cpu_status=$(cpu_is_online $cpu)
+ if [ $cpu_status == 0 ]; then
+ continue
+ fi
+ echo $1 > /sys/devices/system/cpu/cpu$cpu/cpuidle/state$2/disable
+ done
+}
+
+cpuidle_enable_state()
+{
+ state=$1
+ op_state 0 $state
+}
+
+cpuidle_disable_state()
+{
+ state=$1
+ op_state 1 $state
+}
+
+cpu_is_online()
+{
+ cpu=$1
+ if [ ! -f "/sys/devices/system/cpu/cpu$cpu/online" ]; then
+ echo 0
+ return
+ fi
+ status=$(cat /sys/devices/system/cpu/cpu$cpu/online)
+ echo $status
+}
+
+# Extract latency in microseconds and convert to nanoseconds
+extract_latency()
+{
+ for ((state=0; state<NUM_STATES; state++))
+ do
+ latency=$(($(cat /sys/devices/system/cpu/cpu0/cpuidle/state$state/latency) * 1000))
+ latency_arr+=($latency)
+ done
+}
+
+# Run the IPI test
+# $1 run for baseline - busy cpu or regular environment
+# $2 destination cpu
+ipi_test_once()
+{
+ dest_cpu=$2
+ if [ "$1" = "baseline" ]; then
+ # Keep the CPU busy
+ taskset -c $dest_cpu cat /dev/random > /dev/null &
+ task_pid=$!
+ # Wait for the workload to achieve 100% CPU usage
+ sleep 1
+ fi
+ taskset 0x1 echo $dest_cpu > /sys/kernel/debug/latency_test/ipi_cpu_dest
+ ipi_latency=$(cat /sys/kernel/debug/latency_test/ipi_latency_ns)
+ src_cpu=$(cat /sys/kernel/debug/latency_test/ipi_cpu_src)
+ if [ "$1" = "baseline" ]; then
+ kill $task_pid
+ wait $task_pid 2>/dev/null
+ fi
+}
+
+# Incrementally Enable idle states one by one and compute the latency
+run_ipi_tests()
+{
+ extract_latency
+ disable_idle
+ declare -a avg_arr
+ echo -e "--IPI Latency Test---" | tee -a $LOG
+
+ echo -e "--Baseline IPI Latency measurement: CPU Busy--" >> $LOG
+ printf "%s %10s %12s\n" "SRC_CPU" "DEST_CPU" "IPI_Latency(ns)" >> $LOG
+ for ((cpu=0; cpu<NUM_CPUS; cpu+=SMT))
+ do
+ local cpu_status=$(cpu_is_online $cpu)
+ if [ $cpu_status == 0 ]; then
+ continue
+ fi
+ ipi_test_once "baseline" $cpu
+ printf "%-3s %10s %12s\n" $src_cpu $cpu $ipi_latency >> $LOG
+ avg_arr+=($ipi_latency)
+ done
+ compute_average "${avg_arr[@]}"
+ echo -e "Baseline Avg IPI latency(ns): $avg" | tee -a $LOG
+
+ for ((state=0; state<NUM_STATES; state++))
+ do
+ unset avg_arr
+ echo -e "---Enabling state: $state---" >> $LOG
+ cpuidle_enable_state $state
+ printf "%s %10s %12s\n" "SRC_CPU" "DEST_CPU" "IPI_Latency(ns)" >> $LOG
+ for ((cpu=0; cpu<NUM_CPUS; cpu+=SMT))
+ do
+ local cpu_status=$(cpu_is_online $cpu)
+ if [ $cpu_status == 0 ]; then
+ continue
+ fi
+ # Running IPI test and logging results
+ sleep 1
+ ipi_test_once "test" $cpu
+ printf "%-3s %10s %12s\n" $src_cpu $cpu $ipi_latency >> $LOG
+ avg_arr+=($ipi_latency)
+ done
+ compute_average "${avg_arr[@]}"
+ echo -e "Expected IPI latency(ns): ${latency_arr[$state]}" >> $LOG
+ echo -e "Observed Avg IPI latency(ns) - State $state: $avg" | tee -a $LOG
+ cpuidle_disable_state $state
+ done
+}
+
+# Extract the residency in microseconds and convert to nanoseconds.
+# Add 100 ns so that the timer stays for a little longer than the residency
+extract_residency()
+{
+ for ((state=0; state<NUM_STATES; state++))
+ do
+ residency=$(($(cat /sys/devices/system/cpu/cpu0/cpuidle/state$state/residency) * 1000 + 200))
+ residency_arr+=($residency)
+ done
+}
+
+# Run the Timeout test
+# $1 run for baseline - busy cpu or regular environment
+# $2 destination cpu
+# $3 timeout
+timeout_test_once()
+{
+ dest_cpu=$2
+ if [ "$1" = "baseline" ]; then
+ # Keep the CPU busy
+ taskset -c $dest_cpu cat /dev/random > /dev/null &
+ task_pid=$!
+ # Wait for the workload to achieve 100% CPU usage
+ sleep 1
+ fi
+ taskset -c $dest_cpu echo $3 > /sys/kernel/debug/latency_test/timeout_expected_ns
+ # Wait for the result to populate
+ sleep 0.1
+ timeout_diff=$(cat /sys/kernel/debug/latency_test/timeout_diff_ns)
+ src_cpu=$(cat /sys/kernel/debug/latency_test/timeout_cpu_src)
+ if [ "$1" = "baseline" ]; then
+ kill $task_pid
+ wait $task_pid 2>/dev/null
+ fi
+}
+
+run_timeout_tests()
+{
+ extract_residency
+ disable_idle
+ declare -a avg_arr
+ echo -e "\n--Timeout Latency Test--" | tee -a $LOG
+
+ echo -e "--Baseline Timeout Latency measurement: CPU Busy--" >> $LOG
+ printf "%s %10s %10s\n" "Wakeup_src" "Baseline_delay(ns)">> $LOG
+ for ((cpu=0; cpu<NUM_CPUS; cpu+=SMT))
+ do
+ local cpu_status=$(cpu_is_online $cpu)
+ if [ $cpu_status == 0 ]; then
+ continue
+ fi
+ timeout_test_once "baseline" $cpu 1000000
+ printf "%-3s %13s\n" $src_cpu $timeout_diff >> $LOG
+ avg_arr+=($timeout_diff)
+ done
+ compute_average "${avg_arr[@]}"
+ echo -e "Baseline Avg timeout diff(ns): $avg" | tee -a $LOG
+
+ for ((state=0; state<NUM_STATES; state++))
+ do
+ unset avg_arr
+ echo -e "---Enabling state: $state---" >> $LOG
+ cpuidle_enable_state $state
+ printf "%s %10s %10s\n" "Wakeup_src" "Baseline_delay(ns)" "Delay(ns)" >> $LOG
+ for ((cpu=0; cpu<NUM_CPUS; cpu+=SMT))
+ do
+ local cpu_status=$(cpu_is_online $cpu)
+ if [ $cpu_status == 0 ]; then
+ continue
+ fi
+ timeout_test_once "test" $cpu 1000000
+ printf "%-3s %13s %18s\n" $src_cpu $baseline_timeout_diff $timeout_diff >> $LOG
+ avg_arr+=($timeout_diff)
+ done
+ compute_average "${avg_arr[@]}"
+ echo -e "Expected timeout(ns): ${residency_arr[$state]}" >> $LOG
+ echo -e "Observed Avg timeout diff(ns) - State $state: $avg" | tee -a $LOG
+ cpuidle_disable_state $state
+ done
+}
+
+declare -a residency_arr
+declare -a latency_arr
+
+parse_arguments $@
+
+rm -f $LOG
+touch $LOG
+NUM_CPUS=$(nproc --all)
+NUM_STATES=$(ls -1 /sys/devices/system/cpu/cpu0/cpuidle/ | wc -l)
+
+ins_mod $MODULE
+
+run_ipi_tests
+if [ $RUN_TIMER_TEST == 1 ]; then
+ run_timeout_tests
+fi
+
+printf "Removing $MODULE module\n"
+printf "Full Output logged at: $LOG\n"
+rmmod $MODULE
new file mode 100644
@@ -0,0 +1,2 @@
+timeout=0
+
The cpuidle latency selftest provides support to systematically extract, analyse and present IPI and timer based wakeup latencies for each CPU and each idle state available on the system. The selftest leverages test-cpuidle_latency module's debugfs interface to interact and extract latency information from the kernel. The selftest inserts the module if already not inserted, disables all the idle states and enables them one by one testing the following: 1. Keeping source CPU constant, iterate through all the CPUS measuring IPI latency for baseline (CPU is busy with cat /dev/random > /dev/null workload) and then when the CPU is allowed to be at rest 2. Iterating through all the CPUs, sending expected timer durations to be equivalent to the residency of the deepest idle state enabled and extracting the difference in time between the time of wakeup and the expected timer duration The timer based test produces run to run variance on some intel based systems that sport a mechansim "C-state pre-wake" which can pre-wake a CPU from an idle state when timers are armed. For systems and architectures that don't have this mechansim can leverage timer tests with the -i option. To run this test specifically: $ make -C tools/testing/selftests TARGETS="cpuidle" run_tests There are a few optinal arguments too that the script can take [-h <help>] [-i <run timer tests>] [-m <location of the module>] [-o <location of the output>] [-v <verbose> (run on all cpus)] Default Output location in: tools/testing/selftest/cpuidle/cpuidle.log Signed-off-by: Pratik Rajesh Sampat <psampat@linux.ibm.com> --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/cpuidle/Makefile | 6 + tools/testing/selftests/cpuidle/cpuidle.sh | 323 +++++++++++++++++++++ tools/testing/selftests/cpuidle/settings | 2 + 4 files changed, 332 insertions(+) create mode 100644 tools/testing/selftests/cpuidle/Makefile create mode 100755 tools/testing/selftests/cpuidle/cpuidle.sh create mode 100644 tools/testing/selftests/cpuidle/settings