[PATCH 0/2] Selftest for cpuidle latency measurement

@@ -7,6 +7,7 @@ TARGETS += capabilities
 TARGETS += cgroup
 TARGETS += clone3
 TARGETS += cpufreq
+TARGETS += cpuidle
 TARGETS += cpu-hotplug
 TARGETS += drivers/dma-buf
 TARGETS += efivarfs

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+all:
+
+TEST_PROGS := cpuidle.sh
+
+include ../lib.mk

@@ -0,0 +1,240 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+LOG=cpuidle.log
+MODULE=/lib/modules/$(uname -r)/kernel/drivers/cpuidle/test-cpuidle_latency.ko
+
+helpme()
+{
+	printf "Usage: $0 [-h] [-todg args]
+	[-h <help>]
+	[-m <location of the module>]
+	[-o <location of the output>]
+	\n"
+	exit 2
+}
+
+parse_arguments()
+{
+	while getopts ht:m:o: arg
+	do
+		case $arg in
+			h) # --help
+				helpme
+				;;
+			m) # --mod-file
+				MODULE=$OPTARG
+				;;
+			o) # output log files
+				LOG=$OPTARG
+				;;
+			\?)
+				helpme
+				;;
+		esac
+	done
+}
+
+ins_mod()
+{
+	if [ ! -f "$MODULE" ]; then
+		printf "$MODULE module does not exist. Exitting\n"
+		exit 2
+	fi
+	printf "Inserting $MODULE module\n\n"
+	insmod $MODULE
+	if [ $? != 0 ]; then
+		printf "Insmod $MODULE failed\n"
+		exit 2
+	fi
+}
+
+compute_average()
+{
+	arr=("$@")
+	sum=0
+	size=${#arr[@]}
+	for i in "${arr[@]}"
+	do
+		sum=$((sum + i))
+	done
+	avg=$((sum/size))
+}
+
+# Disable all stop states
+disable_idle()
+{
+	for ((cpu=0; cpu<NUM_CPUS; cpu++))
+	do
+		for ((state=0; state<NUM_STATES; state++))
+		do
+			echo 1 > /sys/devices/system/cpu/cpu$cpu/cpuidle/state$state/disable
+		done
+	done
+}
+
+# Enable the idle state supplied
+# $1: State to enable
+enable_state()
+{
+	for ((cpu=0; cpu<NUM_CPUS; cpu++))
+	do
+		echo 0 > /sys/devices/system/cpu/cpu$cpu/cpuidle/state$1/disable
+	done
+}
+
+# Extract latency in microseconds and convert to nanoseconds
+extract_latency()
+{
+	for ((state=0; state<NUM_STATES; state++))
+	do
+		latency=$(($(cat /sys/devices/system/cpu/cpu0/cpuidle/state$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 $dest_cpu yes "" > /dev/null &
+			yes_pid=$!
+        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 $yes_pid
+			wait $yes_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
+        declare -a baseline_avg_array
+
+        echo -e "--IPI Latency Test---" >> $LOG
+        for ((state=0; state<NUM_STATES; state++))
+        do
+			echo -e "---Enabling state: $state---" >> $LOG
+			enable_state $state
+			printf "%s %10s %12s %12s\n" "SRC_CPU" "DEST_CPU" "Base_IPI_Latency(ns)" "IPI_Latency(ns)" >> $LOG
+			unset avg_arr
+			unset baseline_avg_arr
+			for ((cpu=0; cpu<NUM_CPUS; cpu++))
+			do
+				# Running IPI test and logging results
+				ipi_test_once "baseline" $cpu
+				baseline_ipi_latency=$ipi_latency
+				ipi_test_once "test" $cpu
+				printf "%-3s %10s %12s %18s\n" $src_cpu $cpu $baseline_ipi_latency $ipi_latency >> $LOG
+				avg_arr+=($ipi_latency)
+				baseline_avg_arr+=($baseline_ipi_latency)
+			done
+			compute_average "${avg_arr[@]}"
+			local avg_latency=$avg
+			compute_average "${baseline_avg_arr[@]}"
+			local baseline_avg_latency=$avg
+			echo -e "Expected IPI latency(ns): ${latency_arr[$state]}" >> $LOG
+			echo -e "Baseline Average IPI latency(ns): $baseline_avg_latency" >> $LOG
+			echo -e "Observed Average IPI latency(ns): $avg_latency" >> $LOG
+        done
+}
+
+# Extract the residency in microseconds and convert to nanoseconds.
+# Add 100 ns so that the timer stays for a little longer than the residency
+extract_residency()
+{
+	for ((state=0; state<NUM_STATES; state++))
+	do
+		residency=$(($(cat /sys/devices/system/cpu/cpu0/cpuidle/state$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 $dest_cpu yes "" > /dev/null &
+		yes_pid=$!
+	fi
+	taskset -c $dest_cpu echo $3 > /sys/kernel/debug/latency_test/timeout_expected_ns
+	sleep 0.1
+	timeout_diff=$(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 $yes_pid
+		wait $yes_pid 2>/dev/null
+	fi
+}
+
+run_timeout_tests()
+{
+	extract_residency
+	disable_idle
+	declare -a avg_arr
+	declare -a baseline_avg_arr
+	echo -e "\n--Timeout Latency Test--" >> $LOG
+
+	for ((state=0; state<NUM_STATES; state++))
+	do
+		echo -e "---Enabling state: $state---" >> $LOG
+		enable_state $state
+		printf "%s %10s %10s\n" "Wakeup_src" "Baseline_delay(ns)" "Delay(ns)" >> $LOG
+		unset avg_arr
+		unset baseline_avg_arr
+		for ((cpu=0; cpu<NUM_CPUS; cpu++))
+		do
+			timeout_test_once "baseline" $cpu ${residency_arr[$state]}
+			local baseline_timeout_diff=$timeout_diff
+			timeout_test_once "test" $cpu ${residency_arr[$state]}
+			printf "%-3s %13s %18s\n" $src_cpu $baseline_timeout_diff $timeout_diff >> $LOG
+			avg_arr+=($timeout_diff)
+			baseline_avg_arr+=($baseline_timeout_diff)
+		done
+		compute_average "${baseline_avg_arr[@]}"
+		local baseline_avg=$avg
+		compute_average "${avg_arr[@]}"
+		echo -e "Expected timeout(ns): ${residency_arr[$state]}" >> $LOG
+		echo -e "Baseline Average timeout diff(ns): $baseline_avg" >> $LOG
+		echo -e "Observed Average timeout diff(ns): $avg" >> $LOG
+	done
+}
+
+declare -a residency_arr
+declare -a latency_arr
+
+# Parse arguments
+parse_arguments $@
+
+rm -f $LOG
+touch $LOG
+NUM_CPUS=$(nproc --all)
+NUM_STATES=$(ls -1 /sys/devices/system/cpu/cpu0/cpuidle/ | wc -l)
+
+# Insert the module
+ins_mod $MODULE
+
+printf "Started IPI latency tests\n"
+run_ipi_tests
+
+printf "Started Timer latency tests\n"
+run_timeout_tests
+
+printf "Removing $MODULE module\n"
+printf "Output logged at: $LOG\n"
+rmmod $MODULE

@@ -0,0 +1 @@
+timeout=0

@@ -8,6 +8,7 @@ obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
 obj-$(CONFIG_DT_IDLE_STATES)		  += dt_idle_states.o
 obj-$(CONFIG_ARCH_HAS_CPU_RELAX)	  += poll_state.o
 obj-$(CONFIG_HALTPOLL_CPUIDLE)		  += cpuidle-haltpoll.o
+obj-$(CONFIG_IDLE_LATENCY_SELFTEST)	  += test-cpuidle_latency.o
 
 ##################################################################################
 # ARM SoC drivers

@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module-based API test facility for cpuidle latency using IPIs and timers
+ */
+
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/* IPI based wakeup latencies */
+struct latency {
+	unsigned int src_cpu;
+	unsigned int dest_cpu;
+	ktime_t time_start;
+	ktime_t time_end;
+	u64 latency_ns;
+} ipi_wakeup;
+
+static void measure_latency(void *info)
+{
+	struct latency *v;
+	ktime_t time_diff;
+
+	v = (struct latency *)info;
+	v->time_end = ktime_get();
+	time_diff = ktime_sub(v->time_end, v->time_start);
+	v->latency_ns = ktime_to_ns(time_diff);
+}
+
+void run_smp_call_function_test(unsigned int cpu)
+{
+	ipi_wakeup.src_cpu = smp_processor_id();
+	ipi_wakeup.dest_cpu = cpu;
+	ipi_wakeup.time_start = ktime_get();
+	smp_call_function_single(cpu, measure_latency, &ipi_wakeup, 1);
+}
+
+/* Timer based wakeup latencies */
+struct timer_data {
+	unsigned int src_cpu;
+	u64 timeout;
+	ktime_t time_start;
+	ktime_t time_end;
+	struct hrtimer timer;
+	u64 timeout_diff_ns;
+} timer_wakeup;
+
+static enum hrtimer_restart timer_called(struct hrtimer *hrtimer)
+{
+	struct timer_data *w;
+	ktime_t time_diff;
+
+	w = container_of(hrtimer, struct timer_data, timer);
+	w->time_end = ktime_get();
+
+	time_diff = ktime_sub(w->time_end, w->time_start);
+	time_diff = ktime_sub(time_diff, ns_to_ktime(w->timeout));
+	w->timeout_diff_ns = ktime_to_ns(time_diff);
+	return HRTIMER_NORESTART;
+}
+
+static void run_timer_test(unsigned int ns)
+{
+	hrtimer_init(&timer_wakeup.timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	timer_wakeup.timer.function = timer_called;
+	timer_wakeup.time_start = ktime_get();
+	timer_wakeup.src_cpu = smp_processor_id();
+	timer_wakeup.timeout = ns;
+
+	hrtimer_start(&timer_wakeup.timer, ns_to_ktime(ns),
+		      HRTIMER_MODE_REL_PINNED);
+}
+
+static struct dentry *dir;
+
+static int cpu_read_op(void *data, u64 *value)
+{
+	*value = ipi_wakeup.dest_cpu;
+	return 0;
+}
+
+static int cpu_write_op(void *data, u64 value)
+{
+	run_smp_call_function_test(value);
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(ipi_ops, cpu_read_op, cpu_write_op, "%llu\n");
+
+static int timeout_read_op(void *data, u64 *value)
+{
+	*value = timer_wakeup.timeout;
+	return 0;
+}
+
+static int timeout_write_op(void *data, u64 value)
+{
+	run_timer_test(value);
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(timeout_ops, timeout_read_op, timeout_write_op, "%llu\n");
+
+static int __init latency_init(void)
+{
+	struct dentry *temp;
+
+	dir = debugfs_create_dir("latency_test", 0);
+	if (!dir) {
+		pr_alert("latency_test: failed to create /sys/kernel/debug/latency_test\n");
+		return -1;
+	}
+	temp = debugfs_create_file("ipi_cpu_dest",
+				   0666,
+				   dir,
+				   NULL,
+				   &ipi_ops);
+	if (!temp) {
+		pr_alert("latency_test: failed to create /sys/kernel/debug/ipi_cpu_dest\n");
+		return -1;
+	}
+	debugfs_create_u64("ipi_latency_ns", 0444, dir, &ipi_wakeup.latency_ns);
+	debugfs_create_u32("ipi_cpu_src", 0444, dir, &ipi_wakeup.src_cpu);
+
+	temp = debugfs_create_file("timeout_expected_ns",
+				   0666,
+				   dir,
+				   NULL,
+				   &timeout_ops);
+	if (!temp) {
+		pr_alert("latency_test: failed to create /sys/kernel/debug/timeout_expected_ns\n");
+		return -1;
+	}
+	debugfs_create_u64("timeout_diff_ns", 0444, dir, &timer_wakeup.timeout_diff_ns);
+	debugfs_create_u32("timeout_cpu_src", 0444, dir, &timer_wakeup.src_cpu);
+	pr_info("Latency Test module loaded\n");
+	return 0;
+}
+
+static void __exit latency_cleanup(void)
+{
+	pr_info("Cleaning up Latency Test module.\n");
+	debugfs_remove_recursive(dir);
+}
+
+module_init(latency_init);
+module_exit(latency_cleanup);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("IBM Corporation");
+MODULE_DESCRIPTION("Measuring idle latency for IPIs and Timers");

@@ -1375,6 +1375,16 @@ config DEBUG_KOBJECT
 	  If you say Y here, some extra kobject debugging messages will be sent
 	  to the syslog.
 
+config IDLE_LATENCY_SELFTEST
+	tristate "Cpuidle latency selftests"
+	depends on CPU_IDLE
+	help
+	  This option provides a kernel module that runs tests using the IPI and
+	  timers to measure latency.
+
+	  Say M if you want these self tests to build as a module.
+	  Say N if you are unsure.
+
 config DEBUG_KOBJECT_RELEASE
 	bool "kobject release debugging"
 	depends on DEBUG_OBJECTS_TIMERS