From 8c37df3d635eac64a8fbb4b26672fb881e0cb673 Mon Sep 17 00:00:00 2001
From: Thomas Renninger <trenn@suse.de>
Date: Wed, 23 Nov 2022 12:18:10 +0100
Subject: [PATCH] cpupower: rapl monitor - shows the used power consumption in
 uj for each rapl domain

This CPU power monitor shows the power consumption
as exposed by the powercap subsystem, cmp with:
Documentation/power/powercap/powercap.rst

cpupower monitor -m RAPL
    | RAPL
 CPU| pack | core | unco
   0|6853926|967832|442381
   8|6853926|967832|442381
   1|6853926|967832|442381
   9|6853926|967832|442381

Unfortunately RAPL domains cannot be directly mapped to the corresponding
CPU socket/package, core it belongs to.
Not sure this is possible at all with the current data exposed from the
kernel.

Still it can be worthful information for developers trying to optimize
power consumption of workloads or their system in general.

Signed-off-by: Thomas Renninger <trenn@suse.de>
CC: Zhang Rui <rui.zhang@intel.com>
CC: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/Makefile                 |   1 +
 .../utils/idle_monitor/cpupower-monitor.c     |   7 +-
 .../utils/idle_monitor/idle_monitors.def      |   1 +
 .../utils/idle_monitor/rapl_monitor.c         | 148 ++++++++++++++++++
 4 files changed, 154 insertions(+), 3 deletions(-)
 create mode 100644 tools/power/cpupower/utils/idle_monitor/rapl_monitor.c

diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index 9fd3b309b3a6d..59bfa05dec5d8 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -131,6 +131,7 @@ UTIL_OBJS =  utils/helpers/amd.o utils/helpers/msr.o \
 	utils/idle_monitor/hsw_ext_idle.o \
 	utils/idle_monitor/amd_fam14h_idle.o utils/idle_monitor/cpuidle_sysfs.o \
 	utils/idle_monitor/mperf_monitor.o utils/idle_monitor/cpupower-monitor.o \
+	utils/idle_monitor/rapl_monitor.o \
 	utils/cpupower.o utils/cpufreq-info.o utils/cpufreq-set.o \
 	utils/cpupower-set.o utils/cpupower-info.o utils/cpuidle-info.o \
 	utils/cpuidle-set.o utils/powercap-info.o
diff --git a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
index 7c77045fef52f..075e766ff1f30 100644
--- a/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
+++ b/tools/power/cpupower/utils/idle_monitor/cpupower-monitor.c
@@ -459,9 +459,10 @@ int cmd_monitor(int argc, char **argv)
 			print_results(1, cpu);
 	}
 
-	for (num = 0; num < avail_monitors; num++)
-		monitors[num]->unregister();
-
+	for (num = 0; num < avail_monitors; num++) {
+		if (monitors[num]->unregister)
+			monitors[num]->unregister();
+	}
 	cpu_topology_release(cpu_top);
 	return 0;
 }
diff --git a/tools/power/cpupower/utils/idle_monitor/idle_monitors.def b/tools/power/cpupower/utils/idle_monitor/idle_monitors.def
index 0d6ba4dbb9c71..7c926e90c87e5 100644
--- a/tools/power/cpupower/utils/idle_monitor/idle_monitors.def
+++ b/tools/power/cpupower/utils/idle_monitor/idle_monitors.def
@@ -4,5 +4,6 @@ DEF(intel_nhm)
 DEF(intel_snb)
 DEF(intel_hsw_ext)
 DEF(mperf)
+DEF(rapl)
 #endif
 DEF(cpuidle_sysfs)
diff --git a/tools/power/cpupower/utils/idle_monitor/rapl_monitor.c b/tools/power/cpupower/utils/idle_monitor/rapl_monitor.c
new file mode 100644
index 0000000000000..46153f1291c3d
--- /dev/null
+++ b/tools/power/cpupower/utils/idle_monitor/rapl_monitor.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  (C) 2016 SUSE Software Solutions GmbH
+ *           Thomas Renninger <trenn@suse.de>
+ */
+
+#if defined(__i386__) || defined(__x86_64__)
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <time.h>
+#include <string.h>
+
+#include <pci/pci.h>
+
+#include "idle_monitor/cpupower-monitor.h"
+#include "helpers/helpers.h"
+#include "powercap.h"
+
+#define MAX_RAPL_ZONES 10
+
+int rapl_zone_count;
+cstate_t rapl_zones[MAX_RAPL_ZONES];
+struct powercap_zone *rapl_zones_pt[MAX_RAPL_ZONES] = { 0 };
+
+unsigned long long rapl_zone_previous_count[MAX_RAPL_ZONES];
+unsigned long long rapl_zone_current_count[MAX_RAPL_ZONES];
+unsigned long long rapl_max_count;
+
+static int rapl_get_count_uj(unsigned int id, unsigned long long *count,
+			     unsigned int cpu)
+{
+	if (rapl_zones_pt[id] == NULL)
+		/* error */
+		return -1;
+
+	*count = rapl_zone_current_count[id] - rapl_zone_previous_count[id];
+
+	return 0;
+}
+
+static int powercap_count_zones(struct powercap_zone *zone)
+{
+	uint64_t val;
+	int uj;
+
+	if (rapl_zone_count >= MAX_RAPL_ZONES)
+		return -1;
+
+	if (!zone->has_energy_uj)
+		return 0;
+
+	printf("%s\n", zone->sys_name);
+	uj = powercap_get_energy_uj(zone, &val);
+	printf("%d\n", uj);
+
+	strncpy(rapl_zones[rapl_zone_count].name, zone->name, CSTATE_NAME_LEN - 1);
+	strcpy(rapl_zones[rapl_zone_count].desc, "");
+	rapl_zones[rapl_zone_count].id = rapl_zone_count;
+	rapl_zones[rapl_zone_count].range = RANGE_MACHINE;
+	rapl_zones[rapl_zone_count].get_count = rapl_get_count_uj;
+	rapl_zones_pt[rapl_zone_count] = zone;
+	rapl_zone_count++;
+
+	return 0;
+}
+
+static int rapl_start(void)
+{
+	int i, ret;
+	uint64_t uj_val;
+
+	for (i = 0; i < rapl_zone_count; i++) {
+		ret = powercap_get_energy_uj(rapl_zones_pt[i], &uj_val);
+		if (ret)
+			return ret;
+		rapl_zone_previous_count[i] = uj_val;
+	}
+
+	return 0;
+}
+
+static int rapl_stop(void)
+{
+	int i;
+	uint64_t uj_val;
+
+	for (i = 0; i < rapl_zone_count; i++) {
+		int ret;
+
+		ret = powercap_get_energy_uj(rapl_zones_pt[i], &uj_val);
+		if (ret)
+			return ret;
+		rapl_zone_current_count[i] = uj_val;
+		if (rapl_max_count < uj_val)
+			rapl_max_count = uj_val - rapl_zone_previous_count[i];
+	}
+	return 0;
+}
+
+struct cpuidle_monitor *rapl_register(void)
+{
+	struct powercap_zone *root_zone;
+	char line[MAX_LINE_LEN] = "";
+	int ret, val;
+
+	ret = powercap_get_driver(line, MAX_LINE_LEN);
+	if (ret < 0) {
+		dprint("No powercapping driver loaded\n");
+		return NULL;
+	}
+
+	dprint("Driver: %s\n", line);
+	ret = powercap_get_enabled(&val);
+	if (ret < 0)
+		return NULL;
+	if (!val) {
+		dprint("Powercapping is disabled\n");
+		return NULL;
+	}
+
+	dprint("Powercap domain hierarchy:\n\n");
+	root_zone = powercap_init_zones();
+
+	if (root_zone == NULL) {
+		dprint("No powercap info found\n");
+		return NULL;
+	}
+
+	powercap_walk_zones(root_zone, powercap_count_zones);
+	rapl_monitor.hw_states_num = rapl_zone_count;
+
+	return &rapl_monitor;
+}
+
+struct cpuidle_monitor rapl_monitor = {
+	.name			= "RAPL",
+	.hw_states		= rapl_zones,
+	.hw_states_num		= 0,
+	.start			= rapl_start,
+	.stop			= rapl_stop,
+	.do_register		= rapl_register,
+	.flags.needs_root	= 0,
+	.overflow_s		= 60 * 60 * 24 * 100, /* To be implemented */
+};
+
+#endif
-- 
2.30.2