From 549b92c94c7e6db12842c5d64c036e6613dbd902 Mon Sep 17 00:00:00 2001
From: Tomas Glozar <tglozar@redhat.com>
Date: Thu, 17 Oct 2024 16:09:12 +0200
Subject: [PATCH] rtla/timerlat: Add --deepest-idle-state for top

Add option to limit deepest idle state on CPUs where timerlat is running
for the duration of the workload.

Link: https://lore.kernel.org/20241017140914.3200454-5-tglozar@redhat.com
Signed-off-by: Tomas Glozar <tglozar@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/tracing/rtla/src/timerlat_top.c | 42 ++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
index 7fb85c8ee3bc..fca0da3caa87 100644
--- a/tools/tracing/rtla/src/timerlat_top.c
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -48,6 +48,7 @@ struct timerlat_top_params {
 	int			pretty_output;
 	int			warmup;
 	int			buffer_size;
+	int			deepest_idle_state;
 	cpu_set_t		hk_cpu_set;
 	struct sched_attr	sched_param;
 	struct trace_events	*events;
@@ -447,7 +448,7 @@ static void timerlat_top_usage(char *usage)
 		"",
 		"  usage: rtla timerlat [top] [-h] [-q] [-a us] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] \\",
 		"	  [[-t[file]] [-e sys[:event]] [--filter <filter>] [--trigger <trigger>] [-c cpu-list] [-H cpu-list]\\",
-		"	  [-P priority] [--dma-latency us] [--aa-only us] [-C[=cgroup_name]] [-u|-k] [--warm-up s]",
+		"	  [-P priority] [--dma-latency us] [--aa-only us] [-C[=cgroup_name]] [-u|-k] [--warm-up s] [--deepest-idle-state n]",
 		"",
 		"	  -h/--help: print this menu",
 		"	  -a/--auto: set automatic trace mode, stopping the session if argument in us latency is hit",
@@ -481,6 +482,7 @@ static void timerlat_top_usage(char *usage)
 		"	  -U/--user-load: enable timerlat for user-defined user-space workload",
 		"	     --warm-up s: let the workload run for s seconds before collecting data",
 		"	     --trace-buffer-size kB: set the per-cpu trace buffer size in kB",
+		"	     --deepest-idle-state n: only go down to idle state n on cpus used by timerlat to reduce exit from idle latency",
 		NULL,
 	};
 
@@ -518,6 +520,9 @@ static struct timerlat_top_params
 	/* disabled by default */
 	params->dma_latency = -1;
 
+	/* disabled by default */
+	params->deepest_idle_state = -2;
+
 	/* display data in microseconds */
 	params->output_divisor = 1000;
 
@@ -550,6 +555,7 @@ static struct timerlat_top_params
 			{"aa-only",		required_argument,	0, '5'},
 			{"warm-up",		required_argument,	0, '6'},
 			{"trace-buffer-size",	required_argument,	0, '7'},
+			{"deepest-idle-state",	required_argument,	0, '8'},
 			{0, 0, 0, 0}
 		};
 
@@ -726,6 +732,9 @@ static struct timerlat_top_params
 		case '7':
 			params->buffer_size = get_llong_from_str(optarg);
 			break;
+		case '8':
+			params->deepest_idle_state = get_llong_from_str(optarg);
+			break;
 		default:
 			timerlat_top_usage("Invalid option");
 		}
@@ -922,6 +931,7 @@ int timerlat_top_main(int argc, char *argv[])
 	int return_value = 1;
 	char *max_lat;
 	int retval;
+	int nr_cpus, i;
 
 	params = timerlat_top_parse_args(argc, argv);
 	if (!params)
@@ -971,6 +981,28 @@ int timerlat_top_main(int argc, char *argv[])
 		}
 	}
 
+	if (params->deepest_idle_state >= -1) {
+		if (!have_libcpupower_support()) {
+			err_msg("rtla built without libcpupower, --deepest-idle-state is not supported\n");
+			goto out_free;
+		}
+
+		nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+
+		for (i = 0; i < nr_cpus; i++) {
+			if (params->cpus && !CPU_ISSET(i, &params->monitored_cpus))
+				continue;
+			if (save_cpu_idle_disable_state(i) < 0) {
+				err_msg("Could not save cpu idle state.\n");
+				goto out_free;
+			}
+			if (set_deepest_cpu_idle_state(i, params->deepest_idle_state) < 0) {
+				err_msg("Could not set deepest cpu idle state.\n");
+				goto out_free;
+			}
+		}
+	}
+
 	if (params->trace_output) {
 		record = osnoise_init_trace_tool("timerlat");
 		if (!record) {
@@ -1125,6 +1157,13 @@ int timerlat_top_main(int argc, char *argv[])
 	timerlat_aa_destroy();
 	if (dma_latency_fd >= 0)
 		close(dma_latency_fd);
+	if (params->deepest_idle_state >= -1) {
+		for (i = 0; i < nr_cpus; i++) {
+			if (params->cpus && !CPU_ISSET(i, &params->monitored_cpus))
+				continue;
+			restore_cpu_idle_disable_state(i);
+		}
+	}
 	trace_events_destroy(&record->trace, params->events);
 	params->events = NULL;
 out_free:
@@ -1134,6 +1173,7 @@ int timerlat_top_main(int argc, char *argv[])
 	osnoise_destroy_tool(record);
 	osnoise_destroy_tool(top);
 	free(params);
+	free_cpu_idle_disable_states();
 out_exit:
 	exit(return_value);
 }