Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

27 files changed, 10005 insertions, 0 deletions

diff --git a/tools/tracing/rtla/src/Build b/tools/tracing/rtla/src/Build
new file mode 100644
index 000000000..a1f3ab927
--- /dev/null
+++ b/tools/tracing/rtla/src/Build
@@ -0,0 +1,14 @@
+rtla-y += trace.o
+rtla-y += utils.o
+rtla-y += actions.o
+rtla-y += common.o
+rtla-y += osnoise.o
+rtla-y += osnoise_top.o
+rtla-y += osnoise_hist.o
+rtla-y += timerlat.o
+rtla-y += timerlat_top.o
+rtla-y += timerlat_hist.o
+rtla-y += timerlat_u.o
+rtla-y += timerlat_aa.o
+rtla-y += timerlat_bpf.o
+rtla-y += cli.o
diff --git a/tools/tracing/rtla/src/actions.c b/tools/tracing/rtla/src/actions.c
new file mode 100644
index 000000000..bf13d9d68
--- /dev/null
+++ b/tools/tracing/rtla/src/actions.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include "actions.h"
+#include "trace.h"
+#include "utils.h"
+
+/*
+ * actions_init - initialize struct actions
+ */
+void
+actions_init(struct actions *self)
+{
+	self->size = action_default_size;
+	self->list = calloc_fatal(self->size, sizeof(struct action));
+	self->len = 0;
+	self->continue_flag = false;
+
+	/* This has to be set by the user */
+	self->trace_output_inst = NULL;
+}
+
+/*
+ * actions_destroy - destroy struct actions
+ */
+void
+actions_destroy(struct actions *self)
+{
+	/* Free any action-specific data */
+	struct action *action;
+
+	for_each_action(self, action) {
+		if (action->type == ACTION_SHELL)
+			free(action->command);
+		if (action->type == ACTION_TRACE_OUTPUT)
+			free(action->trace_output);
+	}
+
+	/* Free action list */
+	free(self->list);
+}
+
+/*
+ * actions_new - Get pointer to new action
+ */
+static struct action *
+actions_new(struct actions *self)
+{
+	if (self->len >= self->size) {
+		const size_t new_size = self->size * 2;
+
+		self->list = reallocarray_fatal(self->list, new_size, sizeof(struct action));
+		self->size = new_size;
+	}
+
+	return &self->list[self->len++];
+}
+
+/*
+ * actions_add_trace_output - add an action to output trace
+ */
+void
+actions_add_trace_output(struct actions *self, const char *trace_output)
+{
+	struct action *action = actions_new(self);
+
+	self->present[ACTION_TRACE_OUTPUT] = true;
+	action->type = ACTION_TRACE_OUTPUT;
+	action->trace_output = strdup_fatal(trace_output);
+}
+
+/*
+ * actions_add_trace_output - add an action to send signal to a process
+ */
+void
+actions_add_signal(struct actions *self, int signal, int pid)
+{
+	struct action *action = actions_new(self);
+
+	self->present[ACTION_SIGNAL] = true;
+	action->type = ACTION_SIGNAL;
+	action->signal = signal;
+	action->pid = pid;
+}
+
+/*
+ * actions_add_shell - add an action to execute a shell command
+ */
+void
+actions_add_shell(struct actions *self, const char *command)
+{
+	struct action *action = actions_new(self);
+
+	self->present[ACTION_SHELL] = true;
+	action->type = ACTION_SHELL;
+	action->command = strdup_fatal(command);
+}
+
+/*
+ * actions_add_continue - add an action to resume measurement
+ */
+void
+actions_add_continue(struct actions *self)
+{
+	struct action *action = actions_new(self);
+
+	self->present[ACTION_CONTINUE] = true;
+	action->type = ACTION_CONTINUE;
+}
+
+static inline const char *__extract_arg(const char *token, const char *opt, size_t opt_len)
+{
+	const size_t tok_len = strlen(token);
+
+	if (tok_len <= opt_len)
+		return NULL;
+
+	if (strncmp(token, opt, opt_len))
+		return NULL;
+
+	return token + opt_len;
+}
+
+/*
+ * extract_arg - extract argument value from option token
+ * @token: option token (e.g., "file=trace.txt")
+ * @opt: option name to match (e.g., "file")
+ *
+ * Returns pointer to argument value after "=" if token matches "opt=",
+ * otherwise returns NULL.
+ */
+#define extract_arg(token, opt) __extract_arg(token, opt "=", STRING_LENGTH(opt "="))
+
+/*
+ * actions_parse - add an action based on text specification
+ */
+int
+actions_parse(struct actions *self, const char *trigger, const char *tracefn)
+{
+	enum action_type type = ACTION_NONE;
+	const char *token;
+	char trigger_c[strlen(trigger) + 1];
+	const char *arg_value;
+
+	/* For ACTION_SIGNAL */
+	int signal = 0, pid = 0;
+
+	/* For ACTION_TRACE_OUTPUT */
+	const char *trace_output;
+
+	strcpy(trigger_c, trigger);
+	token = strtok(trigger_c, ",");
+	if (!token)
+		return -1;
+
+	if (strcmp(token, "trace") == 0)
+		type = ACTION_TRACE_OUTPUT;
+	else if (strcmp(token, "signal") == 0)
+		type = ACTION_SIGNAL;
+	else if (strcmp(token, "shell") == 0)
+		type = ACTION_SHELL;
+	else if (strcmp(token, "continue") == 0)
+		type = ACTION_CONTINUE;
+	else
+		/* Invalid trigger type */
+		return -1;
+
+	token = strtok(NULL, ",");
+
+	switch (type) {
+	case ACTION_TRACE_OUTPUT:
+		/* Takes no argument */
+		if (token == NULL)
+			trace_output = tracefn;
+		else {
+			trace_output = extract_arg(token, "file");
+			if (!trace_output)
+				/* Invalid argument */
+				return -1;
+
+			token = strtok(NULL, ",");
+			if (token != NULL)
+				/* Only one argument allowed */
+				return -1;
+		}
+		actions_add_trace_output(self, trace_output);
+		break;
+	case ACTION_SIGNAL:
+		/* Takes two arguments, num (signal) and pid */
+		while (token != NULL) {
+			arg_value = extract_arg(token, "num");
+			if (arg_value) {
+				if (strtoi(arg_value, &signal))
+					return -1;
+			} else {
+				arg_value = extract_arg(token, "pid");
+				if (arg_value) {
+					if (strncmp_static(arg_value, "parent") == 0)
+						pid = -1;
+					else if (strtoi(arg_value, &pid))
+						return -1;
+				} else {
+					/* Invalid argument */
+					return -1;
+				}
+			}
+
+			token = strtok(NULL, ",");
+		}
+
+		if (!signal || !pid)
+			/* Missing argument */
+			return -1;
+
+		actions_add_signal(self, signal, pid);
+		break;
+	case ACTION_SHELL:
+		if (token == NULL)
+			return -1;
+		arg_value = extract_arg(token, "command");
+		if (!arg_value)
+			return -1;
+		actions_add_shell(self, arg_value);
+		break;
+	case ACTION_CONTINUE:
+		/* Takes no argument */
+		if (token != NULL)
+			return -1;
+		actions_add_continue(self);
+		break;
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * actions_perform - perform all actions
+ */
+int
+actions_perform(struct actions *self)
+{
+	int pid, retval;
+	const struct action *action;
+
+	self->continue_flag = false;
+
+	for_each_action(self, action) {
+		switch (action->type) {
+		case ACTION_TRACE_OUTPUT:
+			retval = save_trace_to_file(self->trace_output_inst, action->trace_output);
+			if (retval) {
+				err_msg("Error saving trace\n");
+				return retval;
+			}
+			break;
+		case ACTION_SIGNAL:
+			if (action->pid == -1)
+				pid = getppid();
+			else
+				pid = action->pid;
+			retval = kill(pid, action->signal);
+			if (retval) {
+				err_msg("Error sending signal\n");
+				return retval;
+			}
+			break;
+		case ACTION_SHELL:
+			retval = system(action->command);
+			if (retval)
+				return retval;
+			break;
+		case ACTION_CONTINUE:
+			self->continue_flag = true;
+			return 0;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/tracing/rtla/src/actions.h b/tools/tracing/rtla/src/actions.h
new file mode 100644
index 000000000..034048682
--- /dev/null
+++ b/tools/tracing/rtla/src/actions.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <tracefs.h>
+#include <stdbool.h>
+
+enum action_type {
+	ACTION_NONE = 0,
+	ACTION_TRACE_OUTPUT,
+	ACTION_SIGNAL,
+	ACTION_SHELL,
+	ACTION_CONTINUE,
+	ACTION_FIELD_N
+};
+
+struct action {
+	enum action_type type;
+	union {
+		struct {
+			/* For ACTION_TRACE_OUTPUT */
+			char *trace_output;
+		};
+		struct {
+			/* For ACTION_SIGNAL */
+			int signal;
+			int pid;
+		};
+		struct {
+			/* For ACTION_SHELL */
+			char *command;
+		};
+	};
+};
+
+static const int action_default_size = 8;
+
+struct actions {
+	struct action *list;
+	int len, size;
+	bool present[ACTION_FIELD_N];
+	bool continue_flag;
+
+	/* External dependencies */
+	struct tracefs_instance *trace_output_inst;
+};
+
+#define for_each_action(actions, action)			\
+	for ((action) = (actions)->list;			\
+	     (action) < (actions)->list + (actions)->len;	\
+	     (action)++)
+
+void actions_init(struct actions *self);
+void actions_destroy(struct actions *self);
+void actions_add_trace_output(struct actions *self, const char *trace_output);
+void actions_add_signal(struct actions *self, int signal, int pid);
+void actions_add_shell(struct actions *self, const char *command);
+void actions_add_continue(struct actions *self);
+int actions_parse(struct actions *self, const char *trigger, const char *tracefn);
+int actions_perform(struct actions *self);
diff --git a/tools/tracing/rtla/src/cli.c b/tools/tracing/rtla/src/cli.c
new file mode 100644
index 000000000..fb8c972c0
--- /dev/null
+++ b/tools/tracing/rtla/src/cli.c
@@ -0,0 +1,529 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+
+#include <linux/compiler.h>
+
+#define RTLA_ALLOW_CLI_P_H
+#include "cli_p.h"
+
+static const char * const osnoise_top_usage[] = {
+	"rtla osnoise [top] [<options>] [-h|--help]",
+	NULL,
+};
+
+static const char * const osnoise_hist_usage[] = {
+	"rtla osnoise hist [<options>] [-h|--help]",
+	NULL,
+};
+
+static const char * const timerlat_top_usage[] = {
+	"rtla timerlat [top] [<options>] [-h|--help]",
+	NULL,
+};
+
+static const char * const timerlat_hist_usage[] = {
+	"rtla timerlat hist [<options>] [-h|--help]",
+	NULL,
+};
+
+static const char * const hwnoise_usage[] = {
+	"rtla hwnoise [<options>] [-h|--help]",
+	NULL,
+};
+
+static const int common_parse_options_flags = PARSE_OPT_OPTARG_ALLOW_NEXT;
+
+bool in_unit_test;
+
+/*
+ * osnoise_top_parse_args - allocs, parse and fill the cmd line parameters
+ */
+struct common_params *osnoise_top_parse_args(int argc, char **argv)
+{
+	struct osnoise_params *params;
+	struct osnoise_cb_data cb_data;
+	const char * const *usage;
+
+	params = calloc_fatal(1, sizeof(*params));
+
+	cb_data.params = params;
+	cb_data.trace_output = NULL;
+
+	if (strcmp(argv[0], "hwnoise") == 0) {
+		params->mode = MODE_HWNOISE;
+		/*
+		 * Reduce CPU usage for 75% to avoid killing the system.
+		 */
+		params->runtime = 750000;
+		params->period = 1000000;
+		usage = hwnoise_usage;
+	} else {
+		usage = osnoise_top_usage;
+	}
+
+	const struct option osnoise_top_options[] = {
+	OPT_GROUP("Tracing Options:"),
+		OSNOISE_OPT_PERIOD,
+		OSNOISE_OPT_RUNTIME,
+		RTLA_OPT_STOP('s', "stop", "single sample"),
+		RTLA_OPT_STOP_TOTAL('S', "stop-total", "total sample"),
+		OSNOISE_OPT_THRESHOLD,
+		RTLA_OPT_TRACE_OUTPUT("osnoise", opt_osnoise_trace_output_cb),
+
+	OPT_GROUP("Event Configuration:"),
+		RTLA_OPT_EVENT,
+		RTLA_OPT_FILTER,
+		RTLA_OPT_TRIGGER,
+
+	OPT_GROUP("CPU Configuration:"),
+		RTLA_OPT_CPUS,
+		RTLA_OPT_HOUSEKEEPING,
+
+	OPT_GROUP("Thread Configuration:"),
+		RTLA_OPT_PRIORITY,
+		RTLA_OPT_CGROUP,
+
+	OPT_GROUP("Output:"),
+		RTLA_OPT_QUIET,
+
+	OPT_GROUP("System Tuning:"),
+		RTLA_OPT_TRACE_BUFFER_SIZE,
+		RTLA_OPT_WARM_UP,
+
+	OPT_GROUP("Auto Analysis and Actions:"),
+		RTLA_OPT_AUTO(opt_osnoise_auto_cb),
+		RTLA_OPT_ON_THRESHOLD("stop-total", opt_osnoise_on_threshold_cb),
+		RTLA_OPT_ON_END(opt_osnoise_on_end_cb),
+
+	OPT_GROUP("General:"),
+		RTLA_OPT_DURATION,
+		RTLA_OPT_DEBUG,
+
+	OPT_END(),
+	};
+
+	actions_init(&params->common.threshold_actions);
+	actions_init(&params->common.end_actions);
+
+	argc = parse_options(argc, (const char **)argv,
+			     osnoise_top_options,
+			     usage,
+			     common_parse_options_flags);
+	if (argc < 0)
+		return NULL;
+
+	if (cb_data.trace_output)
+		actions_add_trace_output(&params->common.threshold_actions, cb_data.trace_output);
+
+	if (geteuid() && !in_unit_test)
+		fatal("osnoise needs root permission");
+
+	return &params->common;
+}
+
+/*
+ * osnoise_hist_parse_args - allocs, parse and fill the cmd line parameters
+ */
+struct common_params *osnoise_hist_parse_args(int argc, char **argv)
+{
+	struct osnoise_params *params;
+	struct osnoise_cb_data cb_data;
+
+	params = calloc_fatal(1, sizeof(*params));
+
+	cb_data.params = params;
+	cb_data.trace_output = NULL;
+
+	const struct option osnoise_hist_options[] = {
+	OPT_GROUP("Tracing Options:"),
+		OSNOISE_OPT_PERIOD,
+		OSNOISE_OPT_RUNTIME,
+		RTLA_OPT_STOP('s', "stop", "single sample"),
+		RTLA_OPT_STOP_TOTAL('S', "stop-total", "total sample"),
+		OSNOISE_OPT_THRESHOLD,
+		RTLA_OPT_TRACE_OUTPUT("osnoise", opt_osnoise_trace_output_cb),
+
+	OPT_GROUP("Event Configuration:"),
+		RTLA_OPT_EVENT,
+		RTLA_OPT_FILTER,
+		RTLA_OPT_TRIGGER,
+
+	OPT_GROUP("CPU Configuration:"),
+		RTLA_OPT_CPUS,
+		RTLA_OPT_HOUSEKEEPING,
+
+	OPT_GROUP("Thread Configuration:"),
+		RTLA_OPT_PRIORITY,
+		RTLA_OPT_CGROUP,
+
+	OPT_GROUP("Histogram Options:"),
+		HIST_OPT_BUCKET_SIZE,
+		HIST_OPT_ENTRIES,
+		HIST_OPT_NO_HEADER,
+		HIST_OPT_NO_SUMMARY,
+		HIST_OPT_NO_INDEX,
+		HIST_OPT_WITH_ZEROS,
+
+	OPT_GROUP("System Tuning:"),
+		RTLA_OPT_TRACE_BUFFER_SIZE,
+		RTLA_OPT_WARM_UP,
+
+	OPT_GROUP("Auto Analysis and Actions:"),
+		RTLA_OPT_AUTO(opt_osnoise_auto_cb),
+		RTLA_OPT_ON_THRESHOLD("stop-total", opt_osnoise_on_threshold_cb),
+		RTLA_OPT_ON_END(opt_osnoise_on_end_cb),
+
+	OPT_GROUP("General:"),
+		RTLA_OPT_DURATION,
+		RTLA_OPT_DEBUG,
+
+	OPT_END(),
+	};
+
+	actions_init(&params->common.threshold_actions);
+	actions_init(&params->common.end_actions);
+
+	/* set default values */
+	params->common.output_divisor = default_output_divisor;
+	params->common.hist.bucket_size = default_bucket_size;
+	params->common.hist.entries = default_entries;
+
+	argc = parse_options(argc, (const char **)argv,
+			     osnoise_hist_options, osnoise_hist_usage,
+			     common_parse_options_flags);
+	if (argc < 0)
+		return NULL;
+
+	if (cb_data.trace_output)
+		actions_add_trace_output(&params->common.threshold_actions, cb_data.trace_output);
+
+	if (geteuid() && !in_unit_test)
+		fatal("rtla needs root permission");
+
+	if (params->common.hist.no_index && !params->common.hist.with_zeros)
+		fatal("no-index set and with-zeros not set - it does not make sense");
+
+	return &params->common;
+}
+
+struct common_params *timerlat_top_parse_args(int argc, char **argv)
+{
+	struct timerlat_params *params;
+	struct timerlat_cb_data cb_data;
+
+	params = calloc_fatal(1, sizeof(*params));
+
+	cb_data.params = params;
+	cb_data.trace_output = NULL;
+
+	const struct option timerlat_top_options[] = {
+	OPT_GROUP("Tracing Options:"),
+		TIMERLAT_OPT_PERIOD,
+		RTLA_OPT_STOP('i', "irq", "irq latency"),
+		RTLA_OPT_STOP_TOTAL('T', "thread", "thread latency"),
+		TIMERLAT_OPT_STACK,
+		RTLA_OPT_TRACE_OUTPUT("timerlat", opt_timerlat_trace_output_cb),
+
+	OPT_GROUP("Event Configuration:"),
+		RTLA_OPT_EVENT,
+		RTLA_OPT_FILTER,
+		RTLA_OPT_TRIGGER,
+
+	OPT_GROUP("CPU Configuration:"),
+		RTLA_OPT_CPUS,
+		RTLA_OPT_HOUSEKEEPING,
+
+	OPT_GROUP("Thread Configuration:"),
+		RTLA_OPT_PRIORITY,
+		RTLA_OPT_CGROUP,
+		RTLA_OPT_USER_THREADS,
+		RTLA_OPT_KERNEL_THREADS,
+		RTLA_OPT_USER_LOAD,
+		TIMERLAT_OPT_ALIGNED,
+
+	OPT_GROUP("Output:"),
+		TIMERLAT_OPT_NANO,
+		RTLA_OPT_QUIET,
+
+	OPT_GROUP("System Tuning:"),
+		TIMERLAT_OPT_DMA_LATENCY,
+		TIMERLAT_OPT_DEEPEST_IDLE_STATE,
+		RTLA_OPT_TRACE_BUFFER_SIZE,
+		RTLA_OPT_WARM_UP,
+
+	OPT_GROUP("Auto Analysis and Actions:"),
+		RTLA_OPT_AUTO(opt_timerlat_auto_cb),
+		TIMERLAT_OPT_AA_ONLY,
+		TIMERLAT_OPT_NO_AA,
+		TIMERLAT_OPT_DUMPS_TASKS,
+		RTLA_OPT_ON_THRESHOLD("latency", opt_timerlat_on_threshold_cb),
+		RTLA_OPT_ON_END(opt_timerlat_on_end_cb),
+		TIMERLAT_OPT_BPF_ACTION,
+		TIMERLAT_OPT_STACK_FORMAT,
+
+	OPT_GROUP("General:"),
+		RTLA_OPT_DURATION,
+		RTLA_OPT_DEBUG,
+
+	OPT_END(),
+	};
+
+	actions_init(&params->common.threshold_actions);
+	actions_init(&params->common.end_actions);
+
+	/* set default values */
+	params->dma_latency = default_dma_latency;
+	params->deepest_idle_state = default_deepest_idle_state;
+	params->common.output_divisor = default_output_divisor;
+	params->stack_format = default_stack_format;
+
+	/* default to BPF mode */
+	params->mode = TRACING_MODE_BPF;
+
+	argc = parse_options(argc, (const char **)argv,
+			     timerlat_top_options, timerlat_top_usage,
+			     common_parse_options_flags);
+	if (argc < 0)
+		return NULL;
+
+	if (cb_data.trace_output)
+		actions_add_trace_output(&params->common.threshold_actions, cb_data.trace_output);
+
+	if (geteuid() && !in_unit_test)
+		fatal("rtla needs root permission");
+
+	/*
+	 * Auto analysis only happens if stop tracing, thus:
+	 */
+	if (!params->common.stop_us && !params->common.stop_total_us)
+		params->no_aa = 1;
+
+	if (params->no_aa && params->common.aa_only)
+		fatal("--no-aa and --aa-only are mutually exclusive!");
+
+	if (params->common.kernel_workload && params->common.user_workload)
+		fatal("--kernel-threads and --user-threads are mutually exclusive!");
+
+	/*
+	 * If auto-analysis or trace output is enabled, switch from BPF mode to
+	 * mixed mode
+	 */
+	if (params->mode == TRACING_MODE_BPF &&
+		(params->common.threshold_actions.present[ACTION_TRACE_OUTPUT] ||
+		params->common.end_actions.present[ACTION_TRACE_OUTPUT] ||
+		!params->no_aa))
+		params->mode = TRACING_MODE_MIXED;
+
+	return &params->common;
+}
+
+struct common_params *timerlat_hist_parse_args(int argc, char **argv)
+{
+	struct timerlat_params *params;
+	struct timerlat_cb_data cb_data;
+
+	params = calloc_fatal(1, sizeof(*params));
+
+	cb_data.params = params;
+	cb_data.trace_output = NULL;
+
+	const struct option timerlat_hist_options[] = {
+	OPT_GROUP("Tracing Options:"),
+		TIMERLAT_OPT_PERIOD,
+		RTLA_OPT_STOP('i', "irq", "irq latency"),
+		RTLA_OPT_STOP_TOTAL('T', "thread", "thread latency"),
+		TIMERLAT_OPT_STACK,
+		RTLA_OPT_TRACE_OUTPUT("timerlat", opt_timerlat_trace_output_cb),
+
+	OPT_GROUP("Event Configuration:"),
+		RTLA_OPT_EVENT,
+		RTLA_OPT_FILTER,
+		RTLA_OPT_TRIGGER,
+
+	OPT_GROUP("CPU Configuration:"),
+		RTLA_OPT_CPUS,
+		RTLA_OPT_HOUSEKEEPING,
+
+	OPT_GROUP("Thread Configuration:"),
+		RTLA_OPT_PRIORITY,
+		RTLA_OPT_CGROUP,
+		RTLA_OPT_USER_THREADS,
+		RTLA_OPT_KERNEL_THREADS,
+		RTLA_OPT_USER_LOAD,
+		TIMERLAT_OPT_ALIGNED,
+
+	OPT_GROUP("Histogram Options:"),
+		HIST_OPT_BUCKET_SIZE,
+		HIST_OPT_ENTRIES,
+		HIST_OPT_NO_IRQ,
+		HIST_OPT_NO_THREAD,
+		HIST_OPT_NO_HEADER,
+		HIST_OPT_NO_SUMMARY,
+		HIST_OPT_NO_INDEX,
+		HIST_OPT_WITH_ZEROS,
+
+	OPT_GROUP("Output:"),
+		TIMERLAT_OPT_NANO,
+
+	OPT_GROUP("System Tuning:"),
+		TIMERLAT_OPT_DMA_LATENCY,
+		TIMERLAT_OPT_DEEPEST_IDLE_STATE,
+		RTLA_OPT_TRACE_BUFFER_SIZE,
+		RTLA_OPT_WARM_UP,
+
+	OPT_GROUP("Auto Analysis and Actions:"),
+		RTLA_OPT_AUTO(opt_timerlat_auto_cb),
+		TIMERLAT_OPT_NO_AA,
+		TIMERLAT_OPT_DUMPS_TASKS,
+		RTLA_OPT_ON_THRESHOLD("latency", opt_timerlat_on_threshold_cb),
+		RTLA_OPT_ON_END(opt_timerlat_on_end_cb),
+		TIMERLAT_OPT_BPF_ACTION,
+		TIMERLAT_OPT_STACK_FORMAT,
+
+	OPT_GROUP("General:"),
+		RTLA_OPT_DURATION,
+		RTLA_OPT_DEBUG,
+
+	OPT_END(),
+	};
+
+	actions_init(&params->common.threshold_actions);
+	actions_init(&params->common.end_actions);
+
+	/* set default values */
+	params->dma_latency = default_dma_latency;
+	params->deepest_idle_state = default_deepest_idle_state;
+	params->common.output_divisor = default_output_divisor;
+	params->common.hist.bucket_size = default_bucket_size;
+	params->common.hist.entries = default_entries;
+	params->stack_format = default_stack_format;
+
+	/* default to BPF mode */
+	params->mode = TRACING_MODE_BPF;
+
+	argc = parse_options(argc, (const char **)argv,
+			     timerlat_hist_options, timerlat_hist_usage,
+			     common_parse_options_flags);
+	if (argc < 0)
+		return NULL;
+
+	if (cb_data.trace_output)
+		actions_add_trace_output(&params->common.threshold_actions, cb_data.trace_output);
+
+	if (geteuid() && !in_unit_test)
+		fatal("rtla needs root permission");
+
+	if (params->common.hist.no_irq && params->common.hist.no_thread)
+		fatal("no-irq and no-thread set, there is nothing to do here");
+
+	if (params->common.hist.no_index && !params->common.hist.with_zeros)
+		fatal("no-index set with with-zeros is not set - it does not make sense");
+
+	/*
+	 * Auto analysis only happens if stop tracing, thus:
+	 */
+	if (!params->common.stop_us && !params->common.stop_total_us)
+		params->no_aa = 1;
+
+	if (params->common.kernel_workload && params->common.user_workload)
+		fatal("--kernel-threads and --user-threads are mutually exclusive!");
+
+	/*
+	 * If auto-analysis or trace output is enabled, switch from BPF mode to
+	 * mixed mode
+	 */
+	if (params->mode == TRACING_MODE_BPF &&
+		(params->common.threshold_actions.present[ACTION_TRACE_OUTPUT] ||
+		params->common.end_actions.present[ACTION_TRACE_OUTPUT] ||
+		!params->no_aa))
+		params->mode = TRACING_MODE_MIXED;
+
+	return &params->common;
+}
+
+/*
+ * rtla_usage - print rtla usage
+ */
+__noreturn static void rtla_usage(int err)
+{
+	int i;
+
+	static const char * const msg[] = {
+		"",
+		"rtla version " VERSION,
+		"",
+		"  usage: rtla COMMAND ...",
+		"",
+		"  commands:",
+		"     osnoise  - gives information about the operating system noise (osnoise)",
+		"     hwnoise  - gives information about hardware-related noise",
+		"     timerlat - measures the timer irq and thread latency",
+		"",
+		NULL,
+	};
+
+	for (i = 0; msg[i]; i++)
+		fprintf(stderr, "%s\n", msg[i]);
+	exit(err);
+}
+
+/*
+ * run_tool_command - try to run a rtla tool command
+ *
+ * It returns 0 if it fails. The tool's main will generally not
+ * return as they should call exit().
+ */
+int run_tool_command(int argc, char **argv, int start_position)
+{
+	if (strcmp(argv[start_position], "osnoise") == 0) {
+		osnoise_main(argc-start_position, &argv[start_position]);
+		goto ran;
+	} else if (strcmp(argv[start_position], "hwnoise") == 0) {
+		hwnoise_main(argc-start_position, &argv[start_position]);
+		goto ran;
+	} else if (strcmp(argv[start_position], "timerlat") == 0) {
+		timerlat_main(argc-start_position, &argv[start_position]);
+		goto ran;
+	}
+
+	return 0;
+ran:
+	return 1;
+}
+
+/* Set main as weak to allow overriding it for building unit test binary */
+#pragma weak main
+
+int main(int argc, char *argv[])
+{
+	int retval;
+
+	/* is it an alias? */
+	retval = run_tool_command(argc, argv, 0);
+	if (retval)
+		exit(0);
+
+	if (argc < 2)
+		goto usage;
+
+	if (strcmp(argv[1], "-h") == 0)
+		rtla_usage(129);
+	else if (strcmp(argv[1], "--help") == 0)
+		rtla_usage(129);
+
+	retval = run_tool_command(argc, argv, 1);
+	if (retval)
+		exit(0);
+
+usage:
+	rtla_usage(129);
+}
diff --git a/tools/tracing/rtla/src/cli.h b/tools/tracing/rtla/src/cli.h
new file mode 100644
index 000000000..633a2322c
--- /dev/null
+++ b/tools/tracing/rtla/src/cli.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+
+struct common_params *osnoise_top_parse_args(int argc, char **argv);
+struct common_params *osnoise_hist_parse_args(int argc, char **argv);
+struct common_params *timerlat_top_parse_args(int argc, char **argv);
+struct common_params *timerlat_hist_parse_args(int argc, char **argv);
+
+extern bool in_unit_test;
diff --git a/tools/tracing/rtla/src/cli_p.h b/tools/tracing/rtla/src/cli_p.h
new file mode 100644
index 000000000..661240d44
--- /dev/null
+++ b/tools/tracing/rtla/src/cli_p.h
@@ -0,0 +1,854 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+
+#ifndef RTLA_ALLOW_CLI_P_H
+#error "Private header file included outside of cli.c module"
+#endif
+
+#include <errno.h>
+#include <limits.h>
+#include <linux/kernel.h>
+#include <subcmd/parse-options.h>
+
+#include "cli.h"
+#include "osnoise.h"
+#include "timerlat.h"
+
+struct osnoise_cb_data {
+	struct osnoise_params *params;
+	char *trace_output;
+};
+
+struct timerlat_cb_data {
+	struct timerlat_params *params;
+	char *trace_output;
+};
+
+/*
+ * Non-zero default values for parameters
+ */
+static const int default_dma_latency = -1; /* -1 = unset */
+static const int default_deepest_idle_state = -2; /* -1 = disable all, -2 = unset */
+static const int default_output_divisor = 1000;
+static const int default_bucket_size = 1;
+static const int default_entries = 256;
+static const enum stack_format default_stack_format = STACK_FORMAT_TRUNCATE;
+
+/*
+ * Range checking for long long and int option callbacks.
+ *
+ * Pass a pointer to a const struct as opt->data to enable range checking.
+ * If opt->data is NULL, no range check is performed.
+ */
+struct llong_range {
+	long long min;
+	long long max;
+};
+
+struct int_range {
+	int min;
+	int max;
+};
+
+#define LLONG_RANGE(lo, hi) \
+	(&(const struct llong_range){ .min = (lo), .max = (hi) })
+
+#define INT_RANGE(lo, hi) \
+	(&(const struct int_range){ .min = (lo), .max = (hi) })
+
+static int check_llong_range(const struct option *opt, long long value)
+{
+	const struct llong_range *range = opt->data;
+
+	if (!range)
+		return 0;
+	if (value < range->min || value > range->max) {
+		fprintf(stderr, " Error: --%s value %lld is out of range [%lld, %lld]\n",
+			opt->long_name, value, range->min, range->max);
+		return -1;
+	}
+	return 0;
+}
+
+static int check_int_range(const struct option *opt, int value)
+{
+	const struct int_range *range = opt->data;
+
+	if (!range)
+		return 0;
+	if (value < range->min || value > range->max) {
+		fprintf(stderr, " Error: --%s value %d is out of range [%d, %d]\n",
+			opt->long_name, value, range->min, range->max);
+		return -1;
+	}
+	return 0;
+}
+
+/*
+ * OPT_CALLBACK variant that populates .data (for range checking).
+ */
+#define RTLA_OPT_CALLBACK_DATA(s, l, v, a, h, f, d) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
+	  .value = (v), .argh = (a), .help = (h), .callback = (f), \
+	  .data = (void *)(d) }
+
+#define RTLA_OPT_CALLBACK_DATA_DEFVAL(s, l, v, a, h, f, d, dv) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
+	  .value = (v), .argh = (a), .help = (h), .callback = (f), \
+	  .data = (void *)(d), .defval = (intptr_t)(dv) }
+
+/*
+ * Shorthand macros for integer/long long command line options using
+ * opt_int_callback/opt_llong_callback, with variants that set defval
+ * and/or data (for range checking).
+ *
+ * Note: defval's type is intptr_t. opt_int_callback interprets it directly as
+ * an int, opt_llong_callback interprets it as a pointer to a long long, as
+ * long long does not fit into intptr_t on 32-bit architectures.
+ */
+#define RTLA_OPT_LLONG(s, l, v, a, h) \
+	OPT_CALLBACK(s, l, v, a, h, opt_llong_callback)
+
+#define RTLA_OPT_LLONG_DEFVAL(s, l, v, a, h, d) { .type = OPTION_CALLBACK, \
+	.short_name = (s), .long_name = (l), .value = (v), .argh = (a), \
+	.help = (h), .callback = opt_llong_callback, .defval = (intptr_t)(d) }
+
+#define RTLA_OPT_LLONG_DATA(s, l, v, a, h, d) { .type = OPTION_CALLBACK, \
+	.short_name = (s), .long_name = (l), .value = (v), .argh = (a), \
+	.help = (h), .callback = opt_llong_callback, .data = (void *)(d) }
+
+#define RTLA_OPT_INT(s, l, v, a, h) \
+	OPT_CALLBACK(s, l, v, a, h, opt_int_callback)
+
+#define RTLA_OPT_INT_DEFVAL(s, l, v, a, h, d) { .type = OPTION_CALLBACK, \
+	.short_name = (s), .long_name = (l), .value = (v), .argh = (a), \
+	.help = (h), .callback = opt_int_callback, .defval = (intptr_t)(d) }
+
+#define RTLA_OPT_INT_DATA_DEFVAL(s, l, v, a, h, d, dv) { .type = OPTION_CALLBACK, \
+	.short_name = (s), .long_name = (l), .value = (v), .argh = (a), \
+	.help = (h), .callback = opt_int_callback, \
+	.data = (void *)(d), .defval = (intptr_t)(dv) }
+
+/*
+ * Macros for command line options common to all tools
+ *
+ * Note: Some of the options are common to both timerlat and osnoise, but
+ * have a slightly different meaning. Such options take additional arguments
+ * that have to be provided by the *_parse_args() function of the corresponding
+ * tool.
+ *
+ * All macros defined here assume the presence of a params variable of
+ * the corresponding tool type (i.e struct timerlat_params or struct osnoise_params)
+ * and a cb_data variable of the matching type.
+ */
+
+ #define RTLA_OPT_STOP(short, long, name) OPT_CALLBACK_FLAG(short, long, \
+	&params->common.stop_us, \
+	"us", \
+	"stop trace if " name " is higher than the argument in us", \
+	opt_llong_callback, PARSE_OPT_NOAUTONEG)
+
+#define RTLA_OPT_STOP_TOTAL(short, long, name) OPT_CALLBACK_FLAG(short, long, \
+	&params->common.stop_total_us, \
+	"us", \
+	"stop trace if " name " is higher than the argument in us", \
+	opt_llong_callback, PARSE_OPT_NOAUTONEG)
+
+#define RTLA_OPT_TRACE_OUTPUT(tracer, cb) OPT_CALLBACK_OPTARG('t', "trace", \
+	(const char **)&cb_data.trace_output, \
+	tracer "_trace.txt", \
+	"[file]", \
+	"save the stopped trace to [file|" tracer "_trace.txt]", \
+	cb)
+
+#define RTLA_OPT_CPUS OPT_CALLBACK('c', "cpus", &params->common, \
+	"cpu-list", \
+	"run the tracer only on the given cpus", \
+	opt_cpus_cb)
+
+#define RTLA_OPT_CGROUP OPT_CALLBACK_OPTARG('C', "cgroup", &params->common, \
+	"[cgroup_name]", NULL, \
+	"set cgroup, no argument means rtla's cgroup will be inherited", \
+	opt_cgroup_cb)
+
+#define RTLA_OPT_USER_THREADS OPT_CALLBACK_NOOPT('u', "user-threads", params, NULL, \
+	"use rtla user-space threads instead of kernel-space timerlat threads", \
+	opt_user_threads_cb)
+
+#define RTLA_OPT_KERNEL_THREADS OPT_BOOLEAN('k', "kernel-threads", \
+	&params->common.kernel_workload, \
+	"use timerlat kernel-space threads instead of rtla user-space threads")
+
+#define RTLA_OPT_USER_LOAD OPT_BOOLEAN('U', "user-load", &params->common.user_data, \
+	"enable timerlat for user-defined user-space workload")
+
+#define RTLA_OPT_DURATION OPT_CALLBACK('d', "duration", &params->common, \
+	"time[s|m|h|d]", \
+	"set the duration of the session", \
+	opt_duration_cb)
+
+#define RTLA_OPT_EVENT OPT_CALLBACK('e', "event", &params->common.events, \
+	"sys:event", \
+	"enable the <sys:event> in the trace instance, multiple -e are allowed", \
+	opt_event_cb)
+
+#define RTLA_OPT_HOUSEKEEPING OPT_CALLBACK('H', "house-keeping", &params->common, \
+	"cpu-list", \
+	"run rtla control threads only on the given cpus", \
+	opt_housekeeping_cb)
+
+#define RTLA_OPT_PRIORITY OPT_CALLBACK('P', "priority", &params->common, \
+	"o:prio|r:prio|f:prio|d:runtime:period", \
+	"set scheduling parameters", \
+	opt_priority_cb)
+
+#define RTLA_OPT_TRIGGER OPT_CALLBACK(0, "trigger", &params->common.events, \
+	"trigger", \
+	"enable a trace event trigger to the previous -e event", \
+	opt_trigger_cb)
+
+#define RTLA_OPT_FILTER OPT_CALLBACK(0, "filter", &params->common.events, \
+	"filter", \
+	"enable a trace event filter to the previous -e event", \
+	opt_filter_cb)
+
+#define RTLA_OPT_QUIET OPT_BOOLEAN('q', "quiet", &params->common.quiet, \
+	"print only a summary at the end")
+
+#define RTLA_OPT_TRACE_BUFFER_SIZE RTLA_OPT_INT(0, "trace-buffer-size", \
+	&params->common.buffer_size, "kB", \
+	"set the per-cpu trace buffer size in kB")
+
+#define RTLA_OPT_WARM_UP RTLA_OPT_INT(0, "warm-up", &params->common.warmup, "s", \
+	"let the workload run for s seconds before collecting data")
+
+#define RTLA_OPT_AUTO(cb) OPT_CALLBACK('a', "auto", &cb_data, "us", \
+	"set automatic trace mode, stopping the session if argument in us sample is hit", \
+	cb)
+
+#define RTLA_OPT_ON_THRESHOLD(threshold, cb) OPT_CALLBACK(0, "on-threshold", \
+	&params->common.threshold_actions, \
+	"action", \
+	"define action to be executed at " threshold " threshold, multiple are allowed", \
+	cb)
+
+#define RTLA_OPT_ON_END(cb) OPT_CALLBACK(0, "on-end", &params->common.end_actions, \
+	"action", \
+	"define action to be executed at measurement end, multiple are allowed", \
+	cb)
+
+#define RTLA_OPT_DEBUG OPT_BOOLEAN('D', "debug", &config_debug, \
+	"print debug info")
+
+/*
+ * Helper functions for parsing numeric option arguments.
+ */
+static void opt_err(const struct option *opt, const char *arg, const char *msg)
+{
+	fprintf(stderr, " Error: --%s: '%s' %s\n", opt->long_name, arg, msg);
+}
+
+static int strtoll_safe(const struct option *opt, const char *arg, long long *value)
+{
+	long long tmp;
+	char *end;
+
+	errno = 0;
+	tmp = strtoll(arg, &end, 10);
+	if (errno || *end || end == arg) {
+		opt_err(opt, arg, "is not a valid number");
+		return -1;
+	}
+	*value = tmp;
+	return 0;
+}
+
+static int strtoi_safe(const struct option *opt, const char *arg, int *value)
+{
+	int tmp;
+
+	if (strtoi(arg, &tmp)) {
+		opt_err(opt, arg, "is not a valid number");
+		return -1;
+	}
+	*value = tmp;
+	return 0;
+}
+
+/*
+ * Common callback functions for command line options
+ */
+
+static int opt_llong_callback(const struct option *opt, const char *arg, int unset)
+{
+	long long *value = opt->value;
+
+	if (unset) {
+		*value = opt->defval ? *(long long *)opt->defval : 0;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	if (strtoll_safe(opt, arg, value))
+		return -1;
+	if (check_llong_range(opt, *value))
+		return -1;
+	return 0;
+}
+
+static int opt_int_callback(const struct option *opt, const char *arg, int unset)
+{
+	int *value = opt->value;
+
+	if (unset) {
+		*value = (int)opt->defval;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	if (strtoi_safe(opt, arg, value))
+		return -1;
+	if (check_int_range(opt, *value))
+		return -1;
+
+	return 0;
+}
+
+static int opt_cpus_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct common_params *params = opt->value;
+	int retval;
+
+	if (unset) {
+		CPU_ZERO(&params->monitored_cpus);
+		params->cpus = NULL;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	retval = parse_cpu_set((char *)arg, &params->monitored_cpus);
+	if (retval) {
+		opt_err(opt, arg, "is not a valid cpu set");
+		return -1;
+	}
+	params->cpus = (char *)arg;
+
+	return 0;
+}
+
+static int opt_cgroup_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct common_params *params = opt->value;
+
+	if (unset) {
+		params->cgroup = 0;
+		params->cgroup_name = NULL;
+		return 0;
+	}
+
+	params->cgroup = 1;
+	params->cgroup_name = (char *)arg;
+	if (params->cgroup_name && params->cgroup_name[0] == '=')
+		/* Allow -C=<cgroup_name> next to -C[ ]<cgroup_name> */
+		++params->cgroup_name;
+
+	return 0;
+}
+
+static int opt_duration_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct common_params *params = opt->value;
+
+	if (unset) {
+		params->duration = 0;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	params->duration = parse_seconds_duration((char *)arg);
+	if (!params->duration) {
+		opt_err(opt, arg, "is not a valid duration");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int opt_event_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct trace_events **events = opt->value;
+	struct trace_events *tevent;
+
+	if (unset || !arg)
+		return -1;
+
+	tevent = trace_event_alloc((char *)arg);
+	if (!tevent)
+		fatal("Error alloc trace event");
+
+	if (*events)
+		tevent->next = *events;
+	*events = tevent;
+
+	return 0;
+}
+
+static int opt_housekeeping_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct common_params *params = opt->value;
+	int retval;
+
+	if (unset) {
+		params->hk_cpus = 0;
+		CPU_ZERO(&params->hk_cpu_set);
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	params->hk_cpus = 1;
+	retval = parse_cpu_set((char *)arg, &params->hk_cpu_set);
+	if (retval) {
+		opt_err(opt, arg, "is not a valid cpu set");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int opt_priority_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct common_params *params = opt->value;
+	int retval;
+
+	if (unset) {
+		memset(&params->sched_param, 0, sizeof(params->sched_param));
+		params->set_sched = 0;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	retval = parse_prio((char *)arg, &params->sched_param);
+	if (retval == -1) {
+		opt_err(opt, arg, "is not a valid priority");
+		return -1;
+	}
+	params->set_sched = 1;
+
+	return 0;
+}
+
+static int opt_trigger_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct trace_events **events = opt->value;
+
+	if (unset || !arg)
+		return -1;
+
+	if (!*events) {
+		opt_err(opt, arg, "has no previous event to apply to");
+		return -1;
+	}
+
+	trace_event_add_trigger(*events, (char *)arg);
+
+	return 0;
+}
+
+static int opt_filter_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct trace_events **events = opt->value;
+
+	if (unset || !arg)
+		return -1;
+
+	if (!*events) {
+		opt_err(opt, arg, "has no previous event to apply to");
+		return -1;
+	}
+
+	trace_event_add_filter(*events, (char *)arg);
+
+	return 0;
+}
+
+/*
+ * Macros for command line options specific to osnoise
+ */
+#define OSNOISE_OPT_PERIOD RTLA_OPT_LLONG_DATA('p', "period", &params->period, "us", \
+	"osnoise period in us", \
+	LLONG_RANGE(1, 10000000))
+
+#define OSNOISE_OPT_RUNTIME RTLA_OPT_LLONG_DATA('r', "runtime", &params->runtime, "us", \
+	"osnoise runtime in us", \
+	LLONG_RANGE(100, LLONG_MAX))
+
+#define OSNOISE_OPT_THRESHOLD RTLA_OPT_LLONG('T', "threshold", &params->threshold, "us", \
+	"the minimum delta to be considered a noise")
+
+/*
+ * Callback functions for command line options for osnoise tools
+ */
+
+static int opt_osnoise_auto_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct osnoise_cb_data *cb_data = opt->value;
+	struct osnoise_params *params = cb_data->params;
+	long long auto_thresh;
+
+	if (unset) {
+		params->common.stop_us = 0;
+		params->threshold = 0;
+		cb_data->trace_output = NULL;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	if (strtoll_safe(opt, arg, &auto_thresh))
+		return -1;
+	params->common.stop_us = auto_thresh;
+	params->threshold = 1;
+
+	if (!cb_data->trace_output)
+		cb_data->trace_output = "osnoise_trace.txt";
+
+	return 0;
+}
+
+static int opt_osnoise_trace_output_cb(const struct option *opt, const char *arg, int unset)
+{
+	const char **trace_output = opt->value;
+
+	if (unset) {
+		*trace_output = NULL;
+		return 0;
+	}
+
+	if (!arg) {
+		*trace_output = "osnoise_trace.txt";
+	} else {
+		*trace_output = (char *)arg;
+		if (*trace_output && (*trace_output)[0] == '=')
+			/* Allow -t=<trace_output> next to -t[ ]<trace_output> */
+			++*trace_output;
+	}
+
+	return 0;
+}
+
+static int opt_osnoise_on_threshold_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct actions *actions = opt->value;
+	int retval;
+
+	if (unset || !arg)
+		return -1;
+
+	retval = actions_parse(actions, (char *)arg, "osnoise_trace.txt");
+	if (retval) {
+		opt_err(opt, arg, "is not a valid action");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int opt_osnoise_on_end_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct actions *actions = opt->value;
+	int retval;
+
+	if (unset || !arg)
+		return -1;
+
+	retval = actions_parse(actions, (char *)arg, "osnoise_trace.txt");
+	if (retval) {
+		opt_err(opt, arg, "is not a valid action");
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * Macros for command line options specific to timerlat
+ */
+#define TIMERLAT_OPT_PERIOD RTLA_OPT_LLONG_DATA('p', "period", &params->timerlat_period_us, "us", \
+	"timerlat period in us", \
+	LLONG_RANGE(100, 1000000))
+
+#define TIMERLAT_OPT_STACK RTLA_OPT_LLONG('s', "stack", &params->print_stack, "us", \
+	"save the stack trace at the IRQ if a thread latency is higher than the argument in us")
+
+#define TIMERLAT_OPT_NANO OPT_CALLBACK_NOOPT('n', "nano", params, NULL, \
+	"display data in nanoseconds", \
+	opt_nano_cb)
+
+#define TIMERLAT_OPT_DMA_LATENCY RTLA_OPT_INT_DATA_DEFVAL(0, "dma-latency", \
+	&params->dma_latency, "us", \
+	"set /dev/cpu_dma_latency latency <us> to reduce exit from idle latency", \
+	INT_RANGE(0, 10000), default_dma_latency)
+
+#define TIMERLAT_OPT_DEEPEST_IDLE_STATE RTLA_OPT_INT_DATA_DEFVAL(0, "deepest-idle-state", \
+	&params->deepest_idle_state, "n", \
+	"only go down to idle state n on cpus used by timerlat to reduce exit from idle latency", \
+	INT_RANGE(-1, INT_MAX), default_deepest_idle_state)
+
+#define TIMERLAT_OPT_AA_ONLY OPT_CALLBACK(0, "aa-only", params, "us", \
+	"stop if <us> latency is hit, only printing the auto analysis (reduces CPU usage)", \
+	opt_aa_only_cb)
+
+#define TIMERLAT_OPT_NO_AA OPT_BOOLEAN(0, "no-aa", &params->no_aa, \
+	"disable auto-analysis, reducing rtla timerlat cpu usage")
+
+#define TIMERLAT_OPT_DUMPS_TASKS OPT_BOOLEAN(0, "dump-tasks", &params->dump_tasks, \
+	"prints the task running on all CPUs if stop conditions are met (depends on !--no-aa)")
+
+#define TIMERLAT_OPT_BPF_ACTION OPT_STRING(0, "bpf-action", &params->bpf_action_program, \
+	"program", \
+	"load and execute BPF program when latency threshold is exceeded")
+
+#define TIMERLAT_OPT_STACK_FORMAT OPT_CALLBACK(0, "stack-format", &params->stack_format, "format", \
+	"set the stack format (truncate, skip, full)", \
+	opt_stack_format_cb)
+
+#define TIMERLAT_OPT_ALIGNED RTLA_OPT_CALLBACK_DATA('A', "aligned", params, "us", \
+	"align thread wakeups to a specific offset", \
+	opt_timerlat_align_cb, LLONG_RANGE(0, LLONG_MAX))
+
+/*
+ * Callback functions for command line options for timerlat tools
+ */
+
+static int opt_timerlat_auto_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct timerlat_cb_data *cb_data = opt->value;
+	struct timerlat_params *params = cb_data->params;
+	long long auto_thresh;
+
+	if (unset) {
+		params->common.stop_total_us = 0;
+		params->common.stop_us = 0;
+		params->print_stack = 0;
+		cb_data->trace_output = NULL;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	if (strtoll_safe(opt, arg, &auto_thresh))
+		return -1;
+	params->common.stop_total_us = auto_thresh;
+	params->common.stop_us = auto_thresh;
+	params->print_stack = auto_thresh;
+
+	if (!cb_data->trace_output)
+		cb_data->trace_output = "timerlat_trace.txt";
+
+	return 0;
+}
+
+static int opt_aa_only_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct timerlat_params *params = opt->value;
+	long long auto_thresh;
+
+	if (unset) {
+		params->common.stop_total_us = 0;
+		params->common.stop_us = 0;
+		params->print_stack = 0;
+		params->common.aa_only = 0;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	if (strtoll_safe(opt, arg, &auto_thresh))
+		return -1;
+	params->common.stop_total_us = auto_thresh;
+	params->common.stop_us = auto_thresh;
+	params->print_stack = auto_thresh;
+	params->common.aa_only = 1;
+
+	return 0;
+}
+
+static int opt_timerlat_trace_output_cb(const struct option *opt, const char *arg, int unset)
+{
+	const char **trace_output = opt->value;
+
+	if (unset) {
+		*trace_output = NULL;
+		return 0;
+	}
+
+	if (!arg) {
+		*trace_output = "timerlat_trace.txt";
+	} else {
+		*trace_output = (char *)arg;
+		if (*trace_output && (*trace_output)[0] == '=')
+			/* Allow -t=<trace_output> next to -t[ ]<trace_output> */
+			++*trace_output;
+	}
+
+	return 0;
+}
+
+static int opt_timerlat_on_threshold_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct actions *actions = opt->value;
+	int retval;
+
+	if (unset || !arg)
+		return -1;
+
+	retval = actions_parse(actions, (char *)arg, "timerlat_trace.txt");
+	if (retval) {
+		opt_err(opt, arg, "is not a valid action");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int opt_timerlat_on_end_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct actions *actions = opt->value;
+	int retval;
+
+	if (unset || !arg)
+		return -1;
+
+	retval = actions_parse(actions, (char *)arg, "timerlat_trace.txt");
+	if (retval) {
+		opt_err(opt, arg, "is not a valid action");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int opt_user_threads_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct timerlat_params *params = opt->value;
+
+	if (unset) {
+		params->common.user_workload = false;
+		params->common.user_data = false;
+		return 0;
+	}
+
+	params->common.user_workload = true;
+	params->common.user_data = true;
+
+	return 0;
+}
+
+static int opt_nano_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct timerlat_params *params = opt->value;
+
+	if (unset) {
+		params->common.output_divisor = default_output_divisor;
+		return 0;
+	}
+
+	params->common.output_divisor = 1;
+
+	return 0;
+}
+
+static int opt_stack_format_cb(const struct option *opt, const char *arg, int unset)
+{
+	int *format = opt->value;
+
+	if (unset) {
+		*format = default_stack_format;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	*format = parse_stack_format((char *)arg);
+
+	if (*format == -1) {
+		opt_err(opt, arg, "is not a valid stack format");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int opt_timerlat_align_cb(const struct option *opt, const char *arg, int unset)
+{
+	struct timerlat_params *params = opt->value;
+	long long val;
+
+	if (unset) {
+		params->timerlat_align = false;
+		params->timerlat_align_us = 0;
+		return 0;
+	}
+
+	if (!arg)
+		return -1;
+
+	if (strtoll_safe(opt, arg, &val))
+		return -1;
+	if (check_llong_range(opt, val))
+		return -1;
+
+	params->timerlat_align = true;
+	params->timerlat_align_us = val;
+
+	return 0;
+}
+
+/*
+ * Macros for command line options specific to histogram-based tools
+ */
+
+#define HIST_OPT_BUCKET_SIZE RTLA_OPT_INT_DATA_DEFVAL('b', "bucket-size", \
+	&params->common.hist.bucket_size, "N", \
+	"set the histogram bucket size (default 1)", \
+	INT_RANGE(1, 999999), default_bucket_size)
+
+#define HIST_OPT_ENTRIES RTLA_OPT_INT_DATA_DEFVAL('E', "entries", \
+	&params->common.hist.entries, "N", \
+	"set the number of entries of the histogram (default 256)", \
+	INT_RANGE(10, 9999999), default_entries)
+
+#define HIST_OPT_NO_IRQ OPT_BOOLEAN_FLAG(0, "no-irq", &params->common.hist.no_irq, \
+	"ignore IRQ latencies", PARSE_OPT_NOAUTONEG)
+
+#define HIST_OPT_NO_THREAD OPT_BOOLEAN_FLAG(0, "no-thread", &params->common.hist.no_thread, \
+	"ignore thread latencies", PARSE_OPT_NOAUTONEG)
+
+#define HIST_OPT_NO_HEADER OPT_BOOLEAN(0, "no-header", &params->common.hist.no_header, \
+	"do not print header")
+
+#define HIST_OPT_NO_SUMMARY OPT_BOOLEAN(0, "no-summary", &params->common.hist.no_summary, \
+	"do not print summary")
+
+#define HIST_OPT_NO_INDEX OPT_BOOLEAN(0, "no-index", &params->common.hist.no_index, \
+	"do not print index")
+
+#define HIST_OPT_WITH_ZEROS OPT_BOOLEAN(0, "with-zeros", &params->common.hist.with_zeros, \
+	"print zero only entries")
+
diff --git a/tools/tracing/rtla/src/common.c b/tools/tracing/rtla/src/common.c
new file mode 100644
index 000000000..8c7f5e75b
--- /dev/null
+++ b/tools/tracing/rtla/src/common.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <pthread.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/sysinfo.h>
+
+#include "common.h"
+
+struct osnoise_tool *trace_tool;
+volatile int stop_tracing;
+int nr_cpus;
+
+static void stop_trace(int sig)
+{
+	if (stop_tracing) {
+		/*
+		 * Stop requested twice in a row; abort event processing and
+		 * exit immediately
+		 */
+		if (trace_tool)
+			tracefs_iterate_stop(trace_tool->trace.inst);
+		return;
+	}
+	stop_tracing = 1;
+	if (trace_tool) {
+		trace_instance_stop(&trace_tool->trace);
+		if (trace_tool->record)
+			trace_instance_stop(&trace_tool->record->trace);
+	}
+}
+
+/*
+ * set_signals - handles the signal to stop the tool
+ */
+static void set_signals(struct common_params *params)
+{
+	signal(SIGINT, stop_trace);
+	if (params->duration) {
+		signal(SIGALRM, stop_trace);
+		alarm(params->duration);
+	}
+}
+
+/*
+ * unset_signals - unsets the signals to stop the tool
+ */
+static void unset_signals(struct common_params *params)
+{
+	signal(SIGINT, SIG_DFL);
+	if (params->duration) {
+		alarm(0);
+		signal(SIGALRM, SIG_DFL);
+	}
+}
+
+/*
+ * common_apply_config - apply common configs to the initialized tool
+ */
+int
+common_apply_config(struct osnoise_tool *tool, struct common_params *params)
+{
+	int retval, i;
+
+	if (!params->sleep_time)
+		params->sleep_time = 1;
+
+	retval = osnoise_set_cpus(tool->context, params->cpus ? params->cpus : "all");
+	if (retval) {
+		err_msg("Failed to apply CPUs config\n");
+		goto out_err;
+	}
+
+	if (!params->cpus) {
+		for (i = 0; i < nr_cpus; i++)
+			CPU_SET(i, &params->monitored_cpus);
+	}
+
+	if (params->hk_cpus) {
+		retval = sched_setaffinity(getpid(), sizeof(params->hk_cpu_set),
+					   &params->hk_cpu_set);
+		if (retval == -1) {
+			err_msg("Failed to set rtla to the house keeping CPUs\n");
+			goto out_err;
+		}
+	} else if (params->cpus) {
+		/*
+		 * Even if the user do not set a house-keeping CPU, try to
+		 * move rtla to a CPU set different to the one where the user
+		 * set the workload to run.
+		 *
+		 * No need to check results as this is an automatic attempt.
+		 */
+		auto_house_keeping(&params->monitored_cpus);
+	}
+
+	/*
+	 * Set workload according to type of thread if the kernel supports it.
+	 * On kernels without support, user threads will have already failed
+	 * on missing fd, and kernel threads do not need it.
+	 */
+	retval = osnoise_set_workload(tool->context, params->kernel_workload);
+	if (retval < -1) {
+		err_msg("Failed to set OSNOISE_WORKLOAD option\n");
+		goto out_err;
+	}
+
+	return 0;
+
+out_err:
+	return -1;
+}
+
+
+/**
+ * common_threshold_handler - handle latency threshold overflow
+ * @tool: pointer to the osnoise_tool instance containing trace contexts
+ *
+ * Executes the configured threshold actions (e.g., saving trace, printing,
+ * sending signals). If the continue flag is set (--on-threshold continue),
+ * restarts the auxiliary trace instances to continue monitoring.
+ *
+ * Return: 0 for success, -1 for error.
+ */
+int
+common_threshold_handler(const struct osnoise_tool *tool)
+{
+	actions_perform(&tool->params->threshold_actions);
+
+	if (!should_continue_tracing(tool->params))
+		/* continue flag not set, break */
+		return 0;
+
+	/* continue action reached, re-enable tracing */
+	if (tool->record && trace_instance_start(&tool->record->trace))
+		goto err;
+	if (tool->aa && trace_instance_start(&tool->aa->trace))
+		goto err;
+
+	return 0;
+
+err:
+	err_msg("Error restarting trace\n");
+	return -1;
+}
+
+int run_tool(struct tool_ops *ops, int argc, char *argv[])
+{
+	struct common_params *params;
+	enum result return_value = ERROR;
+	struct osnoise_tool *tool;
+	bool stopped;
+	int retval;
+
+	nr_cpus = get_nprocs_conf();
+	params = ops->parse_args(argc, argv);
+	if (!params)
+		exit(1);
+
+	tool = ops->init_tool(params);
+	if (!tool) {
+		err_msg("Could not init osnoise tool\n");
+		goto out_exit;
+	}
+	tool->ops = ops;
+	tool->params = params;
+
+	/*
+	 * Expose the tool to signal handlers so they can stop the trace.
+	 * Otherwise, rtla could loop indefinitely when overloaded.
+	 */
+	trace_tool = tool;
+
+	retval = ops->apply_config(tool);
+	if (retval) {
+		err_msg("Could not apply config\n");
+		goto out_free;
+	}
+
+	retval = enable_tracer_by_name(tool->trace.inst, ops->tracer);
+	if (retval) {
+		err_msg("Failed to enable %s tracer\n", ops->tracer);
+		goto out_free;
+	}
+
+	if (params->set_sched) {
+		retval = set_comm_sched_attr(ops->comm_prefix, &params->sched_param);
+		if (retval) {
+			err_msg("Failed to set sched parameters\n");
+			goto out_free;
+		}
+	}
+
+	if (params->cgroup && !params->user_data) {
+		retval = set_comm_cgroup(ops->comm_prefix, params->cgroup_name);
+		if (!retval) {
+			err_msg("Failed to move threads to cgroup\n");
+			goto out_free;
+		}
+	}
+
+
+	if (params->threshold_actions.present[ACTION_TRACE_OUTPUT] ||
+	    params->end_actions.present[ACTION_TRACE_OUTPUT]) {
+		tool->record = osnoise_init_trace_tool(ops->tracer);
+		if (!tool->record) {
+			err_msg("Failed to enable the trace instance\n");
+			goto out_free;
+		}
+		params->threshold_actions.trace_output_inst = tool->record->trace.inst;
+		params->end_actions.trace_output_inst = tool->record->trace.inst;
+
+		if (params->events) {
+			retval = trace_events_enable(&tool->record->trace, params->events);
+			if (retval)
+				goto out_trace;
+		}
+
+		if (params->buffer_size > 0) {
+			retval = trace_set_buffer_size(&tool->record->trace, params->buffer_size);
+			if (retval)
+				goto out_trace;
+		}
+	}
+
+	if (params->user_workload) {
+		pthread_t user_thread;
+
+		/* rtla asked to stop */
+		params->user.should_run = 1;
+		/* all threads left */
+		params->user.stopped_running = 0;
+
+		params->user.set = &params->monitored_cpus;
+		if (params->set_sched)
+			params->user.sched_param = &params->sched_param;
+		else
+			params->user.sched_param = NULL;
+
+		params->user.cgroup_name = params->cgroup_name;
+
+		retval = pthread_create(&user_thread, NULL, timerlat_u_dispatcher, &params->user);
+		if (retval) {
+			err_msg("Error creating timerlat user-space threads\n");
+			goto out_trace;
+		}
+	}
+
+	retval = ops->enable(tool);
+	if (retval)
+		goto out_trace;
+
+	tool->start_time = time(NULL);
+	set_signals(params);
+
+	retval = ops->main(tool);
+	if (retval)
+		goto out_signals;
+
+	if (params->user_workload && !params->user.stopped_running) {
+		params->user.should_run = 0;
+		sleep(1);
+	}
+
+	ops->print_stats(tool);
+
+	actions_perform(&params->end_actions);
+
+	return_value = PASSED;
+
+	stopped = osnoise_trace_is_off(tool, tool->record) && !stop_tracing;
+	if (stopped) {
+		printf("%s hit stop tracing\n", ops->tracer);
+		return_value = FAILED;
+	}
+
+	if (ops->analyze)
+		ops->analyze(tool, stopped);
+
+out_signals:
+	unset_signals(params);
+out_trace:
+	trace_events_destroy(&tool->record->trace, params->events);
+	params->events = NULL;
+out_free:
+	ops->free(tool);
+	osnoise_destroy_tool(tool->record);
+	osnoise_destroy_tool(tool);
+	actions_destroy(&params->threshold_actions);
+	actions_destroy(&params->end_actions);
+	free(params);
+out_exit:
+	exit(return_value);
+}
+
+int top_main_loop(struct osnoise_tool *tool)
+{
+	struct common_params *params = tool->params;
+	struct trace_instance *trace = &tool->trace;
+	struct osnoise_tool *record = tool->record;
+	int retval;
+
+	while (!stop_tracing) {
+		sleep(params->sleep_time);
+
+		if (params->aa_only && !osnoise_trace_is_off(tool, record))
+			continue;
+
+		retval = tracefs_iterate_raw_events(trace->tep,
+						    trace->inst,
+						    NULL,
+						    0,
+						    collect_registered_events,
+						    trace);
+		if (retval < 0) {
+			err_msg("Error iterating on events\n");
+			return retval;
+		}
+
+		if (!params->quiet)
+			tool->ops->print_stats(tool);
+
+		if (osnoise_trace_is_off(tool, record)) {
+			if (stop_tracing)
+				/* stop tracing requested, do not perform actions */
+				return 0;
+
+			retval = common_threshold_handler(tool);
+			if (retval)
+				return retval;
+
+
+			if (!should_continue_tracing(params))
+				return 0;
+
+			trace_instance_start(trace);
+		}
+
+		/* is there still any user-threads ? */
+		if (params->user_workload) {
+			if (params->user.stopped_running) {
+				debug_msg("timerlat user space threads stopped!\n");
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+int hist_main_loop(struct osnoise_tool *tool)
+{
+	struct common_params *params = tool->params;
+	struct trace_instance *trace = &tool->trace;
+	int retval = 0;
+
+	while (!stop_tracing) {
+		sleep(params->sleep_time);
+
+		retval = tracefs_iterate_raw_events(trace->tep,
+						    trace->inst,
+						    NULL,
+						    0,
+						    collect_registered_events,
+						    trace);
+		if (retval < 0) {
+			err_msg("Error iterating on events\n");
+			break;
+		}
+
+		if (osnoise_trace_is_off(tool, tool->record)) {
+			if (stop_tracing)
+				/* stop tracing requested, do not perform actions */
+				break;
+
+			retval = common_threshold_handler(tool);
+			if (retval)
+				return retval;
+
+			if (!should_continue_tracing(params))
+				return 0;
+
+			trace_instance_start(trace);
+		}
+
+		/* is there still any user-threads ? */
+		if (params->user_workload) {
+			if (params->user.stopped_running) {
+				debug_msg("user-space threads stopped!\n");
+				break;
+			}
+		}
+	}
+
+	return retval;
+}
+
+int osn_set_stop(struct osnoise_tool *tool)
+{
+	struct common_params *params = tool->params;
+	int retval;
+
+	retval = osnoise_set_stop_us(tool->context, params->stop_us);
+	if (retval) {
+		err_msg("Failed to set stop us\n");
+		return retval;
+	}
+
+	retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
+	if (retval) {
+		err_msg("Failed to set stop total us\n");
+		return retval;
+	}
+
+	return 0;
+}
+
+static void print_msg_array(const char * const *msgs)
+{
+	if (!msgs)
+		return;
+
+	for (int i = 0; msgs[i]; i++)
+		fprintf(stderr, "%s\n", msgs[i]);
+}
+
+/*
+ * common_usage - print complete usage information
+ */
+void common_usage(const char *tool, const char *mode,
+		  const char *desc, const char * const *start_msgs, const char * const *opt_msgs)
+{
+	static const char * const common_options[] = {
+		"	  -h/--help: print this menu",
+		NULL
+	};
+	fprintf(stderr, "rtla %s", tool);
+	if (strcmp(mode, ""))
+		fprintf(stderr, " %s", mode);
+	fprintf(stderr, ": %s (version %s)\n\n", desc, VERSION);
+	fprintf(stderr, "  usage: [rtla] %s ", tool);
+
+	if (strcmp(mode, "top") == 0)
+		fprintf(stderr, "[top] [-h] ");
+	else
+		fprintf(stderr, "%s [-h] ", mode);
+
+	print_msg_array(start_msgs);
+	fprintf(stderr, "\n");
+	print_msg_array(common_options);
+	print_msg_array(opt_msgs);
+
+	exit(EXIT_SUCCESS);
+}
diff --git a/tools/tracing/rtla/src/common.h b/tools/tracing/rtla/src/common.h
new file mode 100644
index 000000000..04b287a03
--- /dev/null
+++ b/tools/tracing/rtla/src/common.h
@@ -0,0 +1,192 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+
+#include "actions.h"
+#include "timerlat_u.h"
+#include "trace.h"
+#include "utils.h"
+
+/*
+ * osnoise_context - read, store, write, restore osnoise configs.
+ */
+struct osnoise_context {
+	int			flags;
+	int			ref;
+
+	char			*curr_cpus;
+	char			*orig_cpus;
+
+	/* 0 as init value */
+	unsigned long long	orig_runtime_us;
+	unsigned long long	runtime_us;
+
+	/* 0 as init value */
+	unsigned long long	orig_period_us;
+	unsigned long long	period_us;
+
+	/* 0 as init value */
+	long long		orig_timerlat_period_us;
+	long long		timerlat_period_us;
+
+	/* 0 as init value */
+	long long		orig_tracing_thresh;
+	long long		tracing_thresh;
+
+	/* -1 as init value because 0 is disabled */
+	long long		orig_stop_us;
+	long long		stop_us;
+
+	/* -1 as init value because 0 is disabled */
+	long long		orig_stop_total_us;
+	long long		stop_total_us;
+
+	/* -1 as init value because 0 is disabled */
+	long long		orig_print_stack;
+	long long		print_stack;
+
+	/* -1 as init value because 0 is off */
+	int			orig_opt_irq_disable;
+	int			opt_irq_disable;
+
+	/* -1 as init value because 0 is off */
+	int			orig_opt_workload;
+	int			opt_workload;
+
+	/* -1 as init value because 0 is off */
+	int			orig_opt_timerlat_align;
+	int			opt_timerlat_align;
+
+	/* 0 as init value */
+	unsigned long long	orig_timerlat_align_us;
+	unsigned long long	timerlat_align_us;
+};
+
+extern volatile int stop_tracing;
+
+struct hist_params {
+	bool			no_irq;
+	bool			no_thread;
+	bool			no_header;
+	bool			no_summary;
+	bool			no_index;
+	bool			with_zeros;
+	int			bucket_size;
+	int			entries;
+};
+
+/*
+ * common_params - Parameters shared between timerlat_params and osnoise_params
+ */
+struct common_params {
+	/* trace configuration */
+	char			*cpus;
+	cpu_set_t		monitored_cpus;
+	struct trace_events	*events;
+	int			buffer_size;
+
+	/* Timing parameters */
+	int			warmup;
+	long long		stop_us;
+	long long		stop_total_us;
+	int			sleep_time;
+	int			duration;
+
+	/* Scheduling parameters */
+	int			set_sched;
+	struct sched_attr	sched_param;
+	int			cgroup;
+	char			*cgroup_name;
+	int			hk_cpus;
+	cpu_set_t		hk_cpu_set;
+
+	/* Other parameters */
+	struct hist_params	hist;
+	int			output_divisor;
+	bool			pretty_output;
+	bool			quiet;
+	bool			user_workload;
+	bool			kernel_workload;
+	bool			user_data;
+	bool			aa_only;
+
+	struct actions		threshold_actions;
+	struct actions		end_actions;
+	struct timerlat_u_params user;
+};
+
+extern int nr_cpus;
+
+#define for_each_monitored_cpu(cpu, common) \
+	for (cpu = 0; cpu < nr_cpus; cpu++) \
+		if (!(common)->cpus || CPU_ISSET(cpu, &(common)->monitored_cpus))
+
+struct tool_ops;
+
+/*
+ * osnoise_tool -  osnoise based tool definition.
+ *
+ * Only the "trace" and "context" fields are used for
+ * the additional trace instances (record and aa).
+ */
+struct osnoise_tool {
+	struct tool_ops			*ops;
+	struct trace_instance		trace;
+	struct osnoise_context		*context;
+	void				*data;
+	struct common_params		*params;
+	time_t				start_time;
+	struct osnoise_tool		*record;
+	struct osnoise_tool		*aa;
+};
+
+struct tool_ops {
+	const char *tracer;
+	const char *comm_prefix;
+	struct common_params *(*parse_args)(int argc, char *argv[]);
+	struct osnoise_tool *(*init_tool)(struct common_params *params);
+	int (*apply_config)(struct osnoise_tool *tool);
+	int (*enable)(struct osnoise_tool *tool);
+	int (*main)(struct osnoise_tool *tool);
+	void (*print_stats)(struct osnoise_tool *tool);
+	void (*analyze)(struct osnoise_tool *tool, bool stopped);
+	void (*free)(struct osnoise_tool *tool);
+};
+
+/**
+ * should_continue_tracing - check if tracing should continue after threshold
+ * @params: pointer to the common parameters structure
+ *
+ * Returns true if the continue action was configured (--on-threshold continue),
+ * indicating that tracing should be restarted after handling the threshold event.
+ *
+ * Return: 1 if tracing should continue, 0 otherwise.
+ */
+static inline int
+should_continue_tracing(const struct common_params *params)
+{
+	return params->threshold_actions.continue_flag;
+}
+
+int
+common_threshold_handler(const struct osnoise_tool *tool);
+
+int osnoise_set_cpus(struct osnoise_context *context, char *cpus);
+void osnoise_restore_cpus(struct osnoise_context *context);
+
+int osnoise_set_workload(struct osnoise_context *context, bool onoff);
+
+void osnoise_destroy_tool(struct osnoise_tool *top);
+struct osnoise_tool *osnoise_init_tool(char *tool_name);
+struct osnoise_tool *osnoise_init_trace_tool(const char *tracer);
+bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record);
+int osnoise_set_stop_us(struct osnoise_context *context, long long stop_us);
+int osnoise_set_stop_total_us(struct osnoise_context *context,
+			      long long stop_total_us);
+
+int common_apply_config(struct osnoise_tool *tool, struct common_params *params);
+int top_main_loop(struct osnoise_tool *tool);
+int hist_main_loop(struct osnoise_tool *tool);
+int osn_set_stop(struct osnoise_tool *tool);
+
+void common_usage(const char *tool, const char *mode,
+		  const char *desc, const char * const *start_msgs, const char * const *opt_msgs);
diff --git a/tools/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c
new file mode 100644
index 000000000..4ff5dad01
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise.c
@@ -0,0 +1,1384 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <sched.h>
+
+#include <linux/compiler.h>
+
+#include "osnoise.h"
+
+#define DEFAULT_SAMPLE_PERIOD	1000000			/* 1s */
+#define DEFAULT_SAMPLE_RUNTIME	1000000			/* 1s */
+
+/*
+ * osnoise_get_cpus - return the original "osnoise/cpus" content
+ *
+ * It also saves the value to be restored.
+ */
+char *osnoise_get_cpus(struct osnoise_context *context)
+{
+	if (context->curr_cpus)
+		return context->curr_cpus;
+
+	if (context->orig_cpus)
+		return context->orig_cpus;
+
+	context->orig_cpus = tracefs_instance_file_read(NULL, "osnoise/cpus", NULL);
+
+	/*
+	 * The error value (NULL) is the same for tracefs_instance_file_read()
+	 * and this functions, so:
+	 */
+	return context->orig_cpus;
+}
+
+/*
+ * osnoise_set_cpus - configure osnoise to run on *cpus
+ *
+ * "osnoise/cpus" file is used to set the cpus in which osnoise/timerlat
+ * will run. This function opens this file, saves the current value,
+ * and set the cpus passed as argument.
+ */
+int osnoise_set_cpus(struct osnoise_context *context, char *cpus)
+{
+	char *orig_cpus = osnoise_get_cpus(context);
+	char buffer[1024];
+	int retval;
+
+	if (!orig_cpus)
+		return -1;
+
+	context->curr_cpus = strdup(cpus);
+	if (!context->curr_cpus)
+		return -1;
+
+	snprintf(buffer, ARRAY_SIZE(buffer), "%s\n", cpus);
+
+	debug_msg("setting cpus to %s from %s", cpus, context->orig_cpus);
+
+	retval = tracefs_instance_file_write(NULL, "osnoise/cpus", buffer);
+	if (retval < 0) {
+		free(context->curr_cpus);
+		context->curr_cpus = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_cpus - restore the original "osnoise/cpus"
+ *
+ * osnoise_set_cpus() saves the original data for the "osnoise/cpus"
+ * file. This function restore the original config it was previously
+ * modified.
+ */
+void osnoise_restore_cpus(struct osnoise_context *context)
+{
+	int retval;
+
+	if (!context->orig_cpus)
+		return;
+
+	if (!context->curr_cpus)
+		return;
+
+	/* nothing to do? */
+	if (!strcmp(context->orig_cpus, context->curr_cpus))
+		goto out_done;
+
+	debug_msg("restoring cpus to %s", context->orig_cpus);
+
+	retval = tracefs_instance_file_write(NULL, "osnoise/cpus", context->orig_cpus);
+	if (retval < 0)
+		err_msg("could not restore original osnoise cpus\n");
+
+out_done:
+	free(context->curr_cpus);
+	context->curr_cpus = NULL;
+}
+
+/*
+ * osnoise_put_cpus - restore cpus config and cleanup data
+ */
+void osnoise_put_cpus(struct osnoise_context *context)
+{
+	osnoise_restore_cpus(context);
+
+	if (!context->orig_cpus)
+		return;
+
+	free(context->orig_cpus);
+	context->orig_cpus = NULL;
+}
+
+/*
+ * osnoise_read_ll_config - read a long long value from a config
+ *
+ * returns -1 on error.
+ */
+static long long osnoise_read_ll_config(char *rel_path)
+{
+	long long retval;
+	char *buffer;
+
+	buffer = tracefs_instance_file_read(NULL, rel_path, NULL);
+	if (!buffer)
+		return -1;
+
+	/* get_llong_from_str returns -1 on error */
+	retval = get_llong_from_str(buffer);
+
+	debug_msg("reading %s returned %lld\n", rel_path, retval);
+
+	free(buffer);
+
+	return retval;
+}
+
+/*
+ * osnoise_write_ll_config - write a long long value to a config in rel_path
+ *
+ * returns -1 on error.
+ */
+static long long osnoise_write_ll_config(char *rel_path, long long value)
+{
+	char buffer[BUFF_U64_STR_SIZE];
+	long long retval;
+
+	snprintf(buffer, sizeof(buffer), "%lld\n", value);
+
+	debug_msg("setting %s to %lld\n", rel_path, value);
+
+	retval = tracefs_instance_file_write(NULL, rel_path, buffer);
+	return retval;
+}
+
+/*
+ * osnoise_get_runtime - return the original "osnoise/runtime_us" value
+ *
+ * It also saves the value to be restored.
+ */
+unsigned long long osnoise_get_runtime(struct osnoise_context *context)
+{
+	long long runtime_us;
+
+	if (context->runtime_us != OSNOISE_TIME_INIT_VAL)
+		return context->runtime_us;
+
+	if (context->orig_runtime_us != OSNOISE_TIME_INIT_VAL)
+		return context->orig_runtime_us;
+
+	runtime_us = osnoise_read_ll_config("osnoise/runtime_us");
+	if (runtime_us < 0)
+		goto out_err;
+
+	context->orig_runtime_us = runtime_us;
+	return runtime_us;
+
+out_err:
+	return OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_get_period - return the original "osnoise/period_us" value
+ *
+ * It also saves the value to be restored.
+ */
+unsigned long long osnoise_get_period(struct osnoise_context *context)
+{
+	long long period_us;
+
+	if (context->period_us != OSNOISE_TIME_INIT_VAL)
+		return context->period_us;
+
+	if (context->orig_period_us != OSNOISE_TIME_INIT_VAL)
+		return context->orig_period_us;
+
+	period_us = osnoise_read_ll_config("osnoise/period_us");
+	if (period_us < 0)
+		goto out_err;
+
+	context->orig_period_us = period_us;
+	return period_us;
+
+out_err:
+	return OSNOISE_TIME_INIT_VAL;
+}
+
+static int __osnoise_write_runtime(struct osnoise_context *context,
+				   unsigned long long runtime)
+{
+	int retval;
+
+	if (context->orig_runtime_us == OSNOISE_TIME_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("osnoise/runtime_us", runtime);
+	if (retval < 0)
+		return -1;
+
+	context->runtime_us = runtime;
+	return 0;
+}
+
+static int __osnoise_write_period(struct osnoise_context *context,
+				  unsigned long long period)
+{
+	int retval;
+
+	if (context->orig_period_us == OSNOISE_TIME_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("osnoise/period_us", period);
+	if (retval < 0)
+		return -1;
+
+	context->period_us = period;
+	return 0;
+}
+
+/*
+ * osnoise_set_runtime_period - set osnoise runtime and period
+ *
+ * Osnoise's runtime and period are related as runtime <= period.
+ * Thus, this function saves the original values, and then tries
+ * to set the runtime and period if they are != 0.
+ */
+int osnoise_set_runtime_period(struct osnoise_context *context,
+			       unsigned long long runtime,
+			       unsigned long long period)
+{
+	unsigned long long curr_runtime_us;
+	unsigned long long curr_period_us;
+	int retval;
+
+	if (!period && !runtime)
+		return 0;
+
+	curr_runtime_us = osnoise_get_runtime(context);
+	curr_period_us = osnoise_get_period(context);
+
+	/* error getting any value? */
+	if (curr_period_us == OSNOISE_TIME_INIT_VAL || curr_runtime_us == OSNOISE_TIME_INIT_VAL)
+		return -1;
+
+	if (!period) {
+		if (runtime > curr_period_us)
+			return -1;
+		return __osnoise_write_runtime(context, runtime);
+	} else if (!runtime) {
+		if (period < curr_runtime_us)
+			return -1;
+		return __osnoise_write_period(context, period);
+	}
+
+	if (runtime > curr_period_us) {
+		retval = __osnoise_write_period(context, period);
+		if (retval)
+			return -1;
+		retval = __osnoise_write_runtime(context, runtime);
+		if (retval)
+			return -1;
+	} else {
+		retval = __osnoise_write_runtime(context, runtime);
+		if (retval)
+			return -1;
+		retval = __osnoise_write_period(context, period);
+		if (retval)
+			return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_runtime_period - restore the original runtime and period
+ */
+void osnoise_restore_runtime_period(struct osnoise_context *context)
+{
+	unsigned long long orig_runtime = context->orig_runtime_us;
+	unsigned long long orig_period = context->orig_period_us;
+	unsigned long long curr_runtime = context->runtime_us;
+	unsigned long long curr_period = context->period_us;
+	int retval;
+
+	if ((orig_runtime == OSNOISE_TIME_INIT_VAL) && (orig_period == OSNOISE_TIME_INIT_VAL))
+		return;
+
+	if ((orig_period == curr_period) && (orig_runtime == curr_runtime))
+		goto out_done;
+
+	retval = osnoise_set_runtime_period(context, orig_runtime, orig_period);
+	if (retval)
+		err_msg("Could not restore original osnoise runtime/period\n");
+
+out_done:
+	context->runtime_us = OSNOISE_TIME_INIT_VAL;
+	context->period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_put_runtime_period - restore original values and cleanup data
+ */
+void osnoise_put_runtime_period(struct osnoise_context *context)
+{
+	osnoise_restore_runtime_period(context);
+
+	if (context->orig_runtime_us != OSNOISE_TIME_INIT_VAL)
+		context->orig_runtime_us = OSNOISE_TIME_INIT_VAL;
+
+	if (context->orig_period_us != OSNOISE_TIME_INIT_VAL)
+		context->orig_period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_get_timerlat_period_us - read and save the original "timerlat_period_us"
+ */
+static long long
+osnoise_get_timerlat_period_us(struct osnoise_context *context)
+{
+	long long timerlat_period_us;
+
+	if (context->timerlat_period_us != OSNOISE_TIME_INIT_VAL)
+		return context->timerlat_period_us;
+
+	if (context->orig_timerlat_period_us != OSNOISE_TIME_INIT_VAL)
+		return context->orig_timerlat_period_us;
+
+	timerlat_period_us = osnoise_read_ll_config("osnoise/timerlat_period_us");
+	if (timerlat_period_us < 0)
+		goto out_err;
+
+	context->orig_timerlat_period_us = timerlat_period_us;
+	return timerlat_period_us;
+
+out_err:
+	return OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_set_timerlat_period_us - set "timerlat_period_us"
+ */
+int osnoise_set_timerlat_period_us(struct osnoise_context *context, long long timerlat_period_us)
+{
+	long long curr_timerlat_period_us = osnoise_get_timerlat_period_us(context);
+	int retval;
+
+	if (curr_timerlat_period_us == OSNOISE_TIME_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("osnoise/timerlat_period_us", timerlat_period_us);
+	if (retval < 0)
+		return -1;
+
+	context->timerlat_period_us = timerlat_period_us;
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_timerlat_period_us - restore "timerlat_period_us"
+ */
+void osnoise_restore_timerlat_period_us(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_timerlat_period_us == OSNOISE_TIME_INIT_VAL)
+		return;
+
+	if (context->orig_timerlat_period_us == context->timerlat_period_us)
+		goto out_done;
+
+	retval = osnoise_write_ll_config("osnoise/timerlat_period_us", context->orig_timerlat_period_us);
+	if (retval < 0)
+		err_msg("Could not restore original osnoise timerlat_period_us\n");
+
+out_done:
+	context->timerlat_period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_put_timerlat_period_us - restore original values and cleanup data
+ */
+void osnoise_put_timerlat_period_us(struct osnoise_context *context)
+{
+	osnoise_restore_timerlat_period_us(context);
+
+	if (context->orig_timerlat_period_us == OSNOISE_TIME_INIT_VAL)
+		return;
+
+	context->orig_timerlat_period_us = OSNOISE_TIME_INIT_VAL;
+}
+
+/*
+ * osnoise_get_timerlat_align_us - read and save the original "timerlat_align_us"
+ */
+static long long
+osnoise_get_timerlat_align_us(struct osnoise_context *context)
+{
+	long long timerlat_align_us;
+
+	if (context->timerlat_align_us != OSNOISE_OPTION_INIT_VAL)
+		return context->timerlat_align_us;
+
+	if (context->orig_timerlat_align_us != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_timerlat_align_us;
+
+	timerlat_align_us = osnoise_read_ll_config("osnoise/timerlat_align_us");
+	if (timerlat_align_us < 0)
+		goto out_err;
+
+	context->orig_timerlat_align_us = timerlat_align_us;
+	return timerlat_align_us;
+
+out_err:
+	return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_timerlat_align_us - set "timerlat_align_us"
+ */
+int osnoise_set_timerlat_align_us(struct osnoise_context *context, long long timerlat_align_us)
+{
+	long long curr_timerlat_align_us = osnoise_get_timerlat_align_us(context);
+	int retval;
+
+	if (curr_timerlat_align_us == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("osnoise/timerlat_align_us", timerlat_align_us);
+	if (retval < 0)
+		return -1;
+
+	context->timerlat_align_us = timerlat_align_us;
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_timerlat_align_us - restore "timerlat_align_us"
+ */
+void osnoise_restore_timerlat_align_us(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_timerlat_align_us == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_timerlat_align_us == context->timerlat_align_us)
+		goto out_done;
+
+	retval = osnoise_write_ll_config("osnoise/timerlat_align_us",
+				   context->orig_timerlat_align_us);
+	if (retval < 0)
+		err_msg("Could not restore original osnoise timerlat_align_us\n");
+
+out_done:
+	context->timerlat_align_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_timerlat_align_us - restore original values and cleanup data
+ */
+void osnoise_put_timerlat_align_us(struct osnoise_context *context)
+{
+	osnoise_restore_timerlat_align_us(context);
+
+	if (context->orig_timerlat_align_us == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_timerlat_align_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_get_stop_us - read and save the original "stop_tracing_us"
+ */
+static long long
+osnoise_get_stop_us(struct osnoise_context *context)
+{
+	long long stop_us;
+
+	if (context->stop_us != OSNOISE_OPTION_INIT_VAL)
+		return context->stop_us;
+
+	if (context->orig_stop_us != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_stop_us;
+
+	stop_us = osnoise_read_ll_config("osnoise/stop_tracing_us");
+	if (stop_us < 0)
+		goto out_err;
+
+	context->orig_stop_us = stop_us;
+	return stop_us;
+
+out_err:
+	return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_stop_us - set "stop_tracing_us"
+ */
+int osnoise_set_stop_us(struct osnoise_context *context, long long stop_us)
+{
+	long long curr_stop_us = osnoise_get_stop_us(context);
+	int retval;
+
+	if (curr_stop_us == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("osnoise/stop_tracing_us", stop_us);
+	if (retval < 0)
+		return -1;
+
+	context->stop_us = stop_us;
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_stop_us - restore the original "stop_tracing_us"
+ */
+void osnoise_restore_stop_us(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_stop_us == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_stop_us == context->stop_us)
+		goto out_done;
+
+	retval = osnoise_write_ll_config("osnoise/stop_tracing_us", context->orig_stop_us);
+	if (retval < 0)
+		err_msg("Could not restore original osnoise stop_us\n");
+
+out_done:
+	context->stop_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_stop_us - restore original values and cleanup data
+ */
+void osnoise_put_stop_us(struct osnoise_context *context)
+{
+	osnoise_restore_stop_us(context);
+
+	if (context->orig_stop_us == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_stop_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_get_stop_total_us - read and save the original "stop_tracing_total_us"
+ */
+static long long
+osnoise_get_stop_total_us(struct osnoise_context *context)
+{
+	long long stop_total_us;
+
+	if (context->stop_total_us != OSNOISE_OPTION_INIT_VAL)
+		return context->stop_total_us;
+
+	if (context->orig_stop_total_us != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_stop_total_us;
+
+	stop_total_us = osnoise_read_ll_config("osnoise/stop_tracing_total_us");
+	if (stop_total_us < 0)
+		goto out_err;
+
+	context->orig_stop_total_us = stop_total_us;
+	return stop_total_us;
+
+out_err:
+	return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_stop_total_us - set "stop_tracing_total_us"
+ */
+int osnoise_set_stop_total_us(struct osnoise_context *context, long long stop_total_us)
+{
+	long long curr_stop_total_us = osnoise_get_stop_total_us(context);
+	int retval;
+
+	if (curr_stop_total_us == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("osnoise/stop_tracing_total_us", stop_total_us);
+	if (retval < 0)
+		return -1;
+
+	context->stop_total_us = stop_total_us;
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_stop_total_us - restore the original "stop_tracing_total_us"
+ */
+void osnoise_restore_stop_total_us(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_stop_total_us == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_stop_total_us == context->stop_total_us)
+		goto out_done;
+
+	retval = osnoise_write_ll_config("osnoise/stop_tracing_total_us",
+			context->orig_stop_total_us);
+	if (retval < 0)
+		err_msg("Could not restore original osnoise stop_total_us\n");
+
+out_done:
+	context->stop_total_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_stop_total_us - restore original values and cleanup data
+ */
+void osnoise_put_stop_total_us(struct osnoise_context *context)
+{
+	osnoise_restore_stop_total_us(context);
+
+	if (context->orig_stop_total_us == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_stop_total_us = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_get_print_stack - read and save the original "print_stack"
+ */
+static long long
+osnoise_get_print_stack(struct osnoise_context *context)
+{
+	long long print_stack;
+
+	if (context->print_stack != OSNOISE_OPTION_INIT_VAL)
+		return context->print_stack;
+
+	if (context->orig_print_stack != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_print_stack;
+
+	print_stack = osnoise_read_ll_config("osnoise/print_stack");
+	if (print_stack < 0)
+		goto out_err;
+
+	context->orig_print_stack = print_stack;
+	return print_stack;
+
+out_err:
+	return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_print_stack - set "print_stack"
+ */
+int osnoise_set_print_stack(struct osnoise_context *context, long long print_stack)
+{
+	long long curr_print_stack = osnoise_get_print_stack(context);
+	int retval;
+
+	if (curr_print_stack == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("osnoise/print_stack", print_stack);
+	if (retval < 0)
+		return -1;
+
+	context->print_stack = print_stack;
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_print_stack - restore the original "print_stack"
+ */
+void osnoise_restore_print_stack(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_print_stack == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_print_stack == context->print_stack)
+		goto out_done;
+
+	retval = osnoise_write_ll_config("osnoise/print_stack", context->orig_print_stack);
+	if (retval < 0)
+		err_msg("Could not restore original osnoise print_stack\n");
+
+out_done:
+	context->print_stack = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_print_stack - restore original values and cleanup data
+ */
+void osnoise_put_print_stack(struct osnoise_context *context)
+{
+	osnoise_restore_print_stack(context);
+
+	if (context->orig_print_stack == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_print_stack = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_get_tracing_thresh - read and save the original "tracing_thresh"
+ */
+static long long
+osnoise_get_tracing_thresh(struct osnoise_context *context)
+{
+	long long tracing_thresh;
+
+	if (context->tracing_thresh != OSNOISE_OPTION_INIT_VAL)
+		return context->tracing_thresh;
+
+	if (context->orig_tracing_thresh != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_tracing_thresh;
+
+	tracing_thresh = osnoise_read_ll_config("tracing_thresh");
+	if (tracing_thresh < 0)
+		goto out_err;
+
+	context->orig_tracing_thresh = tracing_thresh;
+	return tracing_thresh;
+
+out_err:
+	return OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_set_tracing_thresh - set "tracing_thresh"
+ */
+int osnoise_set_tracing_thresh(struct osnoise_context *context, long long tracing_thresh)
+{
+	long long curr_tracing_thresh = osnoise_get_tracing_thresh(context);
+	int retval;
+
+	if (curr_tracing_thresh == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	retval = osnoise_write_ll_config("tracing_thresh", tracing_thresh);
+	if (retval < 0)
+		return -1;
+
+	context->tracing_thresh = tracing_thresh;
+
+	return 0;
+}
+
+/*
+ * osnoise_restore_tracing_thresh - restore the original "tracing_thresh"
+ */
+void osnoise_restore_tracing_thresh(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_tracing_thresh == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_tracing_thresh == context->tracing_thresh)
+		goto out_done;
+
+	retval = osnoise_write_ll_config("tracing_thresh", context->orig_tracing_thresh);
+	if (retval < 0)
+		err_msg("Could not restore original tracing_thresh\n");
+
+out_done:
+	context->tracing_thresh = OSNOISE_OPTION_INIT_VAL;
+}
+
+/*
+ * osnoise_put_tracing_thresh - restore original values and cleanup data
+ */
+void osnoise_put_tracing_thresh(struct osnoise_context *context)
+{
+	osnoise_restore_tracing_thresh(context);
+
+	if (context->orig_tracing_thresh == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_tracing_thresh = OSNOISE_OPTION_INIT_VAL;
+}
+
+static int osnoise_options_get_option(char *option)
+{
+	char *options = tracefs_instance_file_read(NULL, "osnoise/options", NULL);
+	char no_option[128];
+	int retval = 0;
+	char *opt;
+
+	if (!options)
+		return OSNOISE_OPTION_INIT_VAL;
+
+	/*
+	 * Check first if the option is disabled.
+	 */
+	snprintf(no_option, sizeof(no_option), "NO_%s", option);
+
+	opt = strstr(options, no_option);
+	if (opt)
+		goto out_free;
+
+	/*
+	 * Now that it is not disabled, if the string is there, it is
+	 * enabled. If the string is not there, the option does not exist.
+	 */
+	opt = strstr(options, option);
+	if (opt)
+		retval = 1;
+	else
+		retval = OSNOISE_OPTION_INIT_VAL;
+
+out_free:
+	free(options);
+	return retval;
+}
+
+static int osnoise_options_set_option(char *option, bool onoff)
+{
+	char no_option[128];
+
+	if (onoff)
+		return tracefs_instance_file_write(NULL, "osnoise/options", option);
+
+	snprintf(no_option, sizeof(no_option), "NO_%s", option);
+
+	return tracefs_instance_file_write(NULL, "osnoise/options", no_option);
+}
+
+static int osnoise_get_irq_disable(struct osnoise_context *context)
+{
+	if (context->opt_irq_disable != OSNOISE_OPTION_INIT_VAL)
+		return context->opt_irq_disable;
+
+	if (context->orig_opt_irq_disable != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_opt_irq_disable;
+
+	context->orig_opt_irq_disable = osnoise_options_get_option("OSNOISE_IRQ_DISABLE");
+
+	return context->orig_opt_irq_disable;
+}
+
+int osnoise_set_irq_disable(struct osnoise_context *context, bool onoff)
+{
+	int opt_irq_disable = osnoise_get_irq_disable(context);
+	int retval;
+
+	if (opt_irq_disable == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	if (opt_irq_disable == onoff)
+		return 0;
+
+	retval = osnoise_options_set_option("OSNOISE_IRQ_DISABLE", onoff);
+	if (retval < 0)
+		return -1;
+
+	context->opt_irq_disable = onoff;
+
+	return 0;
+}
+
+static void osnoise_restore_irq_disable(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_opt_irq_disable == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_opt_irq_disable == context->opt_irq_disable)
+		goto out_done;
+
+	retval = osnoise_options_set_option("OSNOISE_IRQ_DISABLE", context->orig_opt_irq_disable);
+	if (retval < 0)
+		err_msg("Could not restore original OSNOISE_IRQ_DISABLE option\n");
+
+out_done:
+	context->orig_opt_irq_disable = OSNOISE_OPTION_INIT_VAL;
+}
+
+static void osnoise_put_irq_disable(struct osnoise_context *context)
+{
+	osnoise_restore_irq_disable(context);
+
+	if (context->orig_opt_irq_disable == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_opt_irq_disable = OSNOISE_OPTION_INIT_VAL;
+}
+
+static int osnoise_get_workload(struct osnoise_context *context)
+{
+	if (context->opt_workload != OSNOISE_OPTION_INIT_VAL)
+		return context->opt_workload;
+
+	if (context->orig_opt_workload != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_opt_workload;
+
+	context->orig_opt_workload = osnoise_options_get_option("OSNOISE_WORKLOAD");
+
+	return context->orig_opt_workload;
+}
+
+int osnoise_set_workload(struct osnoise_context *context, bool onoff)
+{
+	int opt_workload = osnoise_get_workload(context);
+	int retval;
+
+	if (opt_workload == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	if (opt_workload == onoff)
+		return 0;
+
+	retval = osnoise_options_set_option("OSNOISE_WORKLOAD", onoff);
+	if (retval < 0)
+		return -2;
+
+	context->opt_workload = onoff;
+
+	return 0;
+}
+
+static void osnoise_restore_workload(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_opt_workload == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_opt_workload == context->opt_workload)
+		goto out_done;
+
+	retval = osnoise_options_set_option("OSNOISE_WORKLOAD", context->orig_opt_workload);
+	if (retval < 0)
+		err_msg("Could not restore original OSNOISE_WORKLOAD option\n");
+
+out_done:
+	context->orig_opt_workload = OSNOISE_OPTION_INIT_VAL;
+}
+
+static void osnoise_put_workload(struct osnoise_context *context)
+{
+	osnoise_restore_workload(context);
+
+	if (context->orig_opt_workload == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_opt_workload = OSNOISE_OPTION_INIT_VAL;
+}
+
+static int osnoise_get_timerlat_align(struct osnoise_context *context)
+{
+	if (context->opt_timerlat_align != OSNOISE_OPTION_INIT_VAL)
+		return context->opt_timerlat_align;
+
+	if (context->orig_opt_timerlat_align != OSNOISE_OPTION_INIT_VAL)
+		return context->orig_opt_timerlat_align;
+
+	context->orig_opt_timerlat_align = osnoise_options_get_option("TIMERLAT_ALIGN");
+
+	return context->orig_opt_timerlat_align;
+}
+
+int osnoise_set_timerlat_align(struct osnoise_context *context, bool onoff)
+{
+	int opt_timerlat_align = osnoise_get_timerlat_align(context);
+	int retval;
+
+	if (opt_timerlat_align == OSNOISE_OPTION_INIT_VAL)
+		return -1;
+
+	if (opt_timerlat_align == onoff)
+		return 0;
+
+	retval = osnoise_options_set_option("TIMERLAT_ALIGN", onoff);
+	if (retval < 0)
+		return -2;
+
+	context->opt_timerlat_align = onoff;
+
+	return 0;
+}
+
+static void osnoise_restore_timerlat_align(struct osnoise_context *context)
+{
+	int retval;
+
+	if (context->orig_opt_timerlat_align == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	if (context->orig_opt_timerlat_align == context->opt_timerlat_align)
+		goto out_done;
+
+	retval = osnoise_options_set_option("TIMERLAT_ALIGN", context->orig_opt_timerlat_align);
+	if (retval < 0)
+		err_msg("Could not restore original TIMERLAT_ALIGN option\n");
+
+out_done:
+	context->orig_opt_timerlat_align = OSNOISE_OPTION_INIT_VAL;
+}
+
+static void osnoise_put_timerlat_align(struct osnoise_context *context)
+{
+	osnoise_restore_timerlat_align(context);
+
+	if (context->orig_opt_timerlat_align == OSNOISE_OPTION_INIT_VAL)
+		return;
+
+	context->orig_opt_timerlat_align = OSNOISE_OPTION_INIT_VAL;
+}
+
+enum {
+	FLAG_CONTEXT_NEWLY_CREATED	= (1 << 0),
+	FLAG_CONTEXT_DELETED		= (1 << 1),
+};
+
+/*
+ * osnoise_get_context - increase the usage of a context and return it
+ */
+int osnoise_get_context(struct osnoise_context *context)
+{
+	int ret;
+
+	if (context->flags & FLAG_CONTEXT_DELETED) {
+		ret = -1;
+	} else {
+		context->ref++;
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/*
+ * osnoise_context_alloc - alloc an osnoise_context
+ *
+ * The osnoise context contains the information of the "osnoise/" configs.
+ * It is used to set and restore the config.
+ */
+struct osnoise_context *osnoise_context_alloc(void)
+{
+	struct osnoise_context *context;
+
+	context = calloc_fatal(1, sizeof(*context));
+
+	context->orig_stop_us		= OSNOISE_OPTION_INIT_VAL;
+	context->stop_us		= OSNOISE_OPTION_INIT_VAL;
+
+	context->orig_stop_total_us	= OSNOISE_OPTION_INIT_VAL;
+	context->stop_total_us		= OSNOISE_OPTION_INIT_VAL;
+
+	context->orig_print_stack	= OSNOISE_OPTION_INIT_VAL;
+	context->print_stack		= OSNOISE_OPTION_INIT_VAL;
+
+	context->orig_tracing_thresh	= OSNOISE_OPTION_INIT_VAL;
+	context->tracing_thresh		= OSNOISE_OPTION_INIT_VAL;
+
+	context->orig_opt_irq_disable	= OSNOISE_OPTION_INIT_VAL;
+	context->opt_irq_disable	= OSNOISE_OPTION_INIT_VAL;
+
+	context->orig_opt_workload	= OSNOISE_OPTION_INIT_VAL;
+	context->opt_workload		= OSNOISE_OPTION_INIT_VAL;
+
+	context->orig_opt_timerlat_align	= OSNOISE_OPTION_INIT_VAL;
+	context->opt_timerlat_align		= OSNOISE_OPTION_INIT_VAL;
+
+	context->orig_timerlat_align_us	= OSNOISE_OPTION_INIT_VAL;
+	context->timerlat_align_us	= OSNOISE_OPTION_INIT_VAL;
+
+	osnoise_get_context(context);
+
+	return context;
+}
+
+/*
+ * osnoise_put_context - put the osnoise_put_context
+ *
+ * If there is no other user for the context, the original data
+ * is restored.
+ */
+void osnoise_put_context(struct osnoise_context *context)
+{
+	if (--context->ref < 1)
+		context->flags |= FLAG_CONTEXT_DELETED;
+
+	if (!(context->flags & FLAG_CONTEXT_DELETED))
+		return;
+
+	osnoise_put_cpus(context);
+	osnoise_put_runtime_period(context);
+	osnoise_put_stop_us(context);
+	osnoise_put_stop_total_us(context);
+	osnoise_put_timerlat_period_us(context);
+	osnoise_put_print_stack(context);
+	osnoise_put_tracing_thresh(context);
+	osnoise_put_irq_disable(context);
+	osnoise_put_workload(context);
+	osnoise_put_timerlat_align(context);
+	osnoise_put_timerlat_align_us(context);
+
+	free(context);
+}
+
+/*
+ * osnoise_destroy_tool - disable trace, restore configs and free data
+ */
+void osnoise_destroy_tool(struct osnoise_tool *top)
+{
+	if (!top)
+		return;
+
+	trace_instance_destroy(&top->trace);
+
+	if (top->context)
+		osnoise_put_context(top->context);
+
+	free(top);
+}
+
+/*
+ * osnoise_init_tool - init an osnoise tool
+ *
+ * It allocs data, create a context to store data and
+ * creates a new trace instance for the tool.
+ */
+struct osnoise_tool *osnoise_init_tool(char *tool_name)
+{
+	struct osnoise_tool *top;
+
+	top = calloc_fatal(1, sizeof(*top));
+	top->context = osnoise_context_alloc();
+
+	if (trace_instance_init(&top->trace, tool_name)) {
+		osnoise_destroy_tool(top);
+		return NULL;
+	}
+
+	return top;
+}
+
+/*
+ * osnoise_init_trace_tool - init a tracer instance to trace osnoise events
+ */
+struct osnoise_tool *osnoise_init_trace_tool(const char *tracer)
+{
+	struct osnoise_tool *trace;
+	int retval;
+
+	trace = osnoise_init_tool("osnoise_trace");
+	if (!trace)
+		return NULL;
+
+	retval = tracefs_event_enable(trace->trace.inst, "osnoise", NULL);
+	if (retval < 0 && !errno) {
+		err_msg("Could not find osnoise events\n");
+		goto out_err;
+	}
+
+	retval = enable_tracer_by_name(trace->trace.inst, tracer);
+	if (retval) {
+		err_msg("Could not enable %s tracer for tracing\n", tracer);
+		goto out_err;
+	}
+
+	return trace;
+out_err:
+	osnoise_destroy_tool(trace);
+	return NULL;
+}
+
+bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record)
+{
+	/*
+	 * The tool instance is always present, it is the one used to collect
+	 * data.
+	 */
+	if (!tracefs_trace_is_on(tool->trace.inst))
+		return true;
+
+	/*
+	 * The trace record instance is only enabled when -t is set. IOW, when the system
+	 * is tracing.
+	 */
+	return record && !tracefs_trace_is_on(record->trace.inst);
+}
+
+/*
+ * osnoise_report_missed_events - report number of events dropped by trace
+ * buffer
+ */
+void
+osnoise_report_missed_events(struct osnoise_tool *tool)
+{
+	unsigned long long total_events;
+
+	if (tool->trace.missed_events == UINT64_MAX)
+		printf("unknown number of events missed, results might not be accurate\n");
+	else if (tool->trace.missed_events > 0) {
+		total_events = tool->trace.processed_events + tool->trace.missed_events;
+
+		printf("%lld (%.2f%%) events missed, results might not be accurate\n",
+		       tool->trace.missed_events,
+		       (double) tool->trace.missed_events / total_events * 100.0);
+	}
+}
+
+/*
+ * osnoise_apply_config - apply osnoise configs to the initialized tool
+ */
+int
+osnoise_apply_config(struct osnoise_tool *tool, struct osnoise_params *params)
+{
+	int retval;
+
+	params->common.kernel_workload = true;
+
+	if (params->runtime || params->period) {
+		retval = osnoise_set_runtime_period(tool->context,
+						    params->runtime,
+						    params->period);
+	} else {
+		retval = osnoise_set_runtime_period(tool->context,
+						    DEFAULT_SAMPLE_PERIOD,
+						    DEFAULT_SAMPLE_RUNTIME);
+	}
+
+	if (retval) {
+		err_msg("Failed to set runtime and/or period\n");
+		goto out_err;
+	}
+
+	retval = osnoise_set_tracing_thresh(tool->context, params->threshold);
+	if (retval) {
+		err_msg("Failed to set tracing_thresh\n");
+		goto out_err;
+	}
+
+	return common_apply_config(tool, &params->common);
+
+out_err:
+	return -1;
+}
+
+int osnoise_enable(struct osnoise_tool *tool)
+{
+	struct osnoise_params *params = to_osnoise_params(tool->params);
+	int retval;
+
+	/*
+	 * Start the tracer here, after having set all instances.
+	 *
+	 * Let the trace instance start first for the case of hitting a stop
+	 * tracing while enabling other instances. The trace instance is the
+	 * one with most valuable information.
+	 */
+	if (tool->record)
+		trace_instance_start(&tool->record->trace);
+	trace_instance_start(&tool->trace);
+
+	if (params->common.warmup > 0) {
+		debug_msg("Warming up for %d seconds\n", params->common.warmup);
+		sleep(params->common.warmup);
+		if (stop_tracing)
+			return -1;
+
+		/*
+		 * Clean up the buffer. The osnoise workload do not run
+		 * with tracing off to avoid creating a performance penalty
+		 * when not needed.
+		 */
+		retval = tracefs_instance_file_write(tool->trace.inst, "trace", "");
+		if (retval < 0) {
+			debug_msg("Error cleaning up the buffer");
+			return retval;
+		}
+	}
+
+	retval = osn_set_stop(tool);
+	if (retval)
+		return retval;
+
+	return 0;
+}
+
+__noreturn static void osnoise_usage(int err)
+{
+	int i;
+
+	static const char *msg[] = {
+		"",
+		"osnoise version " VERSION,
+		"",
+		"  usage: [rtla] osnoise [MODE] ...",
+		"",
+		"  modes:",
+		"     top   - prints the summary from osnoise tracer",
+		"     hist  - prints a histogram of osnoise samples",
+		"",
+		"if no MODE is given, the top mode is called, passing the arguments",
+		NULL,
+	};
+
+	for (i = 0; msg[i]; i++)
+		fprintf(stderr, "%s\n", msg[i]);
+	exit(err);
+}
+
+int osnoise_main(int argc, char *argv[])
+{
+	if (argc == 0)
+		goto usage;
+
+	/*
+	 * if osnoise was called without any argument, run the
+	 * default cmdline.
+	 */
+	if (argc == 1) {
+		run_tool(&osnoise_top_ops, argc, argv);
+		exit(0);
+	}
+
+	if ((strcmp(argv[1], "-h") == 0) || (strcmp(argv[1], "--help") == 0)) {
+		osnoise_usage(129);
+	} else if (str_has_prefix(argv[1], "-")) {
+		/* the user skipped the tool, call the default one */
+		run_tool(&osnoise_top_ops, argc, argv);
+		exit(0);
+	} else if (strcmp(argv[1], "top") == 0) {
+		run_tool(&osnoise_top_ops, argc-1, &argv[1]);
+		exit(0);
+	} else if (strcmp(argv[1], "hist") == 0) {
+		run_tool(&osnoise_hist_ops, argc-1, &argv[1]);
+		exit(0);
+	}
+
+usage:
+	osnoise_usage(129);
+}
+
+int hwnoise_main(int argc, char *argv[])
+{
+	run_tool(&osnoise_top_ops, argc, argv);
+	exit(0);
+}
diff --git a/tools/tracing/rtla/src/osnoise.h b/tools/tracing/rtla/src/osnoise.h
new file mode 100644
index 000000000..340ff5a64
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise.h
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+#pragma once
+
+#include "common.h"
+
+enum osnoise_mode {
+	MODE_OSNOISE = 0,
+	MODE_HWNOISE
+};
+
+struct osnoise_params {
+	struct common_params	common;
+	unsigned long long	runtime;
+	unsigned long long	period;
+	long long		threshold;
+	enum osnoise_mode	mode;
+};
+
+#define to_osnoise_params(ptr) container_of(ptr, struct osnoise_params, common)
+
+/*
+ * *_INIT_VALs are also invalid values, they are used to
+ * communicate errors.
+ */
+#define OSNOISE_OPTION_INIT_VAL	(-1)
+#define OSNOISE_TIME_INIT_VAL	(0)
+
+struct osnoise_context *osnoise_context_alloc(void);
+int osnoise_get_context(struct osnoise_context *context);
+void osnoise_put_context(struct osnoise_context *context);
+
+int osnoise_set_runtime_period(struct osnoise_context *context,
+			       unsigned long long runtime,
+			       unsigned long long period);
+void osnoise_restore_runtime_period(struct osnoise_context *context);
+
+void osnoise_restore_stop_us(struct osnoise_context *context);
+void osnoise_restore_stop_total_us(struct osnoise_context *context);
+
+int osnoise_set_timerlat_period_us(struct osnoise_context *context,
+				   long long timerlat_period_us);
+void osnoise_restore_timerlat_period_us(struct osnoise_context *context);
+
+int osnoise_set_tracing_thresh(struct osnoise_context *context,
+			       long long tracing_thresh);
+void osnoise_restore_tracing_thresh(struct osnoise_context *context);
+
+void osnoise_restore_print_stack(struct osnoise_context *context);
+int osnoise_set_print_stack(struct osnoise_context *context,
+			    long long print_stack);
+
+int osnoise_set_timerlat_align_us(struct osnoise_context *context,
+				  long long timerlat_align_us);
+void osnoise_restore_timerlat_align_us(struct osnoise_context *context);
+
+int osnoise_set_timerlat_align(struct osnoise_context *context, bool onoff);
+
+int osnoise_set_irq_disable(struct osnoise_context *context, bool onoff);
+void osnoise_report_missed_events(struct osnoise_tool *tool);
+int osnoise_apply_config(struct osnoise_tool *tool, struct osnoise_params *params);
+
+int osnoise_enable(struct osnoise_tool *tool);
+int osnoise_main(int argc, char **argv);
+int hwnoise_main(int argc, char **argv);
+
+extern struct tool_ops timerlat_top_ops, timerlat_hist_ops;
+extern struct tool_ops osnoise_top_ops, osnoise_hist_ops;
+
+int run_tool(struct tool_ops *ops, int argc, char *argv[]);
diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c
new file mode 100644
index 000000000..dfa91d068
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise_hist.c
@@ -0,0 +1,467 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "osnoise.h"
+#include "cli.h"
+
+struct osnoise_hist_cpu {
+	int			*samples;
+	int			count;
+
+	unsigned long long	min_sample;
+	unsigned long long	sum_sample;
+	unsigned long long	max_sample;
+
+};
+
+struct osnoise_hist_data {
+	struct tracefs_hist	*trace_hist;
+	struct osnoise_hist_cpu	*hist;
+	int			entries;
+	int			bucket_size;
+};
+
+/*
+ * osnoise_free_histogram - free runtime data
+ */
+static void
+osnoise_free_histogram(struct osnoise_hist_data *data)
+{
+	int cpu;
+
+	/* one histogram for IRQ and one for thread, per CPU */
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		if (data->hist[cpu].samples)
+			free(data->hist[cpu].samples);
+	}
+
+	/* one set of histograms per CPU */
+	if (data->hist)
+		free(data->hist);
+
+	free(data);
+}
+
+static void osnoise_free_hist_tool(struct osnoise_tool *tool)
+{
+	osnoise_free_histogram(tool->data);
+}
+
+/*
+ * osnoise_alloc_histogram - alloc runtime data
+ */
+static struct osnoise_hist_data
+*osnoise_alloc_histogram(int entries, int bucket_size)
+{
+	struct osnoise_hist_data *data;
+	int cpu;
+
+	data = calloc(1, sizeof(*data));
+	if (!data)
+		return NULL;
+
+	data->entries = entries;
+	data->bucket_size = bucket_size;
+
+	data->hist = calloc(1, sizeof(*data->hist) * nr_cpus);
+	if (!data->hist)
+		goto cleanup;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		data->hist[cpu].samples = calloc(1, sizeof(*data->hist->samples) * (entries + 1));
+		if (!data->hist[cpu].samples)
+			goto cleanup;
+	}
+
+	/* set the min to max */
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		data->hist[cpu].min_sample = ~0;
+
+	return data;
+
+cleanup:
+	osnoise_free_histogram(data);
+	return NULL;
+}
+
+static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu,
+					 unsigned long long duration, int count)
+{
+	struct osnoise_params *params = to_osnoise_params(tool->params);
+	struct osnoise_hist_data *data = tool->data;
+	unsigned long long total_duration;
+	int entries = data->entries;
+	int bucket;
+	int *hist;
+
+	if (params->common.output_divisor)
+		duration = duration / params->common.output_divisor;
+
+	bucket = duration / data->bucket_size;
+
+	total_duration = duration * count;
+
+	hist = data->hist[cpu].samples;
+	data->hist[cpu].count += count;
+	update_min(&data->hist[cpu].min_sample, &duration);
+	update_sum(&data->hist[cpu].sum_sample, &total_duration);
+	update_max(&data->hist[cpu].max_sample, &duration);
+
+	if (bucket < entries)
+		hist[bucket] += count;
+	else
+		hist[entries] += count;
+}
+
+/*
+ * osnoise_destroy_trace_hist - disable events used to collect histogram
+ */
+static void osnoise_destroy_trace_hist(struct osnoise_tool *tool)
+{
+	struct osnoise_hist_data *data = tool->data;
+
+	tracefs_hist_pause(tool->trace.inst, data->trace_hist);
+	tracefs_hist_destroy(tool->trace.inst, data->trace_hist);
+}
+
+/*
+ * osnoise_init_trace_hist - enable events used to collect histogram
+ */
+static int osnoise_init_trace_hist(struct osnoise_tool *tool)
+{
+	struct osnoise_params *params = to_osnoise_params(tool->params);
+	struct osnoise_hist_data *data = tool->data;
+	int bucket_size;
+	char buff[128];
+	int retval = 0;
+
+	/*
+	 * Set the size of the bucket.
+	 */
+	bucket_size = params->common.output_divisor * params->common.hist.bucket_size;
+	snprintf(buff, sizeof(buff), "duration.buckets=%d", bucket_size);
+
+	data->trace_hist = tracefs_hist_alloc(tool->trace.tep, "osnoise", "sample_threshold",
+			buff, TRACEFS_HIST_KEY_NORMAL);
+	if (!data->trace_hist)
+		return 1;
+
+	retval = tracefs_hist_add_key(data->trace_hist, "cpu", 0);
+	if (retval)
+		goto out_err;
+
+	retval = tracefs_hist_start(tool->trace.inst, data->trace_hist);
+	if (retval)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	osnoise_destroy_trace_hist(tool);
+	return 1;
+}
+
+/*
+ * osnoise_read_trace_hist - parse histogram file and file osnoise histogram
+ */
+static void osnoise_read_trace_hist(struct osnoise_tool *tool)
+{
+	struct osnoise_hist_data *data = tool->data;
+	long long cpu, counter, duration;
+	char *content, *position;
+
+	tracefs_hist_pause(tool->trace.inst, data->trace_hist);
+
+	content = tracefs_event_file_read(tool->trace.inst, "osnoise",
+					  "sample_threshold",
+					  "hist", NULL);
+	if (!content)
+		return;
+
+	position = content;
+	while (true) {
+		position = strstr(position, "duration: ~");
+		if (!position)
+			break;
+		position += strlen("duration: ~");
+		duration = get_llong_from_str(position);
+		if (duration == -1)
+			err_msg("error reading duration from histogram\n");
+
+		position = strstr(position, "cpu:");
+		if (!position)
+			break;
+		position += strlen("cpu: ");
+		cpu = get_llong_from_str(position);
+		if (cpu == -1)
+			err_msg("error reading cpu from histogram\n");
+
+		position = strstr(position, "hitcount:");
+		if (!position)
+			break;
+		position += strlen("hitcount: ");
+		counter = get_llong_from_str(position);
+		if (counter == -1)
+			err_msg("error reading counter from histogram\n");
+
+		osnoise_hist_update_multiple(tool, cpu, duration, counter);
+	}
+	free(content);
+}
+
+/*
+ * osnoise_hist_header - print the header of the tracer to the output
+ */
+static void osnoise_hist_header(struct osnoise_tool *tool)
+{
+	struct osnoise_params *params = to_osnoise_params(tool->params);
+	struct osnoise_hist_data *data = tool->data;
+	struct trace_seq *s = tool->trace.seq;
+	char duration[26];
+	int cpu;
+
+	if (params->common.hist.no_header)
+		return;
+
+	get_duration(tool->start_time, duration, sizeof(duration));
+	trace_seq_printf(s, "# RTLA osnoise histogram\n");
+	trace_seq_printf(s, "# Time unit is %s (%s)\n",
+			params->common.output_divisor == 1 ? "nanoseconds" : "microseconds",
+			params->common.output_divisor == 1 ? "ns" : "us");
+
+	trace_seq_printf(s, "# Duration: %s\n", duration);
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(s, "Index");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].count)
+			continue;
+
+		trace_seq_printf(s, "   CPU-%03d", cpu);
+	}
+	trace_seq_printf(s, "\n");
+
+	trace_seq_do_printf(s);
+	trace_seq_reset(s);
+}
+
+/*
+ * osnoise_print_summary - print the summary of the hist data to the output
+ */
+static void
+osnoise_print_summary(struct osnoise_params *params,
+		       struct trace_instance *trace,
+		       struct osnoise_hist_data *data)
+{
+	int cpu;
+
+	if (params->common.hist.no_summary)
+		return;
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "count:");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+		if (!data->hist[cpu].count)
+			continue;
+
+		trace_seq_printf(trace->seq, "%9d ", data->hist[cpu].count);
+	}
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "min:  ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].count)
+			continue;
+
+		trace_seq_printf(trace->seq, "%9llu ",	data->hist[cpu].min_sample);
+
+	}
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "avg:  ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].count)
+			continue;
+
+		if (data->hist[cpu].count)
+			trace_seq_printf(trace->seq, "%9.2f ",
+				((double) data->hist[cpu].sum_sample) / data->hist[cpu].count);
+		else
+			trace_seq_printf(trace->seq, "        - ");
+	}
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "max:  ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].count)
+			continue;
+
+		trace_seq_printf(trace->seq, "%9llu ", data->hist[cpu].max_sample);
+
+	}
+	trace_seq_printf(trace->seq, "\n");
+	trace_seq_do_printf(trace->seq);
+	trace_seq_reset(trace->seq);
+}
+
+/*
+ * osnoise_print_stats - print data for all CPUs
+ */
+static void
+osnoise_print_stats(struct osnoise_tool *tool)
+{
+	struct osnoise_params *params = to_osnoise_params(tool->params);
+	struct osnoise_hist_data *data = tool->data;
+	struct trace_instance *trace = &tool->trace;
+	int has_samples = 0;
+	int bucket, cpu;
+	int total;
+
+	osnoise_hist_header(tool);
+
+	for (bucket = 0; bucket < data->entries; bucket++) {
+		total = 0;
+
+		if (!params->common.hist.no_index)
+			trace_seq_printf(trace->seq, "%-6d",
+					 bucket * data->bucket_size);
+
+		for_each_monitored_cpu(cpu, &params->common) {
+
+			if (!data->hist[cpu].count)
+				continue;
+
+			total += data->hist[cpu].samples[bucket];
+			trace_seq_printf(trace->seq, "%9d ", data->hist[cpu].samples[bucket]);
+		}
+
+		if (total == 0 && !params->common.hist.with_zeros) {
+			trace_seq_reset(trace->seq);
+			continue;
+		}
+
+		/* There are samples above the threshold */
+		has_samples = 1;
+		trace_seq_printf(trace->seq, "\n");
+		trace_seq_do_printf(trace->seq);
+		trace_seq_reset(trace->seq);
+	}
+
+	/*
+	 * If no samples were recorded, skip calculations, print zeroed statistics
+	 * and return.
+	 */
+	if (!has_samples) {
+		trace_seq_reset(trace->seq);
+		trace_seq_printf(trace->seq, "over: 0\ncount: 0\nmin: 0\navg: 0\nmax: 0\n");
+		trace_seq_do_printf(trace->seq);
+		trace_seq_reset(trace->seq);
+		return;
+	}
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "over: ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].count)
+			continue;
+
+		trace_seq_printf(trace->seq, "%9d ",
+				 data->hist[cpu].samples[data->entries]);
+	}
+	trace_seq_printf(trace->seq, "\n");
+	trace_seq_do_printf(trace->seq);
+	trace_seq_reset(trace->seq);
+
+	osnoise_print_summary(params, trace, data);
+	osnoise_report_missed_events(tool);
+}
+
+/*
+ * osnoise_hist_apply_config - apply the hist configs to the initialized tool
+ */
+static int
+osnoise_hist_apply_config(struct osnoise_tool *tool)
+{
+	return osnoise_apply_config(tool, to_osnoise_params(tool->params));
+}
+
+/*
+ * osnoise_init_hist - initialize a osnoise hist tool with parameters
+ */
+static struct osnoise_tool
+*osnoise_init_hist(struct common_params *params)
+{
+	struct osnoise_tool *tool;
+
+	tool = osnoise_init_tool("osnoise_hist");
+	if (!tool)
+		return NULL;
+
+	tool->data = osnoise_alloc_histogram(params->hist.entries,
+					     params->hist.bucket_size);
+	if (!tool->data)
+		goto out_err;
+
+	return tool;
+
+out_err:
+	osnoise_destroy_tool(tool);
+	return NULL;
+}
+
+static int osnoise_hist_enable(struct osnoise_tool *tool)
+{
+	int retval;
+
+	retval = osnoise_init_trace_hist(tool);
+	if (retval)
+		return retval;
+
+	return osnoise_enable(tool);
+}
+
+static int osnoise_hist_main_loop(struct osnoise_tool *tool)
+{
+	int retval;
+
+	retval = hist_main_loop(tool);
+	osnoise_read_trace_hist(tool);
+
+	return retval;
+}
+
+struct tool_ops osnoise_hist_ops = {
+	.tracer = "osnoise",
+	.comm_prefix = "osnoise/",
+	.parse_args = osnoise_hist_parse_args,
+	.init_tool = osnoise_init_hist,
+	.apply_config = osnoise_hist_apply_config,
+	.enable = osnoise_hist_enable,
+	.main = osnoise_hist_main_loop,
+	.print_stats = osnoise_print_stats,
+	.free = osnoise_free_hist_tool,
+};
diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
new file mode 100644
index 000000000..512a6299c
--- /dev/null
+++ b/tools/tracing/rtla/src/osnoise_top.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "osnoise.h"
+#include "cli.h"
+
+struct osnoise_top_cpu {
+	unsigned long long	sum_runtime;
+	unsigned long long	sum_noise;
+	unsigned long long	max_noise;
+	unsigned long long	max_sample;
+
+	unsigned long long	hw_count;
+	unsigned long long	nmi_count;
+	unsigned long long	irq_count;
+	unsigned long long	softirq_count;
+	unsigned long long	thread_count;
+
+	int			sum_cycles;
+};
+
+struct osnoise_top_data {
+	struct osnoise_top_cpu	*cpu_data;
+};
+
+/*
+ * osnoise_free_top - free runtime data
+ */
+static void osnoise_free_top(struct osnoise_top_data *data)
+{
+	free(data->cpu_data);
+	free(data);
+}
+
+static void osnoise_free_top_tool(struct osnoise_tool *tool)
+{
+	osnoise_free_top(tool->data);
+}
+
+/*
+ * osnoise_alloc_histogram - alloc runtime data
+ */
+static struct osnoise_top_data *osnoise_alloc_top(void)
+{
+	struct osnoise_top_data *data;
+
+	data = calloc(1, sizeof(*data));
+	if (!data)
+		return NULL;
+
+	/* one set of histograms per CPU */
+	data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus);
+	if (!data->cpu_data)
+		goto cleanup;
+
+	return data;
+
+cleanup:
+	osnoise_free_top(data);
+	return NULL;
+}
+
+/*
+ * osnoise_top_handler - this is the handler for osnoise tracer events
+ */
+static int
+osnoise_top_handler(struct trace_seq *s, struct tep_record *record,
+		    struct tep_event *event, void *context)
+{
+	struct trace_instance *trace = context;
+	struct osnoise_tool *tool;
+	unsigned long long val;
+	struct osnoise_top_cpu *cpu_data;
+	struct osnoise_top_data *data;
+	int cpu = record->cpu;
+
+	tool = container_of(trace, struct osnoise_tool, trace);
+
+	data = tool->data;
+	cpu_data = &data->cpu_data[cpu];
+
+	cpu_data->sum_cycles++;
+
+	tep_get_field_val(s, event, "runtime", record, &val, 1);
+	update_sum(&cpu_data->sum_runtime, &val);
+
+	tep_get_field_val(s, event, "noise", record, &val, 1);
+	update_max(&cpu_data->max_noise, &val);
+	update_sum(&cpu_data->sum_noise, &val);
+
+	tep_get_field_val(s, event, "max_sample", record, &val, 1);
+	update_max(&cpu_data->max_sample, &val);
+
+	tep_get_field_val(s, event, "hw_count", record, &val, 1);
+	update_sum(&cpu_data->hw_count, &val);
+
+	tep_get_field_val(s, event, "nmi_count", record, &val, 1);
+	update_sum(&cpu_data->nmi_count, &val);
+
+	tep_get_field_val(s, event, "irq_count", record, &val, 1);
+	update_sum(&cpu_data->irq_count, &val);
+
+	tep_get_field_val(s, event, "softirq_count", record, &val, 1);
+	update_sum(&cpu_data->softirq_count, &val);
+
+	tep_get_field_val(s, event, "thread_count", record, &val, 1);
+	update_sum(&cpu_data->thread_count, &val);
+
+	return 0;
+}
+
+/*
+ * osnoise_top_header - print the header of the tool output
+ */
+static void osnoise_top_header(struct osnoise_tool *top)
+{
+	struct osnoise_params *params = to_osnoise_params(top->params);
+	struct trace_seq *s = top->trace.seq;
+	bool pretty = params->common.pretty_output;
+	char duration[26];
+
+	get_duration(top->start_time, duration, sizeof(duration));
+
+	if (pretty)
+		trace_seq_printf(s, "\033[2;37;40m");
+
+	trace_seq_printf(s, "                                          ");
+
+	if (params->mode == MODE_OSNOISE) {
+		trace_seq_printf(s, "Operating System Noise");
+		trace_seq_printf(s, "                                       ");
+	} else if (params->mode == MODE_HWNOISE) {
+		trace_seq_printf(s, "Hardware-related Noise");
+	}
+
+	trace_seq_printf(s, "                                   ");
+
+	if (pretty)
+		trace_seq_printf(s, "\033[0;0;0m");
+	trace_seq_printf(s, "\n");
+
+	trace_seq_printf(s, "duration: %9s | time is in us\n", duration);
+
+	if (pretty)
+		trace_seq_printf(s, "\033[2;30;47m");
+
+	trace_seq_printf(s, "CPU Period       Runtime ");
+	trace_seq_printf(s, "       Noise ");
+	trace_seq_printf(s, " %% CPU Aval ");
+	trace_seq_printf(s, "  Max Noise   Max Single ");
+	trace_seq_printf(s, "         HW          NMI");
+
+	if (params->mode == MODE_HWNOISE)
+		goto eol;
+
+	trace_seq_printf(s, "          IRQ      Softirq       Thread");
+
+eol:
+	if (pretty)
+		trace_seq_printf(s, "\033[0;0;0m");
+	trace_seq_printf(s, "\n");
+}
+
+/*
+ * clear_terminal - clears the output terminal
+ */
+static void clear_terminal(struct trace_seq *seq)
+{
+	if (!config_debug)
+		trace_seq_printf(seq, "\033c");
+}
+
+/*
+ * osnoise_top_print - prints the output of a given CPU
+ */
+static void osnoise_top_print(struct osnoise_tool *tool, int cpu)
+{
+	struct osnoise_params *params = to_osnoise_params(tool->params);
+	struct trace_seq *s = tool->trace.seq;
+	struct osnoise_top_cpu *cpu_data;
+	struct osnoise_top_data *data;
+	int percentage;
+	int decimal;
+
+	data = tool->data;
+	cpu_data = &data->cpu_data[cpu];
+
+	if (!cpu_data->sum_runtime)
+		return;
+
+	percentage = ((cpu_data->sum_runtime - cpu_data->sum_noise) * 10000000)
+			/ cpu_data->sum_runtime;
+	decimal = percentage % 100000;
+	percentage = percentage / 100000;
+
+	trace_seq_printf(s, "%3d #%-6d %12llu ", cpu, cpu_data->sum_cycles, cpu_data->sum_runtime);
+	trace_seq_printf(s, "%12llu ", cpu_data->sum_noise);
+	trace_seq_printf(s, "  %3d.%05d", percentage, decimal);
+	trace_seq_printf(s, "%12llu %12llu", cpu_data->max_noise, cpu_data->max_sample);
+
+	trace_seq_printf(s, "%12llu ", cpu_data->hw_count);
+	trace_seq_printf(s, "%12llu ", cpu_data->nmi_count);
+
+	if (params->mode == MODE_HWNOISE) {
+		trace_seq_printf(s, "\n");
+		return;
+	}
+
+	trace_seq_printf(s, "%12llu ", cpu_data->irq_count);
+	trace_seq_printf(s, "%12llu ", cpu_data->softirq_count);
+	trace_seq_printf(s, "%12llu\n", cpu_data->thread_count);
+}
+
+/*
+ * osnoise_print_stats - print data for all cpus
+ */
+static void
+osnoise_print_stats(struct osnoise_tool *top)
+{
+	struct osnoise_params *params = to_osnoise_params(top->params);
+	struct trace_instance *trace = &top->trace;
+	int i;
+
+	if (!params->common.quiet)
+		clear_terminal(trace->seq);
+
+	osnoise_top_header(top);
+
+	for_each_monitored_cpu(i, &params->common) {
+		osnoise_top_print(top, i);
+	}
+
+	trace_seq_do_printf(trace->seq);
+	trace_seq_reset(trace->seq);
+	osnoise_report_missed_events(top);
+}
+
+/*
+ * osnoise_top_apply_config - apply the top configs to the initialized tool
+ */
+static int
+osnoise_top_apply_config(struct osnoise_tool *tool)
+{
+	struct osnoise_params *params = to_osnoise_params(tool->params);
+	int retval;
+
+	retval = osnoise_apply_config(tool, params);
+	if (retval)
+		goto out_err;
+
+	if (params->mode == MODE_HWNOISE) {
+		retval = osnoise_set_irq_disable(tool->context, 1);
+		if (retval) {
+			err_msg("Failed to set OSNOISE_IRQ_DISABLE option\n");
+			goto out_err;
+		}
+	}
+
+	if (isatty(STDOUT_FILENO) && !params->common.quiet)
+		params->common.pretty_output = 1;
+
+	return 0;
+
+out_err:
+	return -1;
+}
+
+/*
+ * osnoise_init_top - initialize a osnoise top tool with parameters
+ */
+struct osnoise_tool *osnoise_init_top(struct common_params *params)
+{
+	struct osnoise_tool *tool;
+
+	tool = osnoise_init_tool("osnoise_top");
+	if (!tool)
+		return NULL;
+
+	tool->data = osnoise_alloc_top();
+	if (!tool->data) {
+		osnoise_destroy_tool(tool);
+		return NULL;
+	}
+
+	tep_register_event_handler(tool->trace.tep, -1, "ftrace", "osnoise",
+				   osnoise_top_handler, NULL);
+
+	return tool;
+}
+
+struct tool_ops osnoise_top_ops = {
+	.tracer = "osnoise",
+	.comm_prefix = "osnoise/",
+	.parse_args = osnoise_top_parse_args,
+	.init_tool = osnoise_init_top,
+	.apply_config = osnoise_top_apply_config,
+	.enable = osnoise_enable,
+	.main = top_main_loop,
+	.print_stats = osnoise_print_stats,
+	.free = osnoise_free_top_tool,
+};
diff --git a/tools/tracing/rtla/src/timerlat.bpf.c b/tools/tracing/rtla/src/timerlat.bpf.c
new file mode 100644
index 000000000..549d2d219
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat.bpf.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "timerlat_bpf.h"
+
+#define nosubprog __always_inline
+#define MAX_ENTRIES_DEFAULT 4096
+
+char LICENSE[] SEC("license") = "GPL";
+
+struct trace_event_raw_timerlat_sample {
+	unsigned long long timer_latency;
+	int context;
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, MAX_ENTRIES_DEFAULT);
+	__type(key, unsigned int);
+	__type(value, unsigned long long);
+} hist_irq SEC(".maps"), hist_thread SEC(".maps"), hist_user SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, SUMMARY_FIELD_N);
+	__type(key, unsigned int);
+	__type(value, unsigned long long);
+} summary_irq SEC(".maps"), summary_thread SEC(".maps"), summary_user SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, unsigned int);
+	__type(value, unsigned long long);
+} stop_tracing SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 1);
+} signal_stop_tracing SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(key_size, sizeof(unsigned int));
+	__uint(max_entries, 1);
+	__array(values, unsigned int (void *));
+} bpf_action SEC(".maps") = {
+	.values = {
+		[0] = 0
+	},
+};
+
+/* Params to be set by rtla */
+const volatile int bucket_size = 1;
+const volatile int output_divisor = 1000;
+const volatile int entries = 256;
+const volatile int irq_threshold;
+const volatile int thread_threshold;
+const volatile bool aa_only;
+
+nosubprog unsigned long long map_get(void *map,
+				     unsigned int key)
+{
+	unsigned long long *value_ptr;
+
+	value_ptr = bpf_map_lookup_elem(map, &key);
+
+	return !value_ptr ? 0 : *value_ptr;
+}
+
+nosubprog void map_set(void *map,
+		       unsigned int key,
+		       unsigned long long value)
+{
+	bpf_map_update_elem(map, &key, &value, BPF_ANY);
+}
+
+nosubprog void map_increment(void *map,
+			     unsigned int key)
+{
+	map_set(map, key, map_get(map, key) + 1);
+}
+
+nosubprog void update_main_hist(void *map,
+				int bucket)
+{
+	if (entries == 0)
+		/* No histogram */
+		return;
+
+	if (bucket >= entries)
+		/* Overflow */
+		return;
+
+	map_increment(map, bucket);
+}
+
+nosubprog void update_summary(void *map,
+			      unsigned long long latency,
+			      int bucket)
+{
+	if (aa_only)
+		/* Auto-analysis only, nothing to be done here */
+		return;
+
+	map_set(map, SUMMARY_CURRENT, latency);
+
+	if (bucket >= entries)
+		/* Overflow */
+		map_increment(map, SUMMARY_OVERFLOW);
+
+	if (latency > map_get(map, SUMMARY_MAX))
+		map_set(map, SUMMARY_MAX, latency);
+
+	if (latency < map_get(map, SUMMARY_MIN) || map_get(map, SUMMARY_COUNT) == 0)
+		map_set(map, SUMMARY_MIN, latency);
+
+	map_increment(map, SUMMARY_COUNT);
+	map_set(map, SUMMARY_SUM, map_get(map, SUMMARY_SUM) + latency);
+}
+
+nosubprog void set_stop_tracing(struct trace_event_raw_timerlat_sample *tp_args)
+{
+	int value = 0;
+
+	/* Suppress further sample processing */
+	map_set(&stop_tracing, 0, 1);
+
+	/* Signal to userspace */
+	bpf_ringbuf_output(&signal_stop_tracing, &value, sizeof(value), 0);
+
+	/*
+	 * Call into BPF action program, if attached.
+	 * Otherwise, just silently fail.
+	 */
+	bpf_tail_call(tp_args, &bpf_action, 0);
+}
+
+SEC("tp/osnoise/timerlat_sample")
+int handle_timerlat_sample(struct trace_event_raw_timerlat_sample *tp_args)
+{
+	unsigned long long latency, latency_us;
+	int bucket;
+
+	if (map_get(&stop_tracing, 0))
+		return 0;
+
+	latency = tp_args->timer_latency / output_divisor;
+	latency_us = tp_args->timer_latency / 1000;
+	bucket = latency / bucket_size;
+
+	if (tp_args->context == 0) {
+		update_main_hist(&hist_irq, bucket);
+		update_summary(&summary_irq, latency, bucket);
+
+		if (irq_threshold != 0 && latency_us >= irq_threshold)
+			set_stop_tracing(tp_args);
+	} else if (tp_args->context == 1) {
+		update_main_hist(&hist_thread, bucket);
+		update_summary(&summary_thread, latency, bucket);
+
+		if (thread_threshold != 0 && latency_us >= thread_threshold)
+			set_stop_tracing(tp_args);
+	} else {
+		update_main_hist(&hist_user, bucket);
+		update_summary(&summary_user, latency, bucket);
+
+		if (thread_threshold != 0 && latency_us >= thread_threshold)
+			set_stop_tracing(tp_args);
+	}
+
+	return 0;
+}
diff --git a/tools/tracing/rtla/src/timerlat.c b/tools/tracing/rtla/src/timerlat.c
new file mode 100644
index 000000000..169aa9a65
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+#define _GNU_SOURCE
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <sched.h>
+
+#include <linux/compiler.h>
+
+#include "timerlat.h"
+#include "timerlat_aa.h"
+#include "timerlat_bpf.h"
+
+#define DEFAULT_TIMERLAT_PERIOD	1000			/* 1ms */
+
+static int dma_latency_fd = -1;
+
+/*
+ * timerlat_apply_config - apply common configs to the initialized tool
+ */
+int
+timerlat_apply_config(struct osnoise_tool *tool, struct timerlat_params *params)
+{
+	int retval;
+	const char *const rtla_no_bpf = getenv("RTLA_NO_BPF");
+
+	/*
+	 * Try to enable BPF, unless disabled explicitly.
+	 * If BPF enablement fails, fall back to tracefs mode.
+	 */
+	if (rtla_no_bpf && strncmp_static(rtla_no_bpf, "1") == 0) {
+		debug_msg("RTLA_NO_BPF set, disabling BPF\n");
+		params->mode = TRACING_MODE_TRACEFS;
+	} else if (!tep_find_event_by_name(tool->trace.tep, "osnoise", "timerlat_sample")) {
+		debug_msg("osnoise:timerlat_sample missing, disabling BPF\n");
+		params->mode = TRACING_MODE_TRACEFS;
+	} else {
+		retval = timerlat_bpf_init(params);
+		if (retval) {
+			debug_msg("Could not enable BPF\n");
+			params->mode = TRACING_MODE_TRACEFS;
+		}
+	}
+
+	/* Check if BPF action program is requested but BPF is not available */
+	if (params->bpf_action_program) {
+		if (params->mode == TRACING_MODE_TRACEFS) {
+			err_msg("BPF actions are not supported in tracefs-only mode\n");
+			goto out_err;
+		}
+
+		if (timerlat_load_bpf_action_program(params->bpf_action_program))
+			goto out_err;
+	}
+
+	retval = osnoise_set_timerlat_period_us(tool->context,
+						params->timerlat_period_us ?
+						params->timerlat_period_us :
+						DEFAULT_TIMERLAT_PERIOD);
+	if (retval) {
+		err_msg("Failed to set timerlat period\n");
+		goto out_err;
+	}
+
+
+	retval = osnoise_set_print_stack(tool->context, params->print_stack);
+	if (retval) {
+		err_msg("Failed to set print stack\n");
+		goto out_err;
+	}
+
+	retval = osnoise_set_timerlat_align(tool->context, params->timerlat_align);
+	if (retval && params->timerlat_align) {
+		/*
+		 * We might be running on a kernel that does not support timerlat align.
+		 * Unless user requested it explicitly, ignore the error.
+		 */
+		err_msg("Failed to enable timerlat align\n");
+		goto out_err;
+	}
+
+	if (params->timerlat_align) {
+		retval = osnoise_set_timerlat_align_us(tool->context, params->timerlat_align_us);
+		if (retval) {
+			err_msg("Failed to set timerlat align us\n");
+			goto out_err;
+		}
+	}
+
+	/*
+	 * If the user did not specify a type of thread, try user-threads first.
+	 * Fall back to kernel threads otherwise.
+	 */
+	if (!params->common.kernel_workload && !params->common.user_data) {
+		retval = tracefs_file_exists(NULL, "osnoise/per_cpu/cpu0/timerlat_fd");
+		if (retval) {
+			debug_msg("User-space interface detected, setting user-threads\n");
+			params->common.user_workload = 1;
+			params->common.user_data = 1;
+		} else {
+			debug_msg("User-space interface not detected, setting kernel-threads\n");
+			params->common.kernel_workload = 1;
+		}
+	}
+
+	return common_apply_config(tool, &params->common);
+
+out_err:
+	return -1;
+}
+
+int timerlat_enable(struct osnoise_tool *tool)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	int retval, i;
+
+	if (params->dma_latency >= 0) {
+		dma_latency_fd = set_cpu_dma_latency(params->dma_latency);
+		if (dma_latency_fd < 0) {
+			err_msg("Could not set /dev/cpu_dma_latency.\n");
+			return -1;
+		}
+	}
+
+	if (params->deepest_idle_state >= -1) {
+		if (!have_libcpupower_support()) {
+			err_msg("rtla built without libcpupower, --deepest-idle-state is not supported\n");
+			return -1;
+		}
+
+		for_each_monitored_cpu(i, &params->common) {
+			if (save_cpu_idle_disable_state(i) < 0) {
+				err_msg("Could not save cpu idle state.\n");
+				return -1;
+			}
+			if (set_deepest_cpu_idle_state(i, params->deepest_idle_state) < 0) {
+				err_msg("Could not set deepest cpu idle state.\n");
+				return -1;
+			}
+		}
+	}
+
+	if (!params->no_aa) {
+		tool->aa = osnoise_init_tool("timerlat_aa");
+		if (!tool->aa)
+			return -1;
+
+		retval = timerlat_aa_init(tool->aa, params->dump_tasks, params->stack_format);
+		if (retval) {
+			err_msg("Failed to enable the auto analysis instance\n");
+			return retval;
+		}
+
+		retval = enable_tracer_by_name(tool->aa->trace.inst, "timerlat");
+		if (retval) {
+			err_msg("Failed to enable aa tracer\n");
+			return retval;
+		}
+	}
+
+	if (params->common.warmup > 0) {
+		debug_msg("Warming up for %d seconds\n", params->common.warmup);
+		sleep(params->common.warmup);
+		if (stop_tracing)
+			return -1;
+	}
+
+	/*
+	 * Start the tracers here, after having set all instances.
+	 *
+	 * Let the trace instance start first for the case of hitting a stop
+	 * tracing while enabling other instances. The trace instance is the
+	 * one with most valuable information.
+	 */
+	if (tool->record)
+		trace_instance_start(&tool->record->trace);
+	if (!params->no_aa)
+		trace_instance_start(&tool->aa->trace);
+	if (params->mode == TRACING_MODE_TRACEFS) {
+		trace_instance_start(&tool->trace);
+	} else {
+		retval = timerlat_bpf_attach();
+		if (retval) {
+			err_msg("Error attaching BPF program\n");
+			return retval;
+		}
+	}
+
+	/*
+	 * In tracefs and mixed mode, timerlat tracer handles stopping
+	 * on threshold
+	 */
+	if (params->mode != TRACING_MODE_BPF) {
+		retval = osn_set_stop(tool);
+		if (retval)
+			return retval;
+	}
+
+	return 0;
+}
+
+void timerlat_analyze(struct osnoise_tool *tool, bool stopped)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+
+	if (stopped) {
+		if (!params->no_aa)
+			timerlat_auto_analysis(params->common.stop_us,
+					       params->common.stop_total_us);
+	} else if (params->common.aa_only) {
+		char *max_lat;
+
+		/*
+		 * If the trace did not stop with --aa-only, at least print
+		 * the max known latency.
+		 */
+		max_lat = tracefs_instance_file_read(tool->trace.inst, "tracing_max_latency", NULL);
+		if (max_lat) {
+			printf("  Max latency was %s\n", max_lat);
+			free(max_lat);
+		}
+	}
+}
+
+void timerlat_free(struct osnoise_tool *tool)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	int i;
+
+	timerlat_aa_destroy();
+	if (dma_latency_fd >= 0)
+		close(dma_latency_fd);
+	if (params->deepest_idle_state >= -1) {
+		for_each_monitored_cpu(i, &params->common) {
+			restore_cpu_idle_disable_state(i);
+		}
+	}
+
+	osnoise_destroy_tool(tool->aa);
+
+	if (params->mode != TRACING_MODE_TRACEFS)
+		timerlat_bpf_destroy();
+	free_cpu_idle_disable_states();
+}
+
+__noreturn static void timerlat_usage(int err)
+{
+	int i;
+
+	static const char * const msg[] = {
+		"",
+		"timerlat version " VERSION,
+		"",
+		"  usage: [rtla] timerlat [MODE] ...",
+		"",
+		"  modes:",
+		"     top   - prints the summary from timerlat tracer",
+		"     hist  - prints a histogram of timer latencies",
+		"",
+		"if no MODE is given, the top mode is called, passing the arguments",
+		NULL,
+	};
+
+	for (i = 0; msg[i]; i++)
+		fprintf(stderr, "%s\n", msg[i]);
+	exit(err);
+}
+
+int timerlat_main(int argc, char *argv[])
+{
+	if (argc == 0)
+		goto usage;
+
+	/*
+	 * if timerlat was called without any argument, run the
+	 * default cmdline.
+	 */
+	if (argc == 1) {
+		run_tool(&timerlat_top_ops, argc, argv);
+		exit(0);
+	}
+
+	if ((strcmp(argv[1], "-h") == 0) || (strcmp(argv[1], "--help") == 0)) {
+		timerlat_usage(129);
+	} else if (str_has_prefix(argv[1], "-")) {
+		/* the user skipped the tool, call the default one */
+		run_tool(&timerlat_top_ops, argc, argv);
+		exit(0);
+	} else if (strcmp(argv[1], "top") == 0) {
+		run_tool(&timerlat_top_ops, argc-1, &argv[1]);
+		exit(0);
+	} else if (strcmp(argv[1], "hist") == 0) {
+		run_tool(&timerlat_hist_ops, argc-1, &argv[1]);
+		exit(0);
+	}
+
+usage:
+	timerlat_usage(129);
+}
diff --git a/tools/tracing/rtla/src/timerlat.h b/tools/tracing/rtla/src/timerlat.h
new file mode 100644
index 000000000..84ec6d778
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat.h
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#pragma once
+
+#include "osnoise.h"
+
+/*
+ * Define timerlat tracing mode.
+ *
+ * There are three tracing modes:
+ * - tracefs-only, used when BPF is unavailable.
+ * - BPF-only, used when BPF is available and neither trace saving nor
+ * auto-analysis are enabled.
+ * - mixed mode, used when BPF is available and either trace saving or
+ * auto-analysis is enabled (which rely on sample collection through
+ * tracefs).
+ */
+enum timerlat_tracing_mode {
+	TRACING_MODE_BPF,
+	TRACING_MODE_TRACEFS,
+	TRACING_MODE_MIXED,
+};
+
+struct timerlat_params {
+	struct common_params	common;
+	long long		timerlat_period_us;
+	long long		print_stack;
+	int			dma_latency;
+	bool			no_aa;
+	bool			dump_tasks;
+	int			deepest_idle_state;
+	enum timerlat_tracing_mode mode;
+	const char		*bpf_action_program;
+	enum stack_format	stack_format;
+	bool			timerlat_align;
+	unsigned long long	timerlat_align_us;
+};
+
+#define to_timerlat_params(ptr) container_of(ptr, struct timerlat_params, common)
+
+int timerlat_apply_config(struct osnoise_tool *tool, struct timerlat_params *params);
+int timerlat_main(int argc, char *argv[]);
+int timerlat_enable(struct osnoise_tool *tool);
+void timerlat_analyze(struct osnoise_tool *tool, bool stopped);
+void timerlat_free(struct osnoise_tool *tool);
diff --git a/tools/tracing/rtla/src/timerlat_aa.c b/tools/tracing/rtla/src/timerlat_aa.c
new file mode 100644
index 000000000..a121ff9d2
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_aa.c
@@ -0,0 +1,1075 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#include <stdlib.h>
+#include <errno.h>
+#include "timerlat.h"
+#include <unistd.h>
+
+enum timelat_state {
+	TIMERLAT_INIT = 0,
+	TIMERLAT_WAITING_IRQ,
+	TIMERLAT_WAITING_THREAD,
+};
+
+/* Used to fill spaces in the output */
+static const char *spaces  = "                                                         ";
+
+#define MAX_COMM		24
+
+/*
+ * Per-cpu data statistics and data.
+ */
+struct timerlat_aa_data {
+	/* Current CPU state */
+	int			curr_state;
+
+	/* timerlat IRQ latency */
+	unsigned long long	tlat_irq_seqnum;
+	unsigned long long	tlat_irq_latency;
+	unsigned long long	tlat_irq_timstamp;
+
+	/* timerlat Thread latency */
+	unsigned long long	tlat_thread_seqnum;
+	unsigned long long	tlat_thread_latency;
+	unsigned long long	tlat_thread_timstamp;
+
+	/*
+	 * Information about the thread running when the IRQ
+	 * arrived.
+	 *
+	 * This can be blocking or interference, depending on the
+	 * priority of the thread. Assuming timerlat is the highest
+	 * prio, it is blocking. If timerlat has a lower prio, it is
+	 * interference.
+	 * note: "unsigned long long" because they are fetch using tep_get_field_val();
+	 */
+	unsigned long long	run_thread_pid;
+	char			run_thread_comm[MAX_COMM];
+	unsigned long long	thread_blocking_duration;
+	unsigned long long	max_exit_idle_latency;
+
+	/* Information about the timerlat timer irq */
+	unsigned long long	timer_irq_start_time;
+	unsigned long long	timer_irq_start_delay;
+	unsigned long long	timer_irq_duration;
+	unsigned long long	timer_exit_from_idle;
+
+	/*
+	 * Information about the last IRQ before the timerlat irq
+	 * arrived.
+	 *
+	 * If now - timestamp is <= latency, it might have influenced
+	 * in the timerlat irq latency. Otherwise, ignore it.
+	 */
+	unsigned long long	prev_irq_duration;
+	unsigned long long	prev_irq_timstamp;
+
+	/*
+	 * Interference sum.
+	 */
+	unsigned long long	thread_nmi_sum;
+	unsigned long long	thread_irq_sum;
+	unsigned long long	thread_softirq_sum;
+	unsigned long long	thread_thread_sum;
+
+	/*
+	 * Interference task information.
+	 */
+	struct trace_seq	*prev_irqs_seq;
+	struct trace_seq	*nmi_seq;
+	struct trace_seq	*irqs_seq;
+	struct trace_seq	*softirqs_seq;
+	struct trace_seq	*threads_seq;
+	struct trace_seq	*stack_seq;
+
+	/*
+	 * Current thread.
+	 */
+	char			current_comm[MAX_COMM];
+	unsigned long long	current_pid;
+
+	/*
+	 * Is the system running a kworker?
+	 */
+	unsigned long long	kworker;
+	unsigned long long	kworker_func;
+};
+
+/*
+ * The analysis context and system wide view
+ */
+struct timerlat_aa_context {
+	int dump_tasks;
+	enum stack_format stack_format;
+
+	/* per CPU data */
+	struct timerlat_aa_data *taa_data;
+
+	/*
+	 * required to translate function names and register
+	 * events.
+	 */
+	struct osnoise_tool *tool;
+};
+
+/*
+ * The data is stored as a local variable, but accessed via a helper function.
+ *
+ * It could be stored inside the trace context. But every access would
+ * require container_of() + a series of pointers. Do we need it? Not sure.
+ *
+ * For now keep it simple. If needed, store it in the tool, add the *context
+ * as a parameter in timerlat_aa_get_ctx() and do the magic there.
+ */
+static struct timerlat_aa_context *__timerlat_aa_ctx;
+
+static struct timerlat_aa_context *timerlat_aa_get_ctx(void)
+{
+	return __timerlat_aa_ctx;
+}
+
+/*
+ * timerlat_aa_get_data - Get the per-cpu data from the timerlat context
+ */
+static struct timerlat_aa_data
+*timerlat_aa_get_data(struct timerlat_aa_context *taa_ctx, int cpu)
+{
+	return &taa_ctx->taa_data[cpu];
+}
+
+/*
+ * timerlat_aa_irq_latency - Handles timerlat IRQ event
+ */
+static int timerlat_aa_irq_latency(struct timerlat_aa_data *taa_data,
+				   struct trace_seq *s, struct tep_record *record,
+				   struct tep_event *event)
+{
+	/*
+	 * For interference, we start now looking for things that can delay
+	 * the thread.
+	 */
+	taa_data->curr_state = TIMERLAT_WAITING_THREAD;
+	taa_data->tlat_irq_timstamp = record->ts;
+
+	/*
+	 * Zero values.
+	 */
+	taa_data->thread_nmi_sum = 0;
+	taa_data->thread_irq_sum = 0;
+	taa_data->thread_softirq_sum = 0;
+	taa_data->thread_thread_sum = 0;
+	taa_data->thread_blocking_duration = 0;
+	taa_data->timer_irq_start_time = 0;
+	taa_data->timer_irq_duration = 0;
+	taa_data->timer_exit_from_idle = 0;
+
+	/*
+	 * Zero interference tasks.
+	 */
+	trace_seq_reset(taa_data->nmi_seq);
+	trace_seq_reset(taa_data->irqs_seq);
+	trace_seq_reset(taa_data->softirqs_seq);
+	trace_seq_reset(taa_data->threads_seq);
+
+	/* IRQ latency values */
+	tep_get_field_val(s, event, "timer_latency", record, &taa_data->tlat_irq_latency, 1);
+	tep_get_field_val(s, event, "seqnum", record, &taa_data->tlat_irq_seqnum, 1);
+
+	/* The thread that can cause blocking */
+	tep_get_common_field_val(s, event, "common_pid", record, &taa_data->run_thread_pid, 1);
+
+	/*
+	 * Get exit from idle case.
+	 *
+	 * If it is not idle thread:
+	 */
+	if (taa_data->run_thread_pid)
+		return 0;
+
+	/*
+	 * if the latency is shorter than the known exit from idle:
+	 */
+	if (taa_data->tlat_irq_latency < taa_data->max_exit_idle_latency)
+		return 0;
+
+	/*
+	 * To be safe, ignore the cases in which an IRQ/NMI could have
+	 * interfered with the timerlat IRQ.
+	 */
+	if (taa_data->tlat_irq_timstamp - taa_data->tlat_irq_latency
+	    < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration)
+		return 0;
+
+	taa_data->max_exit_idle_latency = taa_data->tlat_irq_latency;
+
+	return 0;
+}
+
+/*
+ * timerlat_aa_thread_latency - Handles timerlat thread event
+ */
+static int timerlat_aa_thread_latency(struct timerlat_aa_data *taa_data,
+				      struct trace_seq *s, struct tep_record *record,
+				      struct tep_event *event)
+{
+	/*
+	 * For interference, we start now looking for things that can delay
+	 * the IRQ of the next cycle.
+	 */
+	taa_data->curr_state = TIMERLAT_WAITING_IRQ;
+	taa_data->tlat_thread_timstamp = record->ts;
+
+	/* Thread latency values */
+	tep_get_field_val(s, event, "timer_latency", record, &taa_data->tlat_thread_latency, 1);
+	tep_get_field_val(s, event, "seqnum", record, &taa_data->tlat_thread_seqnum, 1);
+
+	return 0;
+}
+
+/*
+ * timerlat_aa_handler - Handle timerlat events
+ *
+ * This function is called to handle timerlat events recording statistics.
+ *
+ * Returns 0 on success, -1 otherwise.
+ */
+static int timerlat_aa_handler(struct trace_seq *s, struct tep_record *record,
+			struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+	unsigned long long thread;
+
+	if (!taa_data)
+		return -1;
+
+	tep_get_field_val(s, event, "context", record, &thread, 1);
+	if (!thread)
+		return timerlat_aa_irq_latency(taa_data, s, record, event);
+	else
+		return timerlat_aa_thread_latency(taa_data, s, record, event);
+}
+
+/*
+ * timerlat_aa_nmi_handler - Handles NMI noise
+ *
+ * It is used to collect information about interferences from NMI. It is
+ * hooked to the osnoise:nmi_noise event.
+ */
+static int timerlat_aa_nmi_handler(struct trace_seq *s, struct tep_record *record,
+				   struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+	unsigned long long duration;
+	unsigned long long start;
+
+	tep_get_field_val(s, event, "duration", record, &duration, 1);
+	tep_get_field_val(s, event, "start", record, &start, 1);
+
+	if (taa_data->curr_state == TIMERLAT_WAITING_IRQ) {
+		taa_data->prev_irq_duration = duration;
+		taa_data->prev_irq_timstamp = start;
+
+		trace_seq_reset(taa_data->prev_irqs_seq);
+		trace_seq_printf(taa_data->prev_irqs_seq, "  %24s %.*s %9.2f us\n",
+				 "nmi",
+				 24, spaces,
+				 ns_to_usf(duration));
+		return 0;
+	}
+
+	taa_data->thread_nmi_sum += duration;
+	trace_seq_printf(taa_data->nmi_seq, "  %24s %.*s %9.2f us\n",
+			 "nmi",
+			 24, spaces, ns_to_usf(duration));
+
+	return 0;
+}
+
+/*
+ * timerlat_aa_irq_handler - Handles IRQ noise
+ *
+ * It is used to collect information about interferences from IRQ. It is
+ * hooked to the osnoise:irq_noise event.
+ *
+ * It is a little bit more complex than the other because it measures:
+ *	- The IRQs that can delay the timer IRQ before it happened.
+ *	- The Timerlat IRQ handler
+ *	- The IRQs that happened between the timerlat IRQ and the timerlat thread
+ *	  (IRQ interference).
+ */
+static int timerlat_aa_irq_handler(struct trace_seq *s, struct tep_record *record,
+				   struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+	unsigned long long expected_start;
+	unsigned long long duration;
+	unsigned long long vector;
+	unsigned long long start;
+	char *desc;
+	int val;
+
+	tep_get_field_val(s, event, "duration", record, &duration, 1);
+	tep_get_field_val(s, event, "start", record, &start, 1);
+	tep_get_field_val(s, event, "vector", record, &vector, 1);
+	desc = tep_get_field_raw(s, event, "desc", record, &val, 1);
+
+	/*
+	 * Before the timerlat IRQ.
+	 */
+	if (taa_data->curr_state == TIMERLAT_WAITING_IRQ) {
+		taa_data->prev_irq_duration = duration;
+		taa_data->prev_irq_timstamp = start;
+
+		trace_seq_reset(taa_data->prev_irqs_seq);
+		trace_seq_printf(taa_data->prev_irqs_seq, "  %24s:%-3llu %.*s %9.2f us\n",
+				 desc, vector,
+				 15, spaces,
+				 ns_to_usf(duration));
+		return 0;
+	}
+
+	/*
+	 * The timerlat IRQ: taa_data->timer_irq_start_time is zeroed at
+	 * the timerlat irq handler.
+	 */
+	if (!taa_data->timer_irq_start_time) {
+		expected_start = taa_data->tlat_irq_timstamp - taa_data->tlat_irq_latency;
+
+		taa_data->timer_irq_start_time = start;
+		taa_data->timer_irq_duration = duration;
+
+		/*
+		 * We are dealing with two different clock sources: the
+		 * external clock source that timerlat uses as a reference
+		 * and the clock used by the tracer. There are also two
+		 * moments: the time reading the clock and the timer in
+		 * which the event is placed in the buffer (the trace
+		 * event timestamp). If the processor is slow or there
+		 * is some hardware noise, the difference between the
+		 * timestamp and the external clock read can be longer
+		 * than the IRQ handler delay, resulting in a negative
+		 * time. If so, set IRQ start delay as 0. In the end,
+		 * it is less relevant than the noise.
+		 */
+		if (expected_start < taa_data->timer_irq_start_time)
+			taa_data->timer_irq_start_delay = taa_data->timer_irq_start_time - expected_start;
+		else
+			taa_data->timer_irq_start_delay = 0;
+
+		/*
+		 * not exit from idle.
+		 */
+		if (taa_data->run_thread_pid)
+			return 0;
+
+		if (expected_start > taa_data->prev_irq_timstamp + taa_data->prev_irq_duration)
+			taa_data->timer_exit_from_idle = taa_data->timer_irq_start_delay;
+
+		return 0;
+	}
+
+	/*
+	 * IRQ interference.
+	 */
+	taa_data->thread_irq_sum += duration;
+	trace_seq_printf(taa_data->irqs_seq, "  %24s:%-3llu %.*s %9.2f us\n",
+			 desc, vector,
+			 24, spaces,
+			 ns_to_usf(duration));
+
+	return 0;
+}
+
+static char *softirq_name[] = { "HI", "TIMER",	"NET_TX", "NET_RX", "BLOCK",
+				"IRQ_POLL", "TASKLET", "SCHED", "HRTIMER", "RCU" };
+
+
+/*
+ * timerlat_aa_softirq_handler - Handles Softirq noise
+ *
+ * It is used to collect information about interferences from Softirq. It is
+ * hooked to the osnoise:softirq_noise event.
+ *
+ * It is only printed in the non-rt kernel, as softirqs become thread on RT.
+ */
+static int timerlat_aa_softirq_handler(struct trace_seq *s, struct tep_record *record,
+				       struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+	unsigned long long duration;
+	unsigned long long vector;
+	unsigned long long start;
+
+	if (taa_data->curr_state == TIMERLAT_WAITING_IRQ)
+		return 0;
+
+	tep_get_field_val(s, event, "duration", record, &duration, 1);
+	tep_get_field_val(s, event, "start", record, &start, 1);
+	tep_get_field_val(s, event, "vector", record, &vector, 1);
+
+	taa_data->thread_softirq_sum += duration;
+
+	trace_seq_printf(taa_data->softirqs_seq, "  %24s:%-3llu %.*s %9.2f us\n",
+			 vector < ARRAY_SIZE(softirq_name) ? softirq_name[vector] : "UNKNOWN",
+			 vector, 24, spaces,
+			 ns_to_usf(duration));
+	return 0;
+}
+
+/*
+ * timerlat_aa_softirq_handler - Handles thread noise
+ *
+ * It is used to collect information about interferences from threads. It is
+ * hooked to the osnoise:thread_noise event.
+ *
+ * Note: if you see thread noise, your timerlat thread was not the highest prio one.
+ */
+static int timerlat_aa_thread_handler(struct trace_seq *s, struct tep_record *record,
+				      struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+	unsigned long long duration;
+	unsigned long long start;
+	unsigned long long pid;
+	const char *comm;
+	int val;
+
+	if (taa_data->curr_state == TIMERLAT_WAITING_IRQ)
+		return 0;
+
+	tep_get_field_val(s, event, "duration", record, &duration, 1);
+	tep_get_field_val(s, event, "start", record, &start, 1);
+
+	tep_get_common_field_val(s, event, "common_pid", record, &pid, 1);
+	comm = tep_get_field_raw(s, event, "comm", record, &val, 1);
+
+	if (pid == taa_data->run_thread_pid && !taa_data->thread_blocking_duration) {
+		taa_data->thread_blocking_duration = duration;
+
+		if (comm)
+			strncpy(taa_data->run_thread_comm, comm, MAX_COMM);
+		else
+			sprintf(taa_data->run_thread_comm, "<...>");
+
+	} else {
+		taa_data->thread_thread_sum += duration;
+
+		trace_seq_printf(taa_data->threads_seq, "  %24s:%-12llu %.*s %9.2f us\n",
+				 comm, pid,
+				 15, spaces,
+				 ns_to_usf(duration));
+	}
+
+	return 0;
+}
+
+/*
+ * timerlat_aa_stack_handler - Handles timerlat IRQ stack trace
+ *
+ * Saves and parse the stack trace generated by the timerlat IRQ.
+ */
+static int timerlat_aa_stack_handler(struct trace_seq *s, struct tep_record *record,
+			      struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+	enum stack_format stack_format = taa_ctx->stack_format;
+	unsigned long *caller;
+	const char *function;
+	int val;
+	unsigned long long i;
+
+	trace_seq_reset(taa_data->stack_seq);
+
+	trace_seq_printf(taa_data->stack_seq, "    Blocking thread stack trace\n");
+	caller = tep_get_field_raw(s, event, "caller", record, &val, 1);
+
+	if (caller) {
+		unsigned long long size;
+		unsigned long long max_entries;
+
+		if (tep_get_field_val(s, event, "size", record, &size, 1) == 0)
+			max_entries = size < 64 ? size : 64;
+		else
+			max_entries = 64;
+
+		for (i = 0; i < max_entries; i++) {
+			function = tep_find_function(taa_ctx->tool->trace.tep, caller[i]);
+			if (!function) {
+				if (stack_format == STACK_FORMAT_TRUNCATE)
+					break;
+				else if (stack_format == STACK_FORMAT_SKIP)
+					continue;
+				else if (stack_format == STACK_FORMAT_FULL)
+					trace_seq_printf(taa_data->stack_seq, " %.*s -> 0x%lx\n",
+						     14, spaces, caller[i]);
+			} else {
+				trace_seq_printf(taa_data->stack_seq, " %.*s -> %s\n",
+						 14, spaces, function);
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * timerlat_aa_sched_switch_handler - Tracks the current thread running on the CPU
+ *
+ * Handles the sched:sched_switch event to trace the current thread running on the
+ * CPU. It is used to display the threads running on the other CPUs when the trace
+ * stops.
+ */
+static int timerlat_aa_sched_switch_handler(struct trace_seq *s, struct tep_record *record,
+					    struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+	const char *comm;
+	int val;
+
+	tep_get_field_val(s, event, "next_pid", record, &taa_data->current_pid, 1);
+	comm = tep_get_field_raw(s, event, "next_comm", record, &val, 1);
+
+	strncpy(taa_data->current_comm, comm, MAX_COMM);
+
+	/*
+	 * If this was a kworker, clean the last kworkers that ran.
+	 */
+	taa_data->kworker = 0;
+	taa_data->kworker_func = 0;
+
+	return 0;
+}
+
+/*
+ * timerlat_aa_kworker_start_handler - Tracks a kworker running on the CPU
+ *
+ * Handles workqueue:workqueue_execute_start event, keeping track of
+ * the job that a kworker could be doing in the CPU.
+ *
+ * We already catch problems of hardware related latencies caused by work queues
+ * running driver code that causes hardware stall. For example, with DRM drivers.
+ */
+static int timerlat_aa_kworker_start_handler(struct trace_seq *s, struct tep_record *record,
+					     struct tep_event *event, void *context)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	struct timerlat_aa_data *taa_data = timerlat_aa_get_data(taa_ctx, record->cpu);
+
+	tep_get_field_val(s, event, "work", record, &taa_data->kworker, 1);
+	tep_get_field_val(s, event, "function", record, &taa_data->kworker_func, 1);
+	return 0;
+}
+
+/*
+ * timerlat_thread_analysis - Prints the analysis of a CPU that hit a stop tracing
+ *
+ * This is the core of the analysis.
+ */
+static void timerlat_thread_analysis(struct timerlat_aa_data *taa_data, int cpu,
+				     int irq_thresh, int thread_thresh)
+{
+	long long exp_irq_ts;
+	int total;
+	int irq;
+
+	/*
+	 * IRQ latency or Thread latency?
+	 */
+	if (taa_data->tlat_irq_seqnum > taa_data->tlat_thread_seqnum) {
+		irq = 1;
+		total = taa_data->tlat_irq_latency;
+	} else {
+		irq = 0;
+		total = taa_data->tlat_thread_latency;
+	}
+
+	/*
+	 * Expected IRQ arrival time using the trace clock as the base.
+	 *
+	 * TODO: Add a list of previous IRQ, and then run the list backwards.
+	 */
+	exp_irq_ts = taa_data->timer_irq_start_time - taa_data->timer_irq_start_delay;
+	if (exp_irq_ts < taa_data->prev_irq_timstamp + taa_data->prev_irq_duration) {
+		if (taa_data->prev_irq_timstamp < taa_data->timer_irq_start_time)
+			printf("  Previous IRQ interference: %.*s up to  %9.2f us\n",
+			       16, spaces,
+			       ns_to_usf(taa_data->prev_irq_duration));
+	}
+
+	/*
+	 * The delay that the IRQ suffered before starting.
+	 */
+	printf("  IRQ handler delay: %.*s %16s  %9.2f us (%.2f %%)\n", 16, spaces,
+	       (ns_to_usf(taa_data->timer_exit_from_idle) > 10) ? "(exit from idle)" : "",
+	       ns_to_usf(taa_data->timer_irq_start_delay),
+	       ns_to_per(total, taa_data->timer_irq_start_delay));
+
+	/*
+	 * Timerlat IRQ.
+	 */
+	printf("  IRQ latency: %.*s %9.2f us\n", 40, spaces,
+	       ns_to_usf(taa_data->tlat_irq_latency));
+
+	if (irq) {
+		/*
+		 * If the trace stopped due to IRQ, the other events will not happen
+		 * because... the trace stopped :-).
+		 *
+		 * That is all folks, the stack trace was printed before the stop,
+		 * so it will be displayed, it is the key.
+		 */
+		printf("  Blocking thread:\n");
+		printf(" %.*s %24s:%-9llu\n", 6, spaces, taa_data->run_thread_comm,
+		       taa_data->run_thread_pid);
+	} else  {
+		/*
+		 * The duration of the IRQ handler that handled the timerlat IRQ.
+		 */
+		printf("  Timerlat IRQ duration: %.*s %9.2f us (%.2f %%)\n",
+		       30, spaces,
+		       ns_to_usf(taa_data->timer_irq_duration),
+		       ns_to_per(total, taa_data->timer_irq_duration));
+
+		/*
+		 * The amount of time that the current thread postponed the scheduler.
+		 *
+		 * Recalling that it is net from NMI/IRQ/Softirq interference, so there
+		 * is no need to compute values here.
+		 */
+		printf("  Blocking thread: %.*s %9.2f us (%.2f %%)\n", 36, spaces,
+		       ns_to_usf(taa_data->thread_blocking_duration),
+		       ns_to_per(total, taa_data->thread_blocking_duration));
+
+		printf(" %.*s %24s:%-9llu %.*s %9.2f us\n", 6, spaces,
+		       taa_data->run_thread_comm, taa_data->run_thread_pid,
+		       12, spaces, ns_to_usf(taa_data->thread_blocking_duration));
+	}
+
+	/*
+	 * Print the stack trace!
+	 */
+	trace_seq_do_printf(taa_data->stack_seq);
+
+	/*
+	 * NMIs can happen during the IRQ, so they are always possible.
+	 */
+	if (taa_data->thread_nmi_sum)
+		printf("  NMI interference %.*s %9.2f us (%.2f %%)\n", 36, spaces,
+		       ns_to_usf(taa_data->thread_nmi_sum),
+		       ns_to_per(total, taa_data->thread_nmi_sum));
+
+	/*
+	 * If it is an IRQ latency, the other factors can be skipped.
+	 */
+	if (irq)
+		goto print_total;
+
+	/*
+	 * Prints the interference caused by IRQs to the thread latency.
+	 */
+	if (taa_data->thread_irq_sum) {
+		printf("  IRQ interference %.*s %9.2f us (%.2f %%)\n", 36, spaces,
+		       ns_to_usf(taa_data->thread_irq_sum),
+		       ns_to_per(total, taa_data->thread_irq_sum));
+
+		trace_seq_do_printf(taa_data->irqs_seq);
+	}
+
+	/*
+	 * Prints the interference caused by Softirqs to the thread latency.
+	 */
+	if (taa_data->thread_softirq_sum) {
+		printf("  Softirq interference %.*s %9.2f us (%.2f %%)\n", 32, spaces,
+		       ns_to_usf(taa_data->thread_softirq_sum),
+		       ns_to_per(total, taa_data->thread_softirq_sum));
+
+		trace_seq_do_printf(taa_data->softirqs_seq);
+	}
+
+	/*
+	 * Prints the interference caused by other threads to the thread latency.
+	 *
+	 * If this happens, your timerlat is not the highest prio. OK, migration
+	 * thread can happen. But otherwise, you are not measuring the "scheduling
+	 * latency" only, and here is the difference from scheduling latency and
+	 * timer handling latency.
+	 */
+	if (taa_data->thread_thread_sum) {
+		printf("  Thread interference %.*s %9.2f us (%.2f %%)\n", 33, spaces,
+		       ns_to_usf(taa_data->thread_thread_sum),
+		       ns_to_per(total, taa_data->thread_thread_sum));
+
+		trace_seq_do_printf(taa_data->threads_seq);
+	}
+
+	/*
+	 * Done.
+	 */
+print_total:
+	printf("------------------------------------------------------------------------\n");
+	printf("  %s latency: %.*s %9.2f us (100%%)\n", irq ? "   IRQ" : "Thread",
+	       37, spaces, ns_to_usf(total));
+}
+
+static int timerlat_auto_analysis_collect_trace(struct timerlat_aa_context *taa_ctx)
+{
+	struct trace_instance *trace = &taa_ctx->tool->trace;
+	int retval;
+
+	retval = tracefs_iterate_raw_events(trace->tep,
+					    trace->inst,
+					    NULL,
+					    0,
+					    collect_registered_events,
+					    trace);
+		if (retval < 0) {
+			err_msg("Error iterating on events\n");
+			return 0;
+		}
+
+	return 1;
+}
+
+/**
+ * timerlat_auto_analysis - Analyze the collected data
+ */
+void timerlat_auto_analysis(int irq_thresh, int thread_thresh)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+	unsigned long long max_exit_from_idle = 0;
+	struct timerlat_aa_data *taa_data;
+	int max_exit_from_idle_cpu;
+	struct tep_handle *tep;
+	int cpu;
+
+	timerlat_auto_analysis_collect_trace(taa_ctx);
+
+	/* bring stop tracing to the ns scale */
+	irq_thresh = irq_thresh * 1000;
+	thread_thresh = thread_thresh * 1000;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		taa_data = timerlat_aa_get_data(taa_ctx, cpu);
+
+		if (irq_thresh && taa_data->tlat_irq_latency >= irq_thresh) {
+			printf("## CPU %d hit stop tracing, analyzing it ##\n", cpu);
+			timerlat_thread_analysis(taa_data, cpu, irq_thresh, thread_thresh);
+		} else if (thread_thresh && (taa_data->tlat_thread_latency) >= thread_thresh) {
+			printf("## CPU %d hit stop tracing, analyzing it ##\n", cpu);
+			timerlat_thread_analysis(taa_data, cpu, irq_thresh, thread_thresh);
+		}
+
+		if (taa_data->max_exit_idle_latency > max_exit_from_idle) {
+			max_exit_from_idle = taa_data->max_exit_idle_latency;
+			max_exit_from_idle_cpu = cpu;
+		}
+
+	}
+
+	if (max_exit_from_idle) {
+		printf("\n");
+		printf("Max timerlat IRQ latency from idle: %.2f us in cpu %d\n",
+			ns_to_usf(max_exit_from_idle), max_exit_from_idle_cpu);
+	}
+	if (!taa_ctx->dump_tasks)
+		return;
+
+	printf("\n");
+	printf("Printing CPU tasks:\n");
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		taa_data = timerlat_aa_get_data(taa_ctx, cpu);
+		tep = taa_ctx->tool->trace.tep;
+
+		printf("    [%.3d] %24s:%llu", cpu, taa_data->current_comm, taa_data->current_pid);
+
+		if (taa_data->kworker_func)
+			printf(" kworker:%s:%s",
+				tep_find_function(tep, taa_data->kworker) ? : "<...>",
+				tep_find_function(tep, taa_data->kworker_func));
+		printf("\n");
+	}
+
+}
+
+/*
+ * timerlat_aa_destroy_seqs - Destroy seq files used to store parsed data
+ */
+static void timerlat_aa_destroy_seqs(struct timerlat_aa_context *taa_ctx)
+{
+	struct timerlat_aa_data *taa_data;
+	int i;
+
+	if (!taa_ctx->taa_data)
+		return;
+
+	for (i = 0; i < nr_cpus; i++) {
+		taa_data = timerlat_aa_get_data(taa_ctx, i);
+
+		if (taa_data->prev_irqs_seq) {
+			trace_seq_destroy(taa_data->prev_irqs_seq);
+			free(taa_data->prev_irqs_seq);
+		}
+
+		if (taa_data->nmi_seq) {
+			trace_seq_destroy(taa_data->nmi_seq);
+			free(taa_data->nmi_seq);
+		}
+
+		if (taa_data->irqs_seq) {
+			trace_seq_destroy(taa_data->irqs_seq);
+			free(taa_data->irqs_seq);
+		}
+
+		if (taa_data->softirqs_seq) {
+			trace_seq_destroy(taa_data->softirqs_seq);
+			free(taa_data->softirqs_seq);
+		}
+
+		if (taa_data->threads_seq) {
+			trace_seq_destroy(taa_data->threads_seq);
+			free(taa_data->threads_seq);
+		}
+
+		if (taa_data->stack_seq) {
+			trace_seq_destroy(taa_data->stack_seq);
+			free(taa_data->stack_seq);
+		}
+	}
+}
+
+/*
+ * timerlat_aa_init_seqs - Init seq files used to store parsed information
+ *
+ * Instead of keeping data structures to store raw data, use seq files to
+ * store parsed data.
+ *
+ * Allocates and initialize seq files.
+ *
+ * Returns 0 on success, -1 otherwise.
+ */
+static int timerlat_aa_init_seqs(struct timerlat_aa_context *taa_ctx)
+{
+	struct timerlat_aa_data *taa_data;
+	int i;
+
+	for (i = 0; i < nr_cpus; i++) {
+
+		taa_data = timerlat_aa_get_data(taa_ctx, i);
+
+		taa_data->prev_irqs_seq = calloc(1, sizeof(*taa_data->prev_irqs_seq));
+		if (!taa_data->prev_irqs_seq)
+			goto out_err;
+
+		trace_seq_init(taa_data->prev_irqs_seq);
+
+		taa_data->nmi_seq = calloc(1, sizeof(*taa_data->nmi_seq));
+		if (!taa_data->nmi_seq)
+			goto out_err;
+
+		trace_seq_init(taa_data->nmi_seq);
+
+		taa_data->irqs_seq = calloc(1, sizeof(*taa_data->irqs_seq));
+		if (!taa_data->irqs_seq)
+			goto out_err;
+
+		trace_seq_init(taa_data->irqs_seq);
+
+		taa_data->softirqs_seq = calloc(1, sizeof(*taa_data->softirqs_seq));
+		if (!taa_data->softirqs_seq)
+			goto out_err;
+
+		trace_seq_init(taa_data->softirqs_seq);
+
+		taa_data->threads_seq = calloc(1, sizeof(*taa_data->threads_seq));
+		if (!taa_data->threads_seq)
+			goto out_err;
+
+		trace_seq_init(taa_data->threads_seq);
+
+		taa_data->stack_seq = calloc(1, sizeof(*taa_data->stack_seq));
+		if (!taa_data->stack_seq)
+			goto out_err;
+
+		trace_seq_init(taa_data->stack_seq);
+	}
+
+	return 0;
+
+out_err:
+	timerlat_aa_destroy_seqs(taa_ctx);
+	return -1;
+}
+
+/*
+ * timerlat_aa_unregister_events - Unregister events used in the auto-analysis
+ */
+static void timerlat_aa_unregister_events(struct osnoise_tool *tool, int dump_tasks)
+{
+
+	tep_unregister_event_handler(tool->trace.tep, -1, "ftrace", "timerlat",
+				     timerlat_aa_handler, tool);
+
+	tracefs_event_disable(tool->trace.inst, "osnoise", NULL);
+
+	tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "nmi_noise",
+				     timerlat_aa_nmi_handler, tool);
+
+	tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "irq_noise",
+				     timerlat_aa_irq_handler, tool);
+
+	tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "softirq_noise",
+				     timerlat_aa_softirq_handler, tool);
+
+	tep_unregister_event_handler(tool->trace.tep, -1, "osnoise", "thread_noise",
+				     timerlat_aa_thread_handler, tool);
+
+	tep_unregister_event_handler(tool->trace.tep, -1, "ftrace", "kernel_stack",
+				     timerlat_aa_stack_handler, tool);
+	if (!dump_tasks)
+		return;
+
+	tracefs_event_disable(tool->trace.inst, "sched", "sched_switch");
+	tep_unregister_event_handler(tool->trace.tep, -1, "sched", "sched_switch",
+				     timerlat_aa_sched_switch_handler, tool);
+
+	tracefs_event_disable(tool->trace.inst, "workqueue", "workqueue_execute_start");
+	tep_unregister_event_handler(tool->trace.tep, -1, "workqueue", "workqueue_execute_start",
+				     timerlat_aa_kworker_start_handler, tool);
+}
+
+/*
+ * timerlat_aa_register_events - Register events used in the auto-analysis
+ *
+ * Returns 0 on success, -1 otherwise.
+ */
+static int timerlat_aa_register_events(struct osnoise_tool *tool, int dump_tasks)
+{
+	int retval;
+
+	tep_register_event_handler(tool->trace.tep, -1, "ftrace", "timerlat",
+				timerlat_aa_handler, tool);
+
+
+	/*
+	 * register auto-analysis handlers.
+	 */
+	retval = tracefs_event_enable(tool->trace.inst, "osnoise", NULL);
+	if (retval < 0 && !errno) {
+		err_msg("Could not find osnoise events\n");
+		goto out_err;
+	}
+
+	tep_register_event_handler(tool->trace.tep, -1, "osnoise", "nmi_noise",
+				   timerlat_aa_nmi_handler, tool);
+
+	tep_register_event_handler(tool->trace.tep, -1, "osnoise", "irq_noise",
+				   timerlat_aa_irq_handler, tool);
+
+	tep_register_event_handler(tool->trace.tep, -1, "osnoise", "softirq_noise",
+				   timerlat_aa_softirq_handler, tool);
+
+	tep_register_event_handler(tool->trace.tep, -1, "osnoise", "thread_noise",
+				   timerlat_aa_thread_handler, tool);
+
+	tep_register_event_handler(tool->trace.tep, -1, "ftrace", "kernel_stack",
+				   timerlat_aa_stack_handler, tool);
+
+	if (!dump_tasks)
+		return 0;
+
+	/*
+	 * Dump task events.
+	 */
+	retval = tracefs_event_enable(tool->trace.inst, "sched", "sched_switch");
+	if (retval < 0 && !errno) {
+		err_msg("Could not find sched_switch\n");
+		goto out_err;
+	}
+
+	tep_register_event_handler(tool->trace.tep, -1, "sched", "sched_switch",
+				   timerlat_aa_sched_switch_handler, tool);
+
+	retval = tracefs_event_enable(tool->trace.inst, "workqueue", "workqueue_execute_start");
+	if (retval < 0 && !errno) {
+		err_msg("Could not find workqueue_execute_start\n");
+		goto out_err;
+	}
+
+	tep_register_event_handler(tool->trace.tep, -1, "workqueue", "workqueue_execute_start",
+				   timerlat_aa_kworker_start_handler, tool);
+
+	return 0;
+
+out_err:
+	timerlat_aa_unregister_events(tool, dump_tasks);
+	return -1;
+}
+
+/**
+ * timerlat_aa_destroy - Destroy timerlat auto-analysis
+ */
+void timerlat_aa_destroy(void)
+{
+	struct timerlat_aa_context *taa_ctx = timerlat_aa_get_ctx();
+
+	if (!taa_ctx)
+		return;
+
+	if (!taa_ctx->taa_data)
+		goto out_ctx;
+
+	timerlat_aa_unregister_events(taa_ctx->tool, taa_ctx->dump_tasks);
+	timerlat_aa_destroy_seqs(taa_ctx);
+	free(taa_ctx->taa_data);
+out_ctx:
+	free(taa_ctx);
+}
+
+/**
+ * timerlat_aa_init - Initialize timerlat auto-analysis
+ *
+ * Returns 0 on success, -1 otherwise.
+ */
+int timerlat_aa_init(struct osnoise_tool *tool, int dump_tasks, enum stack_format stack_format)
+{
+	struct timerlat_aa_context *taa_ctx;
+	int retval;
+
+	taa_ctx = calloc(1, sizeof(*taa_ctx));
+	if (!taa_ctx)
+		return -1;
+
+	__timerlat_aa_ctx = taa_ctx;
+
+	taa_ctx->tool = tool;
+	taa_ctx->dump_tasks = dump_tasks;
+	taa_ctx->stack_format = stack_format;
+
+	taa_ctx->taa_data = calloc(nr_cpus, sizeof(*taa_ctx->taa_data));
+	if (!taa_ctx->taa_data)
+		goto out_err;
+
+	retval = timerlat_aa_init_seqs(taa_ctx);
+	if (retval)
+		goto out_err;
+
+	retval = timerlat_aa_register_events(tool, dump_tasks);
+	if (retval)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	timerlat_aa_destroy();
+	return -1;
+}
diff --git a/tools/tracing/rtla/src/timerlat_aa.h b/tools/tracing/rtla/src/timerlat_aa.h
new file mode 100644
index 000000000..a11b5f30c
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_aa.h
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+int timerlat_aa_init(struct osnoise_tool *tool, int dump_task, enum stack_format stack_format);
+void timerlat_aa_destroy(void);
+
+void timerlat_auto_analysis(int irq_thresh, int thread_thresh);
diff --git a/tools/tracing/rtla/src/timerlat_bpf.c b/tools/tracing/rtla/src/timerlat_bpf.c
new file mode 100644
index 000000000..dd3cf71d7
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_bpf.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifdef HAVE_BPF_SKEL
+#define _GNU_SOURCE
+#include "timerlat.h"
+#include "timerlat_bpf.h"
+#include "timerlat.skel.h"
+
+static struct timerlat_bpf *bpf;
+
+/* BPF object and program for action program */
+static struct bpf_object *obj;
+static struct bpf_program *prog;
+
+/*
+ * timerlat_bpf_init - load and initialize BPF program to collect timerlat data
+ */
+int timerlat_bpf_init(struct timerlat_params *params)
+{
+	int err;
+
+	debug_msg("Loading BPF program\n");
+
+	bpf = timerlat_bpf__open();
+	if (!bpf)
+		return 1;
+
+	/* Pass common options */
+	bpf->rodata->output_divisor = params->common.output_divisor;
+	bpf->rodata->entries = params->common.hist.entries;
+	bpf->rodata->irq_threshold = params->common.stop_us;
+	bpf->rodata->thread_threshold = params->common.stop_total_us;
+	bpf->rodata->aa_only = params->common.aa_only;
+
+	if (params->common.hist.entries != 0) {
+		/* Pass histogram options */
+		bpf->rodata->bucket_size = params->common.hist.bucket_size;
+
+		/* Set histogram array sizes */
+		bpf_map__set_max_entries(bpf->maps.hist_irq, params->common.hist.entries);
+		bpf_map__set_max_entries(bpf->maps.hist_thread, params->common.hist.entries);
+		bpf_map__set_max_entries(bpf->maps.hist_user, params->common.hist.entries);
+	} else {
+		/* No entries, disable histogram */
+		bpf_map__set_autocreate(bpf->maps.hist_irq, false);
+		bpf_map__set_autocreate(bpf->maps.hist_thread, false);
+		bpf_map__set_autocreate(bpf->maps.hist_user, false);
+	}
+
+	if (params->common.aa_only) {
+		/* Auto-analysis only, disable summary */
+		bpf_map__set_autocreate(bpf->maps.summary_irq, false);
+		bpf_map__set_autocreate(bpf->maps.summary_thread, false);
+		bpf_map__set_autocreate(bpf->maps.summary_user, false);
+	}
+
+	/* Load and verify BPF program */
+	err = timerlat_bpf__load(bpf);
+	if (err) {
+		timerlat_bpf__destroy(bpf);
+		return err;
+	}
+
+	return 0;
+}
+
+/*
+ * timerlat_bpf_set_action - set action on threshold executed on BPF side
+ */
+static int timerlat_bpf_set_action(struct bpf_program *prog)
+{
+	unsigned int key = 0, value = bpf_program__fd(prog);
+
+	return bpf_map__update_elem(bpf->maps.bpf_action,
+				    &key, sizeof(key),
+				    &value, sizeof(value),
+				    BPF_ANY);
+}
+
+/*
+ * timerlat_bpf_attach - attach BPF program to collect timerlat data
+ */
+int timerlat_bpf_attach(void)
+{
+	debug_msg("Attaching BPF program\n");
+
+	return timerlat_bpf__attach(bpf);
+}
+
+/*
+ * timerlat_bpf_detach - detach BPF program to collect timerlat data
+ */
+void timerlat_bpf_detach(void)
+{
+	timerlat_bpf__detach(bpf);
+}
+
+/*
+ * timerlat_bpf_detach - destroy BPF program to collect timerlat data
+ */
+void timerlat_bpf_destroy(void)
+{
+	timerlat_bpf__destroy(bpf);
+	bpf = NULL;
+	if (obj)
+		bpf_object__close(obj);
+	obj = NULL;
+	prog = NULL;
+}
+
+static int handle_rb_event(void *ctx, void *data, size_t data_sz)
+{
+	return 0;
+}
+
+/*
+ * timerlat_bpf_wait - wait until tracing is stopped or signal
+ */
+int timerlat_bpf_wait(int timeout)
+{
+	struct ring_buffer *rb;
+	int retval;
+
+	rb = ring_buffer__new(bpf_map__fd(bpf->maps.signal_stop_tracing),
+			      handle_rb_event, NULL, NULL);
+	retval = ring_buffer__poll(rb, timeout * 1000);
+	ring_buffer__free(rb);
+
+	return retval;
+}
+
+/*
+ * timerlat_bpf_restart_tracing - restart stopped tracing
+ */
+int timerlat_bpf_restart_tracing(void)
+{
+	unsigned int key = 0;
+	unsigned long long value = 0;
+
+	return bpf_map__update_elem(bpf->maps.stop_tracing,
+				    &key, sizeof(key),
+				    &value, sizeof(value), BPF_ANY);
+}
+
+static int get_value(struct bpf_map *map_irq,
+		     struct bpf_map *map_thread,
+		     struct bpf_map *map_user,
+		     int key,
+		     long long *value_irq,
+		     long long *value_thread,
+		     long long *value_user)
+{
+	int err;
+
+	err = bpf_map__lookup_elem(map_irq, &key,
+				   sizeof(unsigned int), value_irq,
+				   sizeof(long long) * nr_cpus, 0);
+	if (err)
+		return err;
+	err = bpf_map__lookup_elem(map_thread, &key,
+				   sizeof(unsigned int), value_thread,
+				   sizeof(long long) * nr_cpus, 0);
+	if (err)
+		return err;
+	err = bpf_map__lookup_elem(map_user, &key,
+				   sizeof(unsigned int), value_user,
+				   sizeof(long long) * nr_cpus, 0);
+	if (err)
+		return err;
+	return 0;
+}
+
+/*
+ * timerlat_bpf_get_hist_value - get value from BPF hist map
+ */
+int timerlat_bpf_get_hist_value(int key,
+				long long *value_irq,
+				long long *value_thread,
+				long long *value_user)
+{
+	return get_value(bpf->maps.hist_irq,
+			 bpf->maps.hist_thread,
+			 bpf->maps.hist_user,
+			 key, value_irq, value_thread, value_user);
+}
+
+/*
+ * timerlat_bpf_get_summary_value - get value from BPF summary map
+ */
+int timerlat_bpf_get_summary_value(enum summary_field key,
+				   long long *value_irq,
+				   long long *value_thread,
+				   long long *value_user)
+{
+	return get_value(bpf->maps.summary_irq,
+			 bpf->maps.summary_thread,
+			 bpf->maps.summary_user,
+			 key, value_irq, value_thread, value_user);
+}
+
+/*
+ * timerlat_load_bpf_action_program - load and register a BPF action program
+ */
+int timerlat_load_bpf_action_program(const char *program_path)
+{
+	int err;
+
+	obj = bpf_object__open_file(program_path, NULL);
+	if (!obj) {
+		err_msg("Failed to open BPF action program: %s\n", program_path);
+		goto out_err;
+	}
+
+	err = bpf_object__load(obj);
+	if (err) {
+		err_msg("Failed to load BPF action program: %s\n", program_path);
+		goto out_obj_err;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "action_handler");
+	if (!prog) {
+		err_msg("BPF action program must have 'action_handler' function: %s\n",
+			program_path);
+		goto out_obj_err;
+	}
+
+	err = timerlat_bpf_set_action(prog);
+	if (err) {
+		err_msg("Failed to register BPF action program: %s\n", program_path);
+		goto out_prog_err;
+	}
+
+	return 0;
+
+out_prog_err:
+	prog = NULL;
+out_obj_err:
+	bpf_object__close(obj);
+	obj = NULL;
+out_err:
+	return 1;
+}
+
+#endif /* HAVE_BPF_SKEL */
diff --git a/tools/tracing/rtla/src/timerlat_bpf.h b/tools/tracing/rtla/src/timerlat_bpf.h
new file mode 100644
index 000000000..33f0df6a9
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_bpf.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+
+enum summary_field {
+	SUMMARY_CURRENT,
+	SUMMARY_MIN,
+	SUMMARY_MAX,
+	SUMMARY_COUNT,
+	SUMMARY_SUM,
+	SUMMARY_OVERFLOW,
+	SUMMARY_FIELD_N
+};
+
+#ifndef __bpf__
+#ifdef HAVE_BPF_SKEL
+int timerlat_bpf_init(struct timerlat_params *params);
+int timerlat_bpf_attach(void);
+void timerlat_bpf_detach(void);
+void timerlat_bpf_destroy(void);
+int timerlat_bpf_wait(int timeout);
+int timerlat_bpf_restart_tracing(void);
+int timerlat_bpf_get_hist_value(int key,
+				long long *value_irq,
+				long long *value_thread,
+				long long *value_user);
+int timerlat_bpf_get_summary_value(enum summary_field key,
+				   long long *value_irq,
+				   long long *value_thread,
+				   long long *value_user);
+int timerlat_load_bpf_action_program(const char *program_path);
+static inline int have_libbpf_support(void) { return 1; }
+#else
+static inline int timerlat_bpf_init(struct timerlat_params *params)
+{
+	return -1;
+}
+static inline int timerlat_bpf_attach(void) { return -1; }
+static inline void timerlat_bpf_detach(void) { };
+static inline void timerlat_bpf_destroy(void) { };
+static inline int timerlat_bpf_wait(int timeout) { return -1; }
+static inline int timerlat_bpf_restart_tracing(void) { return -1; };
+static inline int timerlat_bpf_get_hist_value(int key,
+					      long long *value_irq,
+					      long long *value_thread,
+					      long long *value_user)
+{
+	return -1;
+}
+static inline int timerlat_bpf_get_summary_value(enum summary_field key,
+						 long long *value_irq,
+						 long long *value_thread,
+						 long long *value_user)
+{
+	return -1;
+}
+static inline int timerlat_load_bpf_action_program(const char *program_path)
+{
+	return -1;
+}
+static inline int have_libbpf_support(void) { return 0; }
+#endif /* HAVE_BPF_SKEL */
+#endif /* __bpf__ */
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
new file mode 100644
index 000000000..df7b1398a
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -0,0 +1,789 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+#include <sched.h>
+#include <pthread.h>
+
+#include "timerlat.h"
+#include "timerlat_aa.h"
+#include "timerlat_bpf.h"
+#include "cli.h"
+#include "common.h"
+
+struct timerlat_hist_cpu {
+	int			*irq;
+	int			*thread;
+	int			*user;
+
+	unsigned long long	irq_count;
+	unsigned long long	thread_count;
+	unsigned long long	user_count;
+
+	unsigned long long	min_irq;
+	unsigned long long	sum_irq;
+	unsigned long long	max_irq;
+
+	unsigned long long	min_thread;
+	unsigned long long	sum_thread;
+	unsigned long long	max_thread;
+
+	unsigned long long	min_user;
+	unsigned long long	sum_user;
+	unsigned long long	max_user;
+};
+
+struct timerlat_hist_data {
+	struct timerlat_hist_cpu	*hist;
+	int				entries;
+	int				bucket_size;
+};
+
+/*
+ * timerlat_free_histogram - free runtime data
+ */
+static void
+timerlat_free_histogram(struct timerlat_hist_data *data)
+{
+	int cpu;
+
+	/* one histogram for IRQ and one for thread, per CPU */
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		if (data->hist[cpu].irq)
+			free(data->hist[cpu].irq);
+
+		if (data->hist[cpu].thread)
+			free(data->hist[cpu].thread);
+
+		if (data->hist[cpu].user)
+			free(data->hist[cpu].user);
+
+	}
+
+	/* one set of histograms per CPU */
+	if (data->hist)
+		free(data->hist);
+}
+
+static void timerlat_free_histogram_tool(struct osnoise_tool *tool)
+{
+	timerlat_free_histogram(tool->data);
+	timerlat_free(tool);
+}
+
+/*
+ * timerlat_alloc_histogram - alloc runtime data
+ */
+static struct timerlat_hist_data
+*timerlat_alloc_histogram(int entries, int bucket_size)
+{
+	struct timerlat_hist_data *data;
+	int cpu;
+
+	data = calloc(1, sizeof(*data));
+	if (!data)
+		return NULL;
+
+	data->entries = entries;
+	data->bucket_size = bucket_size;
+
+	/* one set of histograms per CPU */
+	data->hist = calloc(1, sizeof(*data->hist) * nr_cpus);
+	if (!data->hist)
+		goto cleanup;
+
+	/* one histogram for IRQ and one for thread, per cpu */
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		data->hist[cpu].irq = calloc(1, sizeof(*data->hist->irq) * (entries + 1));
+		if (!data->hist[cpu].irq)
+			goto cleanup;
+
+		data->hist[cpu].thread = calloc(1, sizeof(*data->hist->thread) * (entries + 1));
+		if (!data->hist[cpu].thread)
+			goto cleanup;
+
+		data->hist[cpu].user = calloc(1, sizeof(*data->hist->user) * (entries + 1));
+		if (!data->hist[cpu].user)
+			goto cleanup;
+	}
+
+	/* set the min to max */
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		data->hist[cpu].min_irq = ~0;
+		data->hist[cpu].min_thread = ~0;
+		data->hist[cpu].min_user = ~0;
+	}
+
+	return data;
+
+cleanup:
+	timerlat_free_histogram(data);
+	return NULL;
+}
+
+/*
+ * timerlat_hist_update - record a new timerlat occurent on cpu, updating data
+ */
+static void
+timerlat_hist_update(struct osnoise_tool *tool, int cpu,
+		     unsigned long long context,
+		     unsigned long long latency)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	struct timerlat_hist_data *data = tool->data;
+	int entries = data->entries;
+	int bucket;
+	int *hist;
+
+	if (params->common.output_divisor)
+		latency = latency / params->common.output_divisor;
+
+	bucket = latency / data->bucket_size;
+
+	if (!context) {
+		hist = data->hist[cpu].irq;
+		data->hist[cpu].irq_count++;
+		update_min(&data->hist[cpu].min_irq, &latency);
+		update_sum(&data->hist[cpu].sum_irq, &latency);
+		update_max(&data->hist[cpu].max_irq, &latency);
+	} else if (context == 1) {
+		hist = data->hist[cpu].thread;
+		data->hist[cpu].thread_count++;
+		update_min(&data->hist[cpu].min_thread, &latency);
+		update_sum(&data->hist[cpu].sum_thread, &latency);
+		update_max(&data->hist[cpu].max_thread, &latency);
+	} else { /* user */
+		hist = data->hist[cpu].user;
+		data->hist[cpu].user_count++;
+		update_min(&data->hist[cpu].min_user, &latency);
+		update_sum(&data->hist[cpu].sum_user, &latency);
+		update_max(&data->hist[cpu].max_user, &latency);
+	}
+
+	if (bucket < entries)
+		hist[bucket]++;
+	else
+		hist[entries]++;
+}
+
+/*
+ * timerlat_hist_handler - this is the handler for timerlat tracer events
+ */
+static int
+timerlat_hist_handler(struct trace_seq *s, struct tep_record *record,
+		     struct tep_event *event, void *data)
+{
+	struct trace_instance *trace = data;
+	unsigned long long context, latency;
+	struct osnoise_tool *tool;
+	int cpu = record->cpu;
+
+	tool = container_of(trace, struct osnoise_tool, trace);
+
+	tep_get_field_val(s, event, "context", record, &context, 1);
+	tep_get_field_val(s, event, "timer_latency", record, &latency, 1);
+
+	timerlat_hist_update(tool, cpu, context, latency);
+
+	return 0;
+}
+
+/*
+ * timerlat_hist_bpf_pull_data - copy data from BPF maps into userspace
+ */
+static int timerlat_hist_bpf_pull_data(struct osnoise_tool *tool)
+{
+	struct timerlat_hist_data *data = tool->data;
+	int i, j, err;
+	long long value_irq[nr_cpus],
+		  value_thread[nr_cpus],
+		  value_user[nr_cpus];
+
+	/* Pull histogram */
+	for (i = 0; i < data->entries; i++) {
+		err = timerlat_bpf_get_hist_value(i, value_irq, value_thread,
+						  value_user);
+		if (err)
+			return err;
+		for (j = 0; j < nr_cpus; j++) {
+			data->hist[j].irq[i] = value_irq[j];
+			data->hist[j].thread[i] = value_thread[j];
+			data->hist[j].user[i] = value_user[j];
+		}
+	}
+
+	/* Pull summary */
+	err = timerlat_bpf_get_summary_value(SUMMARY_COUNT,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->hist[i].irq_count = value_irq[i];
+		data->hist[i].thread_count = value_thread[i];
+		data->hist[i].user_count = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_MIN,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->hist[i].min_irq = value_irq[i];
+		data->hist[i].min_thread = value_thread[i];
+		data->hist[i].min_user = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_MAX,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->hist[i].max_irq = value_irq[i];
+		data->hist[i].max_thread = value_thread[i];
+		data->hist[i].max_user = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_SUM,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->hist[i].sum_irq = value_irq[i];
+		data->hist[i].sum_thread = value_thread[i];
+		data->hist[i].sum_user = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_OVERFLOW,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->hist[i].irq[data->entries] = value_irq[i];
+		data->hist[i].thread[data->entries] = value_thread[i];
+		data->hist[i].user[data->entries] = value_user[i];
+	}
+
+	return 0;
+}
+
+/*
+ * timerlat_hist_header - print the header of the tracer to the output
+ */
+static void timerlat_hist_header(struct osnoise_tool *tool)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	struct timerlat_hist_data *data = tool->data;
+	struct trace_seq *s = tool->trace.seq;
+	char duration[26];
+	int cpu;
+
+	if (params->common.hist.no_header)
+		return;
+
+	get_duration(tool->start_time, duration, sizeof(duration));
+	trace_seq_printf(s, "# RTLA timerlat histogram\n");
+	trace_seq_printf(s, "# Time unit is %s (%s)\n",
+			params->common.output_divisor == 1 ? "nanoseconds" : "microseconds",
+			params->common.output_divisor == 1 ? "ns" : "us");
+
+	trace_seq_printf(s, "# Duration: %s\n", duration);
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(s, "Index");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+			continue;
+
+		if (!params->common.hist.no_irq)
+			trace_seq_printf(s, "   IRQ-%03d", cpu);
+
+		if (!params->common.hist.no_thread)
+			trace_seq_printf(s, "   Thr-%03d", cpu);
+
+		if (params->common.user_data)
+			trace_seq_printf(s, "   Usr-%03d", cpu);
+	}
+	trace_seq_printf(s, "\n");
+
+
+	trace_seq_do_printf(s);
+	trace_seq_reset(s);
+}
+
+/*
+ * format_summary_value - format a line of summary value (min, max or avg)
+ * of hist data
+ */
+static void format_summary_value(struct trace_seq *seq,
+				 int count,
+				 unsigned long long val,
+				 bool avg)
+{
+	if (count)
+		trace_seq_printf(seq, "%9llu ", avg ? val / count : val);
+	else
+		trace_seq_printf(seq, "%9c ", '-');
+}
+
+/*
+ * timerlat_print_summary - print the summary of the hist data to the output
+ */
+static void
+timerlat_print_summary(struct timerlat_params *params,
+		       struct trace_instance *trace,
+		       struct timerlat_hist_data *data)
+{
+	int cpu;
+
+	if (params->common.hist.no_summary)
+		return;
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "count:");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+			continue;
+
+		if (!params->common.hist.no_irq)
+			trace_seq_printf(trace->seq, "%9llu ",
+					data->hist[cpu].irq_count);
+
+		if (!params->common.hist.no_thread)
+			trace_seq_printf(trace->seq, "%9llu ",
+					data->hist[cpu].thread_count);
+
+		if (params->common.user_data)
+			trace_seq_printf(trace->seq, "%9llu ",
+					 data->hist[cpu].user_count);
+	}
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "min:  ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+			continue;
+
+		if (!params->common.hist.no_irq)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].irq_count,
+					     data->hist[cpu].min_irq,
+					     false);
+
+		if (!params->common.hist.no_thread)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].thread_count,
+					     data->hist[cpu].min_thread,
+					     false);
+
+		if (params->common.user_data)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].user_count,
+					     data->hist[cpu].min_user,
+					     false);
+	}
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "avg:  ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+			continue;
+
+		if (!params->common.hist.no_irq)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].irq_count,
+					     data->hist[cpu].sum_irq,
+					     true);
+
+		if (!params->common.hist.no_thread)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].thread_count,
+					     data->hist[cpu].sum_thread,
+					     true);
+
+		if (params->common.user_data)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].user_count,
+					     data->hist[cpu].sum_user,
+					     true);
+	}
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "max:  ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+			continue;
+
+		if (!params->common.hist.no_irq)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].irq_count,
+					     data->hist[cpu].max_irq,
+					     false);
+
+		if (!params->common.hist.no_thread)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].thread_count,
+					     data->hist[cpu].max_thread,
+					     false);
+
+		if (params->common.user_data)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].user_count,
+					     data->hist[cpu].max_user,
+					     false);
+	}
+	trace_seq_printf(trace->seq, "\n");
+	trace_seq_do_printf(trace->seq);
+	trace_seq_reset(trace->seq);
+}
+
+static void
+timerlat_print_stats_all(struct timerlat_params *params,
+			 struct trace_instance *trace,
+			 struct timerlat_hist_data *data)
+{
+	struct timerlat_hist_cpu *cpu_data;
+	struct timerlat_hist_cpu sum;
+	int cpu;
+
+	if (params->common.hist.no_summary)
+		return;
+
+	memset(&sum, 0, sizeof(sum));
+	sum.min_irq = ~0;
+	sum.min_thread = ~0;
+	sum.min_user = ~0;
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+			continue;
+
+		cpu_data = &data->hist[cpu];
+
+		sum.irq_count += cpu_data->irq_count;
+		update_min(&sum.min_irq, &cpu_data->min_irq);
+		update_sum(&sum.sum_irq, &cpu_data->sum_irq);
+		update_max(&sum.max_irq, &cpu_data->max_irq);
+
+		sum.thread_count += cpu_data->thread_count;
+		update_min(&sum.min_thread, &cpu_data->min_thread);
+		update_sum(&sum.sum_thread, &cpu_data->sum_thread);
+		update_max(&sum.max_thread, &cpu_data->max_thread);
+
+		sum.user_count += cpu_data->user_count;
+		update_min(&sum.min_user, &cpu_data->min_user);
+		update_sum(&sum.sum_user, &cpu_data->sum_user);
+		update_max(&sum.max_user, &cpu_data->max_user);
+	}
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "ALL:  ");
+
+	if (!params->common.hist.no_irq)
+		trace_seq_printf(trace->seq, "      IRQ");
+
+	if (!params->common.hist.no_thread)
+		trace_seq_printf(trace->seq, "       Thr");
+
+	if (params->common.user_data)
+		trace_seq_printf(trace->seq, "       Usr");
+
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "count:");
+
+	if (!params->common.hist.no_irq)
+		trace_seq_printf(trace->seq, "%9llu ",
+				 sum.irq_count);
+
+	if (!params->common.hist.no_thread)
+		trace_seq_printf(trace->seq, "%9llu ",
+				 sum.thread_count);
+
+	if (params->common.user_data)
+		trace_seq_printf(trace->seq, "%9llu ",
+				 sum.user_count);
+
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "min:  ");
+
+	if (!params->common.hist.no_irq)
+		format_summary_value(trace->seq,
+				     sum.irq_count,
+				     sum.min_irq,
+				     false);
+
+	if (!params->common.hist.no_thread)
+		format_summary_value(trace->seq,
+				     sum.thread_count,
+				     sum.min_thread,
+				     false);
+
+	if (params->common.user_data)
+		format_summary_value(trace->seq,
+				     sum.user_count,
+				     sum.min_user,
+				     false);
+
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "avg:  ");
+
+	if (!params->common.hist.no_irq)
+		format_summary_value(trace->seq,
+				     sum.irq_count,
+				     sum.sum_irq,
+				     true);
+
+	if (!params->common.hist.no_thread)
+		format_summary_value(trace->seq,
+				     sum.thread_count,
+				     sum.sum_thread,
+				     true);
+
+	if (params->common.user_data)
+		format_summary_value(trace->seq,
+				     sum.user_count,
+				     sum.sum_user,
+				     true);
+
+	trace_seq_printf(trace->seq, "\n");
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "max:  ");
+
+	if (!params->common.hist.no_irq)
+		format_summary_value(trace->seq,
+				     sum.irq_count,
+				     sum.max_irq,
+				     false);
+
+	if (!params->common.hist.no_thread)
+		format_summary_value(trace->seq,
+				     sum.thread_count,
+				     sum.max_thread,
+				     false);
+
+	if (params->common.user_data)
+		format_summary_value(trace->seq,
+				     sum.user_count,
+				     sum.max_user,
+				     false);
+
+	trace_seq_printf(trace->seq, "\n");
+	trace_seq_do_printf(trace->seq);
+	trace_seq_reset(trace->seq);
+}
+
+/*
+ * timerlat_print_stats - print data for each CPUs
+ */
+static void
+timerlat_print_stats(struct osnoise_tool *tool)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	struct timerlat_hist_data *data = tool->data;
+	struct trace_instance *trace = &tool->trace;
+	int bucket, cpu;
+	int total;
+
+	timerlat_hist_header(tool);
+
+	for (bucket = 0; bucket < data->entries; bucket++) {
+		total = 0;
+
+		if (!params->common.hist.no_index)
+			trace_seq_printf(trace->seq, "%-6d",
+					 bucket * data->bucket_size);
+
+		for_each_monitored_cpu(cpu, &params->common) {
+
+			if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+				continue;
+
+			if (!params->common.hist.no_irq) {
+				total += data->hist[cpu].irq[bucket];
+				trace_seq_printf(trace->seq, "%9d ",
+						data->hist[cpu].irq[bucket]);
+			}
+
+			if (!params->common.hist.no_thread) {
+				total += data->hist[cpu].thread[bucket];
+				trace_seq_printf(trace->seq, "%9d ",
+						data->hist[cpu].thread[bucket]);
+			}
+
+			if (params->common.user_data) {
+				total += data->hist[cpu].user[bucket];
+				trace_seq_printf(trace->seq, "%9d ",
+						data->hist[cpu].user[bucket]);
+			}
+
+		}
+
+		if (total == 0 && !params->common.hist.with_zeros) {
+			trace_seq_reset(trace->seq);
+			continue;
+		}
+
+		trace_seq_printf(trace->seq, "\n");
+		trace_seq_do_printf(trace->seq);
+		trace_seq_reset(trace->seq);
+	}
+
+	if (!params->common.hist.no_index)
+		trace_seq_printf(trace->seq, "over: ");
+
+	for_each_monitored_cpu(cpu, &params->common) {
+
+		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
+			continue;
+
+		if (!params->common.hist.no_irq)
+			trace_seq_printf(trace->seq, "%9d ",
+					 data->hist[cpu].irq[data->entries]);
+
+		if (!params->common.hist.no_thread)
+			trace_seq_printf(trace->seq, "%9d ",
+					 data->hist[cpu].thread[data->entries]);
+
+		if (params->common.user_data)
+			trace_seq_printf(trace->seq, "%9d ",
+					 data->hist[cpu].user[data->entries]);
+	}
+	trace_seq_printf(trace->seq, "\n");
+	trace_seq_do_printf(trace->seq);
+	trace_seq_reset(trace->seq);
+
+	timerlat_print_summary(params, trace, data);
+	timerlat_print_stats_all(params, trace, data);
+	osnoise_report_missed_events(tool);
+}
+
+/*
+ * timerlat_hist_apply_config - apply the hist configs to the initialized tool
+ */
+static int
+timerlat_hist_apply_config(struct osnoise_tool *tool)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	int retval;
+
+	retval = timerlat_apply_config(tool, params);
+	if (retval)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	return -1;
+}
+
+/*
+ * timerlat_init_hist - initialize a timerlat hist tool with parameters
+ */
+static struct osnoise_tool
+*timerlat_init_hist(struct common_params *params)
+{
+	struct osnoise_tool *tool;
+
+	tool = osnoise_init_tool("timerlat_hist");
+	if (!tool)
+		return NULL;
+
+	tool->data = timerlat_alloc_histogram(params->hist.entries,
+					      params->hist.bucket_size);
+	if (!tool->data)
+		goto out_err;
+
+	tep_register_event_handler(tool->trace.tep, -1, "ftrace", "timerlat",
+				   timerlat_hist_handler, tool);
+
+	return tool;
+
+out_err:
+	osnoise_destroy_tool(tool);
+	return NULL;
+}
+
+static int timerlat_hist_bpf_main_loop(struct osnoise_tool *tool)
+{
+	int retval;
+
+	while (!stop_tracing) {
+		timerlat_bpf_wait(-1);
+
+		if (!stop_tracing) {
+			/* Threshold overflow, perform actions on threshold */
+			retval = common_threshold_handler(tool);
+			if (retval)
+				return retval;
+
+			if (!should_continue_tracing(tool->params))
+				break;
+
+			if (timerlat_bpf_restart_tracing()) {
+				err_msg("Error restarting BPF trace\n");
+				return -1;
+			}
+		}
+	}
+	timerlat_bpf_detach();
+
+	retval = timerlat_hist_bpf_pull_data(tool);
+	if (retval)
+		err_msg("Error pulling BPF data\n");
+
+	return retval;
+}
+
+static int timerlat_hist_main(struct osnoise_tool *tool)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	int retval;
+
+	if (params->mode == TRACING_MODE_TRACEFS)
+		retval = hist_main_loop(tool);
+	else
+		retval = timerlat_hist_bpf_main_loop(tool);
+
+	return retval;
+}
+
+struct tool_ops timerlat_hist_ops = {
+	.tracer = "timerlat",
+	.comm_prefix = "timerlat/",
+	.parse_args = timerlat_hist_parse_args,
+	.init_tool = timerlat_init_hist,
+	.apply_config = timerlat_hist_apply_config,
+	.enable = timerlat_enable,
+	.main = timerlat_hist_main,
+	.print_stats = timerlat_print_stats,
+	.analyze = timerlat_analyze,
+	.free = timerlat_free_histogram_tool,
+};
diff --git a/tools/tracing/rtla/src/timerlat_top.c b/tools/tracing/rtla/src/timerlat_top.c
new file mode 100644
index 000000000..6206a0a56
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_top.c
@@ -0,0 +1,592 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <time.h>
+#include <sched.h>
+#include <pthread.h>
+
+#include "timerlat.h"
+#include "timerlat_aa.h"
+#include "timerlat_bpf.h"
+#include "cli.h"
+#include "common.h"
+
+struct timerlat_top_cpu {
+	unsigned long long	irq_count;
+	unsigned long long	thread_count;
+	unsigned long long	user_count;
+
+	unsigned long long	cur_irq;
+	unsigned long long	min_irq;
+	unsigned long long	sum_irq;
+	unsigned long long	max_irq;
+
+	unsigned long long	cur_thread;
+	unsigned long long	min_thread;
+	unsigned long long	sum_thread;
+	unsigned long long	max_thread;
+
+	unsigned long long	cur_user;
+	unsigned long long	min_user;
+	unsigned long long	sum_user;
+	unsigned long long	max_user;
+};
+
+struct timerlat_top_data {
+	struct timerlat_top_cpu	*cpu_data;
+};
+
+/*
+ * timerlat_free_top - free runtime data
+ */
+static void timerlat_free_top(struct timerlat_top_data *data)
+{
+	free(data->cpu_data);
+	free(data);
+}
+
+static void timerlat_free_top_tool(struct osnoise_tool *tool)
+{
+	timerlat_free_top(tool->data);
+	timerlat_free(tool);
+}
+
+/*
+ * timerlat_alloc_histogram - alloc runtime data
+ */
+static struct timerlat_top_data *timerlat_alloc_top(void)
+{
+	struct timerlat_top_data *data;
+	int cpu;
+
+	data = calloc(1, sizeof(*data));
+	if (!data)
+		return NULL;
+
+	/* one set of histograms per CPU */
+	data->cpu_data = calloc(1, sizeof(*data->cpu_data) * nr_cpus);
+	if (!data->cpu_data)
+		goto cleanup;
+
+	/* set the min to max */
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		data->cpu_data[cpu].min_irq = ~0;
+		data->cpu_data[cpu].min_thread = ~0;
+		data->cpu_data[cpu].min_user = ~0;
+	}
+
+	return data;
+
+cleanup:
+	timerlat_free_top(data);
+	return NULL;
+}
+
+static void
+timerlat_top_reset_sum(struct timerlat_top_cpu *summary)
+{
+	memset(summary, 0, sizeof(*summary));
+	summary->min_irq = ~0;
+	summary->min_thread = ~0;
+	summary->min_user = ~0;
+}
+
+static void
+timerlat_top_update_sum(struct osnoise_tool *tool, int cpu, struct timerlat_top_cpu *sum)
+{
+	struct timerlat_top_data *data = tool->data;
+	struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu];
+
+	sum->irq_count += cpu_data->irq_count;
+	update_min(&sum->min_irq, &cpu_data->min_irq);
+	update_sum(&sum->sum_irq, &cpu_data->sum_irq);
+	update_max(&sum->max_irq, &cpu_data->max_irq);
+
+	sum->thread_count += cpu_data->thread_count;
+	update_min(&sum->min_thread, &cpu_data->min_thread);
+	update_sum(&sum->sum_thread, &cpu_data->sum_thread);
+	update_max(&sum->max_thread, &cpu_data->max_thread);
+
+	sum->user_count += cpu_data->user_count;
+	update_min(&sum->min_user, &cpu_data->min_user);
+	update_sum(&sum->sum_user, &cpu_data->sum_user);
+	update_max(&sum->max_user, &cpu_data->max_user);
+}
+
+/*
+ * timerlat_hist_update - record a new timerlat occurent on cpu, updating data
+ */
+static void
+timerlat_top_update(struct osnoise_tool *tool, int cpu,
+		    unsigned long long thread,
+		    unsigned long long latency)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	struct timerlat_top_data *data = tool->data;
+	struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu];
+
+	if (params->common.output_divisor)
+		latency = latency / params->common.output_divisor;
+
+	if (!thread) {
+		cpu_data->irq_count++;
+		cpu_data->cur_irq = latency;
+		update_min(&cpu_data->min_irq, &latency);
+		update_sum(&cpu_data->sum_irq, &latency);
+		update_max(&cpu_data->max_irq, &latency);
+	} else if (thread == 1) {
+		cpu_data->thread_count++;
+		cpu_data->cur_thread = latency;
+		update_min(&cpu_data->min_thread, &latency);
+		update_sum(&cpu_data->sum_thread, &latency);
+		update_max(&cpu_data->max_thread, &latency);
+	} else {
+		cpu_data->user_count++;
+		cpu_data->cur_user = latency;
+		update_min(&cpu_data->min_user, &latency);
+		update_sum(&cpu_data->sum_user, &latency);
+		update_max(&cpu_data->max_user, &latency);
+	}
+}
+
+/*
+ * timerlat_top_handler - this is the handler for timerlat tracer events
+ */
+static int
+timerlat_top_handler(struct trace_seq *s, struct tep_record *record,
+		     struct tep_event *event, void *context)
+{
+	struct trace_instance *trace = context;
+	unsigned long long latency, thread;
+	struct osnoise_tool *top;
+	int cpu = record->cpu;
+
+	top = container_of(trace, struct osnoise_tool, trace);
+
+	if (!top->params->aa_only) {
+		tep_get_field_val(s, event, "context", record, &thread, 1);
+		tep_get_field_val(s, event, "timer_latency", record, &latency, 1);
+
+		timerlat_top_update(top, cpu, thread, latency);
+	}
+
+	return 0;
+}
+
+/*
+ * timerlat_top_bpf_pull_data - copy data from BPF maps into userspace
+ */
+static int timerlat_top_bpf_pull_data(struct osnoise_tool *tool)
+{
+	struct timerlat_top_data *data = tool->data;
+	int i, err;
+	long long value_irq[nr_cpus],
+		  value_thread[nr_cpus],
+		  value_user[nr_cpus];
+
+	/* Pull summary */
+	err = timerlat_bpf_get_summary_value(SUMMARY_CURRENT,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->cpu_data[i].cur_irq = value_irq[i];
+		data->cpu_data[i].cur_thread = value_thread[i];
+		data->cpu_data[i].cur_user = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_COUNT,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->cpu_data[i].irq_count = value_irq[i];
+		data->cpu_data[i].thread_count = value_thread[i];
+		data->cpu_data[i].user_count = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_MIN,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->cpu_data[i].min_irq = value_irq[i];
+		data->cpu_data[i].min_thread = value_thread[i];
+		data->cpu_data[i].min_user = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_MAX,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->cpu_data[i].max_irq = value_irq[i];
+		data->cpu_data[i].max_thread = value_thread[i];
+		data->cpu_data[i].max_user = value_user[i];
+	}
+
+	err = timerlat_bpf_get_summary_value(SUMMARY_SUM,
+					     value_irq, value_thread, value_user);
+	if (err)
+		return err;
+	for (i = 0; i < nr_cpus; i++) {
+		data->cpu_data[i].sum_irq = value_irq[i];
+		data->cpu_data[i].sum_thread = value_thread[i];
+		data->cpu_data[i].sum_user = value_user[i];
+	}
+
+	return 0;
+}
+
+/*
+ * timerlat_top_header - print the header of the tool output
+ */
+static void timerlat_top_header(struct timerlat_params *params, struct osnoise_tool *top)
+{
+	struct trace_seq *s = top->trace.seq;
+	bool pretty = params->common.pretty_output;
+	char duration[26];
+
+	get_duration(top->start_time, duration, sizeof(duration));
+
+	if (pretty)
+		trace_seq_printf(s, "\033[2;37;40m");
+
+	trace_seq_printf(s, "                                     Timer Latency                                              ");
+	if (params->common.user_data)
+		trace_seq_printf(s, "                                         ");
+
+	if (pretty)
+		trace_seq_printf(s, "\033[0;0;0m");
+	trace_seq_printf(s, "\n");
+
+	trace_seq_printf(s, "%-6s   |          IRQ Timer Latency (%s)        |         Thread Timer Latency (%s)", duration,
+			params->common.output_divisor == 1 ? "ns" : "us",
+			params->common.output_divisor == 1 ? "ns" : "us");
+
+	if (params->common.user_data) {
+		trace_seq_printf(s, "      |    Ret user Timer Latency (%s)",
+				params->common.output_divisor == 1 ? "ns" : "us");
+	}
+
+	trace_seq_printf(s, "\n");
+	if (pretty)
+		trace_seq_printf(s, "\033[2;30;47m");
+
+	trace_seq_printf(s, "CPU COUNT      |      cur       min       avg       max |      cur       min       avg       max");
+	if (params->common.user_data)
+		trace_seq_printf(s, " |      cur       min       avg       max");
+
+	if (pretty)
+		trace_seq_printf(s, "\033[0;0;0m");
+	trace_seq_printf(s, "\n");
+}
+
+static const char *no_value = "        -";
+
+/*
+ * timerlat_top_print - prints the output of a given CPU
+ */
+static void timerlat_top_print(struct osnoise_tool *top, int cpu)
+{
+	struct timerlat_params *params = to_timerlat_params(top->params);
+	struct timerlat_top_data *data = top->data;
+	struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu];
+	struct trace_seq *s = top->trace.seq;
+
+	/*
+	 * Skip if no data is available: is this cpu offline?
+	 */
+	if (!cpu_data->irq_count && !cpu_data->thread_count)
+		return;
+
+	/*
+	 * Unless trace is being lost, IRQ counter is always the max.
+	 */
+	trace_seq_printf(s, "%3d #%-9llu |", cpu, cpu_data->irq_count);
+
+	if (!cpu_data->irq_count) {
+		trace_seq_printf(s, "%s %s %s %s |", no_value, no_value, no_value, no_value);
+	} else {
+		trace_seq_printf(s, "%9llu ", cpu_data->cur_irq);
+		trace_seq_printf(s, "%9llu ", cpu_data->min_irq);
+		trace_seq_printf(s, "%9llu ", cpu_data->sum_irq / cpu_data->irq_count);
+		trace_seq_printf(s, "%9llu |", cpu_data->max_irq);
+	}
+
+	if (!cpu_data->thread_count) {
+		trace_seq_printf(s, "%s %s %s %s", no_value, no_value, no_value, no_value);
+	} else {
+		trace_seq_printf(s, "%9llu ", cpu_data->cur_thread);
+		trace_seq_printf(s, "%9llu ", cpu_data->min_thread);
+		trace_seq_printf(s, "%9llu ",
+				cpu_data->sum_thread / cpu_data->thread_count);
+		trace_seq_printf(s, "%9llu", cpu_data->max_thread);
+	}
+
+	if (!params->common.user_data) {
+		trace_seq_printf(s, "\n");
+		return;
+	}
+
+	trace_seq_printf(s, " |");
+
+	if (!cpu_data->user_count) {
+		trace_seq_printf(s, "%s %s %s %s\n", no_value, no_value, no_value, no_value);
+	} else {
+		trace_seq_printf(s, "%9llu ", cpu_data->cur_user);
+		trace_seq_printf(s, "%9llu ", cpu_data->min_user);
+		trace_seq_printf(s, "%9llu ",
+				cpu_data->sum_user / cpu_data->user_count);
+		trace_seq_printf(s, "%9llu\n", cpu_data->max_user);
+	}
+}
+
+/*
+ * timerlat_top_print_sum - prints the summary output
+ */
+static void
+timerlat_top_print_sum(struct osnoise_tool *top, struct timerlat_top_cpu *summary)
+{
+	const char *split = "----------------------------------------";
+	struct timerlat_params *params = to_timerlat_params(top->params);
+	unsigned long long count = summary->irq_count;
+	struct trace_seq *s = top->trace.seq;
+	int e = 0;
+
+	/*
+	 * Skip if no data is available: is this cpu offline?
+	 */
+	if (!summary->irq_count && !summary->thread_count)
+		return;
+
+	while (count > 999999) {
+		e++;
+		count /= 10;
+	}
+
+	trace_seq_printf(s, "%.*s|%.*s|%.*s", 15, split, 40, split, 39, split);
+	if (params->common.user_data)
+		trace_seq_printf(s, "-|%.*s", 39, split);
+	trace_seq_printf(s, "\n");
+
+	trace_seq_printf(s, "ALL #%-6llu e%d |", count, e);
+
+	if (!summary->irq_count) {
+		trace_seq_printf(s, "          %s %s %s |", no_value, no_value, no_value);
+	} else {
+		trace_seq_printf(s, "          ");
+		trace_seq_printf(s, "%9llu ", summary->min_irq);
+		trace_seq_printf(s, "%9llu ", summary->sum_irq / summary->irq_count);
+		trace_seq_printf(s, "%9llu |", summary->max_irq);
+	}
+
+	if (!summary->thread_count) {
+		trace_seq_printf(s, "%s %s %s %s", no_value, no_value, no_value, no_value);
+	} else {
+		trace_seq_printf(s, "          ");
+		trace_seq_printf(s, "%9llu ", summary->min_thread);
+		trace_seq_printf(s, "%9llu ",
+				summary->sum_thread / summary->thread_count);
+		trace_seq_printf(s, "%9llu", summary->max_thread);
+	}
+
+	if (!params->common.user_data) {
+		trace_seq_printf(s, "\n");
+		return;
+	}
+
+	trace_seq_printf(s, " |");
+
+	if (!summary->user_count) {
+		trace_seq_printf(s, "          %s %s %s |", no_value, no_value, no_value);
+	} else {
+		trace_seq_printf(s, "          ");
+		trace_seq_printf(s, "%9llu ", summary->min_user);
+		trace_seq_printf(s, "%9llu ",
+				summary->sum_user / summary->user_count);
+		trace_seq_printf(s, "%9llu\n", summary->max_user);
+	}
+}
+
+/*
+ * clear_terminal - clears the output terminal
+ */
+static void clear_terminal(struct trace_seq *seq)
+{
+	if (!config_debug)
+		trace_seq_printf(seq, "\033c");
+}
+
+/*
+ * timerlat_print_stats - print data for all cpus
+ */
+static void
+timerlat_print_stats(struct osnoise_tool *top)
+{
+	struct timerlat_params *params = to_timerlat_params(top->params);
+	struct trace_instance *trace = &top->trace;
+	struct timerlat_top_cpu summary;
+	int i;
+
+	if (params->common.aa_only)
+		return;
+
+	if (!params->common.quiet)
+		clear_terminal(trace->seq);
+
+	timerlat_top_reset_sum(&summary);
+
+	timerlat_top_header(params, top);
+
+	for_each_monitored_cpu(i, &params->common) {
+		timerlat_top_print(top, i);
+		timerlat_top_update_sum(top, i, &summary);
+	}
+
+	timerlat_top_print_sum(top, &summary);
+
+	trace_seq_do_printf(trace->seq);
+	trace_seq_reset(trace->seq);
+	osnoise_report_missed_events(top);
+}
+
+/*
+ * timerlat_top_apply_config - apply the top configs to the initialized tool
+ */
+static int
+timerlat_top_apply_config(struct osnoise_tool *top)
+{
+	struct timerlat_params *params = to_timerlat_params(top->params);
+	int retval;
+
+	retval = timerlat_apply_config(top, params);
+	if (retval)
+		goto out_err;
+
+	if (isatty(STDOUT_FILENO) && !params->common.quiet)
+		params->common.pretty_output = 1;
+
+	return 0;
+
+out_err:
+	return -1;
+}
+
+/*
+ * timerlat_init_top - initialize a timerlat top tool with parameters
+ */
+static struct osnoise_tool
+*timerlat_init_top(struct common_params *params)
+{
+	struct osnoise_tool *top;
+
+	top = osnoise_init_tool("timerlat_top");
+	if (!top)
+		return NULL;
+
+	top->data = timerlat_alloc_top();
+	if (!top->data)
+		goto out_err;
+
+	tep_register_event_handler(top->trace.tep, -1, "ftrace", "timerlat",
+				   timerlat_top_handler, top);
+
+	return top;
+
+out_err:
+	osnoise_destroy_tool(top);
+	return NULL;
+}
+
+/*
+ * timerlat_top_bpf_main_loop - main loop to process events (BPF variant)
+ */
+static int
+timerlat_top_bpf_main_loop(struct osnoise_tool *tool)
+{
+	const struct common_params *params = tool->params;
+	int retval, wait_retval;
+
+	if (params->aa_only) {
+		/* Auto-analysis only, just wait for stop tracing */
+		timerlat_bpf_wait(-1);
+		return 0;
+	}
+
+	/* Pull and display data in a loop */
+	while (!stop_tracing) {
+		wait_retval = timerlat_bpf_wait(params->quiet ? -1 :
+						params->sleep_time);
+
+		retval = timerlat_top_bpf_pull_data(tool);
+		if (retval) {
+			err_msg("Error pulling BPF data\n");
+			return retval;
+		}
+
+		if (!params->quiet)
+			timerlat_print_stats(tool);
+
+		if (wait_retval > 0) {
+			/* Stopping requested by tracer */
+			retval = common_threshold_handler(tool);
+			if (retval)
+				return retval;
+
+			if (!should_continue_tracing(tool->params))
+				break;
+
+			if (timerlat_bpf_restart_tracing()) {
+				err_msg("Error restarting BPF trace\n");
+				return -1;
+			}
+		}
+
+		/* is there still any user-threads ? */
+		if (params->user_workload) {
+			if (params->user.stopped_running) {
+				debug_msg("timerlat user space threads stopped!\n");
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int timerlat_top_main_loop(struct osnoise_tool *tool)
+{
+	struct timerlat_params *params = to_timerlat_params(tool->params);
+	int retval;
+
+	if (params->mode == TRACING_MODE_TRACEFS) {
+		retval = top_main_loop(tool);
+	} else {
+		retval = timerlat_top_bpf_main_loop(tool);
+		timerlat_bpf_detach();
+	}
+
+	return retval;
+}
+
+struct tool_ops timerlat_top_ops = {
+	.tracer = "timerlat",
+	.comm_prefix = "timerlat/",
+	.parse_args = timerlat_top_parse_args,
+	.init_tool = timerlat_init_top,
+	.apply_config = timerlat_top_apply_config,
+	.enable = timerlat_enable,
+	.main = timerlat_top_main_loop,
+	.print_stats = timerlat_print_stats,
+	.analyze = timerlat_analyze,
+	.free = timerlat_free_top_tool,
+};
diff --git a/tools/tracing/rtla/src/timerlat_u.c b/tools/tracing/rtla/src/timerlat_u.c
new file mode 100644
index 000000000..c80edaf07
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_u.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <tracefs.h>
+#include <pthread.h>
+#include <sys/wait.h>
+#include <sys/prctl.h>
+
+#include "common.h"
+#include "timerlat_u.h"
+
+/*
+ * This is the user-space main for the tool timerlatu/ threads.
+ *
+ * It is as simple as this:
+ *  - set affinity
+ *  - set priority
+ *  - open tracer fd
+ *  - spin
+ *  - close
+ */
+static int timerlat_u_main(int cpu, struct timerlat_u_params *params)
+{
+	struct sched_param sp = { .sched_priority = 95 };
+	char buffer[MAX_PATH];
+	int timerlat_fd;
+	cpu_set_t set;
+	int retval;
+
+	/*
+	 * This all is only setting up the tool.
+	 */
+	CPU_ZERO(&set);
+	CPU_SET(cpu, &set);
+
+	retval = sched_setaffinity(gettid(), sizeof(set), &set);
+	if (retval == -1) {
+		debug_msg("Error setting user thread affinity %d, is the CPU online?\n", cpu);
+		exit(1);
+	}
+
+	if (!params->sched_param) {
+		retval = sched_setscheduler(0, SCHED_FIFO, &sp);
+		if (retval < 0)
+			fatal("Error setting timerlat u default priority: %s", strerror(errno));
+	} else {
+		retval = __set_sched_attr(getpid(), params->sched_param);
+		if (retval) {
+			/* __set_sched_attr prints an error message, so */
+			exit(0);
+		}
+	}
+
+	if (params->cgroup_name) {
+		retval = set_pid_cgroup(gettid(), params->cgroup_name);
+		if (!retval) {
+			err_msg("Error setting timerlat u cgroup pid\n");
+			pthread_exit(&retval);
+		}
+	}
+
+	/*
+	 * This is the tool's loop. If you want to use as base for your own tool...
+	 * go ahead.
+	 */
+	snprintf(buffer, sizeof(buffer), "osnoise/per_cpu/cpu%d/timerlat_fd", cpu);
+
+	timerlat_fd = tracefs_instance_file_open(NULL, buffer, O_RDONLY);
+	if (timerlat_fd < 0)
+		fatal("Error opening %s:%s", buffer, strerror(errno));
+
+	debug_msg("User-space timerlat pid %d on cpu %d\n", gettid(), cpu);
+
+	/* add should continue with a signal handler */
+	while (true) {
+		retval = read(timerlat_fd, buffer, ARRAY_SIZE(buffer));
+		if (retval < 0)
+			break;
+	}
+
+	close(timerlat_fd);
+
+	debug_msg("Leaving timerlat pid %d on cpu %d\n", gettid(), cpu);
+	exit(0);
+}
+
+/*
+ * timerlat_u_send_kill - send a kill signal for all processes
+ *
+ * Return the number of processes that received the kill.
+ */
+static int timerlat_u_send_kill(pid_t *procs)
+{
+	int killed = 0;
+	int i, retval;
+
+	for (i = 0; i < nr_cpus; i++) {
+		if (!procs[i])
+			continue;
+		retval = kill(procs[i], SIGKILL);
+		if (!retval)
+			killed++;
+		else
+			err_msg("Error killing child process %d\n", procs[i]);
+	}
+
+	return killed;
+}
+
+/**
+ * timerlat_u_dispatcher - dispatch one timerlatu/ process per monitored CPU
+ *
+ * This is a thread main that will fork one new process for each monitored
+ * CPU. It will wait for:
+ *
+ *  - rtla to tell to kill the child processes
+ *  - some child process to die, and the cleanup all the processes
+ *
+ * whichever comes first.
+ *
+ */
+void *timerlat_u_dispatcher(void *data)
+{
+	struct timerlat_u_params *params = data;
+	char proc_name[128];
+	int procs_count = 0;
+	int retval = 1;
+	pid_t *procs;
+	int wstatus;
+	pid_t pid;
+	int i;
+
+	debug_msg("Dispatching timerlat u procs\n");
+
+	procs = calloc(nr_cpus, sizeof(pid_t));
+	if (!procs)
+		pthread_exit(&retval);
+
+	for (i = 0; i < nr_cpus; i++) {
+		if (params->set && !CPU_ISSET(i, params->set))
+			continue;
+
+		pid = fork();
+
+		/* child */
+		if (!pid) {
+
+			/*
+			 * rename the process
+			 */
+			snprintf(proc_name, sizeof(proc_name), "timerlatu/%d", i);
+			pthread_setname_np(pthread_self(), proc_name);
+			prctl(PR_SET_NAME, (unsigned long)proc_name, 0, 0, 0);
+
+			timerlat_u_main(i, params);
+			/* timerlat_u_main should exit()! Anyways... */
+			pthread_exit(&retval);
+		}
+
+		/* parent */
+		if (pid == -1) {
+			timerlat_u_send_kill(procs);
+			debug_msg("Failed to create child processes");
+			pthread_exit(&retval);
+		}
+
+		procs_count++;
+		procs[i] = pid;
+	}
+
+	while (params->should_run) {
+		/* check if processes died */
+		pid = waitpid(-1, &wstatus, WNOHANG);
+		if (pid != 0) {
+			for (i = 0; i < nr_cpus; i++) {
+				if (procs[i] == pid) {
+					procs[i] = 0;
+					procs_count--;
+				}
+			}
+
+			if (!procs_count)
+				break;
+		}
+
+		sleep(1);
+	}
+
+	timerlat_u_send_kill(procs);
+
+	while (procs_count) {
+		pid = waitpid(-1, &wstatus, 0);
+		if (pid == -1) {
+			err_msg("Failed to monitor child processes");
+			pthread_exit(&retval);
+		}
+		for (i = 0; i < nr_cpus; i++) {
+			if (procs[i] == pid) {
+				procs[i] = 0;
+				procs_count--;
+			}
+		}
+	}
+
+	params->stopped_running = 1;
+
+	free(procs);
+	retval = 0;
+	pthread_exit(&retval);
+
+}
diff --git a/tools/tracing/rtla/src/timerlat_u.h b/tools/tracing/rtla/src/timerlat_u.h
new file mode 100644
index 000000000..a692331bd
--- /dev/null
+++ b/tools/tracing/rtla/src/timerlat_u.h
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#pragma once
+/*
+ * Copyright (C) 2023 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+struct timerlat_u_params {
+	/* timerlat -> timerlat_u: user-space threads can keep running */
+	int should_run;
+	/* timerlat_u -> timerlat: all timerlat_u threads left, no reason to continue */
+	int stopped_running;
+
+	/* threads config */
+	cpu_set_t *set;
+	char *cgroup_name;
+	struct sched_attr *sched_param;
+};
+
+void *timerlat_u_dispatcher(void *data);
diff --git a/tools/tracing/rtla/src/trace.c b/tools/tracing/rtla/src/trace.c
new file mode 100644
index 000000000..e40744777
--- /dev/null
+++ b/tools/tracing/rtla/src/trace.c
@@ -0,0 +1,597 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <sys/sendfile.h>
+#include <tracefs.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+
+#include "trace.h"
+#include "utils.h"
+
+/*
+ * enable_tracer_by_name - enable a tracer on the given instance
+ */
+int enable_tracer_by_name(struct tracefs_instance *inst, const char *tracer_name)
+{
+	enum tracefs_tracers tracer;
+	int retval;
+
+	tracer = TRACEFS_TRACER_CUSTOM;
+
+	debug_msg("Enabling %s tracer\n", tracer_name);
+
+	retval = tracefs_tracer_set(inst, tracer, tracer_name);
+	if (retval < 0) {
+		if (errno == ENODEV)
+			err_msg("Tracer %s not found!\n", tracer_name);
+
+		err_msg("Failed to enable the %s tracer\n", tracer_name);
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * disable_tracer - set nop tracer to the insta
+ */
+void disable_tracer(struct tracefs_instance *inst)
+{
+	enum tracefs_tracers t = TRACEFS_TRACER_NOP;
+	int retval;
+
+	retval = tracefs_tracer_set(inst, t);
+	if (retval < 0)
+		err_msg("Oops, error disabling tracer\n");
+}
+
+/*
+ * create_instance - create a trace instance with *instance_name
+ */
+struct tracefs_instance *create_instance(char *instance_name)
+{
+	return tracefs_instance_create(instance_name);
+}
+
+/*
+ * destroy_instance - remove a trace instance and free the data
+ */
+void destroy_instance(struct tracefs_instance *inst)
+{
+	tracefs_instance_destroy(inst);
+	tracefs_instance_free(inst);
+}
+
+/*
+ * save_trace_to_file - save the trace output of the instance to the file
+ */
+int save_trace_to_file(struct tracefs_instance *inst, const char *filename)
+{
+	const char *file = "trace";
+	mode_t mode = 0644;
+	char buffer[4096];
+	int out_fd, in_fd;
+	int retval = -1;
+	ssize_t n_read;
+	ssize_t n_written;
+
+	if (!inst || !filename)
+		return 0;
+
+	in_fd = tracefs_instance_file_open(inst, file, O_RDONLY);
+	if (in_fd < 0) {
+		err_msg("Failed to open trace file\n");
+		return -1;
+	}
+
+	printf("  Saving trace to %s\n", filename);
+	out_fd = creat(filename, mode);
+	if (out_fd < 0) {
+		err_msg("Failed to create output file %s\n", filename);
+		goto out_close_in;
+	}
+
+	for (;;) {
+		n_read = read(in_fd, buffer, sizeof(buffer));
+		if (n_read < 0) {
+			if (errno == EINTR)
+				continue;
+			err_msg("Error reading trace file: %s\n", strerror(errno));
+			goto out_close;
+		}
+		if (n_read == 0)
+			break;
+
+		n_written = 0;
+		while (n_written < n_read) {
+			const ssize_t w = write(out_fd, buffer + n_written, n_read - n_written);
+
+			if (w < 0) {
+				if (errno == EINTR)
+					continue;
+				err_msg("Error writing trace file: %s\n", strerror(errno));
+				goto out_close;
+			}
+			n_written += w;
+		}
+	}
+
+	retval = 0;
+out_close:
+	close(out_fd);
+out_close_in:
+	close(in_fd);
+	return retval;
+}
+
+/*
+ * collect_registered_events - call the existing callback function for the event
+ *
+ * If an event has a registered callback function, call it.
+ * Otherwise, ignore the event.
+ */
+int
+collect_registered_events(struct tep_event *event, struct tep_record *record,
+			  int cpu, void *context)
+{
+	struct trace_instance *trace = context;
+	struct trace_seq *s = trace->seq;
+
+	trace->processed_events++;
+
+	if (!event->handler)
+		return 0;
+
+	event->handler(s, record, event, context);
+
+	return 0;
+}
+
+/*
+ * collect_missed_events - record number of missed events
+ *
+ * If rtla cannot keep up with events generated by tracer, events are going
+ * to fall out of the ring buffer.
+ * Collect how many events were missed so it can be reported to the user.
+ */
+static int
+collect_missed_events(struct tep_event *event, struct tep_record *record,
+		      int cpu, void *context)
+{
+	struct trace_instance *trace = context;
+
+	if (trace->missed_events == UINT64_MAX)
+		return 0;
+
+	if (record->missed_events > 0)
+		trace->missed_events += record->missed_events;
+	else
+		/* Events missed but no data on how many */
+		trace->missed_events = UINT64_MAX;
+
+	return 0;
+}
+
+/*
+ * trace_instance_destroy - destroy and free a rtla trace instance
+ */
+void trace_instance_destroy(struct trace_instance *trace)
+{
+	if (trace->inst) {
+		disable_tracer(trace->inst);
+		destroy_instance(trace->inst);
+		trace->inst = NULL;
+	}
+
+	if (trace->seq) {
+		free(trace->seq);
+		trace->seq = NULL;
+	}
+
+	if (trace->tep) {
+		tep_free(trace->tep);
+		trace->tep = NULL;
+	}
+}
+
+/*
+ * trace_instance_init - create an rtla trace instance
+ *
+ * It is more than the tracefs instance, as it contains other
+ * things required for the tracing, such as the local events and
+ * a seq file.
+ *
+ * Note that the trace instance is returned disabled. This allows
+ * the tool to apply some other configs, like setting priority
+ * to the kernel threads, before starting generating trace entries.
+ */
+int trace_instance_init(struct trace_instance *trace, char *tool_name)
+{
+	trace->seq = calloc_fatal(1, sizeof(*trace->seq));
+
+	trace_seq_init(trace->seq);
+
+	trace->inst = create_instance(tool_name);
+	if (!trace->inst)
+		goto out_err;
+
+	trace->tep = tracefs_local_events(NULL);
+	if (!trace->tep)
+		goto out_err;
+
+	/*
+	 * Let the main enable the record after setting some other
+	 * things such as the priority of the tracer's threads.
+	 */
+	tracefs_trace_off(trace->inst);
+
+	/*
+	 * Collect the number of events missed due to tracefs buffer
+	 * overflow.
+	 */
+	trace->missed_events = 0;
+	tracefs_follow_missed_events(trace->inst,
+				     collect_missed_events,
+				     trace);
+
+	trace->processed_events = 0;
+
+	return 0;
+
+out_err:
+	trace_instance_destroy(trace);
+	return 1;
+}
+
+/*
+ * trace_instance_start - start tracing a given rtla instance
+ */
+int trace_instance_start(struct trace_instance *trace)
+{
+	return tracefs_trace_on(trace->inst);
+}
+
+/*
+ * trace_instance_stop - stop tracing a given rtla instance
+ */
+int trace_instance_stop(struct trace_instance *trace)
+{
+	return tracefs_trace_off(trace->inst);
+}
+
+/*
+ * trace_events_free - free a list of trace events
+ */
+static void trace_events_free(struct trace_events *events)
+{
+	struct trace_events *tevent = events;
+	struct trace_events *free_event;
+
+	while (tevent) {
+		free_event = tevent;
+
+		tevent = tevent->next;
+
+		if (free_event->filter)
+			free(free_event->filter);
+		if (free_event->trigger)
+			free(free_event->trigger);
+		free(free_event->system);
+		free(free_event);
+	}
+}
+
+/*
+ * trace_event_alloc - alloc and parse a single trace event
+ */
+struct trace_events *trace_event_alloc(const char *event_string)
+{
+	struct trace_events *tevent;
+
+	tevent = calloc_fatal(1, sizeof(*tevent));
+
+	tevent->system = strdup_fatal(event_string);
+
+	tevent->event = strstr(tevent->system, ":");
+	if (tevent->event) {
+		*tevent->event = '\0';
+		tevent->event = &tevent->event[1];
+	}
+
+	return tevent;
+}
+
+/*
+ * trace_event_add_filter - record an event filter
+ */
+void trace_event_add_filter(struct trace_events *event, char *filter)
+{
+	if (event->filter)
+		free(event->filter);
+
+	event->filter = strdup_fatal(filter);
+}
+
+/*
+ * trace_event_add_trigger - record an event trigger action
+ */
+void trace_event_add_trigger(struct trace_events *event, char *trigger)
+{
+	if (event->trigger)
+		free(event->trigger);
+
+	event->trigger = strdup_fatal(trigger);
+}
+
+/*
+ * trace_event_disable_filter - disable an event filter
+ */
+static void trace_event_disable_filter(struct trace_instance *instance,
+				       struct trace_events *tevent)
+{
+	char filter[MAX_PATH];
+	int retval;
+
+	if (!tevent->filter)
+		return;
+
+	if (!tevent->filter_enabled)
+		return;
+
+	debug_msg("Disabling %s:%s filter %s\n", tevent->system,
+		  tevent->event ? : "*", tevent->filter);
+
+	snprintf(filter, ARRAY_SIZE(filter), "!%s\n", tevent->filter);
+
+	retval = tracefs_event_file_write(instance->inst, tevent->system,
+					  tevent->event, "filter", filter);
+	if (retval < 0)
+		err_msg("Error disabling %s:%s filter %s\n", tevent->system,
+			tevent->event ? : "*", tevent->filter);
+}
+
+/*
+ * trace_event_save_hist - save the content of an event hist
+ *
+ * If the trigger is a hist: one, save the content of the hist file.
+ */
+static void trace_event_save_hist(struct trace_instance *instance,
+				  struct trace_events *tevent)
+{
+	size_t index, hist_len;
+	mode_t mode = 0644;
+	char path[MAX_PATH];
+	char *hist;
+	int out_fd;
+
+	if (!tevent)
+		return;
+
+	/* trigger enables hist */
+	if (!tevent->trigger)
+		return;
+
+	/* is this a hist: trigger? */
+	if (!str_has_prefix(tevent->trigger, "hist:"))
+		return;
+
+	snprintf(path, ARRAY_SIZE(path), "%s_%s_hist.txt", tevent->system, tevent->event);
+
+	printf("  Saving event %s:%s hist to %s\n", tevent->system, tevent->event, path);
+
+	out_fd = creat(path, mode);
+	if (out_fd < 0) {
+		err_msg("  Failed to create %s output file\n", path);
+		return;
+	}
+
+	hist = tracefs_event_file_read(instance->inst, tevent->system, tevent->event, "hist", 0);
+	if (!hist) {
+		err_msg("  Failed to read %s:%s hist file\n", tevent->system, tevent->event);
+		goto out_close;
+	}
+
+	index = 0;
+	hist_len = strlen(hist);
+	do {
+		const ssize_t written = write(out_fd, &hist[index], hist_len - index);
+
+		if (written < 0) {
+			if (errno == EINTR)
+				continue;
+			err_msg("  Error writing hist file: %s\n", strerror(errno));
+			break;
+		}
+		index += written;
+	} while (index < hist_len);
+
+	free(hist);
+out_close:
+	close(out_fd);
+}
+
+/*
+ * trace_event_disable_trigger - disable an event trigger
+ */
+static void trace_event_disable_trigger(struct trace_instance *instance,
+					struct trace_events *tevent)
+{
+	char trigger[MAX_PATH];
+	int retval;
+
+	if (!tevent->trigger)
+		return;
+
+	if (!tevent->trigger_enabled)
+		return;
+
+	debug_msg("Disabling %s:%s trigger %s\n", tevent->system,
+		  tevent->event ? : "*", tevent->trigger);
+
+	trace_event_save_hist(instance, tevent);
+
+	snprintf(trigger, ARRAY_SIZE(trigger), "!%s\n", tevent->trigger);
+
+	retval = tracefs_event_file_write(instance->inst, tevent->system,
+					  tevent->event, "trigger", trigger);
+	if (retval < 0)
+		err_msg("Error disabling %s:%s trigger %s\n", tevent->system,
+			tevent->event ? : "*", tevent->trigger);
+}
+
+/*
+ * trace_events_disable - disable all trace events
+ */
+void trace_events_disable(struct trace_instance *instance,
+			  struct trace_events *events)
+{
+	struct trace_events *tevent = events;
+
+	if (!events)
+		return;
+
+	while (tevent) {
+		debug_msg("Disabling event %s:%s\n", tevent->system, tevent->event ? : "*");
+		if (tevent->enabled) {
+			trace_event_disable_filter(instance, tevent);
+			trace_event_disable_trigger(instance, tevent);
+			tracefs_event_disable(instance->inst, tevent->system, tevent->event);
+		}
+
+		tevent->enabled = 0;
+		tevent = tevent->next;
+	}
+}
+
+/*
+ * trace_event_enable_filter - enable an event filter associated with an event
+ */
+static int trace_event_enable_filter(struct trace_instance *instance,
+				     struct trace_events *tevent)
+{
+	char filter[MAX_PATH];
+	int retval;
+
+	if (!tevent->filter)
+		return 0;
+
+	if (!tevent->event) {
+		err_msg("Filter %s applies only for single events, not for all %s:* events\n",
+			tevent->filter, tevent->system);
+		return 1;
+	}
+
+	snprintf(filter, ARRAY_SIZE(filter), "%s\n", tevent->filter);
+
+	debug_msg("Enabling %s:%s filter %s\n", tevent->system,
+		  tevent->event ? : "*", tevent->filter);
+
+	retval = tracefs_event_file_write(instance->inst, tevent->system,
+					  tevent->event, "filter", filter);
+	if (retval < 0) {
+		err_msg("Error enabling %s:%s filter %s\n", tevent->system,
+			tevent->event ? : "*", tevent->filter);
+		return 1;
+	}
+
+	tevent->filter_enabled = 1;
+	return 0;
+}
+
+/*
+ * trace_event_enable_trigger - enable an event trigger associated with an event
+ */
+static int trace_event_enable_trigger(struct trace_instance *instance,
+				      struct trace_events *tevent)
+{
+	char trigger[MAX_PATH];
+	int retval;
+
+	if (!tevent->trigger)
+		return 0;
+
+	if (!tevent->event) {
+		err_msg("Trigger %s applies only for single events, not for all %s:* events\n",
+			tevent->trigger, tevent->system);
+		return 1;
+	}
+
+	snprintf(trigger, ARRAY_SIZE(trigger), "%s\n", tevent->trigger);
+
+	debug_msg("Enabling %s:%s trigger %s\n", tevent->system,
+		  tevent->event ? : "*", tevent->trigger);
+
+	retval = tracefs_event_file_write(instance->inst, tevent->system,
+					  tevent->event, "trigger", trigger);
+	if (retval < 0) {
+		err_msg("Error enabling %s:%s trigger %s\n", tevent->system,
+			tevent->event ? : "*", tevent->trigger);
+		return 1;
+	}
+
+	tevent->trigger_enabled = 1;
+
+	return 0;
+}
+
+/*
+ * trace_events_enable - enable all events
+ */
+int trace_events_enable(struct trace_instance *instance,
+			struct trace_events *events)
+{
+	struct trace_events *tevent = events;
+	int retval;
+
+	while (tevent) {
+		debug_msg("Enabling event %s:%s\n", tevent->system, tevent->event ? : "*");
+		retval = tracefs_event_enable(instance->inst, tevent->system, tevent->event);
+		if (retval < 0) {
+			err_msg("Error enabling event %s:%s\n", tevent->system,
+				tevent->event ? : "*");
+			return 1;
+		}
+
+		retval = trace_event_enable_filter(instance, tevent);
+		if (retval)
+			return 1;
+
+		retval = trace_event_enable_trigger(instance, tevent);
+		if (retval)
+			return 1;
+
+		tevent->enabled = 1;
+		tevent = tevent->next;
+	}
+
+	return 0;
+}
+
+/*
+ * trace_events_destroy - disable and free all trace events
+ */
+void trace_events_destroy(struct trace_instance *instance,
+			  struct trace_events *events)
+{
+	if (!events)
+		return;
+
+	trace_events_disable(instance, events);
+	trace_events_free(events);
+}
+
+/*
+ * trace_set_buffer_size - set the per-cpu tracing buffer size.
+ */
+int trace_set_buffer_size(struct trace_instance *trace, int size)
+{
+	int retval;
+
+	debug_msg("Setting trace buffer size to %d Kb\n", size);
+	retval = tracefs_instance_set_buffer_size(trace->inst, size, -1);
+	if (retval)
+		err_msg("Error setting trace buffer size\n");
+
+	return retval;
+}
diff --git a/tools/tracing/rtla/src/trace.h b/tools/tracing/rtla/src/trace.h
new file mode 100644
index 000000000..95b911a22
--- /dev/null
+++ b/tools/tracing/rtla/src/trace.h
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <tracefs.h>
+#include <stddef.h>
+
+struct trace_events {
+	struct trace_events *next;
+	char *system;
+	char *event;
+	char *filter;
+	char *trigger;
+	char enabled;
+	char filter_enabled;
+	char trigger_enabled;
+};
+
+struct trace_instance {
+	struct tracefs_instance		*inst;
+	struct tep_handle		*tep;
+	struct trace_seq		*seq;
+	unsigned long long		missed_events;
+	unsigned long long		processed_events;
+};
+
+int trace_instance_init(struct trace_instance *trace, char *tool_name);
+int trace_instance_start(struct trace_instance *trace);
+int trace_instance_stop(struct trace_instance *trace);
+void trace_instance_destroy(struct trace_instance *trace);
+
+struct trace_seq *get_trace_seq(void);
+int enable_tracer_by_name(struct tracefs_instance *inst, const char *tracer_name);
+void disable_tracer(struct tracefs_instance *inst);
+
+struct tracefs_instance *create_instance(char *instance_name);
+void destroy_instance(struct tracefs_instance *inst);
+
+int save_trace_to_file(struct tracefs_instance *inst, const char *filename);
+int collect_registered_events(struct tep_event *tep, struct tep_record *record,
+			      int cpu, void *context);
+
+struct trace_events *trace_event_alloc(const char *event_string);
+void trace_events_disable(struct trace_instance *instance,
+			  struct trace_events *events);
+void trace_events_destroy(struct trace_instance *instance,
+			  struct trace_events *events);
+int trace_events_enable(struct trace_instance *instance,
+			  struct trace_events *events);
+
+void trace_event_add_filter(struct trace_events *event, char *filter);
+void trace_event_add_trigger(struct trace_events *event, char *trigger);
+int trace_set_buffer_size(struct trace_instance *trace, int size);
diff --git a/tools/tracing/rtla/src/utils.c b/tools/tracing/rtla/src/utils.c
new file mode 100644
index 000000000..cb187e7d4
--- /dev/null
+++ b/tools/tracing/rtla/src/utils.c
@@ -0,0 +1,1069 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <bristot@kernel.org>
+ */
+
+#define _GNU_SOURCE
+#ifdef HAVE_LIBCPUPOWER_SUPPORT
+#include <cpuidle.h>
+#endif /* HAVE_LIBCPUPOWER_SUPPORT */
+#include <dirent.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <limits.h>
+
+#include "common.h"
+
+#define MAX_MSG_LENGTH	1024
+bool config_debug;
+
+/*
+ * err_msg - print an error message to the stderr
+ */
+void err_msg(const char *fmt, ...)
+{
+	char message[MAX_MSG_LENGTH];
+	va_list ap;
+
+	va_start(ap, fmt);
+	vsnprintf(message, sizeof(message), fmt, ap);
+	va_end(ap);
+
+	fprintf(stderr, "%s", message);
+}
+
+/*
+ * debug_msg - print a debug message to stderr if debug is set
+ */
+void debug_msg(const char *fmt, ...)
+{
+	char message[MAX_MSG_LENGTH];
+	va_list ap;
+
+	if (!config_debug)
+		return;
+
+	va_start(ap, fmt);
+	vsnprintf(message, sizeof(message), fmt, ap);
+	va_end(ap);
+
+	fprintf(stderr, "%s", message);
+}
+
+/*
+ * fatal - print an error message and EOL to stderr and exit with ERROR
+ */
+void fatal(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	fprintf(stderr, "\n");
+
+	exit(ERROR);
+}
+
+/*
+ * get_llong_from_str - get a long long int from a string
+ */
+long long get_llong_from_str(char *start)
+{
+	long long value;
+	char *end;
+
+	errno = 0;
+	value = strtoll(start, &end, 10);
+	if (errno || start == end)
+		return -1;
+
+	return value;
+}
+
+/*
+ * get_duration - fill output with a human readable duration since start_time
+ */
+void get_duration(time_t start_time, char *output, int output_size)
+{
+	time_t now = time(NULL);
+	struct tm *tm_info;
+	time_t duration;
+
+	duration = difftime(now, start_time);
+	tm_info = gmtime(&duration);
+
+	snprintf(output, output_size, "%3d %02d:%02d:%02d",
+			tm_info->tm_yday,
+			tm_info->tm_hour,
+			tm_info->tm_min,
+			tm_info->tm_sec);
+}
+
+/*
+ * parse_cpu_set - parse a cpu_list filling cpu_set_t argument
+ *
+ * Receives a cpu list, like 1-3,5 (cpus 1, 2, 3, 5), and then set
+ * filling cpu_set_t argument.
+ *
+ * Returns 0 on success, 1 otherwise.
+ */
+int parse_cpu_set(char *cpu_list, cpu_set_t *set)
+{
+	const char *p;
+	int end_cpu;
+	int cpu;
+	int i;
+
+	CPU_ZERO(set);
+
+	for (p = cpu_list; *p; ) {
+		cpu = atoi(p);
+		if (cpu < 0 || (!cpu && *p != '0') || cpu >= nr_cpus)
+			goto err;
+
+		while (isdigit(*p))
+			p++;
+		if (*p == '-') {
+			p++;
+			end_cpu = atoi(p);
+			if (end_cpu < cpu || (!end_cpu && *p != '0') || end_cpu >= nr_cpus)
+				goto err;
+			while (isdigit(*p))
+				p++;
+		} else
+			end_cpu = cpu;
+
+		if (cpu == end_cpu) {
+			debug_msg("cpu_set: adding cpu %d\n", cpu);
+			CPU_SET(cpu, set);
+		} else {
+			for (i = cpu; i <= end_cpu; i++) {
+				debug_msg("cpu_set: adding cpu %d\n", i);
+				CPU_SET(i, set);
+			}
+		}
+
+		if (*p == ',')
+			p++;
+	}
+
+	return 0;
+err:
+	debug_msg("Error parsing the cpu set %s\n", cpu_list);
+	return 1;
+}
+
+/*
+ * parse_stack_format - parse the stack format
+ *
+ * Return: the stack format on success, -1 otherwise.
+ */
+int parse_stack_format(char *arg)
+{
+	if (!strcmp(arg, "truncate"))
+		return STACK_FORMAT_TRUNCATE;
+	if (!strcmp(arg, "skip"))
+		return STACK_FORMAT_SKIP;
+	if (!strcmp(arg, "full"))
+		return STACK_FORMAT_FULL;
+
+	debug_msg("Error parsing the stack format %s\n", arg);
+	return -1;
+}
+
+/*
+ * parse_duration - parse duration with s/m/h/d suffix converting it to seconds
+ */
+long parse_seconds_duration(char *val)
+{
+	char *end;
+	long t;
+
+	t = strtol(val, &end, 10);
+
+	if (end) {
+		switch (*end) {
+		case 's':
+		case 'S':
+			break;
+		case 'm':
+		case 'M':
+			t *= 60;
+			break;
+		case 'h':
+		case 'H':
+			t *= 60 * 60;
+			break;
+
+		case 'd':
+		case 'D':
+			t *= 24 * 60 * 60;
+			break;
+		}
+	}
+
+	return t;
+}
+
+/*
+ * match_time_unit - check if str starts with unit followed by end-of-string or ':'
+ *
+ * This allows the time unit parser to work both in standalone duration strings
+ * like "100ms" and in colon-delimited SCHED_DEADLINE specifications like
+ * "d:10ms:100ms", while still rejecting malformed input like "100msx".
+ */
+static bool match_time_unit(const char *str, const char *unit)
+{
+	size_t len = strlen(unit);
+
+	return strncmp(str, unit, len) == 0 &&
+	       (str[len] == '\0' || str[len] == ':');
+}
+
+/*
+ * parse_ns_duration - parse duration with ns/us/ms/s converting it to nanoseconds
+ */
+long parse_ns_duration(char *val)
+{
+	char *end;
+	long t;
+
+	t = strtol(val, &end, 10);
+
+	if (end) {
+		if (match_time_unit(end, "ns")) {
+			return t;
+		} else if (match_time_unit(end, "us")) {
+			t *= 1000;
+			return t;
+		} else if (match_time_unit(end, "ms")) {
+			t *= 1000 * 1000;
+			return t;
+		} else if (match_time_unit(end, "s")) {
+			t *= 1000 * 1000 * 1000;
+			return t;
+		}
+		return -1;
+	}
+
+	return t;
+}
+
+/*
+ * This is a set of helper functions to use SCHED_DEADLINE.
+ */
+#ifndef __NR_sched_setattr
+# ifdef __x86_64__
+#  define __NR_sched_setattr	314
+# elif __i386__
+#  define __NR_sched_setattr	351
+# elif __arm__
+#  define __NR_sched_setattr	380
+# elif __aarch64__ || __riscv
+#  define __NR_sched_setattr	274
+# elif __powerpc__
+#  define __NR_sched_setattr	355
+# elif __s390x__
+#  define __NR_sched_setattr	345
+# elif __loongarch__
+#  define __NR_sched_setattr	274
+# endif
+#endif
+
+#define SCHED_DEADLINE		6
+
+static inline int syscall_sched_setattr(pid_t pid, const struct sched_attr *attr,
+				unsigned int flags) {
+	return syscall(__NR_sched_setattr, pid, attr, flags);
+}
+
+int __set_sched_attr(int pid, struct sched_attr *attr)
+{
+	int flags = 0;
+	int retval;
+
+	retval = syscall_sched_setattr(pid, attr, flags);
+	if (retval < 0) {
+		err_msg("Failed to set sched attributes to the pid %d: %s\n",
+			pid, strerror(errno));
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * procfs_is_workload_pid - check if a procfs entry contains a comm_prefix* comm
+ *
+ * Check if the procfs entry is a directory of a process, and then check if the
+ * process has a comm with the prefix set in char *comm_prefix. As the
+ * current users of this function only check for kernel threads, there is no
+ * need to check for the threads for the process.
+ *
+ * Return: True if the proc_entry contains a comm file with comm_prefix*.
+ * Otherwise returns false.
+ */
+static int procfs_is_workload_pid(const char *comm_prefix, struct dirent *proc_entry)
+{
+	char buffer[MAX_PATH];
+	int comm_fd, retval;
+	char *t_name;
+
+	if (proc_entry->d_type != DT_DIR)
+		return 0;
+
+	if (*proc_entry->d_name == '.')
+		return 0;
+
+	/* check if the string is a pid */
+	for (t_name = proc_entry->d_name; *t_name; t_name++) {
+		if (!isdigit(*t_name))
+			break;
+	}
+
+	if (*t_name != '\0')
+		return 0;
+
+	snprintf(buffer, MAX_PATH, "/proc/%s/comm", proc_entry->d_name);
+	comm_fd = open(buffer, O_RDONLY);
+	if (comm_fd < 0)
+		return 0;
+
+	memset(buffer, 0, MAX_PATH);
+	retval = read(comm_fd, buffer, MAX_PATH);
+
+	close(comm_fd);
+
+	if (retval <= 0)
+		return 0;
+
+	buffer[MAX_PATH-1] = '\0';
+	if (!str_has_prefix(buffer, comm_prefix))
+		return 0;
+
+	/* comm already have \n */
+	debug_msg("Found workload pid:%s comm:%s", proc_entry->d_name, buffer);
+
+	return 1;
+}
+
+/*
+ * set_comm_sched_attr - set sched params to threads starting with char *comm_prefix
+ *
+ * This function uses procfs to list the currently running threads and then set the
+ * sched_attr *attr to the threads that start with char *comm_prefix. It is
+ * mainly used to set the priority to the kernel threads created by the
+ * tracers.
+ */
+int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr)
+{
+	struct dirent *proc_entry;
+	DIR *procfs;
+	int retval;
+	int pid;
+
+	if (strlen(comm_prefix) >= MAX_PATH) {
+		err_msg("Command prefix is too long: %d < strlen(%s)\n",
+			MAX_PATH, comm_prefix);
+		return 1;
+	}
+
+	procfs = opendir("/proc");
+	if (!procfs) {
+		err_msg("Could not open procfs\n");
+		return 1;
+	}
+
+	while ((proc_entry = readdir(procfs))) {
+
+		retval = procfs_is_workload_pid(comm_prefix, proc_entry);
+		if (!retval)
+			continue;
+
+		if (strtoi(proc_entry->d_name, &pid)) {
+			err_msg("'%s' is not a valid pid", proc_entry->d_name);
+			retval = 1;
+			goto out;
+		}
+		/* procfs_is_workload_pid confirmed it is a pid */
+		retval = __set_sched_attr(pid, attr);
+		if (retval) {
+			err_msg("Error setting sched attributes for pid:%s\n", proc_entry->d_name);
+			goto out;
+		}
+
+		debug_msg("Set sched attributes for pid:%s\n", proc_entry->d_name);
+	}
+
+	retval = 0;
+out:
+	closedir(procfs);
+	return retval;
+}
+
+#define INVALID_VAL	(~0L)
+static long get_long_ns_after_colon(char *start)
+{
+	long val = INVALID_VAL;
+
+	/* find the ":" */
+	start = strstr(start, ":");
+	if (!start)
+		return -1;
+
+	/* skip ":" */
+	start++;
+	val = parse_ns_duration(start);
+
+	return val;
+}
+
+static long get_long_after_colon(char *start)
+{
+	long val = INVALID_VAL;
+
+	/* find the ":" */
+	start = strstr(start, ":");
+	if (!start)
+		return -1;
+
+	/* skip ":" */
+	start++;
+	val = get_llong_from_str(start);
+
+	return val;
+}
+
+/*
+ * parse priority in the format:
+ * SCHED_OTHER:
+ *		o:<prio>
+ *		O:<prio>
+ * SCHED_RR:
+ *		r:<prio>
+ *		R:<prio>
+ * SCHED_FIFO:
+ *		f:<prio>
+ *		F:<prio>
+ * SCHED_DEADLINE:
+ *		d:runtime:period
+ *		D:runtime:period
+ */
+int parse_prio(char *arg, struct sched_attr *sched_param)
+{
+	long prio;
+	long runtime;
+	long period;
+
+	memset(sched_param, 0, sizeof(*sched_param));
+	sched_param->size = sizeof(*sched_param);
+
+	switch (arg[0]) {
+	case 'd':
+	case 'D':
+		/* d:runtime:period */
+		if (strlen(arg) < 4)
+			return -1;
+
+		runtime = get_long_ns_after_colon(arg);
+		if (runtime == INVALID_VAL)
+			return -1;
+
+		period = get_long_ns_after_colon(&arg[2]);
+		if (period == INVALID_VAL)
+			return -1;
+
+		if (runtime > period)
+			return -1;
+
+		sched_param->sched_policy   = SCHED_DEADLINE;
+		sched_param->sched_runtime  = runtime;
+		sched_param->sched_deadline = period;
+		sched_param->sched_period   = period;
+		break;
+	case 'f':
+	case 'F':
+		/* f:prio */
+		prio = get_long_after_colon(arg);
+		if (prio == INVALID_VAL)
+			return -1;
+
+		if (prio < sched_get_priority_min(SCHED_FIFO))
+			return -1;
+		if (prio > sched_get_priority_max(SCHED_FIFO))
+			return -1;
+
+		sched_param->sched_policy   = SCHED_FIFO;
+		sched_param->sched_priority = prio;
+		break;
+	case 'r':
+	case 'R':
+		/* r:prio */
+		prio = get_long_after_colon(arg);
+		if (prio == INVALID_VAL)
+			return -1;
+
+		if (prio < sched_get_priority_min(SCHED_RR))
+			return -1;
+		if (prio > sched_get_priority_max(SCHED_RR))
+			return -1;
+
+		sched_param->sched_policy   = SCHED_RR;
+		sched_param->sched_priority = prio;
+		break;
+	case 'o':
+	case 'O':
+		/* o:prio */
+		prio = get_long_after_colon(arg);
+		if (prio == INVALID_VAL)
+			return -1;
+
+		if (prio < MIN_NICE)
+			return -1;
+		if (prio > MAX_NICE)
+			return -1;
+
+		sched_param->sched_policy   = SCHED_OTHER;
+		sched_param->sched_nice = prio;
+		break;
+	default:
+		return -1;
+	}
+	return 0;
+}
+
+/*
+ * set_cpu_dma_latency - set the /dev/cpu_dma_latecy
+ *
+ * This is used to reduce the exit from idle latency. The value
+ * will be reset once the file descriptor of /dev/cpu_dma_latecy
+ * is closed.
+ *
+ * Return: the /dev/cpu_dma_latecy file descriptor
+ */
+int set_cpu_dma_latency(int32_t latency)
+{
+	int retval;
+	int fd;
+
+	fd = open("/dev/cpu_dma_latency", O_RDWR);
+	if (fd < 0) {
+		err_msg("Error opening /dev/cpu_dma_latency\n");
+		return -1;
+	}
+
+	retval = write(fd, &latency, 4);
+	if (retval < 1) {
+		err_msg("Error setting /dev/cpu_dma_latency\n");
+		close(fd);
+		return -1;
+	}
+
+	debug_msg("Set /dev/cpu_dma_latency to %d\n", latency);
+
+	return fd;
+}
+
+#ifdef HAVE_LIBCPUPOWER_SUPPORT
+static unsigned int **saved_cpu_idle_disable_state;
+static size_t saved_cpu_idle_disable_state_alloc_ctr;
+
+/*
+ * save_cpu_idle_state_disable - save disable for all idle states of a cpu
+ *
+ * Saves the current disable of all idle states of a cpu, to be subsequently
+ * restored via restore_cpu_idle_disable_state.
+ *
+ * Return: idle state count on success, negative on error
+ */
+int save_cpu_idle_disable_state(unsigned int cpu)
+{
+	unsigned int nr_states;
+	unsigned int state;
+	int disabled;
+
+	nr_states = cpuidle_state_count(cpu);
+
+	if (nr_states == 0)
+		return 0;
+
+	if (saved_cpu_idle_disable_state == NULL) {
+		saved_cpu_idle_disable_state = calloc(nr_cpus, sizeof(unsigned int *));
+		if (!saved_cpu_idle_disable_state)
+			return -1;
+	}
+
+	saved_cpu_idle_disable_state[cpu] = calloc(nr_states, sizeof(unsigned int));
+	if (!saved_cpu_idle_disable_state[cpu])
+		return -1;
+	saved_cpu_idle_disable_state_alloc_ctr++;
+
+	for (state = 0; state < nr_states; state++) {
+		disabled = cpuidle_is_state_disabled(cpu, state);
+		if (disabled < 0)
+			return disabled;
+		saved_cpu_idle_disable_state[cpu][state] = disabled;
+	}
+
+	return nr_states;
+}
+
+/*
+ * restore_cpu_idle_disable_state - restore disable for all idle states of a cpu
+ *
+ * Restores the current disable state of all idle states of a cpu that was
+ * previously saved by save_cpu_idle_disable_state.
+ *
+ * Return: idle state count on success, negative on error
+ */
+int restore_cpu_idle_disable_state(unsigned int cpu)
+{
+	unsigned int nr_states;
+	unsigned int state;
+	int disabled;
+	int result;
+
+	nr_states = cpuidle_state_count(cpu);
+
+	if (nr_states == 0)
+		return 0;
+
+	if (!saved_cpu_idle_disable_state)
+		return -1;
+
+	for (state = 0; state < nr_states; state++) {
+		if (!saved_cpu_idle_disable_state[cpu])
+			return -1;
+		disabled = saved_cpu_idle_disable_state[cpu][state];
+		result = cpuidle_state_disable(cpu, state, disabled);
+		if (result < 0)
+			return result;
+	}
+
+	free(saved_cpu_idle_disable_state[cpu]);
+	saved_cpu_idle_disable_state[cpu] = NULL;
+	saved_cpu_idle_disable_state_alloc_ctr--;
+	if (saved_cpu_idle_disable_state_alloc_ctr == 0) {
+		free(saved_cpu_idle_disable_state);
+		saved_cpu_idle_disable_state = NULL;
+	}
+
+	return nr_states;
+}
+
+/*
+ * free_cpu_idle_disable_states - free saved idle state disable for all cpus
+ *
+ * Frees the memory used for storing cpu idle state disable for all cpus
+ * and states.
+ *
+ * Normally, the memory is freed automatically in
+ * restore_cpu_idle_disable_state; this is mostly for cleaning up after an
+ * error.
+ */
+void free_cpu_idle_disable_states(void)
+{
+	int cpu;
+
+	if (!saved_cpu_idle_disable_state)
+		return;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		free(saved_cpu_idle_disable_state[cpu]);
+		saved_cpu_idle_disable_state[cpu] = NULL;
+	}
+
+	free(saved_cpu_idle_disable_state);
+	saved_cpu_idle_disable_state = NULL;
+}
+
+/*
+ * set_deepest_cpu_idle_state - limit idle state of cpu
+ *
+ * Disables all idle states deeper than the one given in
+ * deepest_state (assuming states with higher number are deeper).
+ *
+ * This is used to reduce the exit from idle latency. Unlike
+ * set_cpu_dma_latency, it can disable idle states per cpu.
+ *
+ * Return: idle state count on success, negative on error
+ */
+int set_deepest_cpu_idle_state(unsigned int cpu, unsigned int deepest_state)
+{
+	unsigned int nr_states;
+	unsigned int state;
+	int result;
+
+	nr_states = cpuidle_state_count(cpu);
+
+	for (state = deepest_state + 1; state < nr_states; state++) {
+		result = cpuidle_state_disable(cpu, state, 1);
+		if (result < 0)
+			return result;
+	}
+
+	return nr_states;
+}
+#endif /* HAVE_LIBCPUPOWER_SUPPORT */
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
+/*
+ * find_mount - find a the mount point of a given fs
+ *
+ * Returns 0 if mount is not found, otherwise return 1 and fill mp
+ * with the mount point.
+ */
+static const int find_mount(const char *fs, char *mp, int sizeof_mp)
+{
+	char mount_point[MAX_PATH+1];
+	char type[100];
+	int found = 0;
+	FILE *fp;
+
+	fp = fopen("/proc/mounts", "r");
+	if (!fp)
+		return 0;
+
+	while (fscanf(fp, "%*s %" STR(MAX_PATH) "s %99s %*s %*d %*d\n",	mount_point, type) == 2) {
+		if (strcmp(type, fs) == 0) {
+			found = 1;
+			break;
+		}
+	}
+	fclose(fp);
+
+	if (!found)
+		return 0;
+
+	memset(mp, 0, sizeof_mp);
+	strncpy(mp, mount_point, sizeof_mp - 1);
+
+	debug_msg("Fs %s found at %s\n", fs, mp);
+	return 1;
+}
+
+/*
+ * get_self_cgroup - get the current thread cgroup path
+ *
+ * Parse /proc/$$/cgroup file to get the thread's cgroup. As an example of line to parse:
+ *
+ * 0::/user.slice/user-0.slice/session-3.scope'\n'
+ *
+ * This function is interested in the content after the second : and before the '\n'.
+ *
+ * Returns 1 if a string was found, 0 otherwise.
+ */
+static int get_self_cgroup(char *self_cg, int sizeof_self_cg)
+{
+	char path[MAX_PATH], *start;
+	int fd, retval;
+
+	snprintf(path, MAX_PATH, "/proc/%d/cgroup", getpid());
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return 0;
+
+	memset(path, 0, sizeof(path));
+	retval = read(fd, path, MAX_PATH);
+
+	close(fd);
+
+	if (retval <= 0)
+		return 0;
+
+	path[MAX_PATH-1] = '\0';
+	start = path;
+
+	start = strstr(start, ":");
+	if (!start)
+		return 0;
+
+	/* skip ":" */
+	start++;
+
+	start = strstr(start, ":");
+	if (!start)
+		return 0;
+
+	/* skip ":" */
+	start++;
+
+	if (strlen(start) >= sizeof_self_cg)
+		return 0;
+
+	snprintf(self_cg, sizeof_self_cg, "%s", start);
+
+	/* Swap '\n' with '\0' */
+	start = strstr(self_cg, "\n");
+
+	/* there must be '\n' */
+	if (!start)
+		return 0;
+
+	/* ok, it found a string after the second : and before the \n */
+	*start = '\0';
+
+	return 1;
+}
+
+/*
+ * open_cgroup_procs - Open the cgroup.procs file for the given cgroup
+ *
+ * If cgroup argument is not NULL, the cgroup.procs file for that cgroup
+ * will be opened. Otherwise, the cgroup of the calling, i.e., rtla, thread
+ * will be used.
+ *
+ * Supports cgroup v2.
+ *
+ * Returns the file descriptor on success, -1 otherwise.
+ */
+static int open_cgroup_procs(const char *cgroup)
+{
+	char cgroup_path[MAX_PATH - strlen("/cgroup.procs")];
+	char cgroup_procs[MAX_PATH];
+	int retval;
+	int cg_fd;
+	size_t cg_path_len;
+
+	retval = find_mount("cgroup2", cgroup_path, sizeof(cgroup_path));
+	if (!retval) {
+		err_msg("Did not find cgroupv2 mount point\n");
+		return -1;
+	}
+
+	cg_path_len = strlen(cgroup_path);
+
+	if (!cgroup) {
+		retval = get_self_cgroup(&cgroup_path[cg_path_len],
+				sizeof(cgroup_path) - cg_path_len);
+		if (!retval) {
+			err_msg("Did not find self cgroup\n");
+			return -1;
+		}
+	} else {
+		snprintf(&cgroup_path[cg_path_len],
+				sizeof(cgroup_path) - cg_path_len, "%s/", cgroup);
+	}
+
+	snprintf(cgroup_procs, MAX_PATH, "%s/cgroup.procs", cgroup_path);
+
+	debug_msg("Using cgroup path at: %s\n", cgroup_procs);
+
+	cg_fd = open(cgroup_procs, O_RDWR);
+	if (cg_fd < 0)
+		return -1;
+
+	return cg_fd;
+}
+
+/*
+ * set_pid_cgroup - Set cgroup to pid_t pid
+ *
+ * If cgroup argument is not NULL, the threads will move to the given cgroup.
+ * Otherwise, the cgroup of the calling, i.e., rtla, thread will be used.
+ *
+ * Supports cgroup v2.
+ *
+ * Returns 1 on success, 0 otherwise.
+ */
+int set_pid_cgroup(pid_t pid, const char *cgroup)
+{
+	char pid_str[24];
+	int retval;
+	int cg_fd;
+
+	cg_fd = open_cgroup_procs(cgroup);
+	if (cg_fd < 0)
+		return 0;
+
+	snprintf(pid_str, sizeof(pid_str), "%d\n", pid);
+
+	retval = write(cg_fd, pid_str, strlen(pid_str));
+	if (retval < 0)
+		err_msg("Error setting cgroup attributes for pid:%s - %s\n",
+				pid_str, strerror(errno));
+	else
+		debug_msg("Set cgroup attributes for pid:%s\n", pid_str);
+
+	close(cg_fd);
+
+	return (retval >= 0);
+}
+
+/**
+ * set_comm_cgroup - Set cgroup to threads starting with char *comm_prefix
+ *
+ * If cgroup argument is not NULL, the threads will move to the given cgroup.
+ * Otherwise, the cgroup of the calling, i.e., rtla, thread will be used.
+ *
+ * Supports cgroup v2.
+ *
+ * Returns 1 on success, 0 otherwise.
+ */
+int set_comm_cgroup(const char *comm_prefix, const char *cgroup)
+{
+	struct dirent *proc_entry;
+	DIR *procfs;
+	int retval;
+	int cg_fd;
+
+	if (strlen(comm_prefix) >= MAX_PATH) {
+		err_msg("Command prefix is too long: %d < strlen(%s)\n",
+			MAX_PATH, comm_prefix);
+		return 0;
+	}
+
+	cg_fd = open_cgroup_procs(cgroup);
+	if (cg_fd < 0)
+		return 0;
+
+	procfs = opendir("/proc");
+	if (!procfs) {
+		err_msg("Could not open procfs\n");
+		goto out_cg;
+	}
+
+	while ((proc_entry = readdir(procfs))) {
+
+		retval = procfs_is_workload_pid(comm_prefix, proc_entry);
+		if (!retval)
+			continue;
+
+		retval = write(cg_fd, proc_entry->d_name, strlen(proc_entry->d_name));
+		if (retval < 0) {
+			err_msg("Error setting cgroup attributes for pid:%s - %s\n",
+				proc_entry->d_name, strerror(errno));
+			goto out_procfs;
+		}
+
+		debug_msg("Set cgroup attributes for pid:%s\n", proc_entry->d_name);
+	}
+
+	closedir(procfs);
+	close(cg_fd);
+	return 1;
+
+out_procfs:
+	closedir(procfs);
+out_cg:
+	close(cg_fd);
+	return 0;
+}
+
+/**
+ * auto_house_keeping - Automatically move rtla out of measurement threads
+ *
+ * Try to move rtla away from the tracer, if possible.
+ *
+ * Returns 1 on success, 0 otherwise.
+ */
+int auto_house_keeping(cpu_set_t *monitored_cpus)
+{
+	cpu_set_t rtla_cpus, house_keeping_cpus;
+	int retval;
+
+	/* first get the CPUs in which rtla can actually run. */
+	retval = sched_getaffinity(getpid(), sizeof(rtla_cpus), &rtla_cpus);
+	if (retval == -1) {
+		debug_msg("Could not get rtla affinity, rtla might run with the threads!\n");
+		return 0;
+	}
+
+	/* then check if the existing setup is already good. */
+	CPU_AND(&house_keeping_cpus, &rtla_cpus, monitored_cpus);
+	if (!CPU_COUNT(&house_keeping_cpus)) {
+		debug_msg("rtla and the monitored CPUs do not share CPUs.");
+		debug_msg("Skipping auto house-keeping\n");
+		return 1;
+	}
+
+	/* remove the intersection */
+	CPU_XOR(&house_keeping_cpus, &rtla_cpus, monitored_cpus);
+
+	/* get only those that rtla can run */
+	CPU_AND(&house_keeping_cpus, &house_keeping_cpus, &rtla_cpus);
+
+	/* is there any cpu left? */
+	if (!CPU_COUNT(&house_keeping_cpus)) {
+		debug_msg("Could not find any CPU for auto house-keeping\n");
+		return 0;
+	}
+
+	retval = sched_setaffinity(getpid(), sizeof(house_keeping_cpus), &house_keeping_cpus);
+	if (retval == -1) {
+		debug_msg("Could not set affinity for auto house-keeping\n");
+		return 0;
+	}
+
+	debug_msg("rtla automatically moved to an auto house-keeping cpu set\n");
+
+	return 1;
+}
+
+/*
+ * strtoi - convert string to integer with error checking
+ *
+ * Returns 0 on success, -1 if conversion fails or result is out of int range.
+ */
+int strtoi(const char *s, int *res)
+{
+	char *end_ptr;
+	long lres;
+
+	if (!*s)
+		return -1;
+
+	errno = 0;
+	lres = strtol(s, &end_ptr, 0);
+	if (errno || *end_ptr || lres > INT_MAX || lres < INT_MIN)
+		return -1;
+
+	*res = (int) lres;
+	return 0;
+}
+
+static inline void fatal_alloc(void)
+{
+	fatal("Error allocating memory\n");
+}
+
+void *calloc_fatal(size_t n, size_t size)
+{
+	void *p = calloc(n, size);
+
+	if (!p)
+		fatal_alloc();
+
+	return p;
+}
+
+void *reallocarray_fatal(void *p, size_t n, size_t size)
+{
+	p = reallocarray(p, n, size);
+
+	if (!p)
+		fatal_alloc();
+
+	return p;
+}
+
+char *strdup_fatal(const char *s)
+{
+	char *p = strdup(s);
+
+	if (!p)
+		fatal_alloc();
+
+	return p;
+}
diff --git a/tools/tracing/rtla/src/utils.h b/tools/tracing/rtla/src/utils.h
new file mode 100644
index 000000000..2ba333366
--- /dev/null
+++ b/tools/tracing/rtla/src/utils.h
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdint.h>
+#include <string.h>
+#include <time.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+#include <linux/container_of.h>
+
+/*
+ * '18446744073709551615\0'
+ */
+#define BUFF_U64_STR_SIZE	24
+#define MAX_PATH		1024
+#define MAX_NICE		20
+#define MIN_NICE		-19
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+#endif
+
+/* Calculate string length at compile time (excluding null terminator) */
+#define STRING_LENGTH(s) (ARRAY_SIZE(s) - sizeof(*(s)))
+
+/* Compare string with static string, length determined at compile time */
+#define strncmp_static(s1, s2) strncmp(s1, s2, ARRAY_SIZE(s2))
+
+/**
+ * str_has_prefix - Test if a string has a given prefix
+ * @str: The string to test
+ * @prefix: The string to see if @str starts with
+ *
+ * Returns: true if @str starts with @prefix, false otherwise
+ */
+static inline bool str_has_prefix(const char *str, const char *prefix)
+{
+	return strncmp(str, prefix, strlen(prefix)) == 0;
+}
+
+extern bool config_debug;
+void debug_msg(const char *fmt, ...);
+void err_msg(const char *fmt, ...);
+void fatal(const char *fmt, ...);
+
+long parse_seconds_duration(char *val);
+void get_duration(time_t start_time, char *output, int output_size);
+
+long long get_llong_from_str(char *start);
+
+static inline void
+update_min(unsigned long long *a, unsigned long long *b)
+{
+	if (*a > *b)
+		*a = *b;
+}
+
+static inline void
+update_max(unsigned long long *a, unsigned long long *b)
+{
+	if (*a < *b)
+		*a = *b;
+}
+
+static inline void
+update_sum(unsigned long long *a, unsigned long long *b)
+{
+	*a += *b;
+}
+
+#ifndef SCHED_ATTR_SIZE_VER0
+struct sched_attr {
+	uint32_t size;
+	uint32_t sched_policy;
+	uint64_t sched_flags;
+	int32_t sched_nice;
+	uint32_t sched_priority;
+	uint64_t sched_runtime;
+	uint64_t sched_deadline;
+	uint64_t sched_period;
+};
+#endif /* SCHED_ATTR_SIZE_VER0 */
+
+enum stack_format {
+	STACK_FORMAT_TRUNCATE,
+	STACK_FORMAT_SKIP,
+	STACK_FORMAT_FULL
+};
+
+int parse_prio(char *arg, struct sched_attr *sched_param);
+int parse_cpu_set(char *cpu_list, cpu_set_t *set);
+int parse_stack_format(char *arg);
+int __set_sched_attr(int pid, struct sched_attr *attr);
+int set_comm_sched_attr(const char *comm_prefix, struct sched_attr *attr);
+int set_comm_cgroup(const char *comm_prefix, const char *cgroup);
+int set_pid_cgroup(pid_t pid, const char *cgroup);
+int set_cpu_dma_latency(int32_t latency);
+void *calloc_fatal(size_t n, size_t size);
+void *reallocarray_fatal(void *p, size_t n, size_t size);
+char *strdup_fatal(const char *s);
+#ifdef HAVE_LIBCPUPOWER_SUPPORT
+int save_cpu_idle_disable_state(unsigned int cpu);
+int restore_cpu_idle_disable_state(unsigned int cpu);
+void free_cpu_idle_disable_states(void);
+int set_deepest_cpu_idle_state(unsigned int cpu, unsigned int state);
+static inline int have_libcpupower_support(void) { return 1; }
+#else
+static inline int save_cpu_idle_disable_state(unsigned int cpu) { return -1; }
+static inline int restore_cpu_idle_disable_state(unsigned int cpu) { return -1; }
+static inline void free_cpu_idle_disable_states(void) { }
+static inline int set_deepest_cpu_idle_state(unsigned int cpu, unsigned int state) { return -1; }
+static inline int have_libcpupower_support(void) { return 0; }
+#endif /* HAVE_LIBCPUPOWER_SUPPORT */
+int auto_house_keeping(cpu_set_t *monitored_cpus);
+__attribute__((__warn_unused_result__)) int strtoi(const char *s, int *res);
+
+#define ns_to_usf(x) (((double)x/1000))
+#define ns_to_per(total, part) ((part * 100) / (double)total)
+
+enum result {
+	PASSED	= EXIT_SUCCESS,
+	ERROR	= EXIT_FAILURE,
+	FAILED, /* test hit the stop tracing condition */
+};