Merge tag 'trace-tools-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing tooling updates from Steven Rostedt:

- Allow RTLA to collect data via BPF

The current implementation of rtla uses libtracefs and libtraceevent
to pull sample events generated by the timerlat tracer from the trace
buffer. rtla then processes the sample by updating the histogram and
summary (current, maximum, minimum, and sum values) as well as checks
if tracing has been stopped due to threshold overflow.

In use cases where a large number of samples is being generated, that
is, with measurements running on many CPUs and with a low interval,
this sample processing design causes a significant CPU load on the
rtla side. Furthermore, with >100 CPUs and 100us interval, rtla was
reported as not being able to keep up with the samples and dropping
most of them, leading to it being unusable.

Change the way the timerlat trace processes samples by attaching a
BPF program to the trace event using the BPF skeleton feature of
bpftool. Unlike the current implementation, the BPF implementation
does not check whether tracing is stopped (in BPF mode, tracing is
always off to improve performance), but waits for a write to a BPF
ringbuffer instead. This allows rtla to exit immediately when a
threshold is violated, without waiting for the next iteration of the
while loop.

If the requirements for the BPF implementation are not met, either at
build time or at run time, the current implementation is used as
fallback. Which implementation is being used can be seen when running
rtla timerlat with "-D" option. rtla can be forced to run in non-BPF
mode by setting the RTLA_NO_BPF option to 1, for debugging purposes.

- Fix LD_FLAGS from being dropped in build

- Refactor code to remove duplication of save_trace_to_file

- Always set options and do not rely on default settings

Do not rely on the default kernel settings of the tracers when
starting. They could have been changed by the user which gives
inconsistent results. Always set the options that rtla expects.

- Add creation of ctags and TAGS for traversing code

* tag 'trace-tools-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
rtla: Add the ability to create ctags and etags
rtla/tests: Test setting default options
rtla/tests: Reset osnoise options before check
rtla: Always set all tracer options
rtla/osnoise: Set OSNOISE_WORKLOAD to true
rtla: Unify apply_config between top and hist
rtla/osnoise: Unify params struct
rtla: Fix segfault in save_trace_to_file call
tools/build: Use SYSTEM_BPFTOOL for system bpftool
rtla: Refactor save_trace_to_file
tools/rv: Keep user LDFLAGS in build
rtla/timerlat: Test BPF mode
rtla/timerlat_top: Use BPF to collect samples
rtla/timerlat_top: Move divisor to update
rtla/timerlat_hist: Use BPF to collect samples
rtla/timerlat: Add BPF skeleton to collect samples
rtla: Add optional dependency on BPF tooling
tools/build: Add bpftool-skeletons feature test
rtla/timerlat: Unify params struct

tools/build/Makefile.feature

···
          libbpf-bpf_create_map		\
          libpfm4                        \
          libdebuginfod			\
-         clang-bpf-co-re
+         clang-bpf-co-re		\
+         bpftool-skeletons
 
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)

tools/build/feature/Makefile

···
 $(OUTPUT)test-libpfm4.bin:
 	$(BUILD) -lpfm
 
+$(OUTPUT)test-bpftool-skeletons.bin:
+	$(SYSTEM_BPFTOOL) version | grep '^features:.*skeletons' \
+		> $(@:.bin=.make.output) 2>&1
 ###############################
 
 clean:

tools/scripts/Makefile.include

···
 LLVM_OBJCOPY	?= llvm-objcopy
 LLVM_STRIP	?= llvm-strip
 
+# Some tools require bpftool
+SYSTEM_BPFTOOL	?= bpftool
+
 ifeq ($(CC_NO_CLANG), 1)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
 

tools/tracing/rtla/.gitignore

···
 fixdep
 feature
 FEATURE-DUMP
+*.skel.h

tools/tracing/rtla/Makefile

···
 FEATURE_TESTS	:= libtraceevent
 FEATURE_TESTS	+= libtracefs
 FEATURE_TESTS	+= libcpupower
+FEATURE_TESTS	+= libbpf
+FEATURE_TESTS	+= clang-bpf-co-re
+FEATURE_TESTS	+= bpftool-skeletons
 FEATURE_DISPLAY	:= libtraceevent
 FEATURE_DISPLAY	+= libtracefs
 FEATURE_DISPLAY	+= libcpupower
+FEATURE_DISPLAY	+= libbpf
+FEATURE_DISPLAY	+= clang-bpf-co-re
+FEATURE_DISPLAY	+= bpftool-skeletons
 
 all: $(RTLA)
 
···
 
 export CFLAGS OUTPUT srctree
 
+ifeq ($(BUILD_BPF_SKEL),1)
+src/timerlat.bpf.o: src/timerlat.bpf.c
+	$(QUIET_CLANG)$(CLANG) -g -O2 -target bpf -c $(filter %.c,$^) -o $@
+
+src/timerlat.skel.h: src/timerlat.bpf.o
+	$(QUIET_GENSKEL)$(SYSTEM_BPFTOOL) gen skeleton $< > $@
+else
+src/timerlat.skel.h:
+	$(Q)echo '/* BPF skeleton is disabled */' > src/timerlat.skel.h
+endif
+
 $(RTLA): $(RTLA_IN)
 	$(QUIET_LINK)$(CC) $(LDFLAGS) -o $(RTLA) $(RTLA_IN) $(EXTLIBS)
 
···
 rtla.%: fixdep FORCE
 	make -f $(srctree)/tools/build/Makefile.build dir=. $@
 
-$(RTLA_IN): fixdep FORCE
+$(RTLA_IN): fixdep FORCE src/timerlat.skel.h
 	make $(build)=rtla
 
 clean: doc_clean fixdep-clean
···
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)rm -f rtla rtla-static fixdep FEATURE-DUMP rtla-*
 	$(Q)rm -rf feature
+	$(Q)rm -f src/timerlat.bpf.o src/timerlat.skel.h
 check: $(RTLA)
 	RTLA=$(RTLA) prove -o -f tests/
 .PHONY: FORCE clean check

tools/tracing/rtla/Makefile.config

···
   $(info Please install libcpupower-dev/kernel-tools-libs-devel)
 endif
 
+ifndef BUILD_BPF_SKEL
+  # BPF skeletons are used to implement improved sample collection, enable
+  # them by default.
+  BUILD_BPF_SKEL := 1
+endif
+
+ifeq ($(BUILD_BPF_SKEL),0)
+  $(info BPF skeleton support disabled, building without BPF skeleton support.)
+endif
+
+$(call feature_check,libbpf)
+ifeq ($(feature-libbpf), 1)
+  $(call detected,CONFIG_LIBBPF)
+else
+  $(info libbpf is missing, building without BPF skeleton support.)
+  $(info Please install libbpf-dev/libbpf-devel)
+  BUILD_BPF_SKEL := 0
+endif
+
+$(call feature_check,clang-bpf-co-re)
+ifeq ($(feature-clang-bpf-co-re), 1)
+  $(call detected,CONFIG_CLANG_BPF_CO_RE)
+else
+  $(info clang is missing or does not support BPF CO-RE, building without BPF skeleton support.)
+  $(info Please install clang)
+  BUILD_BPF_SKEL := 0
+endif
+
+$(call feature_check,bpftool-skeletons)
+ifeq ($(feature-bpftool-skeletons), 1)
+  $(call detected,CONFIG_BPFTOOL_SKELETONS)
+else
+  $(info bpftool is missing or not supporting skeletons, building without BPF skeleton support.)
+  $(info Please install bpftool)
+  BUILD_BPF_SKEL := 0
+endif
+
+ifeq ($(BUILD_BPF_SKEL),1)
+  CFLAGS += -DHAVE_BPF_SKEL
+  EXTLIBS += -lbpf
+endif
+
 ifeq ($(STOP_ERROR),1)
   $(error Please, check the errors above.)
 endif

tools/tracing/rtla/Makefile.rtla

···
 MKDIR		:= mkdir
 STRIP		:= strip
 BINDIR		:= /usr/bin
+CTAGS		:= ctags
+ETAGS		:= ctags -e
 
 .PHONY: install
 install: doc_install
···
 	@test ! -f $(DESTDIR)$(BINDIR)/timerlat || $(RM) $(DESTDIR)$(BINDIR)/timerlat
 	@$(LN) -s rtla $(DESTDIR)$(BINDIR)/timerlat
 
+.PHONY: tags
+tags:
+	$(CTAGS) -R --extras=+f --c-kinds=+p src
+
+.PHONY: TAGS
+TAGS:
+	$(ETAGS) -R --extras=+f --c-kinds=+p src
+
+.PHONY: tags_clean
+tags_clean:
+	$(RM) tags TAGS
+
 .PHONY: doc doc_clean doc_install
 doc:
 	$(MAKE) -C $(DOCSRC)
···
 doc_install:
 	$(MAKE) -C $(DOCSRC) install
 
-# This section is neesary for the tarball, when the tarball
-# support is removed, we can delete these entries.
+# This section is necessary to make the rtla tarball
 NAME		:= rtla
 DIRS		:= src
 FILES		:= Makefile README.txt

tools/tracing/rtla/src/Build

···
 rtla-y += timerlat_hist.o
 rtla-y += timerlat_u.o
 rtla-y += timerlat_aa.o
+rtla-y += timerlat_bpf.o
 rtla-y += rtla.o

tools/tracing/rtla/src/osnoise.c

···
  * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[e-mail]>
  */
 
+#define _GNU_SOURCE
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <pthread.h>
···
 #include <errno.h>
 #include <fcntl.h>
 #include <stdio.h>
+#include <sched.h>
 
 #include "osnoise.h"
-#include "utils.h"
+
+#define DEFAULT_SAMPLE_PERIOD	1000000			/* 1s */
+#define DEFAULT_SAMPLE_RUNTIME	1000000			/* 1s */
 
 /*
  * osnoise_get_cpus - return the original "osnoise/cpus" content
···
 		       tool->trace.missed_events,
 		       (double) tool->trace.missed_events / total_events * 100.0);
 	}
+}
+
+/*
+ * osnoise_apply_config - apply common configs to the initialized tool
+ */
+int
+osnoise_apply_config(struct osnoise_tool *tool, struct osnoise_params *params)
+{
+	int retval;
+
+	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->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_stop_us(tool->context, params->stop_us);
+	if (retval) {
+		err_msg("Failed to set stop us\n");
+		goto out_err;
+	}
+
+	retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
+	if (retval) {
+		err_msg("Failed to set stop total us\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;
+	}
+
+	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);
+	}
+
+	retval = osnoise_set_workload(tool->context, true);
+	if (retval < -1) {
+		err_msg("Failed to set OSNOISE_WORKLOAD option\n");
+		goto out_err;
+	}
+
+	return 0;
+
+out_err:
+	return -1;
 }
 
 static void osnoise_usage(int err)

tools/tracing/rtla/src/osnoise.h

···
 // SPDX-License-Identifier: GPL-2.0
+#pragma once
+
+#include "utils.h"
 #include "trace.h"
+
+enum osnoise_mode {
+	MODE_OSNOISE = 0,
+	MODE_HWNOISE
+};
+
+struct osnoise_params {
+	/* Common params */
+	char			*cpus;
+	cpu_set_t		monitored_cpus;
+	char			*trace_output;
+	char			*cgroup_name;
+	unsigned long long	runtime;
+	unsigned long long	period;
+	long long		threshold;
+	long long		stop_us;
+	long long		stop_total_us;
+	int			sleep_time;
+	int			duration;
+	int			set_sched;
+	int			cgroup;
+	int			hk_cpus;
+	cpu_set_t		hk_cpu_set;
+	struct sched_attr	sched_param;
+	struct trace_events	*events;
+	int			warmup;
+	int			buffer_size;
+	union {
+		struct {
+			/* top only */
+			int			quiet;
+			int			pretty_output;
+			enum osnoise_mode	mode;
+		};
+		struct {
+			/* hist only */
+			int			output_divisor;
+			char			no_header;
+			char			no_summary;
+			char			no_index;
+			char			with_zeros;
+			int			bucket_size;
+			int			entries;
+		};
+	};
+};
 
 /*
  * osnoise_context - read, store, write, restore osnoise configs.
···
 struct osnoise_tool *osnoise_init_trace_tool(char *tracer);
 void osnoise_report_missed_events(struct osnoise_tool *tool);
 bool osnoise_trace_is_off(struct osnoise_tool *tool, struct osnoise_tool *record);
+int osnoise_apply_config(struct osnoise_tool *tool, struct osnoise_params *params);
 
 int osnoise_hist_main(int argc, char *argv[]);
 int osnoise_top_main(int argc, char **argv);

tools/tracing/rtla/src/osnoise_hist.c

···
 #include <errno.h>
 #include <stdio.h>
 #include <time.h>
-#include <sched.h>
 
-#include "utils.h"
 #include "osnoise.h"
-
-struct osnoise_hist_params {
-	char			*cpus;
-	cpu_set_t		monitored_cpus;
-	char			*trace_output;
-	char			*cgroup_name;
-	unsigned long long	runtime;
-	unsigned long long	period;
-	long long		threshold;
-	long long		stop_us;
-	long long		stop_total_us;
-	int			sleep_time;
-	int			duration;
-	int			set_sched;
-	int			output_divisor;
-	int			cgroup;
-	int			hk_cpus;
-	cpu_set_t		hk_cpu_set;
-	struct sched_attr	sched_param;
-	struct trace_events	*events;
-	char			no_header;
-	char			no_summary;
-	char			no_index;
-	char			with_zeros;
-	int			bucket_size;
-	int			entries;
-	int			warmup;
-	int			buffer_size;
-};
 
 struct osnoise_hist_cpu {
 	int			*samples;
···
 static void osnoise_hist_update_multiple(struct osnoise_tool *tool, int cpu,
 					 unsigned long long duration, int count)
 {
-	struct osnoise_hist_params *params = tool->params;
+	struct osnoise_params *params = tool->params;
 	struct osnoise_hist_data *data = tool->data;
 	unsigned long long total_duration;
 	int entries = data->entries;
···
  */
 static int osnoise_init_trace_hist(struct osnoise_tool *tool)
 {
-	struct osnoise_hist_params *params = tool->params;
+	struct osnoise_params *params = tool->params;
 	struct osnoise_hist_data *data = tool->data;
 	int bucket_size;
 	char buff[128];
···
  */
 static void osnoise_hist_header(struct osnoise_tool *tool)
 {
-	struct osnoise_hist_params *params = tool->params;
+	struct osnoise_params *params = tool->params;
 	struct osnoise_hist_data *data = tool->data;
 	struct trace_seq *s = tool->trace.seq;
 	char duration[26];
···
  * osnoise_print_summary - print the summary of the hist data to the output
  */
 static void
-osnoise_print_summary(struct osnoise_hist_params *params,
+osnoise_print_summary(struct osnoise_params *params,
 		       struct trace_instance *trace,
 		       struct osnoise_hist_data *data)
 {
···
  * osnoise_print_stats - print data for all CPUs
  */
 static void
-osnoise_print_stats(struct osnoise_hist_params *params, struct osnoise_tool *tool)
+osnoise_print_stats(struct osnoise_params *params, struct osnoise_tool *tool)
 {
 	struct osnoise_hist_data *data = tool->data;
 	struct trace_instance *trace = &tool->trace;
···
 /*
  * osnoise_hist_parse_args - allocs, parse and fill the cmd line parameters
  */
-static struct osnoise_hist_params
+static struct osnoise_params
 *osnoise_hist_parse_args(int argc, char *argv[])
 {
-	struct osnoise_hist_params *params;
+	struct osnoise_params *params;
 	struct trace_events *tevent;
 	int retval;
 	int c;
···
  * osnoise_hist_apply_config - apply the hist configs to the initialized tool
  */
 static int
-osnoise_hist_apply_config(struct osnoise_tool *tool, struct osnoise_hist_params *params)
+osnoise_hist_apply_config(struct osnoise_tool *tool, struct osnoise_params *params)
 {
 	int retval;
 
-	if (!params->sleep_time)
-		params->sleep_time = 1;
-
-	if (params->cpus) {
-		retval = osnoise_set_cpus(tool->context, params->cpus);
-		if (retval) {
-			err_msg("Failed to apply CPUs config\n");
-			goto out_err;
-		}
-	}
-
-	if (params->runtime || params->period) {
-		retval = osnoise_set_runtime_period(tool->context,
-						    params->runtime,
-						    params->period);
-		if (retval) {
-			err_msg("Failed to set runtime and/or period\n");
-			goto out_err;
-		}
-	}
-
-	if (params->stop_us) {
-		retval = osnoise_set_stop_us(tool->context, params->stop_us);
-		if (retval) {
-			err_msg("Failed to set stop us\n");
-			goto out_err;
-		}
-	}
-
-	if (params->stop_total_us) {
-		retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
-		if (retval) {
-			err_msg("Failed to set stop total us\n");
-			goto out_err;
-		}
-	}
-
-	if (params->threshold) {
-		retval = osnoise_set_tracing_thresh(tool->context, params->threshold);
-		if (retval) {
-			err_msg("Failed to set tracing_thresh\n");
-			goto out_err;
-		}
-	}
-
-	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);
-	}
+	retval = osnoise_apply_config(tool, params);
+	if (retval)
+		goto out_err;
 
 	return 0;
 
···
  * osnoise_init_hist - initialize a osnoise hist tool with parameters
  */
 static struct osnoise_tool
-*osnoise_init_hist(struct osnoise_hist_params *params)
+*osnoise_init_hist(struct osnoise_params *params)
 {
 	struct osnoise_tool *tool;
 	int nr_cpus;
···
  * osnoise_hist_set_signals - handles the signal to stop the tool
  */
 static void
-osnoise_hist_set_signals(struct osnoise_hist_params *params)
+osnoise_hist_set_signals(struct osnoise_params *params)
 {
 	signal(SIGINT, stop_hist);
 	if (params->duration) {
···
 
 int osnoise_hist_main(int argc, char *argv[])
 {
-	struct osnoise_hist_params *params;
+	struct osnoise_params *params;
 	struct osnoise_tool *record = NULL;
 	struct osnoise_tool *tool = NULL;
 	struct trace_instance *trace;
···
 
 	if (osnoise_trace_is_off(tool, record)) {
 		printf("rtla osnoise hit stop tracing\n");
-		if (params->trace_output) {
-			printf("  Saving trace to %s\n", params->trace_output);
-			save_trace_to_file(record->trace.inst, params->trace_output);
-		}
+		save_trace_to_file(record ? record->trace.inst : NULL,
+				   params->trace_output);
 	}
 
 out_hist:

tools/tracing/rtla/src/osnoise_top.c

···
 #include <unistd.h>
 #include <stdio.h>
 #include <time.h>
-#include <sched.h>
 
 #include "osnoise.h"
-#include "utils.h"
-
-enum osnoise_mode {
-	MODE_OSNOISE = 0,
-	MODE_HWNOISE
-};
-
-/*
- * osnoise top parameters
- */
-struct osnoise_top_params {
-	char			*cpus;
-	cpu_set_t		monitored_cpus;
-	char			*trace_output;
-	char			*cgroup_name;
-	unsigned long long	runtime;
-	unsigned long long	period;
-	long long		threshold;
-	long long		stop_us;
-	long long		stop_total_us;
-	int			sleep_time;
-	int			duration;
-	int			quiet;
-	int			set_sched;
-	int			cgroup;
-	int			hk_cpus;
-	int			warmup;
-	int			buffer_size;
-	int			pretty_output;
-	cpu_set_t		hk_cpu_set;
-	struct sched_attr	sched_param;
-	struct trace_events	*events;
-	enum osnoise_mode	mode;
-};
 
 struct osnoise_top_cpu {
 	unsigned long long	sum_runtime;
···
  */
 static void osnoise_top_header(struct osnoise_tool *top)
 {
-	struct osnoise_top_params *params = top->params;
+	struct osnoise_params *params = top->params;
 	struct trace_seq *s = top->trace.seq;
 	char duration[26];
 
···
  */
 static void osnoise_top_print(struct osnoise_tool *tool, int cpu)
 {
-	struct osnoise_top_params *params = tool->params;
+	struct osnoise_params *params = tool->params;
 	struct trace_seq *s = tool->trace.seq;
 	struct osnoise_top_cpu *cpu_data;
 	struct osnoise_top_data *data;
···
  * osnoise_print_stats - print data for all cpus
  */
 static void
-osnoise_print_stats(struct osnoise_top_params *params, struct osnoise_tool *top)
+osnoise_print_stats(struct osnoise_params *params, struct osnoise_tool *top)
 {
 	struct trace_instance *trace = &top->trace;
 	static int nr_cpus = -1;
···
 /*
  * osnoise_top_usage - prints osnoise top usage message
  */
-static void osnoise_top_usage(struct osnoise_top_params *params, char *usage)
+static void osnoise_top_usage(struct osnoise_params *params, char *usage)
 {
 	int i;
 
···
 /*
  * osnoise_top_parse_args - allocs, parse and fill the cmd line parameters
  */
-struct osnoise_top_params *osnoise_top_parse_args(int argc, char **argv)
+struct osnoise_params *osnoise_top_parse_args(int argc, char **argv)
 {
-	struct osnoise_top_params *params;
+	struct osnoise_params *params;
 	struct trace_events *tevent;
 	int retval;
 	int c;
···
  * osnoise_top_apply_config - apply the top configs to the initialized tool
  */
 static int
-osnoise_top_apply_config(struct osnoise_tool *tool, struct osnoise_top_params *params)
+osnoise_top_apply_config(struct osnoise_tool *tool, struct osnoise_params *params)
 {
 	int retval;
 
-	if (!params->sleep_time)
-		params->sleep_time = 1;
-
-	if (params->cpus) {
-		retval = osnoise_set_cpus(tool->context, params->cpus);
-		if (retval) {
-			err_msg("Failed to apply CPUs config\n");
-			goto out_err;
-		}
-	}
-
-	if (params->runtime || params->period) {
-		retval = osnoise_set_runtime_period(tool->context,
-						    params->runtime,
-						    params->period);
-		if (retval) {
-			err_msg("Failed to set runtime and/or period\n");
-			goto out_err;
-		}
-	}
-
-	if (params->stop_us) {
-		retval = osnoise_set_stop_us(tool->context, params->stop_us);
-		if (retval) {
-			err_msg("Failed to set stop us\n");
-			goto out_err;
-		}
-	}
-
-	if (params->stop_total_us) {
-		retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
-		if (retval) {
-			err_msg("Failed to set stop total us\n");
-			goto out_err;
-		}
-	}
-
-	if (params->threshold) {
-		retval = osnoise_set_tracing_thresh(tool->context, params->threshold);
-		if (retval) {
-			err_msg("Failed to set tracing_thresh\n");
-			goto out_err;
-		}
-	}
+	retval = osnoise_apply_config(tool, params);
+	if (retval)
+		goto out_err;
 
 	if (params->mode == MODE_HWNOISE) {
 		retval = osnoise_set_irq_disable(tool->context, 1);
···
 			err_msg("Failed to set OSNOISE_IRQ_DISABLE option\n");
 			goto out_err;
 		}
-	}
-
-	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);
 	}
 
 	if (isatty(STDOUT_FILENO) && !params->quiet)
···
 /*
  * osnoise_init_top - initialize a osnoise top tool with parameters
  */
-struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params)
+struct osnoise_tool *osnoise_init_top(struct osnoise_params *params)
 {
 	struct osnoise_tool *tool;
 	int nr_cpus;
···
 /*
  * osnoise_top_set_signals - handles the signal to stop the tool
  */
-static void osnoise_top_set_signals(struct osnoise_top_params *params)
+static void osnoise_top_set_signals(struct osnoise_params *params)
 {
 	signal(SIGINT, stop_top);
 	if (params->duration) {
···
 
 int osnoise_top_main(int argc, char **argv)
 {
-	struct osnoise_top_params *params;
+	struct osnoise_params *params;
 	struct osnoise_tool *record = NULL;
 	struct osnoise_tool *tool = NULL;
 	struct trace_instance *trace;
···
 
 	if (osnoise_trace_is_off(tool, record)) {
 		printf("osnoise hit stop tracing\n");
-		if (params->trace_output) {
-			printf("  Saving trace to %s\n", params->trace_output);
-			save_trace_to_file(record->trace.inst, params->trace_output);
-		}
+		save_trace_to_file(record ? record->trace.inst : NULL,
+				   params->trace_output);
 	}
 
 out_top:

tools/tracing/rtla/src/timerlat.bpf.c

···
+// 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_RINGBUF);
+	__uint(max_entries, 1);
+} signal_stop_tracing SEC(".maps");
+
+/* 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;
+
+int stop_tracing;
+
+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(void)
+{
+	int value = 0;
+
+	/* Suppress further sample processing */
+	stop_tracing = 1;
+
+	/* Signal to userspace */
+	bpf_ringbuf_output(&signal_stop_tracing, &value, sizeof(value), 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 (stop_tracing)
+		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();
+	} 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();
+	} else {
+		update_main_hist(&hist_user, bucket);
+		update_summary(&summary_user, latency, bucket);
+	}
+
+	return 0;
+}

tools/tracing/rtla/src/timerlat.c

···
 /*
  * Copyright (C) 2021 Red Hat Inc, Daniel Bristot de Oliveira <[e-mail]>
  */
+#define _GNU_SOURCE
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <pthread.h>
···
 #include <errno.h>
 #include <fcntl.h>
 #include <stdio.h>
+#include <sched.h>
 
 #include "timerlat.h"
+
+#define DEFAULT_TIMERLAT_PERIOD	1000			/* 1ms */
+
+/*
+ * timerlat_apply_config - apply common configs to the initialized tool
+ */
+int
+timerlat_apply_config(struct osnoise_tool *tool, struct timerlat_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 < sysconf(_SC_NPROCESSORS_CONF); i++)
+			CPU_SET(i, &params->monitored_cpus);
+	}
+
+	retval = osnoise_set_stop_us(tool->context, params->stop_us);
+	if (retval) {
+		err_msg("Failed to set stop us\n");
+		goto out_err;
+	}
+
+	retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
+	if (retval) {
+		err_msg("Failed to set stop total us\n");
+		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;
+	}
+
+	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);
+	}
+
+	/*
+	 * If the user did not specify a type of thread, try user-threads first.
+	 * Fall back to kernel threads otherwise.
+	 */
+	if (!params->kernel_workload && !params->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->user_workload = 1;
+			params->user_data = 1;
+		} else {
+			debug_msg("User-space interface not detected, setting kernel-threads\n");
+			params->kernel_workload = 1;
+		}
+	}
+
+	/*
+	 * Set workload according to type of thread if the kernel supports it.
+	 * On kernels without support, user threads will have already failed
+	 * on missing timerlat_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;
+}
 
 static void timerlat_usage(int err)
 {

tools/tracing/rtla/src/timerlat.h

···
 // SPDX-License-Identifier: GPL-2.0
+#include "osnoise.h"
+
+struct timerlat_params {
+	/* Common params */
+	char			*cpus;
+	cpu_set_t		monitored_cpus;
+	char			*trace_output;
+	char			*cgroup_name;
+	unsigned long long	runtime;
+	long long		stop_us;
+	long long		stop_total_us;
+	long long		timerlat_period_us;
+	long long		print_stack;
+	int			sleep_time;
+	int			output_divisor;
+	int			duration;
+	int			set_sched;
+	int			dma_latency;
+	int			no_aa;
+	int			dump_tasks;
+	int			cgroup;
+	int			hk_cpus;
+	int			user_workload;
+	int			kernel_workload;
+	int			user_data;
+	int			warmup;
+	int			buffer_size;
+	int			deepest_idle_state;
+	cpu_set_t		hk_cpu_set;
+	struct sched_attr	sched_param;
+	struct trace_events	*events;
+	union {
+		struct {
+			/* top only */
+			int			quiet;
+			int			aa_only;
+			int			pretty_output;
+		};
+		struct {
+			/* hist only */
+			char			no_irq;
+			char			no_thread;
+			char			no_header;
+			char			no_summary;
+			char			no_index;
+			char			with_zeros;
+			int			bucket_size;
+			int			entries;
+		};
+	};
+};
+
+int timerlat_apply_config(struct osnoise_tool *tool, struct timerlat_params *params);
+
 int timerlat_hist_main(int argc, char *argv[]);
 int timerlat_top_main(int argc, char *argv[]);
 int timerlat_main(int argc, char *argv[]);

tools/tracing/rtla/src/timerlat_aa.c

···
 
 #include <stdlib.h>
 #include <errno.h>
-#include "utils.h"
-#include "osnoise.h"
 #include "timerlat.h"
 #include <unistd.h>
 

tools/tracing/rtla/src/timerlat_bpf.c

···
+// SPDX-License-Identifier: GPL-2.0
+#ifdef HAVE_BPF_SKEL
+#include "timerlat.h"
+#include "timerlat_bpf.h"
+#include "timerlat.skel.h"
+
+static struct timerlat_bpf *bpf;
+
+/*
+ * 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->output_divisor;
+	bpf->rodata->entries = params->entries;
+	bpf->rodata->irq_threshold = params->stop_us;
+	bpf->rodata->thread_threshold = params->stop_total_us;
+	bpf->rodata->aa_only = params->aa_only;
+
+	if (params->entries != 0) {
+		/* Pass histogram options */
+		bpf->rodata->bucket_size = params->bucket_size;
+
+		/* Set histogram array sizes */
+		bpf_map__set_max_entries(bpf->maps.hist_irq, params->entries);
+		bpf_map__set_max_entries(bpf->maps.hist_thread, params->entries);
+		bpf_map__set_max_entries(bpf->maps.hist_user, params->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->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_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);
+}
+
+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;
+}
+
+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 cpus)
+{
+	int err;
+
+	err = bpf_map__lookup_elem(map_irq, &key,
+				   sizeof(unsigned int), value_irq,
+				   sizeof(long long) * cpus, 0);
+	if (err)
+		return err;
+	err = bpf_map__lookup_elem(map_thread, &key,
+				   sizeof(unsigned int), value_thread,
+				   sizeof(long long) * cpus, 0);
+	if (err)
+		return err;
+	err = bpf_map__lookup_elem(map_user, &key,
+				   sizeof(unsigned int), value_user,
+				   sizeof(long long) * 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,
+				int cpus)
+{
+	return get_value(bpf->maps.hist_irq,
+			 bpf->maps.hist_thread,
+			 bpf->maps.hist_user,
+			 key, value_irq, value_thread, value_user, cpus);
+}
+
+/*
+ * 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,
+				   int cpus)
+{
+	return get_value(bpf->maps.summary_irq,
+			 bpf->maps.summary_thread,
+			 bpf->maps.summary_user,
+			 key, value_irq, value_thread, value_user, cpus);
+}
+#endif /* HAVE_BPF_SKEL */

tools/tracing/rtla/src/timerlat_bpf.h

···
+/* 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_get_hist_value(int key,
+				long long *value_irq,
+				long long *value_thread,
+				long long *value_user,
+				int cpus);
+int timerlat_bpf_get_summary_value(enum summary_field key,
+				   long long *value_irq,
+				   long long *value_thread,
+				   long long *value_user,
+				   int cpus);
+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_get_hist_value(int key,
+					      long long *value_irq,
+					      long long *value_thread,
+					      long long *value_user,
+					      int cpus)
+{
+	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,
+						 int cpus)
+{
+	return -1;
+}
+static inline int have_libbpf_support(void) { return 0; }
+#endif /* HAVE_BPF_SKEL */
+#endif /* __bpf__ */

tools/tracing/rtla/src/timerlat_hist.c

···
 #include <sched.h>
 #include <pthread.h>
 
-#include "utils.h"
-#include "osnoise.h"
 #include "timerlat.h"
 #include "timerlat_aa.h"
 #include "timerlat_u.h"
-
-struct timerlat_hist_params {
-	char			*cpus;
-	cpu_set_t		monitored_cpus;
-	char			*trace_output;
-	char			*cgroup_name;
-	unsigned long long	runtime;
-	long long		stop_us;
-	long long		stop_total_us;
-	long long		timerlat_period_us;
-	long long		print_stack;
-	int			sleep_time;
-	int			output_divisor;
-	int			duration;
-	int			set_sched;
-	int			dma_latency;
-	int			cgroup;
-	int			hk_cpus;
-	int			no_aa;
-	int			dump_tasks;
-	int			user_workload;
-	int			kernel_workload;
-	int			user_hist;
-	cpu_set_t		hk_cpu_set;
-	struct sched_attr	sched_param;
-	struct trace_events	*events;
-	char			no_irq;
-	char			no_thread;
-	char			no_header;
-	char			no_summary;
-	char			no_index;
-	char			with_zeros;
-	int			bucket_size;
-	int			entries;
-	int			warmup;
-	int			buffer_size;
-	int			deepest_idle_state;
-};
+#include "timerlat_bpf.h"
 
 struct timerlat_hist_cpu {
 	int			*irq;
···
 		     unsigned long long context,
 		     unsigned long long latency)
 {
-	struct timerlat_hist_params *params = tool->params;
+	struct timerlat_params *params = tool->params;
 	struct timerlat_hist_data *data = tool->data;
 	int entries = data->entries;
 	int bucket;
···
 }
 
 /*
+ * 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[data->nr_cpus],
+		  value_thread[data->nr_cpus],
+		  value_user[data->nr_cpus];
+
+	/* Pull histogram */
+	for (i = 0; i < data->entries; i++) {
+		err = timerlat_bpf_get_hist_value(i, value_irq, value_thread,
+						  value_user, data->nr_cpus);
+		if (err)
+			return err;
+		for (j = 0; j < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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_hist_params *params = tool->params;
+	struct timerlat_params *params = tool->params;
 	struct timerlat_hist_data *data = tool->data;
 	struct trace_seq *s = tool->trace.seq;
 	char duration[26];
···
 		if (!params->no_thread)
 			trace_seq_printf(s, "   Thr-%03d", cpu);
 
-		if (params->user_hist)
+		if (params->user_data)
 			trace_seq_printf(s, "   Usr-%03d", cpu);
 	}
 	trace_seq_printf(s, "\n");
···
  * timerlat_print_summary - print the summary of the hist data to the output
  */
 static void
-timerlat_print_summary(struct timerlat_hist_params *params,
+timerlat_print_summary(struct timerlat_params *params,
 		       struct trace_instance *trace,
 		       struct timerlat_hist_data *data)
 {
···
 			trace_seq_printf(trace->seq, "%9llu ",
 					data->hist[cpu].thread_count);
 
-		if (params->user_hist)
+		if (params->user_data)
 			trace_seq_printf(trace->seq, "%9llu ",
 					 data->hist[cpu].user_count);
 	}
···
 					     data->hist[cpu].min_thread,
 					     false);
 
-		if (params->user_hist)
+		if (params->user_data)
 			format_summary_value(trace->seq,
 					     data->hist[cpu].user_count,
 					     data->hist[cpu].min_user,
···
 					     data->hist[cpu].sum_thread,
 					     true);
 
-		if (params->user_hist)
+		if (params->user_data)
 			format_summary_value(trace->seq,
 					     data->hist[cpu].user_count,
 					     data->hist[cpu].sum_user,
···
 					     data->hist[cpu].max_thread,
 					     false);
 
-		if (params->user_hist)
+		if (params->user_data)
 			format_summary_value(trace->seq,
 					     data->hist[cpu].user_count,
 					     data->hist[cpu].max_user,
···
 }
 
 static void
-timerlat_print_stats_all(struct timerlat_hist_params *params,
+timerlat_print_stats_all(struct timerlat_params *params,
 			 struct trace_instance *trace,
 			 struct timerlat_hist_data *data)
 {
···
 	if (!params->no_thread)
 		trace_seq_printf(trace->seq, "       Thr");
 
-	if (params->user_hist)
+	if (params->user_data)
 		trace_seq_printf(trace->seq, "       Usr");
 
 	trace_seq_printf(trace->seq, "\n");
···
 		trace_seq_printf(trace->seq, "%9llu ",
 				 sum.thread_count);
 
-	if (params->user_hist)
+	if (params->user_data)
 		trace_seq_printf(trace->seq, "%9llu ",
 				 sum.user_count);
 
···
 				     sum.min_thread,
 				     false);
 
-	if (params->user_hist)
+	if (params->user_data)
 		format_summary_value(trace->seq,
 				     sum.user_count,
 				     sum.min_user,
···
 				     sum.sum_thread,
 				     true);
 
-	if (params->user_hist)
+	if (params->user_data)
 		format_summary_value(trace->seq,
 				     sum.user_count,
 				     sum.sum_user,
···
 				     sum.max_thread,
 				     false);
 
-	if (params->user_hist)
+	if (params->user_data)
 		format_summary_value(trace->seq,
 				     sum.user_count,
 				     sum.max_user,
···
  * timerlat_print_stats - print data for each CPUs
  */
 static void
-timerlat_print_stats(struct timerlat_hist_params *params, struct osnoise_tool *tool)
+timerlat_print_stats(struct timerlat_params *params, struct osnoise_tool *tool)
 {
 	struct timerlat_hist_data *data = tool->data;
 	struct trace_instance *trace = &tool->trace;
···
 						data->hist[cpu].thread[bucket]);
 			}
 
-			if (params->user_hist) {
+			if (params->user_data) {
 				total += data->hist[cpu].user[bucket];
 				trace_seq_printf(trace->seq, "%9d ",
 						data->hist[cpu].user[bucket]);
···
 			trace_seq_printf(trace->seq, "%9d ",
 					 data->hist[cpu].thread[data->entries]);
 
-		if (params->user_hist)
+		if (params->user_data)
 			trace_seq_printf(trace->seq, "%9d ",
 					 data->hist[cpu].user[data->entries]);
 	}
···
 /*
  * timerlat_hist_parse_args - allocs, parse and fill the cmd line parameters
  */
-static struct timerlat_hist_params
+static struct timerlat_params
 *timerlat_hist_parse_args(int argc, char *argv[])
 {
-	struct timerlat_hist_params *params;
+	struct timerlat_params *params;
 	struct trace_events *tevent;
 	int auto_thresh;
 	int retval;
···
 			params->user_workload = 1;
 			/* fallback: -u implies in -U */
 		case 'U':
-			params->user_hist = 1;
+			params->user_data = 1;
 			break;
 		case '0': /* no irq */
 			params->no_irq = 1;
···
  * timerlat_hist_apply_config - apply the hist configs to the initialized tool
  */
 static int
-timerlat_hist_apply_config(struct osnoise_tool *tool, struct timerlat_hist_params *params)
+timerlat_hist_apply_config(struct osnoise_tool *tool, struct timerlat_params *params)
 {
-	int retval, i;
+	int retval;
 
-	if (!params->sleep_time)
-		params->sleep_time = 1;
-
-	if (params->cpus) {
-		retval = osnoise_set_cpus(tool->context, params->cpus);
-		if (retval) {
-			err_msg("Failed to apply CPUs config\n");
-			goto out_err;
-		}
-	} else {
-		for (i = 0; i < sysconf(_SC_NPROCESSORS_CONF); i++)
-			CPU_SET(i, &params->monitored_cpus);
-	}
-
-	if (params->stop_us) {
-		retval = osnoise_set_stop_us(tool->context, params->stop_us);
-		if (retval) {
-			err_msg("Failed to set stop us\n");
-			goto out_err;
-		}
-	}
-
-	if (params->stop_total_us) {
-		retval = osnoise_set_stop_total_us(tool->context, params->stop_total_us);
-		if (retval) {
-			err_msg("Failed to set stop total us\n");
-			goto out_err;
-		}
-	}
-
-	if (params->timerlat_period_us) {
-		retval = osnoise_set_timerlat_period_us(tool->context, params->timerlat_period_us);
-		if (retval) {
-			err_msg("Failed to set timerlat period\n");
-			goto out_err;
-		}
-	}
-
-	if (params->print_stack) {
-		retval = osnoise_set_print_stack(tool->context, params->print_stack);
-		if (retval) {
-			err_msg("Failed to set print stack\n");
-			goto out_err;
-		}
-	}
-
-	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);
-	}
-
-	/*
-	 * If the user did not specify a type of thread, try user-threads first.
-	 * Fall back to kernel threads otherwise.
-	 */
-	if (!params->kernel_workload && !params->user_hist) {
-		retval = tracefs_file_exists(NULL, "osnoise/per_cpu/cpu0/timerlat_fd");
-		if (retval) {
-			debug_msg("User-space interface detected, setting user-threads\n");
-			params->user_workload = 1;
-			params->user_hist = 1;
-		} else {
-			debug_msg("User-space interface not detected, setting kernel-threads\n");
-			params->kernel_workload = 1;
-		}
-	}
-
-	/*
-	* Set workload according to type of thread if the kernel supports it.
-	* On kernels without support, user threads will have already failed
-	* on missing timerlat_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");
+	retval = timerlat_apply_config(tool, params);
+	if (retval)
 		goto out_err;
-	}
 
 	return 0;
 
···
  * timerlat_init_hist - initialize a timerlat hist tool with parameters
  */
 static struct osnoise_tool
-*timerlat_init_hist(struct timerlat_hist_params *params)
+*timerlat_init_hist(struct timerlat_params *params)
 {
 	struct osnoise_tool *tool;
 	int nr_cpus;
···
  * timerlat_hist_set_signals - handles the signal to stop the tool
  */
 static void
-timerlat_hist_set_signals(struct timerlat_hist_params *params)
+timerlat_hist_set_signals(struct timerlat_params *params)
 {
 	signal(SIGINT, stop_hist);
 	if (params->duration) {
···
 
 int timerlat_hist_main(int argc, char *argv[])
 {
-	struct timerlat_hist_params *params;
+	struct timerlat_params *params;
 	struct osnoise_tool *record = NULL;
 	struct timerlat_u_params params_u;
 	struct osnoise_tool *tool = NULL;
···
 	pthread_t timerlat_u;
 	int retval;
 	int nr_cpus, i;
+	bool no_bpf = false;
 
 	params = timerlat_hist_parse_args(argc, argv);
 	if (!params)
···
 	 * Otherwise, rtla could loop indefinitely when overloaded.
 	 */
 	hist_inst = trace;
+
+	if (getenv("RTLA_NO_BPF") && strncmp(getenv("RTLA_NO_BPF"), "1", 2) == 0) {
+		debug_msg("RTLA_NO_BPF set, disabling BPF\n");
+		no_bpf = true;
+	}
+
+	if (!no_bpf && !tep_find_event_by_name(trace->tep, "osnoise", "timerlat_sample")) {
+		debug_msg("osnoise:timerlat_sample missing, disabling BPF\n");
+		no_bpf = true;
+	}
+
+	if (!no_bpf) {
+		retval = timerlat_bpf_init(params);
+		if (retval) {
+			debug_msg("Could not enable BPF\n");
+			no_bpf = true;
+		}
+	}
 
 	retval = enable_timerlat(trace);
 	if (retval) {
···
 		trace_instance_start(&record->trace);
 	if (!params->no_aa)
 		trace_instance_start(&aa->trace);
-	trace_instance_start(trace);
+	if (no_bpf) {
+		trace_instance_start(trace);
+	} else {
+		retval = timerlat_bpf_attach();
+		if (retval) {
+			err_msg("Error attaching BPF program\n");
+			goto out_hist;
+		}
+	}
 
 	tool->start_time = time(NULL);
 	timerlat_hist_set_signals(params);
 
-	while (!stop_tracing) {
-		sleep(params->sleep_time);
+	if (no_bpf) {
+		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");
-			goto out_hist;
-		}
-
-		if (osnoise_trace_is_off(tool, record))
-			break;
-
-		/* is there still any user-threads ? */
-		if (params->user_workload) {
-			if (params_u.stopped_running) {
-				debug_msg("timerlat user-space threads stopped!\n");
-				break;
+			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");
+				goto out_hist;
 			}
+
+			if (osnoise_trace_is_off(tool, record))
+				break;
+
+			/* is there still any user-threads ? */
+			if (params->user_workload) {
+				if (params_u.stopped_running) {
+					debug_msg("timerlat user-space threads stopped!\n");
+					break;
+				}
+			}
+		}
+	} else
+		timerlat_bpf_wait(-1);
+
+	if (!no_bpf) {
+		timerlat_bpf_detach();
+		retval = timerlat_hist_bpf_pull_data(tool);
+		if (retval) {
+			err_msg("Error pulling BPF data\n");
+			goto out_hist;
 		}
 	}
 
···
 		if (!params->no_aa)
 			timerlat_auto_analysis(params->stop_us, params->stop_total_us);
 
-		if (params->trace_output) {
-			printf("  Saving trace to %s\n", params->trace_output);
-			save_trace_to_file(record->trace.inst, params->trace_output);
-		}
+		save_trace_to_file(record ? record->trace.inst : NULL,
+				   params->trace_output);
 	}
 
 out_hist:
···
 	osnoise_destroy_tool(tool);
 	free(params);
 	free_cpu_idle_disable_states();
+	if (!no_bpf)
+		timerlat_bpf_destroy();
 out_exit:
 	exit(return_value);
 }

tools/tracing/rtla/src/timerlat_top.c

···
 #include <sched.h>
 #include <pthread.h>
 
-#include "utils.h"
-#include "osnoise.h"
 #include "timerlat.h"
 #include "timerlat_aa.h"
 #include "timerlat_u.h"
-
-struct timerlat_top_params {
-	char			*cpus;
-	cpu_set_t		monitored_cpus;
-	char			*trace_output;
-	char			*cgroup_name;
-	unsigned long long	runtime;
-	long long		stop_us;
-	long long		stop_total_us;
-	long long		timerlat_period_us;
-	long long		print_stack;
-	int			sleep_time;
-	int			output_divisor;
-	int			duration;
-	int			quiet;
-	int			set_sched;
-	int			dma_latency;
-	int			no_aa;
-	int			aa_only;
-	int			dump_tasks;
-	int			cgroup;
-	int			hk_cpus;
-	int			user_top;
-	int			user_workload;
-	int			kernel_workload;
-	int			pretty_output;
-	int			warmup;
-	int			buffer_size;
-	int			deepest_idle_state;
-	cpu_set_t		hk_cpu_set;
-	struct sched_attr	sched_param;
-	struct trace_events	*events;
-};
+#include "timerlat_bpf.h"
 
 struct timerlat_top_cpu {
 	unsigned long long	irq_count;
···
 		    unsigned long long thread,
 		    unsigned long long latency)
 {
+	struct timerlat_params *params = tool->params;
 	struct timerlat_top_data *data = tool->data;
 	struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu];
+
+	if (params->output_divisor)
+		latency = latency / params->output_divisor;
 
 	if (!thread) {
 		cpu_data->irq_count++;
···
 		     struct tep_event *event, void *context)
 {
 	struct trace_instance *trace = context;
-	struct timerlat_top_params *params;
+	struct timerlat_params *params;
 	unsigned long long latency, thread;
 	struct osnoise_tool *top;
 	int cpu = record->cpu;
···
 }
 
 /*
+ * 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[data->nr_cpus],
+		  value_thread[data->nr_cpus],
+		  value_user[data->nr_cpus];
+
+	/* Pull summary */
+	err = timerlat_bpf_get_summary_value(SUMMARY_CURRENT,
+					     value_irq, value_thread, value_user,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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,
+					     data->nr_cpus);
+	if (err)
+		return err;
+	for (i = 0; i < data->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_top_params *params, struct osnoise_tool *top)
+static void timerlat_top_header(struct timerlat_params *params, struct osnoise_tool *top)
 {
 	struct trace_seq *s = top->trace.seq;
 	char duration[26];
···
 		trace_seq_printf(s, "\033[2;37;40m");
 
 	trace_seq_printf(s, "                                     Timer Latency                                              ");
-	if (params->user_top)
+	if (params->user_data)
 		trace_seq_printf(s, "                                         ");
 
 	if (params->pretty_output)
···
 			params->output_divisor == 1 ? "ns" : "us",
 			params->output_divisor == 1 ? "ns" : "us");
 
-	if (params->user_top) {
+	if (params->user_data) {
 		trace_seq_printf(s, "      |    Ret user Timer Latency (%s)",
 				params->output_divisor == 1 ? "ns" : "us");
 	}
···
 		trace_seq_printf(s, "\033[2;30;47m");
 
 	trace_seq_printf(s, "CPU COUNT      |      cur       min       avg       max |      cur       min       avg       max");
-	if (params->user_top)
+	if (params->user_data)
 		trace_seq_printf(s, " |      cur       min       avg       max");
 
 	if (params->pretty_output)
···
 static void timerlat_top_print(struct osnoise_tool *top, int cpu)
 {
 
-	struct timerlat_top_params *params = top->params;
+	struct timerlat_params *params = top->params;
 	struct timerlat_top_data *data = top->data;
 	struct timerlat_top_cpu *cpu_data = &data->cpu_data[cpu];
-	int divisor = params->output_divisor;
 	struct trace_seq *s = top->trace.seq;
-
-	if (divisor == 0)
-		return;
 
 	/*
 	 * Skip if no data is available: is this cpu offline?
···
 	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 / params->output_divisor);
-		trace_seq_printf(s, "%9llu ", cpu_data->min_irq / params->output_divisor);
-		trace_seq_printf(s, "%9llu ", (cpu_data->sum_irq / cpu_data->irq_count) / divisor);
-		trace_seq_printf(s, "%9llu |", cpu_data->max_irq / divisor);
+		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 / divisor);
-		trace_seq_printf(s, "%9llu ", cpu_data->min_thread / divisor);
+		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) / divisor);
-		trace_seq_printf(s, "%9llu", cpu_data->max_thread / divisor);
+				cpu_data->sum_thread / cpu_data->thread_count);
+		trace_seq_printf(s, "%9llu", cpu_data->max_thread);
 	}
 
-	if (!params->user_top) {
+	if (!params->user_data) {
 		trace_seq_printf(s, "\n");
 		return;
 	}
···
 	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 / divisor);
-		trace_seq_printf(s, "%9llu ", cpu_data->min_user / divisor);
+		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) / divisor);
-		trace_seq_printf(s, "%9llu\n", cpu_data->max_user / divisor);
+				cpu_data->sum_user / cpu_data->user_count);
+		trace_seq_printf(s, "%9llu\n", cpu_data->max_user);
 	}
 }
 
···
 timerlat_top_print_sum(struct osnoise_tool *top, struct timerlat_top_cpu *summary)
 {
 	const char *split = "----------------------------------------";
-	struct timerlat_top_params *params = top->params;
+	struct timerlat_params *params = top->params;
 	unsigned long long count = summary->irq_count;
-	int divisor = params->output_divisor;
 	struct trace_seq *s = top->trace.seq;
 	int e = 0;
-
-	if (divisor == 0)
-		return;
 
 	/*
 	 * Skip if no data is available: is this cpu offline?
···
 	}
 
 	trace_seq_printf(s, "%.*s|%.*s|%.*s", 15, split, 40, split, 39, split);
-	if (params->user_top)
+	if (params->user_data)
 		trace_seq_printf(s, "-|%.*s", 39, split);
 	trace_seq_printf(s, "\n");
 
···
 		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 / params->output_divisor);
-		trace_seq_printf(s, "%9llu ", (summary->sum_irq / summary->irq_count) / divisor);
-		trace_seq_printf(s, "%9llu |", summary->max_irq / divisor);
+		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 / divisor);
+		trace_seq_printf(s, "%9llu ", summary->min_thread);
 		trace_seq_printf(s, "%9llu ",
-				(summary->sum_thread / summary->thread_count) / divisor);
-		trace_seq_printf(s, "%9llu", summary->max_thread / divisor);
+				summary->sum_thread / summary->thread_count);
+		trace_seq_printf(s, "%9llu", summary->max_thread);
 	}
 
-	if (!params->user_top) {
+	if (!params->user_data) {
 		trace_seq_printf(s, "\n");
 		return;
 	}
···
 		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 / divisor);
+		trace_seq_printf(s, "%9llu ", summary->min_user);
 		trace_seq_printf(s, "%9llu ",
-				(summary->sum_user / summary->user_count) / divisor);
-		trace_seq_printf(s, "%9llu\n", summary->max_user / divisor);
+				summary->sum_user / summary->user_count);
+		trace_seq_printf(s, "%9llu\n", summary->max_user);
 	}
 }
 
···
  * timerlat_print_stats - print data for all cpus
  */
 static void
-timerlat_print_stats(struct timerlat_top_params *params, struct osnoise_tool *top)
+timerlat_print_stats(struct timerlat_params *params, struct osnoise_tool *top)
 {
 	struct trace_instance *trace = &top->trace;
 	struct timerlat_top_cpu summary;
···
 /*
  * timerlat_top_parse_args - allocs, parse and fill the cmd line parameters
  */
-static struct timerlat_top_params
+static struct timerlat_params
 *timerlat_top_parse_args(int argc, char **argv)
 {
-	struct timerlat_top_params *params;
+	struct timerlat_params *params;
 	struct trace_events *tevent;
 	long long auto_thresh;
 	int retval;
···
 			params->user_workload = true;
 			/* fallback: -u implies -U */
 		case 'U':
-			params->user_top = true;
+			params->user_data = true;
 			break;
 		case '0': /* trigger */
 			if (params->events) {
···
  * timerlat_top_apply_config - apply the top configs to the initialized tool
  */
 static int
-timerlat_top_apply_config(struct osnoise_tool *top, struct timerlat_top_params *params)
+timerlat_top_apply_config(struct osnoise_tool *top, struct timerlat_params *params)
 {
 	int retval;
-	int i;
 
-	if (!params->sleep_time)
-		params->sleep_time = 1;
-
-	if (params->cpus) {
-		retval = osnoise_set_cpus(top->context, params->cpus);
-		if (retval) {
-			err_msg("Failed to apply CPUs config\n");
-			goto out_err;
-		}
-	} else {
-		for (i = 0; i < sysconf(_SC_NPROCESSORS_CONF); i++)
-			CPU_SET(i, &params->monitored_cpus);
-	}
-
-	if (params->stop_us) {
-		retval = osnoise_set_stop_us(top->context, params->stop_us);
-		if (retval) {
-			err_msg("Failed to set stop us\n");
-			goto out_err;
-		}
-	}
-
-	if (params->stop_total_us) {
-		retval = osnoise_set_stop_total_us(top->context, params->stop_total_us);
-		if (retval) {
-			err_msg("Failed to set stop total us\n");
-			goto out_err;
-		}
-	}
-
-
-	if (params->timerlat_period_us) {
-		retval = osnoise_set_timerlat_period_us(top->context, params->timerlat_period_us);
-		if (retval) {
-			err_msg("Failed to set timerlat period\n");
-			goto out_err;
-		}
-	}
-
-
-	if (params->print_stack) {
-		retval = osnoise_set_print_stack(top->context, params->print_stack);
-		if (retval) {
-			err_msg("Failed to set print stack\n");
-			goto out_err;
-		}
-	}
-
-	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);
-	}
-
-	/*
-	 * If the user did not specify a type of thread, try user-threads first.
-	 * Fall back to kernel threads otherwise.
-	 */
-	if (!params->kernel_workload && !params->user_top) {
-		retval = tracefs_file_exists(NULL, "osnoise/per_cpu/cpu0/timerlat_fd");
-		if (retval) {
-			debug_msg("User-space interface detected, setting user-threads\n");
-			params->user_workload = 1;
-			params->user_top = 1;
-		} else {
-			debug_msg("User-space interface not detected, setting kernel-threads\n");
-			params->kernel_workload = 1;
-		}
-	}
-
-	/*
-	* Set workload according to type of thread if the kernel supports it.
-	* On kernels without support, user threads will have already failed
-	* on missing timerlat_fd, and kernel threads do not need it.
-	*/
-	retval = osnoise_set_workload(top->context, params->kernel_workload);
-	if (retval < -1) {
-		err_msg("Failed to set OSNOISE_WORKLOAD option\n");
+	retval = timerlat_apply_config(top, params);
+	if (retval)
 		goto out_err;
-	}
 
 	if (isatty(STDOUT_FILENO) && !params->quiet)
 		params->pretty_output = 1;
···
  * timerlat_init_top - initialize a timerlat top tool with parameters
  */
 static struct osnoise_tool
-*timerlat_init_top(struct timerlat_top_params *params)
+*timerlat_init_top(struct timerlat_params *params)
 {
 	struct osnoise_tool *top;
 	int nr_cpus;
···
  * timerlat_top_set_signals - handles the signal to stop the tool
  */
 static void
-timerlat_top_set_signals(struct timerlat_top_params *params)
+timerlat_top_set_signals(struct timerlat_params *params)
 {
 	signal(SIGINT, stop_top);
 	if (params->duration) {
···
 	}
 }
 
+/*
+ * timerlat_top_main_loop - main loop to process events
+ */
+static int
+timerlat_top_main_loop(struct osnoise_tool *top,
+		       struct osnoise_tool *record,
+		       struct timerlat_params *params,
+		       struct timerlat_u_params *params_u)
+{
+	struct trace_instance *trace = &top->trace;
+	int retval;
+
+	while (!stop_tracing) {
+		sleep(params->sleep_time);
+
+		if (params->aa_only && !osnoise_trace_is_off(top, 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)
+			timerlat_print_stats(params, top);
+
+		if (osnoise_trace_is_off(top, record))
+			break;
+
+		/* is there still any user-threads ? */
+		if (params->user_workload) {
+			if (params_u->stopped_running) {
+				debug_msg("timerlat user space threads stopped!\n");
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * timerlat_top_bpf_main_loop - main loop to process events (BPF variant)
+ */
+static int
+timerlat_top_bpf_main_loop(struct osnoise_tool *top,
+			   struct osnoise_tool *record,
+			   struct timerlat_params *params,
+			   struct timerlat_u_params *params_u)
+{
+	int retval, wait_retval;
+
+	if (params->aa_only) {
+		/* Auto-analysis only, just wait for stop tracing */
+		timerlat_bpf_wait(-1);
+		return 0;
+	}
+
+	if (params->quiet) {
+		/* Quiet mode: wait for stop and then, print results */
+		timerlat_bpf_wait(-1);
+
+		retval = timerlat_top_bpf_pull_data(top);
+		if (retval) {
+			err_msg("Error pulling BPF data\n");
+			return retval;
+		}
+
+		return 0;
+	}
+
+	/* Pull and display data in a loop */
+	while (!stop_tracing) {
+		wait_retval = timerlat_bpf_wait(params->sleep_time);
+
+		retval = timerlat_top_bpf_pull_data(top);
+		if (retval) {
+			err_msg("Error pulling BPF data\n");
+			return retval;
+		}
+
+		timerlat_print_stats(params, top);
+
+		if (wait_retval == 1)
+			/* Stopping requested by tracer */
+			break;
+
+		/* is there still any user-threads ? */
+		if (params->user_workload) {
+			if (params_u->stopped_running) {
+				debug_msg("timerlat user space threads stopped!\n");
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
 int timerlat_top_main(int argc, char *argv[])
 {
-	struct timerlat_top_params *params;
+	struct timerlat_params *params;
 	struct osnoise_tool *record = NULL;
 	struct timerlat_u_params params_u;
 	struct osnoise_tool *top = NULL;
···
 	char *max_lat;
 	int retval;
 	int nr_cpus, i;
+	bool no_bpf = false;
 
 	params = timerlat_top_parse_args(argc, argv);
 	if (!params)
···
 	*/
 	top_inst = trace;
 
+	if (getenv("RTLA_NO_BPF") && strncmp(getenv("RTLA_NO_BPF"), "1", 2) == 0) {
+		debug_msg("RTLA_NO_BPF set, disabling BPF\n");
+		no_bpf = true;
+	}
+
+	if (!no_bpf && !tep_find_event_by_name(trace->tep, "osnoise", "timerlat_sample")) {
+		debug_msg("osnoise:timerlat_sample missing, disabling BPF\n");
+		no_bpf = true;
+	}
+
+	if (!no_bpf) {
+		retval = timerlat_bpf_init(params);
+		if (retval) {
+			debug_msg("Could not enable BPF\n");
+			no_bpf = true;
+		}
+	}
 
 	retval = enable_timerlat(trace);
 	if (retval) {
···
 		}
 	}
 
-	if (params->cgroup && !params->user_top) {
+	if (params->cgroup && !params->user_data) {
 		retval = set_comm_cgroup("timerlat/", params->cgroup_name);
 		if (!retval) {
 			err_msg("Failed to move threads to cgroup\n");
···
 	}
 
 	if (!params->no_aa) {
-		if (params->aa_only) {
-			/* as top is not used for display, use it for aa */
-			aa = top;
-		} else  {
-			/* otherwise, a new instance is needed */
-			aa = osnoise_init_tool("timerlat_aa");
-			if (!aa)
-				goto out_top;
-		}
+		aa = osnoise_init_tool("timerlat_aa");
+		if (!aa)
+			goto out_top;
 
 		retval = timerlat_aa_init(aa, params->dump_tasks);
 		if (retval) {
···
 	 */
 	if (params->trace_output)
 		trace_instance_start(&record->trace);
-	if (!params->no_aa && aa != top)
+	if (!params->no_aa)
 		trace_instance_start(&aa->trace);
-	trace_instance_start(trace);
+	if (no_bpf) {
+		trace_instance_start(trace);
+	} else {
+		retval = timerlat_bpf_attach();
+		if (retval) {
+			err_msg("Error attaching BPF program\n");
+			goto out_top;
+		}
+	}
 
 	top->start_time = time(NULL);
 	timerlat_top_set_signals(params);
 
-	while (!stop_tracing) {
-		sleep(params->sleep_time);
+	if (no_bpf)
+		retval = timerlat_top_main_loop(top, record, params, &params_u);
+	else
+		retval = timerlat_top_bpf_main_loop(top, record, params, &params_u);
 
-		if (params->aa_only && !osnoise_trace_is_off(top, record))
-			continue;
+	if (retval)
+		goto out_top;
 
-		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");
-			goto out_top;
-		}
-
-		if (!params->quiet)
-			timerlat_print_stats(params, top);
-
-		if (osnoise_trace_is_off(top, record))
-			break;
-
-		/* is there still any user-threads ? */
-		if (params->user_workload) {
-			if (params_u.stopped_running) {
-				debug_msg("timerlat user space threads stopped!\n");
-				break;
-			}
-		}
-	}
+	if (!no_bpf)
+		timerlat_bpf_detach();
 
 	if (params->user_workload && !params_u.stopped_running) {
 		params_u.should_run = 0;
···
 		if (!params->no_aa)
 			timerlat_auto_analysis(params->stop_us, params->stop_total_us);
 
-		if (params->trace_output) {
-			printf("  Saving trace to %s\n", params->trace_output);
-			save_trace_to_file(record->trace.inst, params->trace_output);
-		}
+		save_trace_to_file(record ? record->trace.inst : NULL,
+				   params->trace_output);
 	} else if (params->aa_only) {
 		/*
 		 * If the trace did not stop with --aa-only, at least print the

tools/tracing/rtla/src/trace.c

···
 	int out_fd, in_fd;
 	int retval = -1;
 
+	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);

tools/tracing/rtla/tests/engine.sh

···
 	[ -n "$TEST_COUNT" ] && echo "1..$TEST_COUNT"
 }
 
+reset_osnoise() {
+	# Reset osnoise options to default and remove any dangling instances created
+	# by improperly exited rtla runs.
+	pushd /sys/kernel/tracing || return 1
+
+	# Remove dangling instances created by previous rtla run
+	echo 0 > tracing_thresh
+	cd instances
+	for i in osnoise_top osnoise_hist timerlat_top timerlat_hist
+	do
+		[ ! -d "$i" ] && continue
+		rmdir "$i"
+	done
+
+	# Reset options to default
+	# Note: those are copied from the default values of osnoise_data
+	# in kernel/trace/trace_osnoise.c
+	cd ../osnoise
+	echo all > cpus
+	echo DEFAULTS > options
+	echo 1000000 > period_us
+	echo 0 > print_stack
+	echo 1000000 > runtime_us
+	echo 0 > stop_tracing_total_us
+	echo 0 > stop_tracing_us
+	echo 1000 > timerlat_period_us
+
+	popd
+}
+
 check() {
 	# Simple check: run rtla with given arguments and test exit code.
 	# If TEST_COUNT is set, run the test. Otherwise, just count.
 	ctr=$(($ctr + 1))
 	if [ -n "$TEST_COUNT" ]
 	then
+		# Reset osnoise options before running test.
+		[ "$NO_RESET_OSNOISE" == 1 ] || reset_osnoise
 		# Run rtla; in case of failure, include its output as comment
 		# in the test results.
 		result=$(stdbuf -oL $TIMEOUT "$RTLA" $2 2>&1); exitcode=$?
···
 	fi
 }
 
+check_with_osnoise_options() {
+	# Do the same as "check", but with pre-set osnoise options.
+	# Note: rtla should reset the osnoise options, this is used to test
+	# if it indeed does so.
+	# Save original arguments
+	arg1=$1
+	arg2=$2
+
+	# Apply osnoise options (if not dry run)
+	if [ -n "$TEST_COUNT" ]
+	then
+		[ "$NO_RESET_OSNOISE" == 1 ] || reset_osnoise
+		shift
+		while shift
+		do
+			[ "$1" == "" ] && continue
+			option=$(echo $1 | cut -d '=' -f 1)
+			value=$(echo $1 | cut -d '=' -f 2)
+			echo "option: $option, value: $value"
+			echo "$value" > "/sys/kernel/tracing/osnoise/$option" || return 1
+		done
+	fi
+
+	NO_RESET_OSNOISE=1 check "$arg1" "$arg2"
+}
+
 set_timeout() {
 	TIMEOUT="timeout -v -k 15s $1"
 }
 
 unset_timeout() {
 	unset TIMEOUT
+}
+
+set_no_reset_osnoise() {
+	NO_RESET_OSNOISE=1
+}
+
+unset_no_reset_osnoise() {
+	unset NO_RESET_OSNOISE
 }
 
 test_end() {

tools/tracing/rtla/tests/osnoise.t

···
 check "verify the --entries/-E param" \
 	"osnoise hist -P F:1 -c 0 -r 900000 -d 1M -b 10 -E 25"
 
+# Test setting default period by putting an absurdly high period
+# and stopping on threshold.
+# If default period is not set, this will time out.
+check_with_osnoise_options "apply default period" \
+	"osnoise hist -s 1" period_us=600000000
+
 test_end

tools/tracing/rtla/tests/timerlat.t

···
 test_begin
 
 set_timeout 2m
+timerlat_sample_event='/sys/kernel/tracing/events/osnoise/timerlat_sample'
 
+if ldd $RTLA | grep libbpf >/dev/null && [ -d "$timerlat_sample_event" ]
+then
+	# rtla build with BPF and system supports BPF mode
+	no_bpf_options='0 1'
+else
+	no_bpf_options='1'
+fi
+
+# Do every test with and without BPF
+for option in $no_bpf_options
+do
+export RTLA_NO_BPF=$option
 check "verify help page" \
 	"timerlat --help"
 check "verify -s/--stack" \
···
 	"timerlat hist -c 0 -d 30s"
 check "hist test in nanoseconds" \
 	"timerlat hist -i 2 -c 0 -n -d 30s"
+done
 
 test_end

tools/verification/rv/Makefile.rv

···
 
 INCLUDE		:= -Iinclude/
 CFLAGS		:= -g -DVERSION=\"$(VERSION)\" $(FOPTS) $(WOPTS) $(EXTRA_CFLAGS) $(INCLUDE)
-LDFLAGS		:= -ggdb $(EXTRA_LDFLAGS)
+LDFLAGS		:= -ggdb $(LDFLAGS) $(EXTRA_LDFLAGS)
 
 INSTALL		:= install
 MKDIR		:= mkdir