Merge: rtla: Add timerlat BPF sample collection, Set all tracer options by default [rhel-9]

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6686

# Merge Request Required Information

JIRA: https://issues.redhat.com/browse/RHEL-77358
JIRA: https://issues.redhat.com/browse/RHEL-86051

## Summary of Changes

Two upstream patchsets are contained in this merge request:

* Collect timerlat samples using a BPF program instead of pulling them through a tracefs pipe. This helps with both performance and CPU usage, and fixes an issue where on systems with \>100 CPUs, rtla cannot keep up with timerlat samples and drops most of them, making it useless.
* Always set default values of all tracer options (osnoise or timerlat) if not specified otherwise, as they might be set to unexpected values either by another user of the tracers or by a previous abnormally exited run of rtla.

Those are combined into a single MR, because the latter depends on a refactoring done in the former. A dependency (rtla test suite) is also pulled.

## Approved Development Ticket(s)
All submissions to CentOS Stream must reference a ticket in [Red Hat Jira](https://issues.redhat.com/).

<details><summary>Click for formatting instructions</summary>
Please follow the CentOS Stream [contribution documentation](https://docs.centos.org/en-US/stream-contrib/quickstart/) for how to file this ticket and have it approved.

Signed-off-by: Tomas Glozar <tglozar@redhat.com>

List tickets each on their own line of this description using the format "Resolves: RHEL-76229", "Related: RHEL-76229" or "Reverts: RHEL-76229", as appropriate.
</details>

Approved-by: Wander Lairson Costa <wander@redhat.com>
Approved-by: John Kacur <jkacur@redhat.com>
Approved-by: Gabriele Monaco <gmonaco@redhat.com>
Approved-by: Derek Barbosa <debarbos@redhat.com>
Approved-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

include/trace/events/osnoise.h

@@ -3,9 +3,105 @@
 #define TRACE_SYSTEM osnoise
 
 #if !defined(_OSNOISE_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#ifndef _OSNOISE_TRACE_H
 #define _OSNOISE_TRACE_H
+/*
+ * osnoise sample structure definition. Used to store the statistics of a
+ * sample run.
+ */
+struct osnoise_sample {
+	u64			runtime;	/* runtime */
+	u64			noise;		/* noise */
+	u64			max_sample;	/* max single noise sample */
+	int			hw_count;	/* # HW (incl. hypervisor) interference */
+	int			nmi_count;	/* # NMIs during this sample */
+	int			irq_count;	/* # IRQs during this sample */
+	int			softirq_count;	/* # softirqs during this sample */
+	int			thread_count;	/* # threads during this sample */
+};
+
+#ifdef CONFIG_TIMERLAT_TRACER
+/*
+ * timerlat sample structure definition. Used to store the statistics of
+ * a sample run.
+ */
+struct timerlat_sample {
+	u64			timer_latency;	/* timer_latency */
+	unsigned int		seqnum;		/* unique sequence */
+	int			context;	/* timer context */
+};
+#endif // CONFIG_TIMERLAT_TRACER
+#endif // _OSNOISE_TRACE_H
 
 #include <linux/tracepoint.h>
+TRACE_EVENT(osnoise_sample,
+
+	TP_PROTO(struct osnoise_sample *s),
+
+	TP_ARGS(s),
+
+	TP_STRUCT__entry(
+		__field(	u64,		runtime	)
+		__field(	u64,		noise	)
+		__field(	u64,		max_sample	)
+		__field(	int,		hw_count	)
+		__field(	int,		irq_count	)
+		__field(	int,		nmi_count	)
+		__field(	int, 		softirq_count	)
+		__field(	int,		thread_count	)
+	),
+
+	TP_fast_assign(
+		__entry->runtime = s->runtime;
+		__entry->noise = s->noise;
+		__entry->max_sample = s->max_sample;
+		__entry->hw_count = s->hw_count;
+		__entry->irq_count = s->irq_count;
+		__entry->nmi_count = s->nmi_count;
+		__entry->softirq_count = s->softirq_count;
+		__entry->thread_count = s->thread_count;
+	),
+
+	TP_printk("runtime=%llu noise=%llu max_sample=%llu hw_count=%d"
+		  " irq_count=%d nmi_count=%d softirq_count=%d"
+		  " thread_count=%d",
+		  __entry->runtime,
+		  __entry->noise,
+		  __entry->max_sample,
+		  __entry->hw_count,
+		  __entry->irq_count,
+		  __entry->nmi_count,
+		  __entry->softirq_count,
+		  __entry->thread_count)
+);
+
+#ifdef CONFIG_TIMERLAT_TRACER
+TRACE_EVENT(timerlat_sample,
+
+	TP_PROTO(struct timerlat_sample *s),
+
+	TP_ARGS(s),
+
+	TP_STRUCT__entry(
+		__field(	u64,		timer_latency	)
+		__field(	unsigned int,	seqnum		)
+		__field(	int,		context		)
+	),
+
+	TP_fast_assign(
+		__entry->timer_latency = s->timer_latency;
+		__entry->seqnum = s->seqnum;
+		__entry->context = s->context;
+	),
+
+	TP_printk("timer_latency=%llu seqnum=%u context=%d",
+		  __entry->timer_latency,
+		  __entry->seqnum,
+		  __entry->context)
+);
+#endif // CONFIG_TIMERLAT_TRACER
+
 TRACE_EVENT(thread_noise,
 
 	TP_PROTO(struct task_struct *t, u64 start, u64 duration),

kernel/trace/trace_osnoise.c

@@ -315,33 +315,6 @@ static inline void osn_var_reset_all(void)
  */
 bool trace_osnoise_callback_enabled;
 
-/*
- * osnoise sample structure definition. Used to store the statistics of a
- * sample run.
- */
-struct osnoise_sample {
-	u64			runtime;	/* runtime */
-	u64			noise;		/* noise */
-	u64			max_sample;	/* max single noise sample */
-	int			hw_count;	/* # HW (incl. hypervisor) interference */
-	int			nmi_count;	/* # NMIs during this sample */
-	int			irq_count;	/* # IRQs during this sample */
-	int			softirq_count;	/* # softirqs during this sample */
-	int			thread_count;	/* # threads during this sample */
-};
-
-#ifdef CONFIG_TIMERLAT_TRACER
-/*
- * timerlat sample structure definition. Used to store the statistics of
- * a sample run.
- */
-struct timerlat_sample {
-	u64			timer_latency;	/* timer_latency */
-	unsigned int		seqnum;		/* unique sequence */
-	int			context;	/* timer context */
-};
-#endif
-
 /*
  * Tracer data.
  */
@@ -497,7 +470,7 @@ static void print_osnoise_headers(struct seq_file *s)
  * Record an osnoise_sample into the tracer buffer.
  */
 static void
-__trace_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffer)
+__record_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffer)
 {
 	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
@@ -522,17 +495,19 @@ __trace_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffe
 }
 
 /*
- * Record an osnoise_sample on all osnoise instances.
+ * Record an osnoise_sample on all osnoise instances and fire trace event.
  */
-static void trace_osnoise_sample(struct osnoise_sample *sample)
+static void record_osnoise_sample(struct osnoise_sample *sample)
 {
 	struct osnoise_instance *inst;
 	struct trace_buffer *buffer;
 
+	trace_osnoise_sample(sample);
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
 		buffer = inst->tr->array_buffer.buffer;
-		__trace_osnoise_sample(sample, buffer);
+		__record_osnoise_sample(sample, buffer);
 	}
 	rcu_read_unlock();
 }
@@ -576,7 +551,7 @@ static void print_timerlat_headers(struct seq_file *s)
 #endif /* CONFIG_PREEMPT_RT */
 
 static void
-__trace_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buffer)
+__record_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buffer)
 {
 	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
@@ -598,15 +573,17 @@ __trace_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buf
 /*
  * Record an timerlat_sample into the tracer buffer.
  */
-static void trace_timerlat_sample(struct timerlat_sample *sample)
+static void record_timerlat_sample(struct timerlat_sample *sample)
 {
 	struct osnoise_instance *inst;
 	struct trace_buffer *buffer;
 
+	trace_timerlat_sample(sample);
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(inst, &osnoise_instances, list) {
 		buffer = inst->tr->array_buffer.buffer;
-		__trace_timerlat_sample(sample, buffer);
+		__record_timerlat_sample(sample, buffer);
 	}
 	rcu_read_unlock();
 }
@@ -1603,7 +1580,7 @@ static int run_osnoise(void)
 	/* Save interference stats info */
 	diff_osn_sample_stats(osn_var, &s);
 
-	trace_osnoise_sample(&s);
+	record_osnoise_sample(&s);
 
 	notify_new_max_latency(max_noise);
 
@@ -1798,7 +1775,7 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer)
 	s.timer_latency = diff;
 	s.context = IRQ_CONTEXT;
 
-	trace_timerlat_sample(&s);
+	record_timerlat_sample(&s);
 
 	if (osnoise_data.stop_tracing) {
 		if (time_to_us(diff) >= osnoise_data.stop_tracing) {
@@ -1918,7 +1895,7 @@ static int timerlat_main(void *data)
 		s.timer_latency = diff;
 		s.context = THREAD_CONTEXT;
 
-		trace_timerlat_sample(&s);
+		record_timerlat_sample(&s);
 
 		notify_new_max_latency(diff);
 
@@ -2538,7 +2515,7 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
 		s.timer_latency = diff;
 		s.context = THREAD_URET;
 
-		trace_timerlat_sample(&s);
+		record_timerlat_sample(&s);
 
 		notify_new_max_latency(diff);
 
@@ -2573,7 +2550,7 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
 	s.timer_latency = diff;
 	s.context = THREAD_CONTEXT;
 
-	trace_timerlat_sample(&s);
+	record_timerlat_sample(&s);
 
 	if (osnoise_data.stop_tracing_total) {
 		if (time_to_us(diff) >= osnoise_data.stop_tracing_total) {

redhat/kernel.spec.template

@@ -682,6 +682,9 @@ BuildRequires: libcap-devel libcap-ng-devel
 BuildRequires: python3-docutils
 BuildRequires: libtraceevent-devel
 BuildRequires: libtracefs-devel
+BuildRequires: libbpf-devel
+BuildRequires: bpftool
+BuildRequires: clang
 
 %ifnarch s390x
 BuildRequires: pciutils-devel
@@ -1161,6 +1164,7 @@ This package provides debug information for package kernel-tools.
 Summary: Real-Time Linux Analysis tools
 Requires: libtraceevent
 Requires: libtracefs
+Requires: libbpf
 %ifarch %{cpupowerarchs}
 Requires: kernel-tools-libs = %{version}-%{release}
 %endif

tools/build/Makefile.feature

@@ -110,7 +110,8 @@ FEATURE_TESTS_EXTRA :=                  \
          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

@@ -422,6 +422,9 @@ $(OUTPUT)test-file-handle.bin:
 $(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

@@ -85,6 +85,9 @@ LLVM_CONFIG	?= llvm-config
 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

@@ -4,3 +4,4 @@ rtla-static
 fixdep
 feature
 FEATURE-DUMP
+*.skel.h

tools/tracing/rtla/Makefile

@@ -33,9 +33,15 @@ DOCSRC		:= ../../../Documentation/tools/rtla/
 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
 
 ifeq ($(V),1)
   Q		=
@@ -67,6 +73,17 @@ CFLAGS		+= $(INCLUDES) $(LIB_INCLUDES)
 
 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)
 
@@ -77,12 +94,15 @@ static: $(RTLA_IN)
 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
 	$(call QUIET_CLEAN, rtla)
 	$(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
-.PHONY: FORCE clean
+	$(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

@@ -53,6 +53,48 @@ else
   $(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