[PATCH 0/4] Allow osnoise tracer to run without workload

[PATCH 0/4] Allow osnoise tracer to run without workload

[Daniel Bristot de Oliveira]

The osnoise tracer is not only a tracer and a set of tracepoints,
but also a workload dispatcher.

In preparation for having other workloads, e.g., in user-space,
add an option to avoid dispatching the workload.

By not dispatching the workload, the osnoise: tracepoints become
generic events to measure the execution time of *any* task on Linux.

Daniel Bristot de Oliveira (4):
  tracing/osnoise: Fix duration type
  tracing/osnoise: Add osnoise/options file
  tracing/osnoise: Add OSNOISE_WORKLOAD option
  Documentation/osnoise: Add osnoise/options documentation

 Documentation/trace/osnoise-tracer.rst |  12 ++
 kernel/trace/trace_osnoise.c           | 200 ++++++++++++++++++++++++-
 2 files changed, 205 insertions(+), 7 deletions(-)

-- 
2.32.0

[PATCH 1/4] tracing/osnoise: Fix duration type

[Daniel Bristot de Oliveira]

The duration type is a 64 long value, not an int. This was
causing some long noise to report wrong values.

Change the duration to a 64 bits value.

Fixes: bce29ac9ce0b ("trace: Add osnoise tracer")
Cc: Daniel Bristot de Oliveira <bristot@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 kernel/trace/trace_osnoise.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 78d536d3ff3d..4300c5dc4e5d 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -917,7 +917,7 @@ void osnoise_trace_irq_entry(int id)
 void osnoise_trace_irq_exit(int id, const char *desc)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
@@ -1048,7 +1048,7 @@ static void trace_softirq_entry_callback(void *data, unsigned int vec_nr)
 static void trace_softirq_exit_callback(void *data, unsigned int vec_nr)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
@@ -1144,7 +1144,7 @@ thread_entry(struct osnoise_variables *osn_var, struct task_struct *t)
 static void
 thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
 {
-	int duration;
+	s64 duration;
 
 	if (!osn_var->sampling)
 		return;
-- 
2.32.0

[PATCH 2/4] tracing/osnoise: Add osnoise/options file

[Daniel Bristot de Oliveira]

Add the tracing/osnoise/options file to control
osnoise/timerlat tracer features. It is a single
file to contain multiple features, similar to
the sched/features file.

Reading the file displays a list of options. Writing
the OPTION_NAME enables it, writing NO_OPTION_NAME disables
it.

The DEAFULTS is a particular option that resets the options
to the default ones.

It uses a bitmask to keep track of the status of the option. When
needed, we can add a list of static keys, but for now
it does not justify the memory increase.

Cc: Daniel Bristot de Oliveira <bristot@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 kernel/trace/trace_osnoise.c | 170 +++++++++++++++++++++++++++++++++++
 1 file changed, 170 insertions(+)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 4300c5dc4e5d..17b77fe3950b 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -48,6 +48,19 @@
 #define DEFAULT_TIMERLAT_PERIOD	1000			/* 1ms */
 #define DEFAULT_TIMERLAT_PRIO	95			/* FIFO 95 */
 
+/*
+ * osnoise/options entries.
+ */
+enum osnoise_options_index {
+	OSN_DEFAULTS = 0,
+	OSN_MAX
+};
+
+static const char * const osnoise_options_str[OSN_MAX] = { "DEFAULTS" };
+
+#define OSN_DEFAULT_OPTIONS	0
+unsigned long osnoise_options	= OSN_DEFAULT_OPTIONS;
+
 /*
  * trace_array of the enabled osnoise/timerlat instances.
  */
@@ -1860,6 +1873,150 @@ static void osnoise_init_hotplug_support(void)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
+/*
+ * seq file functions for the osnoise/options file.
+ */
+static void *s_options_start(struct seq_file *s, loff_t *pos)
+{
+	int option = *pos;
+
+	mutex_lock(&interface_lock);
+
+	if (option >= OSN_MAX)
+		return NULL;
+
+	return pos;
+}
+
+static void *s_options_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	int option = ++(*pos);
+
+	if (option >= OSN_MAX)
+		return NULL;
+
+	return pos;
+}
+
+static int s_options_show(struct seq_file *s, void *v)
+{
+	loff_t *pos = v;
+	int option = *pos;
+
+	if (option == OSN_DEFAULTS) {
+		if (osnoise_options == OSN_DEFAULT_OPTIONS)
+			seq_printf(s, "%s", osnoise_options_str[option]);
+		else
+			seq_printf(s, "NO_%s", osnoise_options_str[option]);
+		goto out;
+	}
+
+	if (test_bit(option, &osnoise_options))
+		seq_printf(s, "%s", osnoise_options_str[option]);
+	else
+		seq_printf(s, "NO_%s", osnoise_options_str[option]);
+
+out:
+	if (option != OSN_MAX)
+		seq_puts(s, " ");
+
+	return 0;
+}
+
+static void s_options_stop(struct seq_file *s, void *v)
+{
+	seq_puts(s, "\n");
+	mutex_unlock(&interface_lock);
+}
+
+static const struct seq_operations osnoise_options_seq_ops = {
+	.start		= s_options_start,
+	.next		= s_options_next,
+	.show		= s_options_show,
+	.stop		= s_options_stop
+};
+
+static int osnoise_options_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &osnoise_options_seq_ops);
+};
+
+/**
+ * osnoise_options_write - Write function for "options" entry
+ * @filp: The active open file structure
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in @file
+ *
+ * Writing the option name sets the option, writing the "NO_"
+ * prefix in front of the option name disables it.
+ *
+ * Writing "DEFAULTS" resets the option values to the default ones.
+ */
+static ssize_t osnoise_options_write(struct file *filp, const char __user *ubuf,
+				     size_t cnt, loff_t *ppos)
+{
+	int running, option, enable, retval;
+	char buf[256], *option_str;
+
+	if (cnt >= 256)
+		return -EINVAL;
+
+	if (copy_from_user(buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	if (strncmp(buf, "NO_", 3)) {
+		option_str = strstrip(buf);
+		enable = true;
+	} else {
+		option_str = strstrip(&buf[3]);
+		enable = false;
+	}
+
+	option = match_string(osnoise_options_str, OSN_MAX, option_str);
+	if (option < 0)
+		return -EINVAL;
+
+	/*
+	 * trace_types_lock is taken to avoid concurrency on start/stop.
+	 */
+	mutex_lock(&trace_types_lock);
+	running = osnoise_has_registered_instances();
+	if (running)
+		stop_per_cpu_kthreads();
+
+	mutex_lock(&interface_lock);
+	/*
+	 * avoid CPU hotplug operations that might read options.
+	 */
+	cpus_read_lock();
+
+	retval = cnt;
+
+	if (enable) {
+		if (option == OSN_DEFAULTS)
+			osnoise_options = OSN_DEFAULT_OPTIONS;
+		else
+			set_bit(option, &osnoise_options);
+	} else {
+		if (option == OSN_DEFAULTS)
+			retval = -EINVAL;
+		else
+			clear_bit(option, &osnoise_options);
+	}
+
+	cpus_read_unlock();
+	mutex_unlock(&interface_lock);
+
+	if (running)
+		start_per_cpu_kthreads();
+	mutex_unlock(&trace_types_lock);
+
+	return retval;
+}
+
 /*
  * osnoise_cpus_read - Read function for reading the "cpus" file
  * @filp: The active open file structure
@@ -2042,6 +2199,14 @@ static const struct file_operations cpus_fops = {
 	.llseek		= generic_file_llseek,
 };
 
+static const struct file_operations osnoise_options_fops = {
+	.open		= osnoise_options_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+	.write		= osnoise_options_write
+};
+
 #ifdef CONFIG_TIMERLAT_TRACER
 #ifdef CONFIG_STACKTRACE
 static int init_timerlat_stack_tracefs(struct dentry *top_dir)
@@ -2128,6 +2293,11 @@ static int init_tracefs(void)
 	if (!tmp)
 		goto err;
 
+	tmp = trace_create_file("options", TRACE_MODE_WRITE, top_dir, NULL,
+				&osnoise_options_fops);
+	if (!tmp)
+		goto err;
+
 	ret = init_timerlat_tracefs(top_dir);
 	if (ret)
 		goto err;
-- 
2.32.0

[PATCH 3/4] tracing/osnoise: Add OSNOISE_WORKLOAD option

[Daniel Bristot de Oliveira]

The osnoise tracer is not only a tracer, and a set of tracepoints,
but also a workload dispatcher.

In preparation for having other workloads, e.g., in user-space,
add an option to avoid dispatching the workload.

By not dispatching the workload, the osnoise: tracepoints become
generic events to measure the execution time of *any* task on Linux.

For example:

  # cd /sys/kernel/tracing/
  # cat osnoise/options
  DEFAULTS OSNOISE_WORKLOAD
  # echo NO_OSNOISE_WORKLOAD > osnoise/options
  # cat osnoise/options
  NO_DEFAULTS NO_OSNOISE_WORKLOAD
  # echo osnoise > set_event
  # echo osnoise > current_tracer
  # tail -8 trace
      make-94722   [002] d..3.  1371.794507: thread_noise:     make:94722 start 1371.794302286 duration 200897 ns
        sh-121042  [020] d..3.  1371.794534: thread_noise:       sh:121042 start 1371.781610976 duration 8943683 ns
      make-121097  [005] d..3.  1371.794542: thread_noise:     make:121097 start 1371.794481522 duration 60444 ns
     <...>-40      [005] d..3.  1371.794550: thread_noise: migration/5:40 start 1371.794542256 duration 7154 ns
    <idle>-0       [018] dNh2.  1371.794554: irq_noise: reschedule:253 start 1371.794553547 duration 40 ns
    <idle>-0       [018] dNh2.  1371.794561: irq_noise: local_timer:236 start 1371.794556222 duration 4890 ns
    <idle>-0       [018] .Ns2.  1371.794563: softirq_noise:    SCHED:7 start 1371.794561803 duration 992 ns
    <idle>-0       [018] d..3.  1371.794566: thread_noise: swapper/18:0 start 1371.781368110 duration 13191798 ns

In preparation for the rtla exec_time tracer/tool and
rtla osnoise --user option.

Cc: Daniel Bristot de Oliveira <bristot@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 kernel/trace/trace_osnoise.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index 17b77fe3950b..3f10dd1f2f1c 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -53,12 +53,13 @@
  */
 enum osnoise_options_index {
 	OSN_DEFAULTS = 0,
+	OSN_WORKLOAD,
 	OSN_MAX
 };
 
-static const char * const osnoise_options_str[OSN_MAX] = { "DEFAULTS" };
+static const char * const osnoise_options_str[OSN_MAX] = { "DEFAULTS", "OSNOISE_WORKLOAD" };
 
-#define OSN_DEFAULT_OPTIONS	0
+#define OSN_DEFAULT_OPTIONS	0x2
 unsigned long osnoise_options	= OSN_DEFAULT_OPTIONS;
 
 /*
@@ -1186,11 +1187,12 @@ trace_sched_switch_callback(void *data, bool preempt,
 			    unsigned int prev_state)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
+	int workload = test_bit(OSN_WORKLOAD, &osnoise_options);
 
-	if (p->pid != osn_var->pid)
+	if ((p->pid != osn_var->pid) || !workload)
 		thread_exit(osn_var, p);
 
-	if (n->pid != osn_var->pid)
+	if ((n->pid != osn_var->pid) || !workload)
 		thread_entry(osn_var, n);
 }
 
@@ -1723,9 +1725,16 @@ static void stop_kthread(unsigned int cpu)
 	struct task_struct *kthread;
 
 	kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
-	if (kthread)
+	if (kthread) {
 		kthread_stop(kthread);
-	per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
+		per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
+	} else {
+		if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
+			per_cpu(per_cpu_osnoise_var, cpu).sampling = false;
+			barrier();
+			return;
+		}
+	}
 }
 
 /*
@@ -1759,6 +1768,13 @@ static int start_kthread(unsigned int cpu)
 		snprintf(comm, 24, "timerlat/%d", cpu);
 		main = timerlat_main;
 	} else {
+		/* if no workload, just return */
+		if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
+			per_cpu(per_cpu_osnoise_var, cpu).sampling = true;
+			barrier();
+			return 0;
+		}
+
 		snprintf(comm, 24, "osnoise/%d", cpu);
 	}
 
-- 
2.32.0

[PATCH 4/4] Documentation/osnoise: Add osnoise/options documentation

[Daniel Bristot de Oliveira]

Add the documentation about the osnoise/options file, along
with an explanation about the OSNOISE_WORKLOAD option.

Cc: Daniel Bristot de Oliveira <bristot@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
---
 Documentation/trace/osnoise-tracer.rst | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/Documentation/trace/osnoise-tracer.rst b/Documentation/trace/osnoise-tracer.rst
index 963def9f97c6..e1eed255a4ac 100644
--- a/Documentation/trace/osnoise-tracer.rst
+++ b/Documentation/trace/osnoise-tracer.rst
@@ -109,6 +109,11 @@ The tracer has a set of options inside the osnoise directory, they are:
  - tracing_threshold: the minimum delta between two time() reads to be
    considered as noise, in us. When set to 0, the default value will
    be used, which is currently 5 us.
+ - osnoise/options: a set of on/off options that can be enabled by
+   writing the option name to the file or disabled by writing the option
+   name preceded with the 'NO_' prefix. For example, writing
+   NO_OSNOISE_WORKLOAD disables the OSNOISE_WORKLOAD option. The
+   special DEAFAULTS option resets all options to the default value.
 
 Additional Tracing
 ------------------
@@ -150,3 +155,10 @@ tracepoints is smaller than eight us reported in the sample_threshold.
 The reason roots in the overhead of the entry and exit code that happens
 before and after any interference execution. This justifies the dual
 approach: measuring thread and tracing.
+
+Running osnoise tracer without workload
+---------------------------------------
+
+By enabling the osnoise tracer with the NO_OSNOISE_WORKLOAD option set,
+the osnoise: tracepoints serve to measure the execution time of
+any type of Linux task, free from the interference of other tasks.
-- 
2.32.0

Re: [PATCH 1/4] tracing/osnoise: Fix duration type

[Masami Hiramatsu]

On Thu, 17 Nov 2022 14:46:17 +0100
Daniel Bristot de Oliveira <bristot@kernel.org> wrote:

> The duration type is a 64 long value, not an int. This was
> causing some long noise to report wrong values.
> 
> Change the duration to a 64 bits value.

This looks good to me.

Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>

Thank you!

> 
> Fixes: bce29ac9ce0b ("trace: Add osnoise tracer")
> Cc: Daniel Bristot de Oliveira <bristot@kernel.org>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> Cc: Masami Hiramatsu <mhiramat@kernel.org>
> Cc: Jonathan Corbet <corbet@lwn.net>
> Signed-off-by: Daniel Bristot de Oliveira <bristot@kernel.org>
> ---
>  kernel/trace/trace_osnoise.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
> index 78d536d3ff3d..4300c5dc4e5d 100644
> --- a/kernel/trace/trace_osnoise.c
> +++ b/kernel/trace/trace_osnoise.c
> @@ -917,7 +917,7 @@ void osnoise_trace_irq_entry(int id)
>  void osnoise_trace_irq_exit(int id, const char *desc)
>  {
>  	struct osnoise_variables *osn_var = this_cpu_osn_var();
> -	int duration;
> +	s64 duration;
>  
>  	if (!osn_var->sampling)
>  		return;
> @@ -1048,7 +1048,7 @@ static void trace_softirq_entry_callback(void *data, unsigned int vec_nr)
>  static void trace_softirq_exit_callback(void *data, unsigned int vec_nr)
>  {
>  	struct osnoise_variables *osn_var = this_cpu_osn_var();
> -	int duration;
> +	s64 duration;
>  
>  	if (!osn_var->sampling)
>  		return;
> @@ -1144,7 +1144,7 @@ thread_entry(struct osnoise_variables *osn_var, struct task_struct *t)
>  static void
>  thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
>  {
> -	int duration;
> +	s64 duration;
>  
>  	if (!osn_var->sampling)
>  		return;
> -- 
> 2.32.0
> 


-- 
Masami Hiramatsu (Google) <mhiramat@kernel.org>

Re: [PATCH 1/4] tracing/osnoise: Fix duration type

[Daniel Bristot de Oliveira]

On 11/21/22 23:18, Masami Hiramatsu (Google) wrote:
> On Thu, 17 Nov 2022 14:46:17 +0100
> Daniel Bristot de Oliveira <bristot@kernel.org> wrote:
> 
>> The duration type is a 64 long value, not an int. This was
>> causing some long noise to report wrong values.
>>
>> Change the duration to a 64 bits value.
> This looks good to me.
> 
> Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>

Thanks, Masami!

Btw, this patch can be applied independently of the other as a fix. It
is only here because I noticed the problem while adding the features in
the next patches.

-- Daniel