trace: Add timerlat tracer

The timerlat tracer aims to help the preemptive kernel developers to
found souces of wakeup latencies of real-time threads. Like cyclictest,
the tracer sets a periodic timer that wakes up a thread. The thread then
computes a *wakeup latency* value as the difference between the *current
time* and the *absolute time* that the timer was set to expire. The main
goal of timerlat is tracing in such a way to help kernel developers.

Usage

Write the ASCII text "timerlat" into the current_tracer file of the
tracing system (generally mounted at /sys/kernel/tracing).

For example:

        [root@f32 ~]# cd /sys/kernel/tracing/
        [root@f32 tracing]# echo timerlat > current_tracer

It is possible to follow the trace by reading the trace trace file:

  [root@f32 tracing]# cat trace
  # tracer: timerlat
  #
  #                              _-----=> irqs-off
  #                             / _----=> need-resched
  #                            | / _---=> hardirq/softirq
  #                            || / _--=> preempt-depth
  #                            || /
  #                            ||||             ACTIVATION
  #         TASK-PID      CPU# ||||   TIMESTAMP    ID            CONTEXT                LATENCY
  #            | |         |   ||||      |         |                  |                       |
          <idle>-0       [000] d.h1    54.029328: #1     context    irq timer_latency       932 ns
           <...>-867     [000] ....    54.029339: #1     context thread timer_latency     11700 ns
          <idle>-0       [001] dNh1    54.029346: #1     context    irq timer_latency      2833 ns
           <...>-868     [001] ....    54.029353: #1     context thread timer_latency      9820 ns
          <idle>-0       [000] d.h1    54.030328: #2     context    irq timer_latency       769 ns
           <...>-867     [000] ....    54.030330: #2     context thread timer_latency      3070 ns
          <idle>-0       [001] d.h1    54.030344: #2     context    irq timer_latency       935 ns
           <...>-868     [001] ....    54.030347: #2     context thread timer_latency      4351 ns

The tracer creates a per-cpu kernel thread with real-time priority that
prints two lines at every activation. The first is the *timer latency*
observed at the *hardirq* context before the activation of the thread.
The second is the *timer latency* observed by the thread, which is the
same level that cyclictest reports. The ACTIVATION ID field
serves to relate the *irq* execution to its respective *thread* execution.

The irq/thread splitting is important to clarify at which context
the unexpected high value is coming from. The *irq* context can be
delayed by hardware related actions, such as SMIs, NMIs, IRQs
or by a thread masking interrupts. Once the timer happens, the delay
can also be influenced by blocking caused by threads. For example, by
postponing the scheduler execution via preempt_disable(),  by the
scheduler execution, or by masking interrupts. Threads can
also be delayed by the interference from other threads and IRQs.

The timerlat can also take advantage of the osnoise: traceevents.
For example:

        [root@f32 ~]# cd /sys/kernel/tracing/
        [root@f32 tracing]# echo timerlat > current_tracer
        [root@f32 tracing]# echo osnoise > set_event
        [root@f32 tracing]# echo 25 > osnoise/stop_tracing_total_us
        [root@f32 tracing]# tail -10 trace
             cc1-87882   [005] d..h...   548.771078: #402268 context    irq timer_latency      1585 ns
             cc1-87882   [005] dNLh1..   548.771082: irq_noise: local_timer:236 start 548.771077442 duration 4597 ns
             cc1-87882   [005] dNLh2..   548.771083: irq_noise: reschedule:253 start 548.771083017 duration 56 ns
             cc1-87882   [005] dNLh2..   548.771086: irq_noise: call_function_single:251 start 548.771083811 duration 2048 ns
             cc1-87882   [005] dNLh2..   548.771088: irq_noise: call_function_single:251 start 548.771086814 duration 1495 ns
             cc1-87882   [005] dNLh2..   548.771091: irq_noise: call_function_single:251 start 548.771089194 duration 1558 ns
             cc1-87882   [005] dNLh2..   548.771094: irq_noise: call_function_single:251 start 548.771091719 duration 1932 ns
             cc1-87882   [005] dNLh2..   548.771096: irq_noise: call_function_single:251 start 548.771094696 duration 1050 ns
             cc1-87882   [005] d...3..   548.771101: thread_noise:      cc1:87882 start 548.771078243 duration 10909 ns
      timerlat/5-1035    [005] .......   548.771103: #402268 context thread timer_latency     25960 ns

For further information see: Documentation/trace/timerlat-tracer.rst

Link: https://lkml.kernel.org/r/71f18efc013e1194bcaea1e54db957de2b19ba62.1624372313.git.bristot@redhat.com

Cc: Phil Auld <pauld@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Kate Carcia <kcarcia@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexandre Chartre <alexandre.chartre@oracle.com>
Cc: Clark Willaims <williams@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

1 files changed, 47 insertions, 0 deletions

diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 642b6584eba5..a0bf446bb034 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1301,6 +1301,52 @@ static struct trace_event trace_osnoise_event = {
 	.funcs		= &trace_osnoise_funcs,
 };
 
+/* TRACE_TIMERLAT */
+static enum print_line_t
+trace_timerlat_print(struct trace_iterator *iter, int flags,
+		     struct trace_event *event)
+{
+	struct trace_entry *entry = iter->ent;
+	struct trace_seq *s = &iter->seq;
+	struct timerlat_entry *field;
+
+	trace_assign_type(field, entry);
+
+	trace_seq_printf(s, "#%-5u context %6s timer_latency %9llu ns\n",
+			 field->seqnum,
+			 field->context ? "thread" : "irq",
+			 field->timer_latency);
+
+	return trace_handle_return(s);
+}
+
+static enum print_line_t
+trace_timerlat_raw(struct trace_iterator *iter, int flags,
+		   struct trace_event *event)
+{
+	struct timerlat_entry *field;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(field, iter->ent);
+
+	trace_seq_printf(s, "%u %d %llu\n",
+			 field->seqnum,
+			 field->context,
+			 field->timer_latency);
+
+	return trace_handle_return(s);
+}
+
+static struct trace_event_functions trace_timerlat_funcs = {
+	.trace		= trace_timerlat_print,
+	.raw		= trace_timerlat_raw,
+};
+
+static struct trace_event trace_timerlat_event = {
+	.type		= TRACE_TIMERLAT,
+	.funcs		= &trace_timerlat_funcs,
+};
+
 /* TRACE_BPUTS */
 static enum print_line_t
 trace_bputs_print(struct trace_iterator *iter, int flags,
@@ -1512,6 +1558,7 @@ static struct trace_event *events[] __initdata = {
 	&trace_print_event,
 	&trace_hwlat_event,
 	&trace_osnoise_event,
+	&trace_timerlat_event,
 	&trace_raw_data_event,
 	&trace_func_repeats_event,
 	NULL