[PATCH v2] perf trace: Introduce --show-cpu option to display cpu id

[Aaron Tomlin <atomlin@atomlin.com>]

When tracing system-wide workloads or specific events, it is highly
valuable to know exactly which CPU executed a specific event. Currently,
perf trace output defaults to omitting CPU information.

Introduce a new "--show-cpu" command-line option. When provided, this
flag extracts the CPU from the perf sample and prints it in a "[000]"
format immediately following the timestamp. This mirrors the behaviour of
other tracing tools like ftrace and perf script. For example:

  # perf trace -e sched:sched_switch --max-events 5 --show-cpu
       0.000 [002] :0/0 sched:sched_switch(prev_comm: "swapper/2", prev_prio: 120, next_comm: "rcu_preempt", next_pid: 16 (rcu_preempt), next_prio: 120)
       0.009 [002] rcu_preempt/16 sched:sched_switch(prev_comm: "rcu_preempt", prev_pid: 16 (rcu_preempt), prev_prio: 120, prev_state: 128, next_comm: "swapper/2", next_prio: 120)
       0.033 [002] :0/0 sched:sched_switch(prev_comm: "swapper/2", prev_prio: 120, next_comm: "kworker/u32:48", next_pid: 35840 (kworker/u32:48-), next_prio: 120)
       0.041 [002] kworker/u32:48/35840 sched:sched_switch(prev_comm: "kworker/u32:48", prev_pid: 35840 (kworker/u32:48-), prev_prio: 120, prev_state: 128, next_comm: "swapper/2", next_prio: 120)
       0.045 [002] :0/0 sched:sched_switch(prev_comm: "swapper/2", prev_prio: 120, next_comm: "kworker/u32:48", next_pid: 35840 (kworker/u32:48-), next_prio: 120)

The feature is implemented strictly as an opt-in toggle to prevent
cluttering the standard output and to preserve backwards compatibility
for scripts parsing the default output format.

Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
Changes since v1 [1]:
 - Fixed a silent failure where core trace events (e.g., system calls and
   page faults) ignored the --show-cpu flag. All primary workload events
   correctly display the CPU ID when required

 - Updated all core event handlers (i.e., trace__sys_enter,
   trace__sys_exit, trace__pgfault and trace__printf_interrupted_entry)
   to extract sample->cpu and pass it down into the entry head
   formatter

 - Abstracted the CPU formatting logic into a dedicated, documented helper
   function trace__fprintf_cpu()

 - Added a safety guard to verify the CPU data is actually present
   (cpu != (u32)-1) before attempting to print it, preventing dummy
   values from polluting the output when sample data is missing

[1]: https://lore.kernel.org/linux-perf-users/20260421203934.64032-1-atomlin@atomlin.com/
---
 tools/perf/Documentation/perf-trace.txt |  3 ++
 tools/perf/builtin-trace.c              | 49 ++++++++++++++++++++++---
 2 files changed, 47 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 892c82a9bf40..d0b6c771a1b9 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -199,6 +199,9 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --show-on-off-events::
 	Show the --switch-on/off events too.
 
+--show-cpu::
+	Show cpu id.
+
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e58c49d047a2..6314332ad711 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -217,6 +217,7 @@ struct trace {
 	bool			kernel_syscallchains;
 	s16			args_alignment;
 	bool			show_tstamp;
+	bool			show_cpu;
 	bool			show_duration;
 	bool			show_zeros;
 	bool			show_arg_names;
@@ -1893,6 +1894,27 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
 	return fprintf(fp, "         ? ");
 }
 
+/**
+ * trace__fprintf_cpu - Print the CPU ID to a given file stream
+ * @cpu: The CPU ID to print
+ * @fp: The file stream to write to
+ *
+ * Formats and prints the specified CPU ID enclosed in brackets
+ * (e.g., "[003] ") to the provided file pointer. It is used to
+ * align and display the CPU ID consistently within the trace output.
+ *
+ * Return: The number of characters printed.
+ */
+static size_t trace__fprintf_cpu(u32 cpu, FILE *fp)
+{
+	size_t printed = 0;
+
+	if (cpu >= 0)
+		printed += fprintf(fp, "[%03d] ", cpu);
+
+	return printed;
+}
+
 static pid_t workload_pid = -1;
 static volatile sig_atomic_t done = false;
 static volatile sig_atomic_t interrupted = false;
@@ -1923,12 +1945,15 @@ static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread
 }
 
 static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
-					u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
+					u64 duration, bool duration_calculated,
+					u64 tstamp, u32 cpu, FILE *fp)
 {
 	size_t printed = 0;
 
 	if (trace->show_tstamp)
 		printed = trace__fprintf_tstamp(trace, tstamp, fp);
+	if (trace->show_cpu && cpu != (u32)-1)
+		printed += trace__fprintf_cpu(cpu, fp);
 	if (trace->show_duration)
 		printed += fprintf_duration(duration, duration_calculated, fp);
 	return printed + trace__fprintf_comm_tid(trace, thread, fp);
@@ -2707,7 +2732,9 @@ static int trace__printf_interrupted_entry(struct trace *trace)
 	if (!ttrace->entry_pending)
 		return 0;
 
-	printed  = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
+	printed = trace__fprintf_entry_head(trace, trace->current, 0, false,
+					    ttrace->entry_time, 0,
+					    trace->output);
 	printed += len = fprintf(trace->output, "%s)", ttrace->entry_str);
 
 	if (len < trace->args_alignment - 4)
@@ -2835,7 +2862,9 @@ static int trace__sys_enter(struct trace *trace, struct evsel *evsel,
 		if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
 			int alignment = 0;
 
-			trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
+			trace__fprintf_entry_head(trace, thread, 0, false,
+						  ttrace->entry_time,
+						  sample->cpu, trace->output);
 			printed = fprintf(trace->output, "%s)", ttrace->entry_str);
 			if (trace->args_alignment > printed)
 				alignment = trace->args_alignment - printed;
@@ -2980,7 +3009,9 @@ static int trace__sys_exit(struct trace *trace, struct evsel *evsel,
 	if (trace->summary_only || (ret >= 0 && trace->failure_only))
 		goto out;
 
-	trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
+	trace__fprintf_entry_head(trace, thread, duration,
+				  duration_calculated, ttrace->entry_time,
+				  sample->cpu, trace->output);
 
 	if (ttrace->entry_pending) {
 		printed = fprintf(trace->output, "%s", ttrace->entry_str);
@@ -3280,6 +3311,9 @@ static int trace__event_handler(struct trace *trace, struct evsel *evsel,
 	trace__printf_interrupted_entry(trace);
 	trace__fprintf_tstamp(trace, sample->time, trace->output);
 
+	if (trace->show_cpu && sample->cpu != (u32)-1)
+		fprintf(trace->output, "[%03d] ", sample->cpu);
+
 	if (trace->trace_syscalls && trace->show_duration)
 		fprintf(trace->output, "(         ): ");
 
@@ -3405,7 +3439,8 @@ static int trace__pgfault(struct trace *trace,
 
 	thread__find_symbol(thread, sample->cpumode, sample->ip, &al);
 
-	trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
+	trace__fprintf_entry_head(trace, thread, 0, true, sample->time,
+				  sample->cpu, trace->output);
 
 	fprintf(trace->output, "%sfault [",
 		evsel->core.attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
@@ -5432,6 +5467,7 @@ int cmd_trace(int argc, const char **argv)
 	OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
 		     "number of mmap data pages", evlist__parse_mmap_pages),
 	OPT_STRING('u', "uid", &trace.uid_str, "user", "user to profile"),
+	OPT_BOOLEAN(0, "show-cpu", &trace.show_cpu, "show cpu id"),
 	OPT_CALLBACK(0, "duration", &trace, "float",
 		     "show only events with duration > N.M ms",
 		     trace__set_duration),
@@ -5566,6 +5602,9 @@ int cmd_trace(int argc, const char **argv)
 			goto out;
 	}
 
+	if (trace.show_cpu)
+		trace.opts.sample_cpu = true;
+
 	if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) {
 		usage_with_options_msg(trace_usage, trace_options,
 				       "cgroup monitoring only available in system-wide mode");
-- 
2.51.0