perf report: Add 'tgid' sort key

Sometimes we need to analyze the data in process level but current sort
keys only work on thread level.  Let's add 'tgid' sort key for that as
'pid' is already taken for thread.

This will look mostly the same, but it only uses tgid instead of tid.
Here's an example of a process with two threads (thloop).

  $ perf record -- perf test -w thloop

  $ perf report --stdio -s tgid,pid -H
  ...
  #
  #    Overhead  Tgid:Command / Pid:Command
  # ...........  ..........................
  #
     100.00%     2018407:perf
         50.34%     2018407:perf
         49.66%     2018409:perf

Suggested-by: Stephane Eranian <eranian@google.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250509210421.197245-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-report.txt

@@ -94,6 +94,7 @@ OPTIONS
 
 	- comm: command (name) of the task which can be read via /proc/<pid>/comm
 	- pid: command and tid of the task
+	- tgid: command and tgid of the task
 	- dso: name of library or module executed at the time of sample
 	- dso_size: size of library or module executed at the time of sample
 	- symbol: name of function executed at the time of sample

tools/perf/util/hist.h

@@ -42,6 +42,7 @@ enum hist_column {
 	HISTC_TIME,
 	HISTC_DSO,
 	HISTC_THREAD,
+	HISTC_TGID,
 	HISTC_COMM,
 	HISTC_CGROUP_ID,
 	HISTC_CGROUP,

tools/perf/util/sort.c

@@ -141,6 +141,43 @@ struct sort_entry sort_thread = {
 	.se_width_idx	= HISTC_THREAD,
 };
 
+/* --sort tgid */
+
+static int64_t
+sort__tgid_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return thread__pid(right->thread) - thread__pid(left->thread);
+}
+
+static int hist_entry__tgid_snprintf(struct hist_entry *he, char *bf,
+				       size_t size, unsigned int width)
+{
+	int tgid = thread__pid(he->thread);
+	const char *comm = NULL;
+
+	/* display comm of the thread-group leader */
+	if (thread__pid(he->thread) == thread__tid(he->thread)) {
+		comm = thread__comm_str(he->thread);
+	} else {
+		struct maps *maps = thread__maps(he->thread);
+		struct thread *leader = machine__find_thread(maps__machine(maps),
+							     tgid, tgid);
+		if (leader) {
+			comm = thread__comm_str(leader);
+			thread__put(leader);
+		}
+	}
+	width = max(7U, width) - 8;
+	return repsep_snprintf(bf, size, "%7d:%-*.*s", tgid, width, width, comm ?: "");
+}
+
+struct sort_entry sort_tgid = {
+	.se_header	= "   Tgid:Command",
+	.se_cmp		= sort__tgid_cmp,
+	.se_snprintf	= hist_entry__tgid_snprintf,
+	.se_width_idx	= HISTC_TGID,
+};
+
 /* --sort simd */
 
 static int64_t
@@ -2508,6 +2545,7 @@ static void sort_dimension_add_dynamic_header(struct sort_dimension *sd)
 
 static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_PID, "pid", sort_thread),
+	DIM(SORT_TGID, "tgid", sort_tgid),
 	DIM(SORT_COMM, "comm", sort_comm),
 	DIM(SORT_DSO, "dso", sort_dso),
 	DIM(SORT_SYM, "symbol", sort_sym),

tools/perf/util/sort.h

@@ -73,6 +73,7 @@ enum sort_type {
 	SORT_SYM_OFFSET,
 	SORT_ANNOTATE_DATA_TYPE_CACHELINE,
 	SORT_PARALLELISM,
+	SORT_TGID,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,