perf ftrace profile: Add --graph-opts option

Like trace subcommand, it should be able to pass some options to control
the tracing behavior for the function graph tracer.

But some options are limited in order to maintain the internal behavior.

For example, it can limit the function call depth like below:

  # perf ftrace profile --graph-opts depth=5 -- myprog

Committer testing:

  root@number:~# perf ftrace profile --graph-opts thresh=1000 -- sleep 1
  # Total (us)   Avg (us)   Max (us)      Count   Function
   1001419.301 500709.650 1000032.000          2   x64_sys_call
   1000032.000 1000032.000 1000032.000          1   __x64_sys_clock_nanosleep
   1000032.000 1000032.000 1000032.000          1   common_nsleep
   1000031.000 1000031.000 1000031.000          1   do_nanosleep
   1000031.000 1000031.000 1000031.000          1   hrtimer_nanosleep
   1000024.000 1000024.000 1000024.000          1   schedule
      1387.208   1387.208   1387.208          1   __x64_sys_execve
      1386.691   1386.691   1386.691          1   do_execveat_common.isra.0
      1334.170   1334.170   1334.170          1   bprm_execve
      1258.413   1258.413   1258.413          1   load_elf_binary
      1123.068   1123.068   1123.068          1   begin_new_exec
      1113.550   1113.550   1113.550          1   mmput
      1109.237   1109.237   1109.237          1   exit_mmap
  root@number:~# perf ftrace profile --graph-opts thresh=1200 -- sleep 1
  # Total (us)   Avg (us)   Max (us)      Count   Function
   1001448.204 500724.102 1000018.000          2   x64_sys_call
   1000017.000 1000017.000 1000017.000          1   __x64_sys_clock_nanosleep
   1000017.000 1000017.000 1000017.000          1   common_nsleep
   1000017.000 1000017.000 1000017.000          1   hrtimer_nanosleep
   1000016.000 1000016.000 1000016.000          1   do_nanosleep
   1000012.000 1000012.000 1000012.000          1   schedule
      1430.112   1430.112   1430.112          1   __x64_sys_execve
      1429.581   1429.581   1429.581          1   do_execveat_common.isra.0
      1376.289   1376.289   1376.289          1   bprm_execve
      1301.743   1301.743   1301.743          1   load_elf_binary
  root@number:~#

Reviewed-by: James Clark <james.clark@linaro.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.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/20250107224352.1128669-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-ftrace.txt

@@ -201,6 +201,14 @@ OPTIONS for 'perf ftrace profile'
 	Sort the result by the given field.  Available values are:
 	total, avg, max, count, name.  Default is 'total'.
 
+--graph-opts::
+	List of options allowed to set:
+
+	  - nosleep-time - Measure on-CPU time only for function_graph tracer.
+	  - noirqs       - Ignore functions that happen inside interrupt.
+	  - thresh=<n>   - Setup trace duration threshold in microseconds.
+	  - depth=<n>    - Set max depth for function graph tracer to follow.
+
 
 SEE ALSO
 --------

tools/perf/builtin-ftrace.c

@@ -1064,6 +1064,7 @@ static int prepare_func_profile(struct perf_ftrace *ftrace)
 {
 	ftrace->tracer = "function_graph";
 	ftrace->graph_tail = 1;
+	ftrace->graph_verbose = 0;
 
 	ftrace->profile_hash = hashmap__new(profile_hash, profile_equal, NULL);
 	if (ftrace->profile_hash == NULL)
@@ -1650,6 +1651,9 @@ int cmd_ftrace(int argc, const char **argv)
 	OPT_CALLBACK('s', "sort", &profile_sort, "key",
 		     "Sort result by key: total (default), avg, max, count, name.",
 		     parse_sort_key),
+	OPT_CALLBACK(0, "graph-opts", &ftrace, "options",
+		     "Graph tracer options, available options: nosleep-time,noirqs,thresh=<n>,depth=<n>",
+		     parse_graph_tracer_opts),
 	OPT_PARENT(common_options),
 	};
 	const struct option *options = ftrace_options;