perf sched: Replace (void*)1 sentinel with proper runtime allocation

map__findnew_thread() marks color-pid threads by storing (void*)1 as
the thread private data via thread__set_priv().  This sentinel value
causes two problems:

1. thread__get_runtime() returns (void*)1 as a struct thread_runtime
   pointer.  Any field access (e.g. tr->shortname) dereferences address
   1, which is an unmapped page — immediate segfault.

2. cmd_sched() registers free() as the thread priv destructor, so thread
   cleanup calls free((void*)1) — undefined behavior that corrupts the
   heap on many allocators.

Fix by adding a 'color' flag to struct thread_runtime and allocating a
real runtime struct for color-pid threads.  thread__has_color() now
checks the flag instead of relying on priv being non-NULL.

Reported-by: sashiko-bot <sashiko-bot@kernel.org>
Fixes: 58a606149c60d5da ("perf sched: Avoid union type punning undefined behavior")
Reviewed-by: Ian Rogers <irogers@google.com>
Cc: Ian Rogers <irogers@google.com>
Assisted-by: Claude:claude-opus-4.6
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 17 insertions, 6 deletions

diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5f16caebd964..7fd63a9db457 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -274,6 +274,7 @@ struct thread_runtime {
 	u64 migrations;
 
 	int prio;
+	bool color;
 };
 
 /* per event run time data */
@@ -1589,22 +1590,32 @@ static int process_sched_wakeup_ignore(const struct perf_tool *tool __maybe_unus
 
 static bool thread__has_color(struct thread *thread)
 {
-	return thread__priv(thread) != NULL;
+	struct thread_runtime *tr = thread__priv(thread);
+
+	return tr != NULL && tr->color;
 }
 
 static struct thread*
 map__findnew_thread(struct perf_sched *sched, struct machine *machine, pid_t pid, pid_t tid)
 {
 	struct thread *thread = machine__findnew_thread(machine, pid, tid);
-	bool color = false;
 
-	if (!sched->map.color_pids || !thread || thread__priv(thread))
+	if (!sched->map.color_pids || !thread)
 		return thread;
 
-	if (thread_map__has(sched->map.color_pids, tid))
-		color = true;
+	/*
+	 * Always check the color-pids map, even if thread__priv() is
+	 * already set.  COMM events processed before the first sched_switch
+	 * allocate a thread_runtime via thread__get_runtime(), so priv is
+	 * non-NULL before we ever get here.  Skipping the check on non-NULL
+	 * priv would prevent those threads from being colored.
+	 */
+	if (thread_map__has(sched->map.color_pids, tid)) {
+		struct thread_runtime *tr = thread__get_runtime(thread);
 
-	thread__set_priv(thread, color ? ((void*)1) : NULL);
+		if (tr)
+			tr->color = true;
+	}
 	return thread;
 }