perf tools: Ensure thread-stack is flushed

The thread-stack represents a thread's current stack. When a thread
exits there can still be many functions on the stack e.g. exit() can be
called many levels deep, so all the callers will never return. To get
that information output, the thread-stack must be flushed.

Previously it was assumed the thread-stack would be flushed when the
struct thread was deleted. With thread ref-counting it is no longer
clear when that will be, if ever. So instead explicitly flush all the
thread-stacks at the end of a session.

Signed-off-by: Adrian Hunter <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/util/machine.c

···
 	return rc;
 }
 
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv)
+{
+	struct rb_node *nd;
+	int rc = 0;
+
+	rc = machine__for_each_thread(&machines->host, fn, priv);
+	if (rc != 0)
+		return rc;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		rc = machine__for_each_thread(machine, fn, priv);
+		if (rc != 0)
+			return rc;
+	}
+	return rc;
+}
+
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap)

tools/perf/util/machine.h

···
 int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv);
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,

tools/perf/util/session.c

···
 #include "perf_regs.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
+#include "thread-stack.h"
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,
···
 	events_stats__auxtrace_error_warn(stats);
 }
 
+static int perf_session__flush_thread_stack(struct thread *thread,
+					    void *p __maybe_unused)
+{
+	return thread_stack__flush(thread);
+}
+
+static int perf_session__flush_thread_stacks(struct perf_session *session)
+{
+	return machines__for_each_thread(&session->machines,
+					 perf_session__flush_thread_stack,
+					 NULL);
+}
+
 volatile int session_done;
 
 static int __perf_session__process_pipe_events(struct perf_session *session)
···
 	if (err)
 		goto out_err;
 	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session);
···
 	if (err)
 		goto out_err;
 	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session);

tools/perf/util/thread-stack.c

···
 	return crp->process(&cr, crp->data);
 }
 
-static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 {
 	struct call_return_processor *crp = ts->crp;
 	int err;
···
 			return err;
 		}
 	}
+
+	return 0;
+}
+
+int thread_stack__flush(struct thread *thread)
+{
+	if (thread->ts)
+		return __thread_stack__flush(thread, thread->ts);
 
 	return 0;
 }
···
 	 */
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 
···
 
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 }
···
 void thread_stack__free(struct thread *thread)
 {
 	if (thread->ts) {
-		thread_stack__flush(thread, thread->ts);
+		__thread_stack__flush(thread, thread->ts);
 		zfree(&thread->ts->stack);
 		zfree(&thread->ts);
 	}
···
 
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
-		err = thread_stack__flush(thread, ts);
+		err = __thread_stack__flush(thread, ts);
 		if (err)
 			return err;
 		ts->comm = comm;

tools/perf/util/thread-stack.h

···
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 			  size_t sz, u64 ip);
+int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 
 struct call_return_processor *