ftrace: Add 'function-fork' trace option

The function-fork option is same as event-fork that it tracks task
fork/exit and set the pid filter properly.  This can be useful if user
wants to trace selected tasks including their children only.

Link: http://lkml.kernel.org/r/20170417024430.21194-3-namhyung@kernel.org

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

kernel/trace/ftrace.c

@@ -5600,6 +5600,43 @@ ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
 		       trace_ignore_this_task(pid_list, next));
 }
 
+static void
+ftrace_pid_follow_sched_process_fork(void *data,
+				     struct task_struct *self,
+				     struct task_struct *task)
+{
+	struct trace_pid_list *pid_list;
+	struct trace_array *tr = data;
+
+	pid_list = rcu_dereference_sched(tr->function_pids);
+	trace_filter_add_remove_task(pid_list, self, task);
+}
+
+static void
+ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task)
+{
+	struct trace_pid_list *pid_list;
+	struct trace_array *tr = data;
+
+	pid_list = rcu_dereference_sched(tr->function_pids);
+	trace_filter_add_remove_task(pid_list, NULL, task);
+}
+
+void ftrace_pid_follow_fork(struct trace_array *tr, bool enable)
+{
+	if (enable) {
+		register_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
+						  tr);
+		register_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+						  tr);
+	} else {
+		unregister_trace_sched_process_fork(ftrace_pid_follow_sched_process_fork,
+						    tr);
+		unregister_trace_sched_process_exit(ftrace_pid_follow_sched_process_exit,
+						    tr);
+	}
+}
+
 static void clear_ftrace_pids(struct trace_array *tr)
 {
 	struct trace_pid_list *pid_list;

kernel/trace/trace.c

@@ -257,7 +257,7 @@ unsigned long long ns2usecs(u64 nsec)
 
 /* trace_flags that are default zero for instances */
 #define ZEROED_TRACE_FLAGS \
-	TRACE_ITER_EVENT_FORK
+	(TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK)
 
 /*
  * The global_trace is the descriptor that holds the top-level tracing
@@ -4205,6 +4205,9 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 	if (mask == TRACE_ITER_EVENT_FORK)
 		trace_event_follow_fork(tr, enabled);
 
+	if (mask == TRACE_ITER_FUNC_FORK)
+		ftrace_pid_follow_fork(tr, enabled);
+
 	if (mask == TRACE_ITER_OVERWRITE) {
 		ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled);
 #ifdef CONFIG_TRACER_MAX_TRACE

kernel/trace/trace.h

@@ -897,6 +897,7 @@ void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
 void ftrace_init_tracefs_toplevel(struct trace_array *tr,
 				  struct dentry *d_tracer);
 int init_function_trace(void);
+void ftrace_pid_follow_fork(struct trace_array *tr, bool enable);
 #else
 static inline int ftrace_trace_task(struct trace_array *tr)
 {
@@ -916,6 +917,7 @@ static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
 static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
 static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
 static inline int init_function_trace(void) { return 0; }
+static inline void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) { }
 /* ftace_func_t type is not defined, use macro instead of static inline */
 #define ftrace_init_array_ops(tr, func) do { } while (0)
 #endif /* CONFIG_FUNCTION_TRACER */
@@ -989,11 +991,13 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 
 #ifdef CONFIG_FUNCTION_TRACER
 # define FUNCTION_FLAGS						\
-		C(FUNCTION,		"function-trace"),
+		C(FUNCTION,		"function-trace"),	\
+		C(FUNC_FORK,		"function-fork"),
 # define FUNCTION_DEFAULT_FLAGS		TRACE_ITER_FUNCTION
 #else
 # define FUNCTION_FLAGS
 # define FUNCTION_DEFAULT_FLAGS		0UL
+# define TRACE_ITER_FUNC_FORK		0UL
 #endif
 
 #ifdef CONFIG_STACKTRACE