ftrace: Make function trace pid filtering a bit more exact

The set_ftrace_pid file is used to filter function tracing to only trace
tasks that are listed in that file. Instead of testing the pids listed in
that file (it's a bitmask) at each function trace event, the logic is done
via a sched_switch hook. A flag is set when the next task to run is in the
list of pids in the set_ftrace_pid file. But the sched_switch hook is not at
the exact location of when the task switches, and the flag gets set before
the task to be traced actually runs. This leaves a residue of traced
functions that do not belong to the pid that should be filtered on.

By changing the logic slightly, where instead of having  a boolean flag to
test, record the pid that should be traced, with special values for not to
trace and always trace. Then at each function call, a check will be made to
see if the function should be ignored, or if the current pid matches the
function that should be traced, and only trace if it matches (or if it has
the special value to always trace).
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

kernel/trace/ftrace.c

@@ -139,13 +139,23 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops)
 #endif
 }
 
+#define FTRACE_PID_IGNORE	-1
+#define FTRACE_PID_TRACE	-2
+
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
 	struct trace_array *tr = op->private;
+	int pid;
 
-	if (tr && this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid))
-		return;
+	if (tr) {
+		pid = this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid);
+		if (pid == FTRACE_PID_IGNORE)
+			return;
+		if (pid != FTRACE_PID_TRACE &&
+		    pid != current->pid)
+			return;
+	}
 
 	op->saved_func(ip, parent_ip, op, regs);
 }
@@ -6924,8 +6934,12 @@ ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
 
 	pid_list = rcu_dereference_sched(tr->function_pids);
 
-	this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
-		       trace_ignore_this_task(pid_list, next));
+	if (trace_ignore_this_task(pid_list, next))
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       FTRACE_PID_IGNORE);
+	else
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       next->pid);
 }
 
 static void
@@ -6978,7 +6992,7 @@ static void clear_ftrace_pids(struct trace_array *tr)
 	unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr);
 
 	for_each_possible_cpu(cpu)
-		per_cpu_ptr(tr->array_buffer.data, cpu)->ftrace_ignore_pid = false;
+		per_cpu_ptr(tr->array_buffer.data, cpu)->ftrace_ignore_pid = FTRACE_PID_TRACE;
 
 	rcu_assign_pointer(tr->function_pids, NULL);
 
@@ -7103,8 +7117,12 @@ static void ignore_task_cpu(void *data)
 	pid_list = rcu_dereference_protected(tr->function_pids,
 					     mutex_is_locked(&ftrace_lock));
 
-	this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
-		       trace_ignore_this_task(pid_list, current));
+	if (trace_ignore_this_task(pid_list, current))
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       FTRACE_PID_IGNORE);
+	else
+		this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid,
+			       current->pid);
 }
 
 static ssize_t

kernel/trace/trace.h

@@ -178,10 +178,10 @@ struct trace_array_cpu {
 	kuid_t			uid;
 	char			comm[TASK_COMM_LEN];
 
-	bool			ignore_pid;
 #ifdef CONFIG_FUNCTION_TRACER
-	bool			ftrace_ignore_pid;
+	int			ftrace_ignore_pid;
 #endif
+	bool			ignore_pid;
 };
 
 struct tracer;