ftrace: Add set_graph_notrace filter

The set_graph_notrace filter is analogous to set_ftrace_notrace and
can be used for eliminating uninteresting part of function graph trace
output.  It also works with set_graph_function nicely.

  # cd /sys/kernel/debug/tracing/
  # echo do_page_fault > set_graph_function
  # perf ftrace live true
   2)               |  do_page_fault() {
   2)               |    __do_page_fault() {
   2)   0.381 us    |      down_read_trylock();
   2)   0.055 us    |      __might_sleep();
   2)   0.696 us    |      find_vma();
   2)               |      handle_mm_fault() {
   2)               |        handle_pte_fault() {
   2)               |          __do_fault() {
   2)               |            filemap_fault() {
   2)               |              find_get_page() {
   2)   0.033 us    |                __rcu_read_lock();
   2)   0.035 us    |                __rcu_read_unlock();
   2)   1.696 us    |              }
   2)   0.031 us    |              __might_sleep();
   2)   2.831 us    |            }
   2)               |            _raw_spin_lock() {
   2)   0.046 us    |              add_preempt_count();
   2)   0.841 us    |            }
   2)   0.033 us    |            page_add_file_rmap();
   2)               |            _raw_spin_unlock() {
   2)   0.057 us    |              sub_preempt_count();
   2)   0.568 us    |            }
   2)               |            unlock_page() {
   2)   0.084 us    |              page_waitqueue();
   2)   0.126 us    |              __wake_up_bit();
   2)   1.117 us    |            }
   2)   7.729 us    |          }
   2)   8.397 us    |        }
   2)   8.956 us    |      }
   2)   0.085 us    |      up_read();
   2) + 12.745 us   |    }
   2) + 13.401 us   |  }
  ...

  # echo handle_mm_fault > set_graph_notrace
  # perf ftrace live true
   1)               |  do_page_fault() {
   1)               |    __do_page_fault() {
   1)   0.205 us    |      down_read_trylock();
   1)   0.041 us    |      __might_sleep();
   1)   0.344 us    |      find_vma();
   1)   0.069 us    |      up_read();
   1)   4.692 us    |    }
   1)   5.311 us    |  }
  ...

Link: http://lkml.kernel.org/r/1381739066-7531-5-git-send-email-namhyung@kernel.org

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

kernel/trace/trace_functions_graph.c

@@ -114,16 +114,37 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
 		return -EBUSY;
 	}
 
+	/*
+	 * The curr_ret_stack is an index to ftrace return stack of
+	 * current task.  Its value should be in [0, FTRACE_RETFUNC_
+	 * DEPTH) when the function graph tracer is used.  To support
+	 * filtering out specific functions, it makes the index
+	 * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH)
+	 * so when it sees a negative index the ftrace will ignore
+	 * the record.  And the index gets recovered when returning
+	 * from the filtered function by adding the FTRACE_NOTRACE_
+	 * DEPTH and then it'll continue to record functions normally.
+	 *
+	 * The curr_ret_stack is initialized to -1 and get increased
+	 * in this function.  So it can be less than -1 only if it was
+	 * filtered out via ftrace_graph_notrace_addr() which can be
+	 * set from set_graph_notrace file in debugfs by user.
+	 */
+	if (current->curr_ret_stack < -1)
+		return -EBUSY;
+
 	calltime = trace_clock_local();
 
 	index = ++current->curr_ret_stack;
+	if (ftrace_graph_notrace_addr(func))
+		current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH;
 	barrier();
 	current->ret_stack[index].ret = ret;
 	current->ret_stack[index].func = func;
 	current->ret_stack[index].calltime = calltime;
 	current->ret_stack[index].subtime = 0;
 	current->ret_stack[index].fp = frame_pointer;
-	*depth = index;
+	*depth = current->curr_ret_stack;
 
 	return 0;
 }
@@ -137,7 +158,17 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 
 	index = current->curr_ret_stack;
 
-	if (unlikely(index < 0)) {
+	/*
+	 * A negative index here means that it's just returned from a
+	 * notrace'd function.  Recover index to get an original
+	 * return address.  See ftrace_push_return_trace().
+	 *
+	 * TODO: Need to check whether the stack gets corrupted.
+	 */
+	if (index < 0)
+		index += FTRACE_NOTRACE_DEPTH;
+
+	if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) {
 		ftrace_graph_stop();
 		WARN_ON(1);
 		/* Might as well panic, otherwise we have no where to go */
@@ -193,6 +224,15 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	trace.rettime = trace_clock_local();
 	barrier();
 	current->curr_ret_stack--;
+	/*
+	 * The curr_ret_stack can be less than -1 only if it was
+	 * filtered out and it's about to return from the function.
+	 * Recover the index and continue to trace normal functions.
+	 */
+	if (current->curr_ret_stack < -1) {
+		current->curr_ret_stack += FTRACE_NOTRACE_DEPTH;
+		return ret;
+	}
 
 	/*
 	 * The trace should run after decrementing the ret counter
@@ -259,10 +299,20 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 
 	/* trace it when it is-nested-in or is a function enabled. */
 	if ((!(trace->depth || ftrace_graph_addr(trace->func)) ||
-	     ftrace_graph_ignore_irqs()) ||
+	     ftrace_graph_ignore_irqs()) || (trace->depth < 0) ||
 	    (max_depth && trace->depth >= max_depth))
 		return 0;
 
+	/*
+	 * Do not trace a function if it's filtered by set_graph_notrace.
+	 * Make the index of ret stack negative to indicate that it should
+	 * ignore further functions.  But it needs its own ret stack entry
+	 * to recover the original index in order to continue tracing after
+	 * returning from the function.
+	 */
+	if (ftrace_graph_notrace_addr(trace->func))
+		return 1;
+
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->trace_buffer.data, cpu);