function_graph: Support recording and printing the return value of function

Analyzing system call failures with the function_graph tracer can be a
time-consuming process, particularly when locating the kernel function
that first returns an error in the trace logs. This change aims to
simplify the process by recording the function return value to the
'retval' member of 'ftrace_graph_ret' and printing it when outputting
the trace log.

We have introduced new trace options: funcgraph-retval and
funcgraph-retval-hex. The former controls whether to display the return
value, while the latter controls the display format.

Please note that even if a function's return type is void, a return
value will still be printed. You can simply ignore it.

This patch only establishes the fundamental infrastructure. Subsequent
patches will make this feature available on some commonly used processor
architectures.

Here is an example:

I attempted to attach the demo process to a cpu cgroup, but it failed:

echo `pidof demo` > /sys/fs/cgroup/cpu/test/tasks
-bash: echo: write error: Invalid argument

The strace logs indicate that the write system call returned -EINVAL(-22):
...
write(1, "273\n", 4)                    = -1 EINVAL (Invalid argument)
...

To capture trace logs during a write system call, use the following
commands:

cd /sys/kernel/debug/tracing/
echo 0 > tracing_on
echo > trace
echo *sys_write > set_graph_function
echo *spin* > set_graph_notrace
echo *rcu* >> set_graph_notrace
echo *alloc* >> set_graph_notrace
echo preempt* >> set_graph_notrace
echo kfree* >> set_graph_notrace
echo $$ > set_ftrace_pid
echo function_graph > current_tracer
echo 1 > options/funcgraph-retval
echo 0 > options/funcgraph-retval-hex
echo 1 > tracing_on
echo `pidof demo` > /sys/fs/cgroup/cpu/test/tasks
echo 0 > tracing_on
cat trace > ~/trace.log

To locate the root cause, search for error code -22 directly in the file
trace.log and identify the first function that returned -22. Once you
have identified this function, examine its code to determine the root
cause.

For example, in the trace log below, cpu_cgroup_can_attach
returned -22 first, so we can focus our analysis on this function to
identify the root cause.

...

 1)          | cgroup_migrate() {
 1) 0.651 us |   cgroup_migrate_add_task(); /* = 0xffff93fcfd346c00 */
 1)          |   cgroup_migrate_execute() {
 1)          |     cpu_cgroup_can_attach() {
 1)          |       cgroup_taskset_first() {
 1) 0.732 us |         cgroup_taskset_next(); /* = 0xffff93fc8fb20000 */
 1) 1.232 us |       } /* cgroup_taskset_first = 0xffff93fc8fb20000 */
 1) 0.380 us |       sched_rt_can_attach(); /* = 0x0 */
 1) 2.335 us |     } /* cpu_cgroup_can_attach = -22 */
 1) 4.369 us |   } /* cgroup_migrate_execute = -22 */
 1) 7.143 us | } /* cgroup_migrate = -22 */

...

Link: https://lkml.kernel.org/r/1fc502712c981e0e6742185ba242992170ac9da8.1680954589.git.pengdonglin@sangfor.com.cn

Tested-by: Florian Kauer <florian.kauer@linutronix.de>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Donglin Peng <pengdonglin@sangfor.com.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 22 insertions, 1 deletions

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index ea3d7bb235d3..cd2c35b1dd8f 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -243,12 +243,16 @@ struct fgraph_ret_regs;
  * Send the trace to the ring-buffer.
  * @return the original return address.
  */
-unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
+static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs,
+						unsigned long frame_pointer)
 {
 	struct ftrace_graph_ret trace;
 	unsigned long ret;
 
 	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+	trace.retval = fgraph_ret_regs_return_value(ret_regs);
+#endif
 	trace.rettime = trace_clock_local();
 	ftrace_graph_return(&trace);
 	/*
@@ -269,6 +273,23 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	return ret;
 }
 
+/*
+ * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can
+ * leave only ftrace_return_to_handler(ret_regs).
+ */
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
+unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs)
+{
+	return __ftrace_return_to_handler(ret_regs,
+				fgraph_ret_regs_frame_pointer(ret_regs));
+}
+#else
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
+{
+	return __ftrace_return_to_handler(NULL, frame_pointer);
+}
+#endif
+
 /**
  * ftrace_graph_get_ret_stack - return the entry of the shadow stack
  * @task: The task to read the shadow stack from