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, 83 insertions, 10 deletions

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 203204cadf92..c35fbaab2a47 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -58,6 +58,12 @@ static struct tracer_opt trace_opts[] = {
 	{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
 	/* Display function name after trailing } */
 	{ TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) },
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+	/* Display function return value ? */
+	{ TRACER_OPT(funcgraph-retval, TRACE_GRAPH_PRINT_RETVAL) },
+	/* Display function return value in hexadecimal format ? */
+	{ TRACER_OPT(funcgraph-retval-hex, TRACE_GRAPH_PRINT_RETVAL_HEX) },
+#endif
 	/* Include sleep time (scheduled out) between entry and return */
 	{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
 
@@ -619,6 +625,56 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration,
 	trace_seq_puts(s, "|  ");
 }
 
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+
+#define __TRACE_GRAPH_PRINT_RETVAL TRACE_GRAPH_PRINT_RETVAL
+
+static void print_graph_retval(struct trace_seq *s, unsigned long retval,
+				bool leaf, void *func, bool hex_format)
+{
+	unsigned long err_code = 0;
+
+	if (retval == 0 || hex_format)
+		goto done;
+
+	/* Check if the return value matches the negative format */
+	if (IS_ENABLED(CONFIG_64BIT) && (retval & BIT(31)) &&
+		(((u64)retval) >> 32) == 0) {
+		/* sign extension */
+		err_code = (unsigned long)(s32)retval;
+	} else {
+		err_code = retval;
+	}
+
+	if (!IS_ERR_VALUE(err_code))
+		err_code = 0;
+
+done:
+	if (leaf) {
+		if (hex_format || (err_code == 0))
+			trace_seq_printf(s, "%ps(); /* = 0x%lx */\n",
+					func, retval);
+		else
+			trace_seq_printf(s, "%ps(); /* = %ld */\n",
+					func, err_code);
+	} else {
+		if (hex_format || (err_code == 0))
+			trace_seq_printf(s, "} /* %ps = 0x%lx */\n",
+					func, retval);
+		else
+			trace_seq_printf(s, "} /* %ps = %ld */\n",
+					func, err_code);
+	}
+}
+
+#else
+
+#define __TRACE_GRAPH_PRINT_RETVAL 0
+
+#define print_graph_retval(_seq, _retval, _leaf, _func, _format) do {} while (0)
+
+#endif
+
 /* Case of a leaf function on its call entry */
 static enum print_line_t
 print_graph_entry_leaf(struct trace_iterator *iter,
@@ -663,7 +719,15 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++)
 		trace_seq_putc(s, ' ');
 
-	trace_seq_printf(s, "%ps();\n", (void *)call->func);
+	/*
+	 * Write out the function return value if the option function-retval is
+	 * enabled.
+	 */
+	if (flags & __TRACE_GRAPH_PRINT_RETVAL)
+		print_graph_retval(s, graph_ret->retval, true, (void *)call->func,
+				!!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
+	else
+		trace_seq_printf(s, "%ps();\n", (void *)call->func);
 
 	print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
 			cpu, iter->ent->pid, flags);
@@ -942,16 +1006,25 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 		trace_seq_putc(s, ' ');
 
 	/*
-	 * If the return function does not have a matching entry,
-	 * then the entry was lost. Instead of just printing
-	 * the '}' and letting the user guess what function this
-	 * belongs to, write out the function name. Always do
-	 * that if the funcgraph-tail option is enabled.
+	 * Always write out the function name and its return value if the
+	 * function-retval option is enabled.
 	 */
-	if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
-		trace_seq_puts(s, "}\n");
-	else
-		trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+	if (flags & __TRACE_GRAPH_PRINT_RETVAL) {
+		print_graph_retval(s, trace->retval, false, (void *)trace->func,
+			!!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
+	} else {
+		/*
+		 * If the return function does not have a matching entry,
+		 * then the entry was lost. Instead of just printing
+		 * the '}' and letting the user guess what function this
+		 * belongs to, write out the function name. Always do
+		 * that if the funcgraph-tail option is enabled.
+		 */
+		if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL))
+			trace_seq_puts(s, "}\n");
+		else
+			trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+	}
 
 	/* Overrun */
 	if (flags & TRACE_GRAPH_PRINT_OVERRUN)