ftrace: Get the true parent ip for function tracer

When using both function tracer and function graph simultaneously,
it is found that function tracer sometimes captures a fake parent ip
(return_to_handler) instead of the true parent ip.

This issue is easy to reproduce. Below are my reproduction steps:

jeff-labs:~/bin # ./trace-net.sh

jeff-labs:~/bin # cat /sys/kernel/debug/tracing/instances/foo/trace | grep return_to_handler
    trace-net.sh-405     [001] ...2.    31.859501: avc_has_perm+0x4/0x190 <-return_to_handler+0x0/0x40
    trace-net.sh-405     [001] ...2.    31.859503: simple_setattr+0x4/0x70 <-return_to_handler+0x0/0x40
    trace-net.sh-405     [001] ...2.    31.859503: truncate_pagecache+0x4/0x60 <-return_to_handler+0x0/0x40
    trace-net.sh-405     [001] ...2.    31.859505: unmap_mapping_range+0x4/0x140 <-return_to_handler+0x0/0x40
    trace-net.sh-405     [001] ...3.    31.859508: _raw_spin_unlock+0x4/0x30 <-return_to_handler+0x0/0x40
    [...]

The following is my simple trace script:

<snip>
jeff-labs:~/bin # cat ./trace-net.sh
TRACE_PATH="/sys/kernel/tracing"

set_events() {
        echo 1 > $1/events/net/enable
        echo 1 > $1/events/tcp/enable
        echo 1 > $1/events/sock/enable
        echo 1 > $1/events/napi/enable
        echo 1 > $1/events/fib/enable
        echo 1 > $1/events/neigh/enable
}

set_events ${TRACE_PATH}
echo 1 > ${TRACE_PATH}/options/sym-offset
echo 1 > ${TRACE_PATH}/options/funcgraph-tail
echo 1 > ${TRACE_PATH}/options/funcgraph-proc
echo 1 > ${TRACE_PATH}/options/funcgraph-abstime

echo 'tcp_orphan*' > ${TRACE_PATH}/set_ftrace_notrace
echo function_graph > ${TRACE_PATH}/current_tracer

INSTANCE_FOO=${TRACE_PATH}/instances/foo
if [ ! -e $INSTANCE_FOO ]; then
        mkdir ${INSTANCE_FOO}
fi
set_events ${INSTANCE_FOO}
echo 1 > ${INSTANCE_FOO}/options/sym-offset
echo 'tcp_orphan*' > ${INSTANCE_FOO}/set_ftrace_notrace
echo function > ${INSTANCE_FOO}/current_tracer

echo 1 > ${TRACE_PATH}/tracing_on
echo 1 > ${INSTANCE_FOO}/tracing_on

echo > ${TRACE_PATH}/trace
echo > ${INSTANCE_FOO}/trace
</snip>

Link: https://lore.kernel.org/20241008033159.22459-1-jeff.xie@linux.dev
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jeff Xie <jeff.xie@linux.dev>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 26 insertions, 0 deletions

diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 65fed0bbc5c2..74c353164ca1 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -176,6 +176,27 @@ static void function_trace_start(struct trace_array *tr)
 	tracing_reset_online_cpus(&tr->array_buffer);
 }
 
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static __always_inline unsigned long
+function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs)
+{
+	unsigned long true_parent_ip;
+	int idx = 0;
+
+	true_parent_ip = parent_ip;
+	if (unlikely(parent_ip == (unsigned long)&return_to_handler) && fregs)
+		true_parent_ip = ftrace_graph_ret_addr(current, &idx, parent_ip,
+				(unsigned long *)ftrace_regs_get_stack_pointer(fregs));
+	return true_parent_ip;
+}
+#else
+static __always_inline unsigned long
+function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs)
+{
+	return parent_ip;
+}
+#endif
+
 static void
 function_trace_call(unsigned long ip, unsigned long parent_ip,
 		    struct ftrace_ops *op, struct ftrace_regs *fregs)
@@ -192,6 +213,8 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
+
 	trace_ctx = tracing_gen_ctx();
 
 	data = this_cpu_ptr(tr->array_buffer.data);
@@ -239,6 +262,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	 * recursive protection is performed.
 	 */
 	local_irq_save(flags);
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 	disabled = atomic_inc_return(&data->disabled);
@@ -306,6 +330,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (bit < 0)
 		return;
 
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	data = this_cpu_ptr(tr->array_buffer.data);
 	if (atomic_read(&data->disabled))
 		goto out;
@@ -352,6 +377,7 @@ function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	 * recursive protection is performed.
 	 */
 	local_irq_save(flags);
+	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
 	disabled = atomic_inc_return(&data->disabled);