function_graph: Support recording and printing the function return address

When using function_graph tracer to analyze the flow of kernel function
execution, it is often necessary to quickly locate the exact line of code
where the call occurs. While this may be easy at times, it can be more
time-consuming when some functions are inlined or the flow is too long.

This feature aims to simplify the process by recording the return address
of traced funcions and printing it when outputing trace logs.

To enhance human readability, the prefix 'ret=' is used for the kernel return
value, while '<-' serves as the prefix for the return address in trace logs to
make it look more like the function tracer.

A new trace option named 'funcgraph-retaddr' has been introduced, and the
existing option 'sym-addr' can be used to control the format of the return
address.

See below logs with both funcgraph-retval and funcgraph-retaddr enabled.

0)             | load_elf_binary() { /* <-bprm_execve+0x249/0x600 */
0)             |   load_elf_phdrs() { /* <-load_elf_binary+0x84/0x1730 */
0)             |     __kmalloc_noprof() { /* <-load_elf_phdrs+0x4a/0xb0 */
0)   3.657 us  |       __cond_resched(); /* <-__kmalloc_noprof+0x28c/0x390 ret=0x0 */
0) + 24.335 us |     } /* __kmalloc_noprof ret=0xffff8882007f3000 */
0)             |     kernel_read() { /* <-load_elf_phdrs+0x6c/0xb0 */
0)             |       rw_verify_area() { /* <-kernel_read+0x2b/0x50 */
0)             |         security_file_permission() { /* <-kernel_read+0x2b/0x50 */
0)             |           selinux_file_permission() { /* <-security_file_permission+0x26/0x40 */
0)             |             __inode_security_revalidate() { /* <-selinux_file_permission+0x6d/0x140 */
0)   2.034 us  |               __cond_resched(); /* <-__inode_security_revalidate+0x5f/0x80 ret=0x0 */
0)   6.602 us  |             } /* __inode_security_revalidate ret=0x0 */
0)   2.214 us  |             avc_policy_seqno(); /* <-selinux_file_permission+0x107/0x140 ret=0x0 */
0) + 16.670 us |           } /* selinux_file_permission ret=0x0 */
0) + 20.809 us |         } /* security_file_permission ret=0x0 */
0) + 25.217 us |       } /* rw_verify_area ret=0x0 */
0)             |       __kernel_read() { /* <-load_elf_phdrs+0x6c/0xb0 */
0)             |         ext4_file_read_iter() { /* <-__kernel_read+0x160/0x2e0 */

Then, we can use the faddr2line to locate the source code, for example:

$ ./scripts/faddr2line ./vmlinux load_elf_phdrs+0x6c/0xb0
load_elf_phdrs+0x6c/0xb0:
elf_read at fs/binfmt_elf.c:471
(inlined by) load_elf_phdrs at fs/binfmt_elf.c:531

Link: https://lore.kernel.org/20240915032912.1118397-1-dolinux.peng@gmail.com
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202409150605.HgUmU8ea-lkp@intel.com/
Signed-off-by: Donglin Peng <dolinux.peng@gmail.com>
[ Rebased to handle text_delta offsets ]
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 25 insertions, 2 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e684addf6508..2ac3b3b53cd0 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1041,6 +1041,17 @@ struct ftrace_graph_ent {
 } __packed;
 
 /*
+ * Structure that defines an entry function trace with retaddr.
+ * It's already packed but the attribute "packed" is needed
+ * to remove extra padding at the end.
+ */
+struct fgraph_retaddr_ent {
+	unsigned long func; /* Current function */
+	int depth;
+	unsigned long retaddr;  /* Return address */
+} __packed;
+
+/*
  * Structure that defines a return function trace.
  * It's already packed but the attribute "packed" is needed
  * to remove extra padding at the end.
@@ -1057,19 +1068,29 @@ struct ftrace_graph_ret {
 	unsigned long long rettime;
 } __packed;
 
+struct fgraph_extras;
 struct fgraph_ops;
 
 /* Type of the callback handlers for tracing function graph*/
 typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *,
 				       struct fgraph_ops *); /* return */
 typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *,
-				      struct fgraph_ops *); /* entry */
+				      struct fgraph_ops *,
+				      struct fgraph_extras *); /* entry */
 
-extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
+extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
+				   struct fgraph_ops *gops,
+				   struct fgraph_extras *extras);
 bool ftrace_pids_enabled(struct ftrace_ops *ops);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
+/* Used to convey some extra datas when creating a graph entry */
+struct fgraph_extras {
+	u32 flags;
+	unsigned long retaddr;
+};
+
 struct fgraph_ops {
 	trace_func_graph_ent_t		entryfunc;
 	trace_func_graph_ret_t		retfunc;
@@ -1115,6 +1136,8 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp);
 unsigned long *fgraph_get_task_var(struct fgraph_ops *gops);
 
+u32 graph_tracer_flags_get(u32 flags);
+
 /*
  * Sometimes we don't want to trace a function with the function
  * graph tracer but we want them to keep traced by the usual function