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, 10 insertions, 1 deletions

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2f8017f8d34d..13f08f257c0b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -46,6 +46,7 @@ enum trace_type {
 	TRACE_BRANCH,
 	TRACE_GRAPH_RET,
 	TRACE_GRAPH_ENT,
+	TRACE_GRAPH_RETADDR_ENT,
 	TRACE_USER_STACK,
 	TRACE_BLK,
 	TRACE_BPUTS,
@@ -512,6 +513,8 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
 		IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry,	\
 			  TRACE_GRAPH_ENT);		\
+		IF_ASSIGN(var, ent, struct fgraph_retaddr_ent_entry,\
+			  TRACE_GRAPH_RETADDR_ENT);		\
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
 		IF_ASSIGN(var, ent, struct func_repeats_entry,		\
@@ -692,7 +695,8 @@ void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
 
 void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
-int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
+int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
+		      struct fgraph_extras *extras);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
@@ -879,6 +883,7 @@ static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
 #define TRACE_GRAPH_GRAPH_TIME          0x400
 #define TRACE_GRAPH_PRINT_RETVAL        0x800
 #define TRACE_GRAPH_PRINT_RETVAL_HEX    0x1000
+#define TRACE_GRAPH_PRINT_RETADDR       0x2000
 #define TRACE_GRAPH_PRINT_FILL_SHIFT	28
 #define TRACE_GRAPH_PRINT_FILL_MASK	(0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
 
@@ -900,6 +905,10 @@ extern void graph_trace_close(struct trace_iterator *iter);
 extern int __trace_graph_entry(struct trace_array *tr,
 			       struct ftrace_graph_ent *trace,
 			       unsigned int trace_ctx);
+extern int __trace_graph_retaddr_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned int trace_ctx,
+				unsigned long retaddr);
 extern void __trace_graph_return(struct trace_array *tr,
 				 struct ftrace_graph_ret *trace,
 				 unsigned int trace_ctx);