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/[email protected]
Reported-by: kernel test robot <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
Signed-off-by: Donglin Peng <[email protected]>
[ Rebased to handle text_delta offsets ]
Signed-off-by: Steven Rostedt (Google) <[email protected]>

Author: Donglin Peng

include/linux/ftrace.h

@@ -1040,6 +1040,17 @@ struct ftrace_graph_ent {
 	int depth;
 } __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
@@ -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

kernel/trace/Kconfig

@@ -242,6 +242,16 @@ config FUNCTION_GRAPH_RETVAL
 	  enable it via the trace option funcgraph-retval.
 	  See Documentation/trace/ftrace.rst
 
+config FUNCTION_GRAPH_RETADDR
+	bool "Kernel Function Graph Return Address"
+	depends on FUNCTION_GRAPH_TRACER
+	default n
+	help
+	  Support recording and printing the function return address when
+	  using function graph tracer. It can be helpful to locate code line that
+	  the function is called. This feature is off by default, and you can
+	  enable it via the trace option funcgraph-retaddr.
+
 config DYNAMIC_FTRACE
 	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER

kernel/trace/fgraph.c

@@ -290,7 +290,8 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset)
 }
 
 /* ftrace_graph_entry set to this to tell some archs to run function graph */
-static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops)
+static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops,
+		     struct fgraph_extras *extras)
 {
 	return 0;
 }
@@ -518,7 +519,8 @@ int __weak ftrace_disable_ftrace_graph_caller(void)
 #endif
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
-			    struct fgraph_ops *gops)
+			    struct fgraph_ops *gops,
+			    struct fgraph_extras *extras)
 {
 	return 0;
 }
@@ -646,13 +648,20 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 			 unsigned long frame_pointer, unsigned long *retp)
 {
 	struct ftrace_graph_ent trace;
+	struct fgraph_extras extras;
 	unsigned long bitmap = 0;
 	int offset;
 	int i;
+	int idx = 0;
 
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 
+	extras.flags = graph_tracer_flags_get(TRACE_GRAPH_PRINT_RETADDR);
+	if (IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR)
+		&& extras.flags & TRACE_GRAPH_PRINT_RETADDR)
+		extras.retaddr = ftrace_graph_ret_addr(current, &idx, ret, retp);
+
 	offset = ftrace_push_return_trace(ret, func, frame_pointer, retp, 0);
 	if (offset < 0)
 		goto out;
@@ -661,7 +670,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	if (static_branch_likely(&fgraph_do_direct)) {
 		int save_curr_ret_stack = current->curr_ret_stack;
 
-		if (static_call(fgraph_func)(&trace, fgraph_direct_gops))
+		if (static_call(fgraph_func)(&trace, fgraph_direct_gops, &extras))
 			bitmap |= BIT(fgraph_direct_gops->idx);
 		else
 			/* Clear out any saved storage */
@@ -679,7 +688,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 
 			save_curr_ret_stack = current->curr_ret_stack;
 			if (ftrace_ops_test(&gops->ops, func, NULL) &&
-			    gops->entryfunc(&trace, gops))
+			    gops->entryfunc(&trace, gops, &extras))
 				bitmap |= BIT(i);
 			else
 				/* Clear out any saved storage */
@@ -1136,7 +1145,8 @@ void ftrace_graph_exit_task(struct task_struct *t)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 static int fgraph_pid_func(struct ftrace_graph_ent *trace,
-			   struct fgraph_ops *gops)
+			   struct fgraph_ops *gops,
+			   struct fgraph_extras *extras)
 {
 	struct trace_array *tr = gops->ops.private;
 	int pid;
@@ -1150,7 +1160,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace,
 			return 0;
 	}
 
-	return gops->saved_func(trace, gops);
+	return gops->saved_func(trace, gops, NULL);
 }
 
 void fgraph_update_pid_func(void)

kernel/trace/ftrace.c

@@ -827,7 +827,8 @@ struct profile_fgraph_data {
 };
 
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_ops *gops,
+			       struct fgraph_extras *extras)
 {
 	struct profile_fgraph_data *profile_data;
 

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);

kernel/trace/trace_entries.h

@@ -85,9 +85,35 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry,
 	F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth)
 );
 
-/* Function return entry */
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+
+/* Function call entry with a return address */
+FTRACE_ENTRY_PACKED(fgraph_retaddr_entry, fgraph_retaddr_ent_entry,
+
+	TRACE_GRAPH_RETADDR_ENT,
+
+	F_STRUCT(
+		__field_struct(	struct fgraph_retaddr_ent,	graph_ent	)
+		__field_packed(	unsigned long,	graph_ent,	func		)
+		__field_packed(	int,		graph_ent,	depth		)
+		__field_packed(	unsigned long,	graph_ent,	retaddr		)
+	),
+
+	F_printk("--> %ps (%d) <- %ps", (void *)__entry->func, __entry->depth,
+		(void *)__entry->retaddr)
+);
+
+#else
+
+#ifndef fgraph_retaddr_ent_entry
+#define fgraph_retaddr_ent_entry ftrace_graph_ent_entry
+#endif
+
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
 
+/* Function return entry */
 FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	TRACE_GRAPH_RET,
@@ -110,6 +136,7 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 #else
 
+/* Function return entry */
 FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 
 	TRACE_GRAPH_RET,