From 3c9880f3ab52b52b5b4e1850a70e80dd7329cb4c Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Sat, 14 Sep 2024 17:48:07 -0400
Subject: ftrace: Use a running sleeptime instead of saving on shadow stack

The fgraph "sleep-time" option tells the function graph tracer and the
profiler whether to include the time a function "sleeps" (is scheduled off
the CPU) in its duration for the function. By default it is true, which
means the duration of a function is calculated by the timestamp of when the
function was entered to the timestamp of when it exits.

If the "sleep-time" option is disabled, it needs to remove the time that the
task was not running on the CPU during the function. Currently it is done in
a sched_switch tracepoint probe where it moves the "calltime" (time of entry
of the function) forward by the sleep time calculated. It updates all the
calltime in the shadow stack.

This is time consuming for those users of the function graph tracer that
does not care about the sleep time. Instead, add a "ftrace_sleeptime" to the
task_struct that gets the sleep time added each time the task wakes up. Then
have the function entry save the current "ftrace_sleeptime" and on function
exit, move the calltime forward by the difference of the current
"ftrace_sleeptime" from the saved sleeptime.

This removes one dependency of "calltime" needed to be on the shadow stack.
It also simplifies the code that removes the sleep time of functions.

TODO: Only enable the sched_switch tracepoint when this is needed.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <olsajiri@gmail.com>
Link: https://lore.kernel.org/20240914214826.938908568@goodmis.org
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'kernel/trace/trace_functions_graph.c')

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a569daaac4c4..bbd898f5a73c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -133,6 +133,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
 	struct trace_array_cpu *data;
+	unsigned long *sleeptime;
 	unsigned long flags;
 	unsigned int trace_ctx;
 	long disabled;
@@ -167,6 +168,13 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	if (ftrace_graph_ignore_irqs())
 		return 0;
 
+	/* save the current sleep time if we are to ignore it */
+	if (!fgraph_sleep_time) {
+		sleeptime = fgraph_reserve_data(gops->idx, sizeof(*sleeptime));
+		if (sleeptime)
+			*sleeptime = current->ftrace_sleeptime;
+	}
+
 	/*
 	 * Stop here if tracing_threshold is set. We only write function return
 	 * events to the ring buffer.
@@ -238,6 +246,22 @@ void __trace_graph_return(struct trace_array *tr,
 		trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
+static void handle_nosleeptime(struct ftrace_graph_ret *trace,
+			       struct fgraph_ops *gops)
+{
+	unsigned long long *sleeptime;
+	int size;
+
+	if (fgraph_sleep_time)
+		return;
+
+	sleeptime = fgraph_retrieve_data(gops->idx, &size);
+	if (!sleeptime)
+		return;
+
+	trace->calltime += current->ftrace_sleeptime - *sleeptime;
+}
+
 void trace_graph_return(struct ftrace_graph_ret *trace,
 			struct fgraph_ops *gops)
 {
@@ -256,6 +280,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 		return;
 	}
 
+	handle_nosleeptime(trace, gops);
+
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = per_cpu_ptr(tr->array_buffer.data, cpu);
@@ -278,6 +304,8 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 		return;
 	}
 
+	handle_nosleeptime(trace, gops);
+
 	if (tracing_thresh &&
 	    (trace->rettime - trace->calltime < tracing_thresh))
 		return;
-- 
cgit v1.2.3


From f1f36e22bee967db5e812a65e24389e54c46f3c2 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Sat, 14 Sep 2024 17:48:08 -0400
Subject: ftrace: Have calltime be saved in the fgraph storage

The calltime field in the shadow stack frame is only used by the function
graph tracer and profiler. But now that there's other users of the function
graph infrastructure, this adds overhead and wastes space on the shadow
stack. Move the calltime to the fgraph data storage, where the function
graph and profiler entry functions will save it in its own graph storage and
retrieve it in its exit functions.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jiri Olsa <olsajiri@gmail.com>
Link: https://lore.kernel.org/20240914214827.096968730@goodmis.org
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ftrace.h               |  1 -
 kernel/trace/fgraph.c                |  5 ---
 kernel/trace/ftrace.c                | 19 ++++++------
 kernel/trace/trace_functions_graph.c | 60 ++++++++++++++++++++++++------------
 4 files changed, 51 insertions(+), 34 deletions(-)

(limited to 'kernel/trace/trace_functions_graph.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index aabd348cad4a..e684addf6508 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1091,7 +1091,6 @@ void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth);
 struct ftrace_ret_stack {
 	unsigned long ret;
 	unsigned long func;
-	unsigned long long calltime;
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	unsigned long fp;
 #endif
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index b2e95bf82211..58a28ec35dab 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -558,7 +558,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 			 int fgraph_idx)
 {
 	struct ftrace_ret_stack *ret_stack;
-	unsigned long long calltime;
 	unsigned long val;
 	int offset;
 
@@ -588,8 +587,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 		return -EBUSY;
 	}
 
-	calltime = trace_clock_local();
-
 	offset = READ_ONCE(current->curr_ret_stack);
 	ret_stack = RET_STACK(current, offset);
 	offset += FGRAPH_FRAME_OFFSET;
@@ -623,7 +620,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 
 	ret_stack->ret = ret;
 	ret_stack->func = func;
-	ret_stack->calltime = calltime;
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	ret_stack->fp = frame_pointer;
 #endif
@@ -757,7 +753,6 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret,
 	*offset += FGRAPH_FRAME_OFFSET;
 	*ret = ret_stack->ret;
 	trace->func = ret_stack->func;
-	trace->calltime = ret_stack->calltime;
 	trace->overrun = atomic_read(&current->trace_overrun);
 	trace->depth = current->curr_ret_depth;
 	/*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 90b3975d5315..cae388122ca8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -821,6 +821,7 @@ void ftrace_graph_graph_time_control(bool enable)
 }
 
 struct profile_fgraph_data {
+	unsigned long long		calltime;
 	unsigned long long		subtime;
 	unsigned long long		sleeptime;
 };
@@ -842,6 +843,7 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 
 	profile_data->subtime = 0;
 	profile_data->sleeptime = current->ftrace_sleeptime;
+	profile_data->calltime = trace_clock_local();
 
 	return 1;
 }
@@ -850,9 +852,9 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 				 struct fgraph_ops *gops)
 {
 	struct profile_fgraph_data *profile_data;
-	struct profile_fgraph_data *parent_data;
 	struct ftrace_profile_stat *stat;
 	unsigned long long calltime;
+	unsigned long long rettime = trace_clock_local();
 	struct ftrace_profile *rec;
 	unsigned long flags;
 	int size;
@@ -862,29 +864,28 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
+	profile_data = fgraph_retrieve_data(gops->idx, &size);
+
 	/* If the calltime was zero'd ignore it */
-	if (!trace->calltime)
+	if (!profile_data || !profile_data->calltime)
 		goto out;
 
-	calltime = trace->rettime - trace->calltime;
+	calltime = rettime - profile_data->calltime;
 
 	if (!fgraph_sleep_time) {
-		profile_data = fgraph_retrieve_data(gops->idx, &size);
-		if (profile_data && current->ftrace_sleeptime)
+		if (current->ftrace_sleeptime)
 			calltime -= current->ftrace_sleeptime - profile_data->sleeptime;
 	}
 
 	if (!fgraph_graph_time) {
+		struct profile_fgraph_data *parent_data;
 
 		/* Append this call time to the parent time to subtract */
 		parent_data = fgraph_retrieve_parent_data(gops->idx, &size, 1);
 		if (parent_data)
 			parent_data->subtime += calltime;
 
-		if (!profile_data)
-			profile_data = fgraph_retrieve_data(gops->idx, &size);
-
-		if (profile_data && profile_data->subtime && profile_data->subtime < calltime)
+		if (profile_data->subtime && profile_data->subtime < calltime)
 			calltime -= profile_data->subtime;
 		else
 			calltime = 0;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index bbd898f5a73c..5c1b150fbba3 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -127,13 +127,18 @@ static inline int ftrace_graph_ignore_irqs(void)
 	return in_hardirq();
 }
 
+struct fgraph_times {
+	unsigned long long		calltime;
+	unsigned long long		sleeptime; /* may be optional! */
+};
+
 int trace_graph_entry(struct ftrace_graph_ent *trace,
 		      struct fgraph_ops *gops)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
 	struct trace_array_cpu *data;
-	unsigned long *sleeptime;
+	struct fgraph_times *ftimes;
 	unsigned long flags;
 	unsigned int trace_ctx;
 	long disabled;
@@ -168,12 +173,18 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	if (ftrace_graph_ignore_irqs())
 		return 0;
 
-	/* save the current sleep time if we are to ignore it */
-	if (!fgraph_sleep_time) {
-		sleeptime = fgraph_reserve_data(gops->idx, sizeof(*sleeptime));
-		if (sleeptime)
-			*sleeptime = current->ftrace_sleeptime;
+	if (fgraph_sleep_time) {
+		/* Only need to record the calltime */
+		ftimes = fgraph_reserve_data(gops->idx, sizeof(ftimes->calltime));
+	} else {
+		ftimes = fgraph_reserve_data(gops->idx, sizeof(*ftimes));
+		if (ftimes)
+			ftimes->sleeptime = current->ftrace_sleeptime;
 	}
+	if (!ftimes)
+		return 0;
+
+	ftimes->calltime = trace_clock_local();
 
 	/*
 	 * Stop here if tracing_threshold is set. We only write function return
@@ -247,19 +258,13 @@ void __trace_graph_return(struct trace_array *tr,
 }
 
 static void handle_nosleeptime(struct ftrace_graph_ret *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_times *ftimes,
+			       int size)
 {
-	unsigned long long *sleeptime;
-	int size;
-
-	if (fgraph_sleep_time)
-		return;
-
-	sleeptime = fgraph_retrieve_data(gops->idx, &size);
-	if (!sleeptime)
+	if (fgraph_sleep_time || size < sizeof(*ftimes))
 		return;
 
-	trace->calltime += current->ftrace_sleeptime - *sleeptime;
+	ftimes->calltime += current->ftrace_sleeptime - ftimes->sleeptime;
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace,
@@ -268,9 +273,11 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
 	struct trace_array_cpu *data;
+	struct fgraph_times *ftimes;
 	unsigned long flags;
 	unsigned int trace_ctx;
 	long disabled;
+	int size;
 	int cpu;
 
 	ftrace_graph_addr_finish(gops, trace);
@@ -280,7 +287,13 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 		return;
 	}
 
-	handle_nosleeptime(trace, gops);
+	ftimes = fgraph_retrieve_data(gops->idx, &size);
+	if (!ftimes)
+		return;
+
+	handle_nosleeptime(trace, ftimes, size);
+
+	trace->calltime = ftimes->calltime;
 
 	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
@@ -297,6 +310,9 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 				      struct fgraph_ops *gops)
 {
+	struct fgraph_times *ftimes;
+	int size;
+
 	ftrace_graph_addr_finish(gops, trace);
 
 	if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) {
@@ -304,10 +320,16 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 		return;
 	}
 
-	handle_nosleeptime(trace, gops);
+	ftimes = fgraph_retrieve_data(gops->idx, &size);
+	if (!ftimes)
+		return;
+
+	handle_nosleeptime(trace, ftimes, size);
+
+	trace->calltime = ftimes->calltime;
 
 	if (tracing_thresh &&
-	    (trace->rettime - trace->calltime < tracing_thresh))
+	    (trace->rettime - ftimes->calltime < tracing_thresh))
 		return;
 	else
 		trace_graph_return(trace, gops);
-- 
cgit v1.2.3


From 21e92806d39c68af2accd1fb238c2daecfcf9fbd Mon Sep 17 00:00:00 2001
From: Donglin Peng <pengdonglin@xiaomi.com>
Date: Sat, 14 Sep 2024 20:29:12 -0700
Subject: 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>
---
 include/linux/ftrace.h                             |  27 ++-
 kernel/trace/Kconfig                               |  10 +
 kernel/trace/fgraph.c                              |  22 ++-
 kernel/trace/ftrace.c                              |   3 +-
 kernel/trace/trace.h                               |  11 +-
 kernel/trace/trace_entries.h                       |  29 ++-
 kernel/trace/trace_functions_graph.c               | 216 ++++++++++++++++-----
 kernel/trace/trace_irqsoff.c                       |   3 +-
 kernel/trace/trace_sched_wakeup.c                  |   3 +-
 kernel/trace/trace_selftest.c                      |   9 +-
 .../ftrace/test.d/ftrace/fgraph-retval.tc          |   2 +-
 11 files changed, 274 insertions(+), 61 deletions(-)

(limited to 'kernel/trace/trace_functions_graph.c')

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
@@ -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
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 721c3b221048..74c2b1d43bb9 100644
--- a/kernel/trace/Kconfig
+++ b/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
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 58a28ec35dab..875aefe60a13 100644
--- a/kernel/trace/fgraph.c
+++ b/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)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index cae388122ca8..5d87dac83b80 100644
--- a/kernel/trace/ftrace.c
+++ b/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;
 
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);
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index c47422b20908..82fd174ebbe0 100644
--- a/kernel/trace/trace_entries.h
+++ b/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,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 5c1b150fbba3..3dd63ae2afe8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -31,7 +31,10 @@ struct fgraph_data {
 	struct fgraph_cpu_data __percpu *cpu_data;
 
 	/* Place to preserve last processed entry. */
-	struct ftrace_graph_ent_entry	ent;
+	union {
+		struct ftrace_graph_ent_entry	ent;
+		struct fgraph_retaddr_ent_entry	rent;
+	} ent;
 	struct ftrace_graph_ret_entry	ret;
 	int				failed;
 	int				cpu;
@@ -63,6 +66,10 @@ static struct tracer_opt trace_opts[] = {
 	{ 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
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	/* Display function return address ? */
+	{ TRACER_OPT(funcgraph-retaddr, TRACE_GRAPH_PRINT_RETADDR) },
 #endif
 	/* Include sleep time (scheduled out) between entry and return */
 	{ TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) },
@@ -83,6 +90,11 @@ static struct tracer_flags tracer_flags = {
 	.opts = trace_opts
 };
 
+u32 graph_tracer_flags_get(u32 flags)
+{
+	return tracer_flags.val & flags;
+}
+
 /*
  * DURATION column is being also used to display IRQ signs,
  * following values are used by print_graph_irq and others
@@ -119,6 +131,40 @@ int __trace_graph_entry(struct trace_array *tr,
 	return 1;
 }
 
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+int __trace_graph_retaddr_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned int trace_ctx,
+				unsigned long retaddr)
+{
+	struct trace_event_call *call = &event_fgraph_retaddr_entry;
+	struct ring_buffer_event *event;
+	struct trace_buffer *buffer = tr->array_buffer.buffer;
+	struct fgraph_retaddr_ent_entry *entry;
+
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RETADDR_ENT,
+					  sizeof(*entry), trace_ctx);
+	if (!event)
+		return 0;
+	entry	= ring_buffer_event_data(event);
+	entry->graph_ent.func = trace->func;
+	entry->graph_ent.depth = trace->depth;
+	entry->graph_ent.retaddr = retaddr;
+	if (!call_filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit_nostack(buffer, event);
+
+	return 1;
+}
+#else
+int __trace_graph_retaddr_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned int trace_ctx,
+				unsigned long retaddr)
+{
+	return 1;
+}
+#endif
+
 static inline int ftrace_graph_ignore_irqs(void)
 {
 	if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
@@ -133,7 +179,8 @@ struct fgraph_times {
 };
 
 int trace_graph_entry(struct ftrace_graph_ent *trace,
-		      struct fgraph_ops *gops)
+		      struct fgraph_ops *gops,
+		      struct fgraph_extras *extras)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
@@ -199,7 +246,12 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		trace_ctx = tracing_gen_ctx_flags(flags);
-		ret = __trace_graph_entry(tr, trace, trace_ctx);
+		if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && extras
+				&& (extras->flags & TRACE_GRAPH_PRINT_RETADDR)))
+			ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx,
+							  extras->retaddr);
+		else
+			ret = __trace_graph_entry(tr, trace, trace_ctx);
 	} else {
 		ret = 0;
 	}
@@ -507,7 +559,7 @@ get_return_for_leaf(struct trace_iterator *iter,
 	 * then we just reuse the data from before.
 	 */
 	if (data && data->failed) {
-		curr = &data->ent;
+		curr = &data->ent.ent;
 		next = &data->ret;
 	} else {
 
@@ -537,7 +589,10 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * Save current and next entries for later reference
 			 * if the output fails.
 			 */
-			data->ent = *curr;
+			if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT))
+				data->ent.rent = *(struct fgraph_retaddr_ent_entry *)curr;
+			else
+				data->ent.ent = *curr;
 			/*
 			 * If the next event is not a return type, then
 			 * we only care about what type it is. Otherwise we can
@@ -701,52 +756,96 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration,
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
-
 #define __TRACE_GRAPH_PRINT_RETVAL TRACE_GRAPH_PRINT_RETVAL
+#else
+#define __TRACE_GRAPH_PRINT_RETVAL 0
+#endif
 
-static void print_graph_retval(struct trace_seq *s, unsigned long retval,
-				bool leaf, void *func, bool hex_format)
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+#define __TRACE_GRAPH_PRINT_RETADDR TRACE_GRAPH_PRINT_RETADDR
+static void print_graph_retaddr(struct trace_seq *s, struct fgraph_retaddr_ent_entry *entry,
+				u32 trace_flags, bool comment)
+{
+	if (comment)
+		trace_seq_puts(s, " /*");
+
+	trace_seq_puts(s, " <-");
+	seq_print_ip_sym(s, entry->graph_ent.retaddr, trace_flags | TRACE_ITER_SYM_OFFSET);
+
+	if (comment)
+		trace_seq_puts(s, " */");
+}
+#else
+#define __TRACE_GRAPH_PRINT_RETADDR 0
+#define print_graph_retaddr(_seq, _entry, _tflags, _comment)		do { } while (0)
+#endif
+
+#if defined(CONFIG_FUNCTION_GRAPH_RETVAL) || defined(CONFIG_FUNCTION_GRAPH_RETADDR)
+
+static void print_graph_retval(struct trace_seq *s, struct ftrace_graph_ent_entry *entry,
+				struct ftrace_graph_ret *graph_ret, void *func,
+				u32 opt_flags, u32 trace_flags)
 {
 	unsigned long err_code = 0;
+	unsigned long retval = 0;
+	bool print_retaddr = false;
+	bool print_retval = false;
+	bool hex_format = !!(opt_flags & TRACE_GRAPH_PRINT_RETVAL_HEX);
 
-	if (retval == 0 || hex_format)
-		goto done;
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+	retval = graph_ret->retval;
+	print_retval = !!(opt_flags & TRACE_GRAPH_PRINT_RETVAL);
+#endif
 
-	/* 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;
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	print_retaddr = !!(opt_flags & TRACE_GRAPH_PRINT_RETADDR);
+#endif
+
+	if (print_retval && retval && !hex_format) {
+		/* Check if the return value matches the negative format */
+		if (IS_ENABLED(CONFIG_64BIT) && (retval & BIT(31)) &&
+			(((u64)retval) >> 32) == 0) {
+			err_code = sign_extend64(retval, 31);
+		} else {
+			err_code = retval;
+		}
+
+		if (!IS_ERR_VALUE(err_code))
+			err_code = 0;
 	}
 
-	if (!IS_ERR_VALUE(err_code))
-		err_code = 0;
+	if (entry) {
+		if (entry->ent.type != TRACE_GRAPH_RETADDR_ENT)
+			print_retaddr = false;
 
-done:
-	if (leaf) {
-		if (hex_format || (err_code == 0))
-			trace_seq_printf(s, "%ps(); /* = 0x%lx */\n",
-					func, retval);
+		trace_seq_printf(s, "%ps();", func);
+		if (print_retval || print_retaddr)
+			trace_seq_puts(s, " /*");
 		else
-			trace_seq_printf(s, "%ps(); /* = %ld */\n",
-					func, err_code);
+			trace_seq_putc(s, '\n');
 	} else {
+		print_retaddr = false;
+		trace_seq_printf(s, "} /* %ps", func);
+	}
+
+	if (print_retaddr)
+		print_graph_retaddr(s, (struct fgraph_retaddr_ent_entry *)entry,
+				    trace_flags, false);
+
+	if (print_retval) {
 		if (hex_format || (err_code == 0))
-			trace_seq_printf(s, "} /* %ps = 0x%lx */\n",
-					func, retval);
+			trace_seq_printf(s, " ret=0x%lx", retval);
 		else
-			trace_seq_printf(s, "} /* %ps = %ld */\n",
-					func, err_code);
+			trace_seq_printf(s, " ret=%ld", err_code);
 	}
+
+	if (!entry || print_retval || print_retaddr)
+		trace_seq_puts(s, " */\n");
 }
 
 #else
 
-#define __TRACE_GRAPH_PRINT_RETVAL 0
-
-#define print_graph_retval(_seq, _retval, _leaf, _func, _format) do {} while (0)
+#define print_graph_retval(_seq, _ent, _ret, _func, _opt_flags, _trace_flags) do {} while (0)
 
 #endif
 
@@ -798,14 +897,15 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 		trace_seq_putc(s, ' ');
 
 	/*
-	 * Write out the function return value if the option function-retval is
-	 * enabled.
+	 * Write out the function return value or return address
 	 */
-	if (flags & __TRACE_GRAPH_PRINT_RETVAL)
-		print_graph_retval(s, graph_ret->retval, true, (void *)func,
-				!!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
-	else
+	if (flags & (__TRACE_GRAPH_PRINT_RETVAL | __TRACE_GRAPH_PRINT_RETADDR)) {
+		print_graph_retval(s, entry, graph_ret,
+				   (void *)graph_ret->func + iter->tr->text_delta,
+				   flags, tr->trace_flags);
+	} else {
 		trace_seq_printf(s, "%ps();\n", (void *)func);
+	}
 
 	print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
 			cpu, iter->ent->pid, flags);
@@ -846,7 +946,12 @@ print_graph_entry_nested(struct trace_iterator *iter,
 
 	func = call->func + iter->tr->text_delta;
 
-	trace_seq_printf(s, "%ps() {\n", (void *)func);
+	trace_seq_printf(s, "%ps() {", (void *)func);
+	if (flags & __TRACE_GRAPH_PRINT_RETADDR  &&
+		entry->ent.type == TRACE_GRAPH_RETADDR_ENT)
+		print_graph_retaddr(s, (struct fgraph_retaddr_ent_entry *)entry,
+			tr->trace_flags, true);
+	trace_seq_putc(s, '\n');
 
 	if (trace_seq_has_overflowed(s))
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -1093,11 +1198,10 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 
 	/*
 	 * Always write out the function name and its return value if the
-	 * function-retval option is enabled.
+	 * funcgraph-retval option is enabled.
 	 */
 	if (flags & __TRACE_GRAPH_PRINT_RETVAL) {
-		print_graph_retval(s, trace->retval, false, (void *)func,
-			!!(flags & TRACE_GRAPH_PRINT_RETVAL_HEX));
+		print_graph_retval(s, NULL, trace, (void *)func, flags, tr->trace_flags);
 	} else {
 		/*
 		 * If the return function does not have a matching entry,
@@ -1212,7 +1316,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 	 * to print out the missing entry which would never go out.
 	 */
 	if (data && data->failed) {
-		field = &data->ent;
+		field = &data->ent.ent;
 		iter->cpu = data->cpu;
 		ret = print_graph_entry(field, s, iter, flags);
 		if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
@@ -1236,6 +1340,16 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 		saved = *field;
 		return print_graph_entry(&saved, s, iter, flags);
 	}
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	case TRACE_GRAPH_RETADDR_ENT: {
+		struct fgraph_retaddr_ent_entry saved;
+		struct fgraph_retaddr_ent_entry *rfield;
+
+		trace_assign_type(rfield, entry);
+		saved = *rfield;
+		return print_graph_entry((struct ftrace_graph_ent_entry *)&saved, s, iter, flags);
+	}
+#endif
 	case TRACE_GRAPH_RET: {
 		struct ftrace_graph_ret_entry *field;
 		trace_assign_type(field, entry);
@@ -1430,6 +1544,13 @@ static struct trace_event graph_trace_entry_event = {
 	.funcs		= &graph_functions,
 };
 
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+static struct trace_event graph_trace_retaddr_entry_event = {
+	.type		= TRACE_GRAPH_RETADDR_ENT,
+	.funcs		= &graph_functions,
+};
+#endif
+
 static struct trace_event graph_trace_ret_event = {
 	.type		= TRACE_GRAPH_RET,
 	.funcs		= &graph_functions
@@ -1516,6 +1637,13 @@ static __init int init_graph_trace(void)
 		return 1;
 	}
 
+#ifdef CONFIG_FUNCTION_GRAPH_RETADDR
+	if (!register_trace_event(&graph_trace_retaddr_entry_event)) {
+		pr_warn("Warning: could not register graph trace retaddr events\n");
+		return 1;
+	}
+#endif
+
 	if (!register_trace_event(&graph_trace_ret_event)) {
 		pr_warn("Warning: could not register graph trace events\n");
 		return 1;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index fce064e20570..eb3aa36cf10f 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -176,7 +176,8 @@ static int irqsoff_display_graph(struct trace_array *tr, int set)
 }
 
 static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_ops *gops,
+			       struct fgraph_extras *extras)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index ae2ace5e515a..155de2551507 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -113,7 +113,8 @@ static int wakeup_display_graph(struct trace_array *tr, int set)
 }
 
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops)
+			      struct fgraph_ops *gops,
+			      struct fgraph_extras *extras)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index c4ad7cd7e778..fbb99f8c8062 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -17,6 +17,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_PRINT:
 	case TRACE_BRANCH:
 	case TRACE_GRAPH_ENT:
+	case TRACE_GRAPH_RETADDR_ENT:
 	case TRACE_GRAPH_RET:
 		return 1;
 	}
@@ -773,7 +774,8 @@ struct fgraph_fixture {
 };
 
 static __init int store_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops)
+			      struct fgraph_ops *gops,
+			      struct fgraph_extras *extras)
 {
 	struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops);
 	const char *type = fixture->store_type_name;
@@ -1024,7 +1026,8 @@ static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
 static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
-				      struct fgraph_ops *gops)
+				      struct fgraph_ops *gops,
+				      struct fgraph_extras *extras)
 {
 	/* This is harmlessly racy, we want to approximately detect a hang */
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
@@ -1038,7 +1041,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
 		return 0;
 	}
 
-	return trace_graph_entry(trace, gops);
+	return trace_graph_entry(trace, gops, NULL);
 }
 
 static struct fgraph_ops fgraph_ops __initdata  = {
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc
index e34c0bdef3ed..e8e46378b88d 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-retval.tc
@@ -29,7 +29,7 @@ set -e
 
 : "Test printing the error code in signed decimal format"
 echo 0 > options/funcgraph-retval-hex
-count=`cat trace | grep 'proc_reg_write' | grep '= -5' | wc -l`
+count=`cat trace | grep 'proc_reg_write' | grep '=-5' | wc -l`
 if [ $count -eq 0 ]; then
     fail "Return value can not be printed in signed decimal format"
 fi
-- 
cgit v1.2.3


From 49e4154f4b16345da5e219b23ed9737a6e735bc1 Mon Sep 17 00:00:00 2001
From: Zheng Yejian <zhengyejian@huaweicloud.com>
Date: Wed, 11 Sep 2024 09:00:26 +0800
Subject: tracing: Remove TRACE_EVENT_FL_FILTERED logic

After commit dcb0b5575d24 ("tracing: Remove TRACE_EVENT_FL_USE_CALL_FILTER
 logic"), no one's going to set the TRACE_EVENT_FL_FILTERED or change the
call->filter, so remove related logic.

Link: https://lore.kernel.org/20240911010026.2302849-1-zhengyejian@huaweicloud.com
Signed-off-by: Zheng Yejian <zhengyejian@huaweicloud.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/trace_events.h         |  4 ----
 kernel/trace/trace.c                 | 44 ++++++++----------------------------
 kernel/trace/trace.h                 |  4 ----
 kernel/trace/trace_branch.c          |  4 +---
 kernel/trace/trace_events.c          |  2 --
 kernel/trace/trace_functions_graph.c |  8 ++-----
 kernel/trace/trace_hwlat.c           |  4 +---
 kernel/trace/trace_mmiotrace.c       |  8 ++-----
 kernel/trace/trace_osnoise.c         | 12 +++-------
 kernel/trace/trace_sched_wakeup.c    |  8 ++-----
 10 files changed, 20 insertions(+), 78 deletions(-)

(limited to 'kernel/trace/trace_functions_graph.c')

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 42bedcddd511..f8f2e52653df 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -326,7 +326,6 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
 void trace_event_buffer_commit(struct trace_event_buffer *fbuffer);
 
 enum {
-	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
 	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
 	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
@@ -341,7 +340,6 @@ enum {
 
 /*
  * Event flags:
- *  FILTERED	  - The event has a filter attached
  *  CAP_ANY	  - Any user can enable for perf
  *  NO_SET_FILTER - Set when filter has error and is to be ignored
  *  IGNORE_ENABLE - For trace internal events, do not enable with debugfs file
@@ -356,7 +354,6 @@ enum {
  *                   to a tracepoint yet, then it is cleared when it is.
  */
 enum {
-	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
 	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
 	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
@@ -381,7 +378,6 @@ struct trace_event_call {
 	};
 	struct trace_event	event;
 	char			*print_fmt;
-	struct event_filter	*filter;
 	/*
 	 * Static events can disappear with modules,
 	 * where as dynamic ones need their own ref count.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1c69ca1f1088..bdb776e6ceb9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -593,19 +593,6 @@ int tracing_check_open_get_tr(struct trace_array *tr)
 	return 0;
 }
 
-int call_filter_check_discard(struct trace_event_call *call, void *rec,
-			      struct trace_buffer *buffer,
-			      struct ring_buffer_event *event)
-{
-	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
-	    !filter_match_preds(call->filter, rec)) {
-		__trace_event_discard_commit(buffer, event);
-		return 1;
-	}
-
-	return 0;
-}
-
 /**
  * trace_find_filtered_pid - check if a pid exists in a filtered_pid list
  * @filtered_pids: The list of pids to check
@@ -2889,7 +2876,6 @@ void
 trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 	       parent_ip, unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_function;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
@@ -2902,11 +2888,9 @@ trace_function(struct trace_array *tr, unsigned long ip, unsigned long
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		if (static_branch_unlikely(&trace_function_exports_enabled))
-			ftrace_exports(event, TRACE_EXPORT_FUNCTION);
-		__buffer_unlock_commit(buffer, event);
-	}
+	if (static_branch_unlikely(&trace_function_exports_enabled))
+		ftrace_exports(event, TRACE_EXPORT_FUNCTION);
+	__buffer_unlock_commit(buffer, event);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -2932,7 +2916,6 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 				 unsigned int trace_ctx,
 				 int skip, struct pt_regs *regs)
 {
-	struct trace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	unsigned int size, nr_entries;
 	struct ftrace_stack *fstack;
@@ -2986,8 +2969,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer,
 	memcpy(&entry->caller, fstack->calls,
 	       flex_array_size(entry, caller, nr_entries));
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		__buffer_unlock_commit(buffer, event);
+	__buffer_unlock_commit(buffer, event);
 
  out:
 	/* Again, don't let gcc optimize things here */
@@ -3060,7 +3042,6 @@ static void
 ftrace_trace_userstack(struct trace_array *tr,
 		       struct trace_buffer *buffer, unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
 
@@ -3094,8 +3075,7 @@ ftrace_trace_userstack(struct trace_array *tr,
 	memset(&entry->caller, 0, sizeof(entry->caller));
 
 	stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		__buffer_unlock_commit(buffer, event);
+	__buffer_unlock_commit(buffer, event);
 
  out_drop_count:
 	__this_cpu_dec(user_stack_count);
@@ -3264,7 +3244,6 @@ static void trace_printk_start_stop_comm(int enabled)
  */
 int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
-	struct trace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer;
 	struct trace_array *tr = READ_ONCE(printk_trace);
@@ -3308,10 +3287,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
-	}
+	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
 
 out:
 	ring_buffer_nest_end(buffer);
@@ -3331,7 +3308,6 @@ static int
 __trace_array_vprintk(struct trace_buffer *buffer,
 		      unsigned long ip, const char *fmt, va_list args)
 {
-	struct trace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	int len = 0, size;
 	struct print_entry *entry;
@@ -3366,10 +3342,8 @@ __trace_array_vprintk(struct trace_buffer *buffer,
 	entry->ip = ip;
 
 	memcpy(&entry->buf, tbuffer, len + 1);
-	if (!call_filter_check_discard(call, entry, buffer, event)) {
-		__buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
-	}
+	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
 
 out:
 	ring_buffer_nest_end(buffer);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c866991b9c78..638f452eec10 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1429,10 +1429,6 @@ struct trace_subsystem_dir {
 	int				nr_events;
 };
 
-extern int call_filter_check_discard(struct trace_event_call *call, void *rec,
-				     struct trace_buffer *buffer,
-				     struct ring_buffer_event *event);
-
 void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 				     struct trace_buffer *buffer,
 				     struct ring_buffer_event *event,
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index aa63548873c3..6d08a5523ce0 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -30,7 +30,6 @@ static struct trace_array *branch_tracer;
 static void
 probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 {
-	struct trace_event_call *call = &event_branch;
 	struct trace_array *tr = branch_tracer;
 	struct trace_buffer *buffer;
 	struct trace_array_cpu *data;
@@ -80,8 +79,7 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 	entry->line = f->data.line;
 	entry->correct = val == expect;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 
  out:
 	current->trace_recursion &= ~TRACE_BRANCH_BIT;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 7266ec2a4eea..77e68efbd43e 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -3149,8 +3149,6 @@ static void __trace_remove_event_call(struct trace_event_call *call)
 {
 	event_remove(call);
 	trace_destroy_fields(call);
-	free_event_filter(call->filter);
-	call->filter = NULL;
 }
 
 static int probe_remove_event_call(struct trace_event_call *call)
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index a569daaac4c4..ab57ec78ca04 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -102,7 +102,6 @@ int __trace_graph_entry(struct trace_array *tr,
 				struct ftrace_graph_ent *trace,
 				unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_funcgraph_entry;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ftrace_graph_ent_entry *entry;
@@ -113,8 +112,7 @@ int __trace_graph_entry(struct trace_array *tr,
 		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 
 	return 1;
 }
@@ -223,7 +221,6 @@ void __trace_graph_return(struct trace_array *tr,
 				struct ftrace_graph_ret *trace,
 				unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_funcgraph_exit;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ftrace_graph_ret_entry *entry;
@@ -234,8 +231,7 @@ void __trace_graph_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace,
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 3bd6071441ad..b65353ec2837 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -130,7 +130,6 @@ static bool hwlat_busy;
 static void trace_hwlat_sample(struct hwlat_sample *sample)
 {
 	struct trace_array *tr = hwlat_trace;
-	struct trace_event_call *call = &event_hwlat;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct hwlat_entry *entry;
@@ -148,8 +147,7 @@ static void trace_hwlat_sample(struct hwlat_sample *sample)
 	entry->nmi_count		= sample->nmi_count;
 	entry->count			= sample->count;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /* Macros to encapsulate the time capturing infrastructure */
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 64e77b513697..ba5858866b2f 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -294,7 +294,6 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_rw *rw)
 {
-	struct trace_event_call *call = &event_mmiotrace_rw;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_rw *entry;
@@ -310,8 +309,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->rw			= *rw;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 void mmio_trace_rw(struct mmiotrace_rw *rw)
@@ -325,7 +323,6 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_map *map)
 {
-	struct trace_event_call *call = &event_mmiotrace_map;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_map *entry;
@@ -341,8 +338,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 	entry	= ring_buffer_event_data(event);
 	entry->map			= *map;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 void mmio_trace_mapping(struct mmiotrace_map *map)
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index a50ed23bee77..b9f96c77527d 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -499,7 +499,6 @@ static void print_osnoise_headers(struct seq_file *s)
 static void
 __trace_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffer)
 {
-	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
 	struct osnoise_entry *entry;
 
@@ -517,8 +516,7 @@ __trace_osnoise_sample(struct osnoise_sample *sample, struct trace_buffer *buffe
 	entry->softirq_count	= sample->softirq_count;
 	entry->thread_count	= sample->thread_count;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /*
@@ -578,7 +576,6 @@ static void print_timerlat_headers(struct seq_file *s)
 static void
 __trace_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buffer)
 {
-	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
 	struct timerlat_entry *entry;
 
@@ -591,8 +588,7 @@ __trace_timerlat_sample(struct timerlat_sample *sample, struct trace_buffer *buf
 	entry->context			= sample->context;
 	entry->timer_latency		= sample->timer_latency;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /*
@@ -654,7 +650,6 @@ static void timerlat_save_stack(int skip)
 static void
 __timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, unsigned int size)
 {
-	struct trace_event_call *call = &event_osnoise;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 
@@ -668,8 +663,7 @@ __timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, u
 	memcpy(&entry->caller, fstack->calls, size);
 	entry->size = fstack->nr_entries;
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
 /*
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index ae2ace5e515a..d6c7f18daa15 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -378,7 +378,6 @@ tracing_sched_switch_trace(struct trace_array *tr,
 			   struct task_struct *next,
 			   unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_context_switch;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
@@ -396,8 +395,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_state		= task_state_index(next);
 	entry->next_cpu	= task_cpu(next);
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 static void
@@ -406,7 +404,6 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 			   struct task_struct *curr,
 			   unsigned int trace_ctx)
 {
-	struct trace_event_call *call = &event_wakeup;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
@@ -424,8 +421,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_state		= task_state_index(wakee);
 	entry->next_cpu			= task_cpu(wakee);
 
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
+	trace_buffer_unlock_commit(tr, buffer, event, trace_ctx);
 }
 
 static void notrace
-- 
cgit v1.2.3


From 0a6c61bc9c636e9a32d9f5a4d6d3b031d08763ab Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 10 Oct 2024 23:59:09 +0900
Subject: fgraph: Simplify return address printing in function graph tracer

Simplify return address printing in the function graph tracer by removing
fgraph_extras. Since this feature is only used by the function graph
tracer and the feature flags can directly accessible from the function
graph tracer, fgraph_extras can be removed from the fgraph callback.

Cc: Donglin Peng <dolinux.peng@gmail.com>
Link: https://lore.kernel.org/172857234900.270774.15378354017601069781.stgit@devnote2
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ftrace.h               | 16 +++----------
 kernel/trace/fgraph.c                | 45 +++++++++++++++++++++++-------------
 kernel/trace/ftrace.c                |  3 +--
 kernel/trace/trace.h                 |  3 +--
 kernel/trace/trace_functions_graph.c | 18 +++++++--------
 kernel/trace/trace_irqsoff.c         |  3 +--
 kernel/trace/trace_sched_wakeup.c    |  3 +--
 kernel/trace/trace_selftest.c        |  8 +++----
 8 files changed, 48 insertions(+), 51 deletions(-)

(limited to 'kernel/trace/trace_functions_graph.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 2ac3b3b53cd0..4c7dd5e58c9f 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1068,29 +1068,20 @@ 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 *,
-				      struct fgraph_extras *); /* entry */
+				      struct fgraph_ops *); /* entry */
 
 extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
-				   struct fgraph_ops *gops,
-				   struct fgraph_extras *extras);
+				   struct fgraph_ops *gops);
 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;
@@ -1131,13 +1122,12 @@ function_graph_enter(unsigned long ret, unsigned long func,
 
 struct ftrace_ret_stack *
 ftrace_graph_get_ret_stack(struct task_struct *task, int skip);
+unsigned long ftrace_graph_top_ret_addr(struct task_struct *task);
 
 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
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 27e523f01ed2..ee829d65f301 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -290,8 +290,7 @@ 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,
-		     struct fgraph_extras *extras)
+static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops)
 {
 	return 0;
 }
@@ -519,8 +518,7 @@ 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_extras *extras)
+			    struct fgraph_ops *gops)
 {
 	return 0;
 }
@@ -648,20 +646,13 @@ 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;
@@ -670,7 +661,7 @@ 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, &extras))
+		if (static_call(fgraph_func)(&trace, fgraph_direct_gops))
 			bitmap |= BIT(fgraph_direct_gops->idx);
 		else
 			/* Clear out any saved storage */
@@ -688,7 +679,7 @@ 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, &extras))
+			    gops->entryfunc(&trace, gops))
 				bitmap |= BIT(i);
 			else
 				/* Clear out any saved storage */
@@ -905,6 +896,29 @@ ftrace_graph_get_ret_stack(struct task_struct *task, int idx)
 	return ret_stack;
 }
 
+/**
+ * ftrace_graph_top_ret_addr - return the top return address in the shadow stack
+ * @task: The task to read the shadow stack from.
+ *
+ * Return the first return address on the shadow stack of the @task, which is
+ * not the fgraph's return_to_handler.
+ */
+unsigned long ftrace_graph_top_ret_addr(struct task_struct *task)
+{
+	unsigned long return_handler = (unsigned long)dereference_kernel_function_descriptor(return_to_handler);
+	struct ftrace_ret_stack *ret_stack = NULL;
+	int offset = task->curr_ret_stack;
+
+	if (offset < 0)
+		return 0;
+
+	do {
+		ret_stack = get_ret_stack(task, offset, &offset);
+	} while (ret_stack && ret_stack->ret == return_handler);
+
+	return ret_stack ? ret_stack->ret : 0;
+}
+
 /**
  * ftrace_graph_ret_addr - return the original value of the return address
  * @task: The task the unwinder is being executed on
@@ -1145,8 +1159,7 @@ 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_extras *extras)
+			   struct fgraph_ops *gops)
 {
 	struct trace_array *tr = gops->ops.private;
 	int pid;
@@ -1160,7 +1173,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace,
 			return 0;
 	}
 
-	return gops->saved_func(trace, gops, NULL);
+	return gops->saved_func(trace, gops);
 }
 
 void fgraph_update_pid_func(void)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 5d87dac83b80..cae388122ca8 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -827,8 +827,7 @@ struct profile_fgraph_data {
 };
 
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops,
-			       struct fgraph_extras *extras)
+			       struct fgraph_ops *gops)
 {
 	struct profile_fgraph_data *profile_data;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 13f08f257c0b..6adf48ef4312 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -695,8 +695,7 @@ 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,
-		      struct fgraph_extras *extras);
+int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3dd63ae2afe8..20d0c579d3b5 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -90,9 +90,9 @@ static struct tracer_flags tracer_flags = {
 	.opts = trace_opts
 };
 
-u32 graph_tracer_flags_get(u32 flags)
+static bool tracer_flags_is_set(u32 flags)
 {
-	return tracer_flags.val & flags;
+	return (tracer_flags.val & flags) == flags;
 }
 
 /*
@@ -179,8 +179,7 @@ struct fgraph_times {
 };
 
 int trace_graph_entry(struct ftrace_graph_ent *trace,
-		      struct fgraph_ops *gops,
-		      struct fgraph_extras *extras)
+		      struct fgraph_ops *gops)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
@@ -246,11 +245,12 @@ int trace_graph_entry(struct ftrace_graph_ent *trace,
 	disabled = atomic_inc_return(&data->disabled);
 	if (likely(disabled == 1)) {
 		trace_ctx = tracing_gen_ctx_flags(flags);
-		if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) && extras
-				&& (extras->flags & TRACE_GRAPH_PRINT_RETADDR)))
-			ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx,
-							  extras->retaddr);
-		else
+		if (unlikely(IS_ENABLED(CONFIG_FUNCTION_GRAPH_RETADDR) &&
+			tracer_flags_is_set(TRACE_GRAPH_PRINT_RETADDR))) {
+			unsigned long retaddr = ftrace_graph_top_ret_addr(current);
+
+			ret = __trace_graph_retaddr_entry(tr, trace, trace_ctx, retaddr);
+		} else
 			ret = __trace_graph_entry(tr, trace, trace_ctx);
 	} else {
 		ret = 0;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index eb3aa36cf10f..fce064e20570 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -176,8 +176,7 @@ static int irqsoff_display_graph(struct trace_array *tr, int set)
 }
 
 static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops,
-			       struct fgraph_extras *extras)
+			       struct fgraph_ops *gops)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 155de2551507..ae2ace5e515a 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -113,8 +113,7 @@ static int wakeup_display_graph(struct trace_array *tr, int set)
 }
 
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops,
-			      struct fgraph_extras *extras)
+			      struct fgraph_ops *gops)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index fbb99f8c8062..d3a14ae47e26 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -774,8 +774,7 @@ struct fgraph_fixture {
 };
 
 static __init int store_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops,
-			      struct fgraph_extras *extras)
+			      struct fgraph_ops *gops)
 {
 	struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops);
 	const char *type = fixture->store_type_name;
@@ -1026,8 +1025,7 @@ static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
 static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
-				      struct fgraph_ops *gops,
-				      struct fgraph_extras *extras)
+				      struct fgraph_ops *gops)
 {
 	/* This is harmlessly racy, we want to approximately detect a hang */
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
@@ -1041,7 +1039,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
 		return 0;
 	}
 
-	return trace_graph_entry(trace, gops, NULL);
+	return trace_graph_entry(trace, gops);
 }
 
 static struct fgraph_ops fgraph_ops __initdata  = {
-- 
cgit v1.2.3


From c73eb02a4781aee53ee4122132967356361e4f1a Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 10 Oct 2024 19:40:20 -0400
Subject: fgragh: No need to invoke the function call_filter_check_discard()

The function call_filter_check_discard() has been removed in the
commit 49e4154f4b16 ("tracing: Remove TRACE_EVENT_FL_FILTERED logic"),
from another topic branch. But when merged together with commit
21e92806d39c6 ("function_graph: Support recording and printing the
function return address") which added another call to
call_filter_check_discard(), it caused the build to fail. Since the
function call_filter_check_discard() is useless, it can simply be removed
regardless of being merged with commit 49e4154f4b16 or not.

Link: https://lore.kernel.org/all/20241010134649.43ed357c@canb.auug.org.au/

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Donglin Peng <dolinux.peng@gmail.com>
Link: https://lore.kernel.org/20241010194020.46192b21@gandalf.local.home
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 21e92806d39c6 ("function_graph: Support recording and printing the function return address")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'kernel/trace/trace_functions_graph.c')

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 20d0c579d3b5..03c5a0d300a5 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -137,7 +137,6 @@ int __trace_graph_retaddr_entry(struct trace_array *tr,
 				unsigned int trace_ctx,
 				unsigned long retaddr)
 {
-	struct trace_event_call *call = &event_fgraph_retaddr_entry;
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
 	struct fgraph_retaddr_ent_entry *entry;
@@ -150,8 +149,7 @@ int __trace_graph_retaddr_entry(struct trace_array *tr,
 	entry->graph_ent.func = trace->func;
 	entry->graph_ent.depth = trace->depth;
 	entry->graph_ent.retaddr = retaddr;
-	if (!call_filter_check_discard(call, entry, buffer, event))
-		trace_buffer_unlock_commit_nostack(buffer, event);
+	trace_buffer_unlock_commit_nostack(buffer, event);
 
 	return 1;
 }
-- 
cgit v1.2.3