[for-next][PATCH 0/5] tracing/ftrace: Updates for 6.13

[for-next][PATCH 0/5] tracing/ftrace: Updates for 6.13

[Steven Rostedt]

  git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
ftrace/for-next

Head SHA1: f1f36e22bee967db5e812a65e24389e54c46f3c2


Masami Hiramatsu (Google) (2):
      tracing: Fix function timing profiler to initialize hashtable
      tracing: Add a comment about ftrace_regs definition

Steven Rostedt (3):
      fgraph: Use fgraph data to store subtime for profiler
      ftrace: Use a running sleeptime instead of saving on shadow stack
      ftrace: Have calltime be saved in the fgraph storage

----
 include/linux/ftrace.h               | 31 +++++++++++--
 include/linux/sched.h                |  1 +
 kernel/trace/fgraph.c                | 85 +++++++++++++++++++++---------------
 kernel/trace/ftrace.c                | 49 +++++++++++++++------
 kernel/trace/trace.h                 |  1 +
 kernel/trace/trace_functions_graph.c | 52 +++++++++++++++++++++-
 6 files changed, 167 insertions(+), 52 deletions(-)

[for-next][PATCH 1/5] tracing: Fix function timing profiler to initialize hashtable

[Steven Rostedt]

From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>

Since the new fgraph requires to initialize fgraph_ops.ops.func_hash before
calling register_ftrace_graph(), initialize it with default (tracing all
functions) parameter.

Cc: stable@vger.kernel.org
Fixes: 5fccc7552ccb ("ftrace: Add subops logic to allow one ops to manage many")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4c28dd177ca6..d2dd71d04b8a 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -883,6 +883,10 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 }
 
 static struct fgraph_ops fprofiler_ops = {
+	.ops = {
+		.flags = FTRACE_OPS_FL_INITIALIZED,
+		INIT_OPS_HASH(fprofiler_ops.ops)
+	},
 	.entryfunc = &profile_graph_entry,
 	.retfunc = &profile_graph_return,
 };
-- 
2.45.2

[for-next][PATCH 2/5] tracing: Add a comment about ftrace_regs definition

[Steven Rostedt]

From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>

To clarify what will be expected on ftrace_regs, add a comment to the
architecture independent definition of the ftrace_regs.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index fd5e84d0ec47..42106b3de396 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -117,6 +117,32 @@ extern int ftrace_enabled;
 
 #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
+/**
+ * ftrace_regs - ftrace partial/optimal register set
+ *
+ * ftrace_regs represents a group of registers which is used at the
+ * function entry and exit. There are three types of registers.
+ *
+ * - Registers for passing the parameters to callee, including the stack
+ *   pointer. (e.g. rcx, rdx, rdi, rsi, r8, r9 and rsp on x86_64)
+ * - Registers for passing the return values to caller.
+ *   (e.g. rax and rdx on x86_64)
+ * - Registers for hooking the function call and return including the
+ *   frame pointer (the frame pointer is architecture/config dependent)
+ *   (e.g. rip, rbp and rsp for x86_64)
+ *
+ * Also, architecture dependent fields can be used for internal process.
+ * (e.g. orig_ax on x86_64)
+ *
+ * On the function entry, those registers will be restored except for
+ * the stack pointer, so that user can change the function parameters
+ * and instruction pointer (e.g. live patching.)
+ * On the function exit, only registers which is used for return values
+ * are restored.
+ *
+ * NOTE: user *must not* access regs directly, only do it via APIs, because
+ * the member can be changed according to the architecture.
+ */
 struct ftrace_regs {
 	struct pt_regs		regs;
 };
-- 
2.45.2

[for-next][PATCH 3/5] fgraph: Use fgraph data to store subtime for profiler

[Steven Rostedt]

From: Steven Rostedt <rostedt@goodmis.org>

Instead of having the "subtime" for the function profiler in the
infrastructure ftrace_ret_stack structure, have it use the fgraph data
reserve and retrieve functions.

This will keep the limited shadow stack from wasting 8 bytes for something
that is seldom used.

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/20240914214826.780323141@goodmis.org
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  4 +--
 kernel/trace/fgraph.c  | 64 ++++++++++++++++++++++++++++++++----------
 kernel/trace/ftrace.c  | 23 +++++++--------
 3 files changed, 62 insertions(+), 29 deletions(-)

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 42106b3de396..aabd348cad4a 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1081,6 +1081,7 @@ struct fgraph_ops {
 
 void *fgraph_reserve_data(int idx, int size_bytes);
 void *fgraph_retrieve_data(int idx, int *size_bytes);
+void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth);
 
 /*
  * Stack of return addresses for functions
@@ -1091,9 +1092,6 @@ struct ftrace_ret_stack {
 	unsigned long ret;
 	unsigned long func;
 	unsigned long long calltime;
-#ifdef CONFIG_FUNCTION_PROFILER
-	unsigned long long subtime;
-#endif
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	unsigned long fp;
 #endif
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index d7d4fb403f6f..095ceb752b28 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -390,21 +390,7 @@ void *fgraph_reserve_data(int idx, int size_bytes)
  */
 void *fgraph_retrieve_data(int idx, int *size_bytes)
 {
-	int offset = current->curr_ret_stack - 1;
-	unsigned long val;
-
-	val = get_fgraph_entry(current, offset);
-	while (__get_type(val) == FGRAPH_TYPE_DATA) {
-		if (__get_data_index(val) == idx)
-			goto found;
-		offset -= __get_data_size(val) + 1;
-		val = get_fgraph_entry(current, offset);
-	}
-	return NULL;
-found:
-	if (size_bytes)
-		*size_bytes = __get_data_size(val) * sizeof(long);
-	return get_data_type_data(current, offset);
+	return fgraph_retrieve_parent_data(idx, size_bytes, 0);
 }
 
 /**
@@ -460,6 +446,54 @@ get_ret_stack(struct task_struct *t, int offset, int *frame_offset)
 	return RET_STACK(t, offset);
 }
 
+/**
+ * fgraph_retrieve_parent_data - get data from a parent function
+ * @idx: The index into the fgraph_array (fgraph_ops::idx)
+ * @size_bytes: A pointer to retrieved data size
+ * @depth: The depth to find the parent (0 is the current function)
+ *
+ * This is similar to fgraph_retrieve_data() but can be used to retrieve
+ * data from a parent caller function.
+ *
+ * Return: a pointer to the specified parent data or NULL if not found
+ */
+void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth)
+{
+	struct ftrace_ret_stack *ret_stack = NULL;
+	int offset = current->curr_ret_stack;
+	unsigned long val;
+
+	if (offset <= 0)
+		return NULL;
+
+	for (;;) {
+		int next_offset;
+
+		ret_stack = get_ret_stack(current, offset, &next_offset);
+		if (!ret_stack || --depth < 0)
+			break;
+		offset = next_offset;
+	}
+
+	if (!ret_stack)
+		return NULL;
+
+	offset--;
+
+	val = get_fgraph_entry(current, offset);
+	while (__get_type(val) == FGRAPH_TYPE_DATA) {
+		if (__get_data_index(val) == idx)
+			goto found;
+		offset -= __get_data_size(val) + 1;
+		val = get_fgraph_entry(current, offset);
+	}
+	return NULL;
+found:
+	if (size_bytes)
+		*size_bytes = __get_data_size(val) * sizeof(long);
+	return get_data_type_data(current, offset);
+}
+
 /* Both enabled by default (can be cleared by function_graph tracer flags */
 static bool fgraph_sleep_time = true;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d2dd71d04b8a..bac1f2ee1983 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -823,7 +823,7 @@ void ftrace_graph_graph_time_control(bool enable)
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
 			       struct fgraph_ops *gops)
 {
-	struct ftrace_ret_stack *ret_stack;
+	unsigned long long *subtime;
 
 	function_profile_call(trace->func, 0, NULL, NULL);
 
@@ -831,9 +831,9 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 	if (!current->ret_stack)
 		return 0;
 
-	ret_stack = ftrace_graph_get_ret_stack(current, 0);
-	if (ret_stack)
-		ret_stack->subtime = 0;
+	subtime = fgraph_reserve_data(gops->idx, sizeof(*subtime));
+	if (subtime)
+		*subtime = 0;
 
 	return 1;
 }
@@ -841,11 +841,12 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 static void profile_graph_return(struct ftrace_graph_ret *trace,
 				 struct fgraph_ops *gops)
 {
-	struct ftrace_ret_stack *ret_stack;
 	struct ftrace_profile_stat *stat;
 	unsigned long long calltime;
+	unsigned long long *subtime;
 	struct ftrace_profile *rec;
 	unsigned long flags;
+	int size;
 
 	local_irq_save(flags);
 	stat = this_cpu_ptr(&ftrace_profile_stats);
@@ -861,13 +862,13 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 	if (!fgraph_graph_time) {
 
 		/* Append this call time to the parent time to subtract */
-		ret_stack = ftrace_graph_get_ret_stack(current, 1);
-		if (ret_stack)
-			ret_stack->subtime += calltime;
+		subtime = fgraph_retrieve_parent_data(gops->idx, &size, 1);
+		if (subtime)
+			*subtime += calltime;
 
-		ret_stack = ftrace_graph_get_ret_stack(current, 0);
-		if (ret_stack && ret_stack->subtime < calltime)
-			calltime -= ret_stack->subtime;
+		subtime = fgraph_retrieve_data(gops->idx, &size);
+		if (subtime && *subtime && *subtime < calltime)
+			calltime -= *subtime;
 		else
 			calltime = 0;
 	}
-- 
2.45.2

[for-next][PATCH 4/5] ftrace: Use a running sleeptime instead of saving on shadow stack

[Steven Rostedt]

From: Steven Rostedt <rostedt@goodmis.org>

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>
---
 include/linux/sched.h                |  1 +
 kernel/trace/fgraph.c                | 16 ++----------
 kernel/trace/ftrace.c                | 39 ++++++++++++++++++++--------
 kernel/trace/trace.h                 |  1 +
 kernel/trace/trace_functions_graph.c | 28 ++++++++++++++++++++
 5 files changed, 60 insertions(+), 25 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e6ee4258169a..c08f3bdb11a5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1441,6 +1441,7 @@ struct task_struct {
 
 	/* Timestamp for last schedule: */
 	unsigned long long		ftrace_timestamp;
+	unsigned long long		ftrace_sleeptime;
 
 	/*
 	 * Number of functions that haven't been traced
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 095ceb752b28..b2e95bf82211 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -495,7 +495,7 @@ void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth)
 }
 
 /* Both enabled by default (can be cleared by function_graph tracer flags */
-static bool fgraph_sleep_time = true;
+bool fgraph_sleep_time = true;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 /*
@@ -1046,9 +1046,7 @@ ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 				struct task_struct *next,
 				unsigned int prev_state)
 {
-	struct ftrace_ret_stack *ret_stack;
 	unsigned long long timestamp;
-	int offset;
 
 	/*
 	 * Does the user want to count the time a function was asleep.
@@ -1065,17 +1063,7 @@ ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
 	if (!next->ftrace_timestamp)
 		return;
 
-	/*
-	 * Update all the counters in next to make up for the
-	 * time next was sleeping.
-	 */
-	timestamp -= next->ftrace_timestamp;
-
-	for (offset = next->curr_ret_stack; offset > 0; ) {
-		ret_stack = get_ret_stack(next, offset, &offset);
-		if (ret_stack)
-			ret_stack->calltime += timestamp;
-	}
+	next->ftrace_sleeptime += timestamp - next->ftrace_timestamp;
 }
 
 static DEFINE_PER_CPU(unsigned long *, idle_ret_stack);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bac1f2ee1983..90b3975d5315 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -820,10 +820,15 @@ void ftrace_graph_graph_time_control(bool enable)
 	fgraph_graph_time = enable;
 }
 
+struct profile_fgraph_data {
+	unsigned long long		subtime;
+	unsigned long long		sleeptime;
+};
+
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
 			       struct fgraph_ops *gops)
 {
-	unsigned long long *subtime;
+	struct profile_fgraph_data *profile_data;
 
 	function_profile_call(trace->func, 0, NULL, NULL);
 
@@ -831,9 +836,12 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 	if (!current->ret_stack)
 		return 0;
 
-	subtime = fgraph_reserve_data(gops->idx, sizeof(*subtime));
-	if (subtime)
-		*subtime = 0;
+	profile_data = fgraph_reserve_data(gops->idx, sizeof(*profile_data));
+	if (!profile_data)
+		return 0;
+
+	profile_data->subtime = 0;
+	profile_data->sleeptime = current->ftrace_sleeptime;
 
 	return 1;
 }
@@ -841,9 +849,10 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 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 *subtime;
 	struct ftrace_profile *rec;
 	unsigned long flags;
 	int size;
@@ -859,16 +868,24 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 
 	calltime = trace->rettime - trace->calltime;
 
+	if (!fgraph_sleep_time) {
+		profile_data = fgraph_retrieve_data(gops->idx, &size);
+		if (profile_data && current->ftrace_sleeptime)
+			calltime -= current->ftrace_sleeptime - profile_data->sleeptime;
+	}
+
 	if (!fgraph_graph_time) {
 
 		/* Append this call time to the parent time to subtract */
-		subtime = fgraph_retrieve_parent_data(gops->idx, &size, 1);
-		if (subtime)
-			*subtime += calltime;
+		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);
 
-		subtime = fgraph_retrieve_data(gops->idx, &size);
-		if (subtime && *subtime && *subtime < calltime)
-			calltime -= *subtime;
+		if (profile_data && profile_data->subtime && profile_data->subtime < calltime)
+			calltime -= profile_data->subtime;
 		else
 			calltime = 0;
 	}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c866991b9c78..2f8017f8d34d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1048,6 +1048,7 @@ static inline void ftrace_graph_addr_finish(struct fgraph_ops *gops, struct ftra
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 extern unsigned int fgraph_max_depth;
+extern bool fgraph_sleep_time;
 
 static inline bool
 ftrace_graph_ignore_func(struct fgraph_ops *gops, struct ftrace_graph_ent *trace)
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;
-- 
2.45.2

[for-next][PATCH 5/5] ftrace: Have calltime be saved in the fgraph storage

[Steven Rostedt]

From: Steven Rostedt <rostedt@goodmis.org>

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(-)

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);
-- 
2.45.2