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 <[email protected]>
Cc: Mathieu Desnoyers <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Jiri Olsa <[email protected]>
Link: https://lore.kernel.org/[email protected]
Acked-by: Masami Hiramatsu (Google) <[email protected]>
Signed-off-by: Steven Rostedt (Google) <[email protected]>

Author: rostedt

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

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;
 	/*

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;

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();
@@ -297,17 +310,26 @@ 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)) {
 		trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT);
 		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);