From: Steven Rostedt (Google) <rostedt@goodmis.org>
Date: Mon, 3 Jun 2024 19:07:29 +0000 (-0400)
Subject: function_graph: Use static_call and branch to optimize return function
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=fe835e3ca40e172aa8ad12f4ed2898c181fafab0;p=users%2Fdwmw2%2Flinux.git

function_graph: Use static_call and branch to optimize return function

In most cases function graph is used by a single user. Instead of calling
a loop to call function graph callbacks in this case, call the function
return callback directly.

Use the static_key that is set when the function graph tracer has less
than 2 callbacks registered. It will do the direct call in that case, and
will do the loop over all callers when there are 2 or more callbacks
registered.

Link: https://lore.kernel.org/linux-trace-kernel/20240603190824.921460797@goodmis.org

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: bpf <bpf@vger.kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Guo Ren <guoren@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 7c3b0261b1bbb..4bf91eebbb083 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -514,6 +514,7 @@ static struct fgraph_ops fgraph_stub = {
 
 static struct fgraph_ops *fgraph_direct_gops = &fgraph_stub;
 DEFINE_STATIC_CALL(fgraph_func, ftrace_graph_entry_stub);
+DEFINE_STATIC_CALL(fgraph_retfunc, ftrace_graph_ret_stub);
 DEFINE_STATIC_KEY_TRUE(fgraph_do_direct);
 
 /**
@@ -808,13 +809,21 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 
 	bitmap = get_bitmap_bits(current, offset);
 
-	for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) {
-		struct fgraph_ops *gops = fgraph_array[i];
+#ifdef CONFIG_HAVE_STATIC_CALL
+	if (static_branch_likely(&fgraph_do_direct)) {
+		if (test_bit(fgraph_direct_gops->idx, &bitmap))
+			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops);
+	} else
+#endif
+	{
+		for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) {
+			struct fgraph_ops *gops = fgraph_array[i];
 
-		if (gops == &fgraph_stub)
-			continue;
+			if (gops == &fgraph_stub)
+				continue;
 
-		gops->retfunc(&trace, gops);
+			gops->retfunc(&trace, gops);
+		}
 	}
 
 	/*
@@ -1232,17 +1241,20 @@ static void init_task_vars(int idx)
 static void ftrace_graph_enable_direct(bool enable_branch)
 {
 	trace_func_graph_ent_t func = NULL;
+	trace_func_graph_ret_t retfunc = NULL;
 	int i;
 
 	for_each_set_bit(i, &fgraph_array_bitmask,
 			 sizeof(fgraph_array_bitmask) * BITS_PER_BYTE) {
 		func = fgraph_array[i]->entryfunc;
+		retfunc = fgraph_array[i]->retfunc;
 		fgraph_direct_gops = fgraph_array[i];
 	 }
 	if (WARN_ON_ONCE(!func))
 		return;
 
 	static_call_update(fgraph_func, func);
+	static_call_update(fgraph_retfunc, retfunc);
 	if (enable_branch)
 		static_branch_disable(&fgraph_do_direct);
 }
@@ -1252,6 +1264,7 @@ static void ftrace_graph_disable_direct(bool disable_branch)
 	if (disable_branch)
 		static_branch_disable(&fgraph_do_direct);
 	static_call_update(fgraph_func, ftrace_graph_entry_stub);
+	static_call_update(fgraph_retfunc, ftrace_graph_ret_stub);
 	fgraph_direct_gops = &fgraph_stub;
 }