[RFC 2/3] arm64: refactor save_stack_trace()

[Steven Rostedt]

Here's the patch I now have in my local repo, and plan on pushing to my
repo on korg.

-- Steve

From d21f02a45fa367beaf97b153aa29849c06ac5609 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt at goodmis.org>
Date: Thu, 16 Jul 2015 13:24:54 -0400
Subject: [PATCH] tracing: Clean up stack tracing and fix fentry updates

Akashi Takahiro was porting the stack tracer to arm64 and found some
issues with it. One was that it repeats the top function, due to the
stack frame added by the mcount caller and added by itself. This
was added when fentry came in, and before fentry created its own stack
frame. But x86's fentry now creates its own stack frame, and there's
no need to insert the function again.

This also cleans up the code a bit, where it doesn't need to do something
special for fentry, and doesn't include insertion of a duplicate
entry for the called function being traced.

Link: http://lkml.kernel.org/r/55A646EE.6030402@linaro.org

Some-Suggestions-by: Jungseok Lee <jungseoklee85 at gmail.com>
Reported-by: AKASHI Takahiro <takahiro.akashi at linaro.org>
Signed-off-by: Steven Rostedt <rostedt at goodmis.org>
---
 kernel/trace/trace_stack.c | 62 ++++++++++++++--------------------------------
 1 file changed, 19 insertions(+), 43 deletions(-)

diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 3f34496244e9..e615cdc9e38a 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -18,12 +18,6 @@
 
 #define STACK_TRACE_ENTRIES 500
 
-#ifdef CC_USING_FENTRY
-# define fentry		1
-#else
-# define fentry		0
-#endif
-
 static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
 	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
 static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
@@ -35,7 +29,7 @@ static unsigned stack_dump_index[STACK_TRACE_ENTRIES];
  */
 static struct stack_trace max_stack_trace = {
 	.max_entries		= STACK_TRACE_ENTRIES - 1,
-	.entries		= &stack_dump_trace[1],
+	.entries		= &stack_dump_trace[0],
 };
 
 static unsigned long max_stack_size;
@@ -77,7 +71,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 	unsigned long this_size, flags; unsigned long *p, *top, *start;
 	static int tracer_frame;
 	int frame_size = ACCESS_ONCE(tracer_frame);
-	int i;
+	int i, x;
 
 	this_size = ((unsigned long)stack) & (THREAD_SIZE-1);
 	this_size = THREAD_SIZE - this_size;
@@ -105,26 +99,20 @@ check_stack(unsigned long ip, unsigned long *stack)
 	max_stack_size = this_size;
 
 	max_stack_trace.nr_entries = 0;
-
-	if (using_ftrace_ops_list_func())
-		max_stack_trace.skip = 4;
-	else
-		max_stack_trace.skip = 3;
+	max_stack_trace.skip = 3;
 
 	save_stack_trace(&max_stack_trace);
 
-	/*
-	 * Add the passed in ip from the function tracer.
-	 * Searching for this on the stack will skip over
-	 * most of the overhead from the stack tracer itself.
-	 */
-	stack_dump_trace[0] = ip;
-	max_stack_trace.nr_entries++;
+	/* Skip over the overhead of the stack tracer itself */
+	for (i = 0; i < max_stack_trace.nr_entries; i++) {
+		if (stack_dump_trace[i] == ip)
+			break;
+	}
 
 	/*
 	 * Now find where in the stack these are.
 	 */
-	i = 0;
+	x = 0;
 	start = stack;
 	top = (unsigned long *)
 		(((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE);
@@ -139,12 +127,13 @@ check_stack(unsigned long ip, unsigned long *stack)
 	while (i < max_stack_trace.nr_entries) {
 		int found = 0;
 
-		stack_dump_index[i] = this_size;
+		stack_dump_index[x] = this_size;
 		p = start;
 
 		for (; p < top && i < max_stack_trace.nr_entries; p++) {
 			if (*p == stack_dump_trace[i]) {
-				this_size = stack_dump_index[i++] =
+				stack_dump_trace[x] = stack_dump_trace[i++];
+				this_size = stack_dump_index[x++] =
 					(top - p) * sizeof(unsigned long);
 				found = 1;
 				/* Start the search from here */
@@ -168,6 +157,10 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
+	max_stack_trace.nr_entries = x;
+	for (; x < i; x++)
+		stack_dump_trace[x] = ULONG_MAX;
+
 	if (task_stack_end_corrupted(current)) {
 		print_max_stack();
 		BUG();
@@ -192,24 +185,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (per_cpu(trace_active, cpu)++ != 0)
 		goto out;
 
-	/*
-	 * When fentry is used, the traced function does not get
-	 * its stack frame set up, and we lose the parent.
-	 * The ip is pretty useless because the function tracer
-	 * was called before that function set up its stack frame.
-	 * In this case, we use the parent ip.
-	 *
-	 * By adding the return address of either the parent ip
-	 * or the current ip we can disregard most of the stack usage
-	 * caused by the stack tracer itself.
-	 *
-	 * The function tracer always reports the address of where the
-	 * mcount call was, but the stack will hold the return address.
-	 */
-	if (fentry)
-		ip = parent_ip;
-	else
-		ip += MCOUNT_INSN_SIZE;
+	ip += MCOUNT_INSN_SIZE;
 
 	check_stack(ip, &stack);
 
@@ -284,7 +260,7 @@ __next(struct seq_file *m, loff_t *pos)
 {
 	long n = *pos - 1;
 
-	if (n >= max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+	if (n > max_stack_trace.nr_entries || stack_dump_trace[n] == ULONG_MAX)
 		return NULL;
 
 	m->private = (void *)n;
@@ -354,7 +330,7 @@ static int t_show(struct seq_file *m, void *v)
 		seq_printf(m, "        Depth    Size   Location"
 			   "    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   max_stack_trace.nr_entries - 1);
+			   max_stack_trace.nr_entries);
 
 		if (!stack_tracer_enabled && !max_stack_size)
 			print_disabled(m);
-- 
1.8.3.1