ftrace: add stack tracer

This is another tracer using the ftrace infrastructure, that examines
at each function call the size of the stack. If the stack use is greater
than the previous max it is recorded.

You can always see (and set) the max stack size seen. By setting it
to zero will start the recording again. The backtrace is also available.

For example:

# cat /debug/tracing/stack_max_size
1856

# cat /debug/tracing/stack_trace
[<c027764d>] stack_trace_call+0x8f/0x101
[<c021b966>] ftrace_call+0x5/0x8
[<c02553cc>] clocksource_get_next+0x12/0x48
[<c02542a5>] update_wall_time+0x538/0x6d1
[<c0245913>] do_timer+0x23/0xb0
[<c0257657>] tick_do_update_jiffies64+0xd9/0xf1
[<c02576b9>] tick_sched_timer+0x4a/0xad
[<c0250fe6>] __run_hrtimer+0x3e/0x75
[<c02518ed>] hrtimer_interrupt+0xf1/0x154
[<c022c870>] smp_apic_timer_interrupt+0x71/0x84
[<c021b7e9>] apic_timer_interrupt+0x2d/0x34
[<c0238597>] finish_task_switch+0x29/0xa0
[<c05abd13>] schedule+0x765/0x7be
[<c05abfca>] schedule_timeout+0x1b/0x90
[<c05ab4d4>] wait_for_common+0xab/0x101
[<c05ab5ac>] wait_for_completion+0x12/0x14
[<c033cfc3>] blk_execute_rq+0x84/0x99
[<c0402470>] scsi_execute+0xc2/0x105
[<c040250a>] scsi_execute_req+0x57/0x7f
[<c043afe0>] sr_test_unit_ready+0x3e/0x97
[<c043bbd6>] sr_media_change+0x43/0x205
[<c046b59f>] media_changed+0x48/0x77
[<c046b5ff>] cdrom_media_changed+0x31/0x37
[<c043b091>] sr_block_media_changed+0x16/0x18
[<c02b9e69>] check_disk_change+0x1b/0x63
[<c046f4c3>] cdrom_open+0x7a1/0x806
[<c043b148>] sr_block_open+0x78/0x8d
[<c02ba4c0>] do_open+0x90/0x257
[<c02ba869>] blkdev_open+0x2d/0x56
[<c0296a1f>] __dentry_open+0x14d/0x23c
[<c0296b32>] nameidata_to_filp+0x24/0x38
[<c02a1c68>] do_filp_open+0x347/0x626
[<c02967ef>] do_sys_open+0x47/0xbc
[<c02968b0>] sys_open+0x23/0x2b
[<c021aadd>] sysenter_do_call+0x12/0x26

I've tested this on both x86_64 and i386.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 254 insertions, 0 deletions

diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
new file mode 100644
index 00000000000..4d1e522e3fe
--- /dev/null
+++ b/kernel/trace/trace_stack.c
@@ -0,0 +1,254 @@
+/*
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/stacktrace.h>
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include "trace.h"
+
+#define STACK_TRACE_ENTRIES 500
+
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES] =
+	{ [0 ... (STACK_TRACE_ENTRIES-1)] = ULONG_MAX };
+static struct stack_trace max_stack_trace = {
+	.max_entries		= STACK_TRACE_ENTRIES,
+	.entries		= stack_dump_trace,
+};
+
+static unsigned long max_stack_size;
+static raw_spinlock_t max_stack_lock =
+	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+
+static int stack_trace_disabled __read_mostly;
+static DEFINE_PER_CPU(int, trace_active);
+
+static inline void check_stack(void)
+{
+	unsigned long this_size;
+	unsigned long flags;
+
+	this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1);
+	this_size = THREAD_SIZE - this_size;
+
+	if (this_size <= max_stack_size)
+		return;
+
+	raw_local_irq_save(flags);
+	__raw_spin_lock(&max_stack_lock);
+
+	/* a race could have already updated it */
+	if (this_size <= max_stack_size)
+		goto out;
+
+	max_stack_size = this_size;
+
+	max_stack_trace.nr_entries	= 0;
+	max_stack_trace.skip		= 1;
+
+	save_stack_trace(&max_stack_trace);
+
+ out:
+	__raw_spin_unlock(&max_stack_lock);
+	raw_local_irq_restore(flags);
+}
+
+static void
+stack_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+	int cpu, resched;
+
+	if (unlikely(!ftrace_enabled || stack_trace_disabled))
+		return;
+
+	resched = need_resched();
+	preempt_disable_notrace();
+
+	cpu = raw_smp_processor_id();
+	/* no atomic needed, we only modify this variable by this cpu */
+	if (per_cpu(trace_active, cpu)++ != 0)
+		goto out;
+
+	check_stack();
+
+ out:
+	per_cpu(trace_active, cpu)--;
+	/* prevent recursion in schedule */
+	if (resched)
+		preempt_enable_no_resched_notrace();
+	else
+		preempt_enable_notrace();
+}
+
+static struct ftrace_ops trace_ops __read_mostly =
+{
+	.func = stack_trace_call,
+};
+
+static ssize_t
+stack_max_size_read(struct file *filp, char __user *ubuf,
+		    size_t count, loff_t *ppos)
+{
+	unsigned long *ptr = filp->private_data;
+	char buf[64];
+	int r;
+
+	r = snprintf(buf, sizeof(buf), "%ld\n", *ptr);
+	if (r > sizeof(buf))
+		r = sizeof(buf);
+	return simple_read_from_buffer(ubuf, count, ppos, buf, r);
+}
+
+static ssize_t
+stack_max_size_write(struct file *filp, const char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	long *ptr = filp->private_data;
+	unsigned long val, flags;
+	char buf[64];
+	int ret;
+
+	if (count >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, count))
+		return -EFAULT;
+
+	buf[count] = 0;
+
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	raw_local_irq_save(flags);
+	__raw_spin_lock(&max_stack_lock);
+	*ptr = val;
+	__raw_spin_unlock(&max_stack_lock);
+	raw_local_irq_restore(flags);
+
+	return count;
+}
+
+static struct file_operations stack_max_size_fops = {
+	.open		= tracing_open_generic,
+	.read		= stack_max_size_read,
+	.write		= stack_max_size_write,
+};
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	unsigned long *t = m->private;
+
+	(*pos)++;
+
+	if (!t || *t == ULONG_MAX)
+		return NULL;
+
+	t++;
+	m->private = t;
+
+	return t;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	unsigned long *t = m->private;
+	loff_t l = 0;
+
+	local_irq_disable();
+	__raw_spin_lock(&max_stack_lock);
+
+	for (; t && l < *pos; t = t_next(m, t, &l))
+		;
+
+	return t;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+	__raw_spin_unlock(&max_stack_lock);
+	local_irq_enable();
+}
+
+static int trace_lookup_stack(struct seq_file *m, unsigned long addr)
+{
+#ifdef CONFIG_KALLSYMS
+	char str[KSYM_SYMBOL_LEN];
+
+	sprint_symbol(str, addr);
+
+	return seq_printf(m, "[<%p>] %s\n", (void*)addr, str);
+#else
+	return seq_printf(m, "%p\n", (void*)addr);
+#endif
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+	unsigned long *t = v;
+
+	if (!t || *t == ULONG_MAX)
+		return 0;
+
+	trace_lookup_stack(m, *t);
+
+	return 0;
+}
+
+static struct seq_operations stack_trace_seq_ops = {
+	.start		= t_start,
+	.next		= t_next,
+	.stop		= t_stop,
+	.show		= t_show,
+};
+
+static int stack_trace_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = seq_open(file, &stack_trace_seq_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = stack_dump_trace;
+	}
+
+	return ret;
+}
+
+static struct file_operations stack_trace_fops = {
+	.open		= stack_trace_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+static __init int stack_trace_init(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+
+	entry = debugfs_create_file("stack_max_size", 0644, d_tracer,
+				    &max_stack_size, &stack_max_size_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs 'stack_max_size' entry\n");
+
+	entry = debugfs_create_file("stack_trace", 0444, d_tracer,
+				    NULL, &stack_trace_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs 'stack_trace' entry\n");
+
+	register_ftrace_function(&trace_ops);
+
+	return 0;
+}
+
+device_initcall(stack_trace_init);