[PATCH] stacktrace: add /proc/<pid>/stack to dump task's stack trace

[Ken Chen]

Impact: add the new (root-only) /proc/<pid>/stack debug facility

This patch adds the ability to query a task's current stack trace via
/proc/<pid>/stack.

It is considered to be more useful than /proc/pid/wchan as it provides
full stack trace instead of single depth.

It is also more useful than sysrq-t because it does not overflow the
dmesg like sysrq-t often does, can be read in a finegrained per-task
way and can be read programmatically as well.

It works on sleeping and running tasks as well.

Also, move up PROC_BLOCK_SIZE a bit so that proc_pid_stack() can use it.

[ mingo@xxxxxxx: small cleanups, comments ]

Signed-off-by: Ken Chen <kenchen@xxxxxxxxxx>
Acked-by: Alexey Dobriyan <adobriyan@xxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
---
 Documentation/filesystems/proc.txt |    1 +
 fs/proc/base.c                     |   52 ++++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index bcceb99..11f5b75 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -139,6 +139,7 @@ Table 1-1: Process specific entries in /proc
  statm		Process memory status information
  status		Process status in human readable form
  wchan		If CONFIG_KALLSYMS is set, a pre-decoded wchan
+ stack		Report full stack trace, enable via CONFIG_STACKTRACE
  smaps		Extension based on maps, the rss size for each mapped file
 ..............................................................................
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 486cf3f..805e514 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -65,6 +65,7 @@
 #include <linux/mm.h>
 #include <linux/rcupdate.h>
 #include <linux/kallsyms.h>
+#include <linux/stacktrace.h>
 #include <linux/resource.h>
 #include <linux/module.h>
 #include <linux/mount.h>
@@ -130,6 +131,12 @@ struct pid_entry {
 		{ .proc_show = &proc_##OTYPE } )
 
 /*
+ * buffer size used for proc read.  See proc_info_read().
+ * 4K page size but our output routines use some slack for overruns
+ */
+#define PROC_BLOCK_SIZE	(3*1024)
+
+/*
  * Count the number of hardlinks for the pid_entry table, excluding the .
  * and .. links.
  */
@@ -340,6 +347,46 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
 }
 #endif /* CONFIG_KALLSYMS */
 
+#ifdef CONFIG_STACKTRACE
+
+#define MAX_STACK_TRACE_DEPTH	64
+
+static int proc_pid_stack(struct task_struct *task, char *buffer)
+{
+	struct stack_trace trace;
+	unsigned long *entries;
+	int i, len = 0;
+
+	entries = kmalloc(sizeof(*entries)*MAX_STACK_TRACE_DEPTH, GFP_KERNEL);
+	if (!entries)
+		return -ENOMEM;
+
+	trace.nr_entries	= 0;
+	trace.max_entries	= MAX_STACK_TRACE_DEPTH;
+	trace.entries		= entries;
+	trace.skip		= 0;
+
+	/*
+	 * Protect against the task exiting (and deallocating its
+	 * stack, etc.) while we save its backtrace:
+	 */
+	read_lock(&tasklist_lock);
+	save_stack_trace_tsk(task, &trace);
+	read_unlock(&tasklist_lock);
+
+	for (i = 0; i < trace.nr_entries; i++) {
+		len += snprintf(buffer + len, PROC_BLOCK_SIZE - len,
+				"[<%p>] %pS\n",
+				(void *)entries[i], (void *)entries[i]);
+		if (!len)
+			break;
+	}
+	kfree(entries);
+
+	return len;
+}
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 /*
  * Provides /proc/PID/schedstat
@@ -688,8 +735,6 @@ static const struct file_operations proc_mountstats_operations = {
 	.release	= mounts_release,
 };
 
-#define PROC_BLOCK_SIZE	(3*1024)		/* 4K page size but our output routines use some slack for overruns */
-
 static ssize_t proc_info_read(struct file * file, char __user * buf,
 			  size_t count, loff_t *ppos)
 {
@@ -2491,6 +2536,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_KALLSYMS
 	INF("wchan",      S_IRUGO, pid_wchan),
 #endif
+#ifdef CONFIG_STACKTRACE
+	INF("stack",      S_IRUSR, pid_stack),
+#endif
 #ifdef CONFIG_SCHEDSTATS
 	INF("schedstat",  S_IRUGO, pid_schedstat),
 #endif
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/