proc: add /proc/*/stack

/proc/*/stack adds the ability to query a task's stack trace. It is more
useful than /proc/*/wchan as it provides full stack trace instead of single
depth. Example output:

	$ cat /proc/self/stack
	[<c010a271>] save_stack_trace_tsk+0x17/0x35
	[<c01827b4>] proc_pid_stack+0x4a/0x76
	[<c018312d>] proc_single_show+0x4a/0x5e
	[<c016bdec>] seq_read+0xf3/0x29f
	[<c015a004>] vfs_read+0x6d/0x91
	[<c015a0c1>] sys_read+0x3b/0x60
	[<c0102eda>] syscall_call+0x7/0xb
	[<ffffffff>] 0xffffffff

[add save_stack_trace_tsk() on mips, ACK Ralf --adobriyan]
Signed-off-by: Ken Chen <kenchen@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>

3 files changed, 57 insertions, 6 deletions

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 71df353e367..334ef2f983f 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -140,6 +140,7 @@ 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/arch/mips/kernel/stacktrace.c b/arch/mips/kernel/stacktrace.c
index 0632e2a849c..58f5cd76c8c 100644
--- a/arch/mips/kernel/stacktrace.c
+++ b/arch/mips/kernel/stacktrace.c
@@ -32,7 +32,8 @@ static void save_raw_context_stack(struct stack_trace *trace,
 	}
 }
 
-static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs)
+static void save_context_stack(struct stack_trace *trace,
+	struct task_struct *tsk, struct pt_regs *regs)
 {
 	unsigned long sp = regs->regs[29];
 #ifdef CONFIG_KALLSYMS
@@ -41,7 +42,7 @@ static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs)
 
 	if (raw_show_trace || !__kernel_text_address(pc)) {
 		unsigned long stack_page =
-			(unsigned long)task_stack_page(current);
+			(unsigned long)task_stack_page(tsk);
 		if (stack_page && sp >= stack_page &&
 		    sp <= stack_page + THREAD_SIZE - 32)
 			save_raw_context_stack(trace, sp);
@@ -54,7 +55,7 @@ static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs)
 			trace->entries[trace->nr_entries++] = pc;
 		if (trace->nr_entries >= trace->max_entries)
 			break;
-		pc = unwind_stack(current, &sp, pc, &ra);
+		pc = unwind_stack(tsk, &sp, pc, &ra);
 	} while (pc);
 #else
 	save_raw_context_stack(trace, sp);
@@ -66,12 +67,23 @@ static void save_context_stack(struct stack_trace *trace, struct pt_regs *regs)
  */
 void save_stack_trace(struct stack_trace *trace)
 {
+	save_stack_trace_tsk(current, trace);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
 	struct pt_regs dummyregs;
 	struct pt_regs *regs = &dummyregs;
 
 	WARN_ON(trace->nr_entries || !trace->max_entries);
 
-	prepare_frametrace(regs);
-	save_context_stack(trace, regs);
+	if (tsk != current) {
+		regs->regs[29] = tsk->thread.reg29;
+		regs->regs[31] = 0;
+		regs->cp0_epc = tsk->thread.reg31;
+	} else
+		prepare_frametrace(regs);
+	save_context_stack(trace, tsk, regs);
 }
-EXPORT_SYMBOL_GPL(save_stack_trace);
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ce7a6da1b6a..eb7b4654d6a 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>
@@ -337,6 +338,37 @@ 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 seq_file *m, struct pid_namespace *ns,
+			  struct pid *pid, struct task_struct *task)
+{
+	struct stack_trace trace;
+	unsigned long *entries;
+	int i;
+
+	entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
+	if (!entries)
+		return -ENOMEM;
+
+	trace.nr_entries	= 0;
+	trace.max_entries	= MAX_STACK_TRACE_DEPTH;
+	trace.entries		= entries;
+	trace.skip		= 0;
+	save_stack_trace_tsk(task, &trace);
+
+	for (i = 0; i < trace.nr_entries; i++) {
+		seq_printf(m, "[<%p>] %pS\n",
+			   (void *)entries[i], (void *)entries[i]);
+	}
+	kfree(entries);
+
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_SCHEDSTATS
 /*
  * Provides /proc/PID/schedstat
@@ -2500,6 +2532,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_KALLSYMS
 	INF("wchan",      S_IRUGO, proc_pid_wchan),
 #endif
+#ifdef CONFIG_STACKTRACE
+	ONE("stack",      S_IRUSR, proc_pid_stack),
+#endif
 #ifdef CONFIG_SCHEDSTATS
 	INF("schedstat",  S_IRUGO, proc_pid_schedstat),
 #endif
@@ -2835,6 +2870,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_KALLSYMS
 	INF("wchan",     S_IRUGO, proc_pid_wchan),
 #endif
+#ifdef CONFIG_STACKTRACE
+	ONE("stack",      S_IRUSR, proc_pid_stack),
+#endif
 #ifdef CONFIG_SCHEDSTATS
 	INF("schedstat", S_IRUGO, proc_pid_schedstat),
 #endif