[PATCH V2] use canary at end of stack to indicate overruns at oopstime

[Eric Sandeen]

(Updated with a common max-stack-used checker that knows about
the canary, as suggested by Joe Perches)

Use a canary at the end of the stack to clearly indicate
at oops time whether the stack has ever overflowed.

This is a very simple implementation with a couple of
drawbacks:

1) a thread may legitimately use exactly up to the last 
   word on the stack

 -- but the chances of doing this and then oopsing later seem slim

2) it's possible that the stack usage isn't dense enough
   that the canary location could get skipped over

 -- but the worst that happens is that we don't flag the overrun
 -- though this happens fairly often in my testing :(

With the code in place, an intentionally-bloated stack oops might
do:

BUG: unable to handle kernel paging request at ffff8103f84cc680
IP: [<ffffffff810253df>] update_curr+0x9a/0xa8
PGD 8063 PUD 0 
Thread overran stack or stack corrupted
Oops: 0000 [1] SMP 
CPU 0 
...

... unless the stack overrun is so bad that it corrupts some other
thread.

Signed-off-by: Eric Sandeen <sandeen@xxxxxxxxxx>
---

Index: linux-2.6.25/arch/x86/mm/fault.c
===================================================================
--- linux-2.6.25.orig/arch/x86/mm/fault.c
+++ linux-2.6.25/arch/x86/mm/fault.c
@@ -25,6 +25,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/magic.h>
 
 #include <asm/system.h>
 #include <asm/desc.h>
@@ -581,6 +582,8 @@ void __kprobes do_page_fault(struct pt_r
 	unsigned long address;
 	int write, si_code;
 	int fault;
+	unsigned long *stackend;
+
 #ifdef CONFIG_X86_64
 	unsigned long flags;
 #endif
@@ -850,6 +853,10 @@ no_context:
 
 	show_fault_oops(regs, error_code, address);
 
+ 	stackend = end_of_stack(tsk);
+	if (*stackend != STACK_END_MAGIC)
+		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
 	tsk->thread.cr2 = address;
 	tsk->thread.trap_no = 14;
 	tsk->thread.error_code = error_code;
Index: linux-2.6.25/include/linux/magic.h
===================================================================
--- linux-2.6.25.orig/include/linux/magic.h
+++ linux-2.6.25/include/linux/magic.h
@@ -42,4 +42,5 @@
 #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
 #define INOTIFYFS_SUPER_MAGIC	0x2BAD1DEA
 
+#define STACK_END_MAGIC		0x57AC6E9D
 #endif /* __LINUX_MAGIC_H__ */
Index: linux-2.6.25/kernel/fork.c
===================================================================
--- linux-2.6.25.orig/kernel/fork.c
+++ linux-2.6.25/kernel/fork.c
@@ -53,6 +53,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <linux/magic.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -167,6 +168,8 @@ static struct task_struct *dup_task_stru
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
+	unsigned long *stackend;
+
 	int err;
 
 	prepare_to_copy(orig);
@@ -192,6 +195,8 @@ static struct task_struct *dup_task_stru
 	}
 
 	setup_thread_stack(tsk, orig);
+	stackend = end_of_stack(tsk);
+	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	tsk->stack_canary = get_random_int();
Index: linux-2.6.25/kernel/exit.c
===================================================================
--- linux-2.6.25.orig/kernel/exit.c
+++ linux-2.6.25/kernel/exit.c
@@ -823,12 +823,9 @@ static void check_stack_usage(void)
 {
 	static DEFINE_SPINLOCK(low_water_lock);
 	static int lowest_to_date = THREAD_SIZE;
-	unsigned long *n = end_of_stack(current);
 	unsigned long free;
 
-	while (*n == 0)
-		n++;
-	free = (unsigned long)n - (unsigned long)end_of_stack(current);
+	free = stack_not_used(current);
 
 	if (free >= lowest_to_date)
 		return;
Index: linux-2.6.25/kernel/sched.c
===================================================================
--- linux-2.6.25.orig/kernel/sched.c
+++ linux-2.6.25/kernel/sched.c
@@ -5188,12 +5188,7 @@ void sched_show_task(struct task_struct 
 		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
-	{
-		unsigned long *n = end_of_stack(p);
-		while (!*n)
-			n++;
-		free = (unsigned long)n - (unsigned long)end_of_stack(p);
-	}
+	free = stack_not_used(p);
 #endif
 	printk(KERN_CONT "%5lu %5d %6d\n", free,
 		task_pid_nr(p), task_pid_nr(p->real_parent));
Index: linux-2.6.25/include/linux/sched.h
===================================================================
--- linux-2.6.25.orig/include/linux/sched.h
+++ linux-2.6.25/include/linux/sched.h
@@ -1893,6 +1893,19 @@ static inline unsigned long *end_of_stac
 
 #endif
 
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+	unsigned long *n = end_of_stack(p);
+
+	do { 	/* Skip over canary */
+		n++;
+	} while (!*n);
+
+	return (unsigned long)n - (unsigned long)end_of_stack(p);
+}
+#endif
+
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */

--
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/