[ 020/184] ptrace: ensure arch_ptrace/ptrace_request can never

[Willy Tarreau]

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------
 race with SIGKILL

From: Oleg Nesterov <oleg@xxxxxxxxxx>

ptrace: ensure arch_ptrace/ptrace_request can never race with SIGKILL

CVE-2013-0871

BugLink: http://bugs.launchpad.net/bugs/1129192

putreg() assumes that the tracee is not running and pt_regs_access() can
safely play with its stack.  However a killed tracee can return from
ptrace_stop() to the low-level asm code and do RESTORE_REST, this means
that debugger can actually read/modify the kernel stack until the tracee
does SAVE_REST again.

set_task_blockstep() can race with SIGKILL too and in some sense this
race is even worse, the very fact the tracee can be woken up breaks the
logic.

As Linus suggested we can clear TASK_WAKEKILL around the arch_ptrace()
call, this ensures that nobody can ever wakeup the tracee while the
debugger looks at it.  Not only this fixes the mentioned problems, we
can do some cleanups/simplifications in arch_ptrace() paths.

Probably ptrace_unfreeze_traced() needs more callers, for example it
makes sense to make the tracee killable for oom-killer before
access_process_vm().

While at it, add the comment into may_ptrace_stop() to explain why
ptrace_stop() still can't rely on SIGKILL and signal_pending_state().

Reported-by: Salman Qazi <sqazi@xxxxxxxxxx>
Reported-by: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
(backported from commit 9899d11f654474d2d54ea52ceaa2a1f4db3abd68)

Conflicts:
	arch/x86/kernel/step.c
	kernel/ptrace.c
	kernel/signal.c

Signed-off-by: Luis Henriques <luis.henriques@xxxxxxxxxxxxx>
Acked-by: Colin King <colin.king@xxxxxxxxxxxxx>
Signed-off-by: Tim Gardner <tim.gardner@xxxxxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
---
 kernel/ptrace.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++-----------
 kernel/signal.c |  4 ++++
 2 files changed, 55 insertions(+), 12 deletions(-)

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 37850f9..d0036f0 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -80,6 +80,36 @@ void __ptrace_unlink(struct task_struct *child)
 		ptrace_untrace(child);
 }
 
+/* Ensure that nothing can wake it up, even SIGKILL */
+static bool ptrace_freeze_traced(struct task_struct *task)
+{
+	bool ret = false;
+
+	spin_lock_irq(&task->sighand->siglock);
+	if (task_is_traced(task) && !__fatal_signal_pending(task)) {
+		task->state = __TASK_TRACED;
+		ret = true;
+	}
+	spin_unlock_irq(&task->sighand->siglock);
+
+	return ret;
+}
+
+static void ptrace_unfreeze_traced(struct task_struct *task)
+{
+	if (task->state != __TASK_TRACED)
+		return;
+
+	WARN_ON(!task->ptrace || task->parent != current);
+
+	spin_lock_irq(&task->sighand->siglock);
+	if (__fatal_signal_pending(task))
+		wake_up_state(task, __TASK_TRACED);
+	else
+		task->state = TASK_TRACED;
+	spin_unlock_irq(&task->sighand->siglock);
+}
+
 /*
  * Check that we have indeed attached to the thing..
  */
@@ -95,25 +125,29 @@ int ptrace_check_attach(struct task_struct *child, int kill)
 	 * be changed by us so it's not changing right after this.
 	 */
 	read_lock(&tasklist_lock);
-	if ((child->ptrace & PT_PTRACED) && child->parent == current) {
-		ret = 0;
+	if (child->ptrace && child->parent == current) {
+		WARN_ON(child->state == __TASK_TRACED);
 		/*
 		 * child->sighand can't be NULL, release_task()
 		 * does ptrace_unlink() before __exit_signal().
 		 */
-		spin_lock_irq(&child->sighand->siglock);
-		if (task_is_stopped(child))
-			child->state = TASK_TRACED;
-		else if (!task_is_traced(child) && !kill)
-			ret = -ESRCH;
-		spin_unlock_irq(&child->sighand->siglock);
+		if (kill || ptrace_freeze_traced(child))
+			ret = 0;
 	}
 	read_unlock(&tasklist_lock);
 
-	if (!ret && !kill)
-		ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
+	if (!ret && !kill) {
+		if (!wait_task_inactive(child, __TASK_TRACED)) {
+			/*
+			 * This can only happen if may_ptrace_stop() fails and
+			 * ptrace_stop() changes ->state back to TASK_RUNNING,
+			 * so we should not worry about leaking __TASK_TRACED.
+			 */
+			WARN_ON(child->state == __TASK_TRACED);
+			ret = -ESRCH;
+		}
+	}
 
-	/* All systems go.. */
 	return ret;
 }
 
@@ -637,6 +671,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 		goto out_put_task_struct;
 
 	ret = arch_ptrace(child, request, addr, data);
+	if (ret || request != PTRACE_DETACH)
+		ptrace_unfreeze_traced(child);
 
  out_put_task_struct:
 	put_task_struct(child);
@@ -752,8 +788,11 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 	}
 
 	ret = ptrace_check_attach(child, request == PTRACE_KILL);
-	if (!ret)
+	if (!ret) {
 		ret = compat_arch_ptrace(child, request, addr, data);
+		if (ret || request != PTRACE_DETACH)
+			ptrace_unfreeze_traced(child);
+	}
 
  out_put_task_struct:
 	put_task_struct(child);
diff --git a/kernel/signal.c b/kernel/signal.c
index b40f4f0..1929014 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1527,6 +1527,10 @@ static inline int may_ptrace_stop(void)
 	 * If SIGKILL was already sent before the caller unlocked
 	 * ->siglock we must see ->core_state != NULL. Otherwise it
 	 * is safe to enter schedule().
+	 *
+	 * This is almost outdated, a task with the pending SIGKILL can't
+	 * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported
+	 * after SIGKILL was already dequeued.
 	 */
 	if (unlikely(current->mm->core_state) &&
 	    unlikely(current->mm == current->parent->mm))
-- 
1.7.12.2.21.g234cd45.dirty



--
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/