5 files changed, 84 insertions, 30 deletions

diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index cd3b2438a98..9b4d51d0c0d 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -165,10 +165,11 @@ void set_task_blockstep(struct task_struct *task, bool on)
 	 * Ensure irq/preemption can't change debugctl in between.
 	 * Note also that both TIF_BLOCKSTEP and debugctl should
 	 * be changed atomically wrt preemption.
-	 * FIXME: this means that set/clear TIF_BLOCKSTEP is simply
-	 * wrong if task != current, SIGKILL can wakeup the stopped
-	 * tracee and set/clear can play with the running task, this
-	 * can confuse the next __switch_to_xtra().
+	 *
+	 * NOTE: this means that set/clear TIF_BLOCKSTEP is only safe if
+	 * task is current or it can't be running, otherwise we can race
+	 * with __switch_to_xtra(). We rely on ptrace_freeze_traced() but
+	 * PTRACE_KILL is not safe.
 	 */
 	local_irq_disable();
 	debugctl = get_debugctlmsr();
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6fc8f45de4e..d2112477ff5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2714,7 +2714,16 @@ static inline void thread_group_cputime_init(struct signal_struct *sig)
 extern void recalc_sigpending_and_wake(struct task_struct *t);
 extern void recalc_sigpending(void);
 
-extern void signal_wake_up(struct task_struct *t, int resume_stopped);
+extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
+
+static inline void signal_wake_up(struct task_struct *t, bool resume)
+{
+	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+}
+static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
+{
+	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+}
 
 /*
  * Wrappers for p->thread_info->cpu access. No-op on UP.
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 612a5612685..6cbeaae4406 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -117,11 +117,45 @@ void __ptrace_unlink(struct task_struct *child)
 	 * TASK_KILLABLE sleeps.
 	 */
 	if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child))
-		signal_wake_up(child, task_is_traced(child));
+		ptrace_signal_wake_up(child, true);
 
 	spin_unlock(&child->sighand->siglock);
 }
 
+/* Ensure that nothing can wake it up, even SIGKILL */
+static bool ptrace_freeze_traced(struct task_struct *task)
+{
+	bool ret = false;
+
+	/* Lockless, nobody but us can set this flag */
+	if (task->jobctl & JOBCTL_LISTENING)
+		return ret;
+
+	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);
+}
+
 /**
  * ptrace_check_attach - check whether ptracee is ready for ptrace operation
  * @child: ptracee to check for
@@ -151,24 +185,29 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	 * be changed by us so it's not changing right after this.
 	 */
 	read_lock(&tasklist_lock);
-	if ((child->ptrace & PT_PTRACED) && child->parent == current) {
+	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);
-		WARN_ON_ONCE(task_is_stopped(child));
-		if (ignore_state || (task_is_traced(child) &&
-				     !(child->jobctl & JOBCTL_LISTENING)))
+		if (ignore_state || ptrace_freeze_traced(child))
 			ret = 0;
-		spin_unlock_irq(&child->sighand->siglock);
 	}
 	read_unlock(&tasklist_lock);
 
-	if (!ret && !ignore_state)
-		ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH;
+	if (!ret && !ignore_state) {
+		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;
 }
 
@@ -317,7 +356,7 @@ static int ptrace_attach(struct task_struct *task, long request,
 	 */
 	if (task_is_stopped(task) &&
 	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
-		signal_wake_up(task, 1);
+		signal_wake_up_state(task, __TASK_STOPPED);
 
 	spin_unlock(&task->sighand->siglock);
 
@@ -737,7 +776,7 @@ int ptrace_request(struct task_struct *child, long request,
 		 * tracee into STOP.
 		 */
 		if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP)))
-			signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);
+			ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);
 
 		unlock_task_sighand(child, &flags);
 		ret = 0;
@@ -763,7 +802,7 @@ int ptrace_request(struct task_struct *child, long request,
 			 * start of this trap and now.  Trigger re-trap.
 			 */
 			if (child->jobctl & JOBCTL_TRAP_NOTIFY)
-				signal_wake_up(child, true);
+				ptrace_signal_wake_up(child, true);
 			ret = 0;
 		}
 		unlock_task_sighand(child, &flags);
@@ -900,6 +939,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 		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);
@@ -1039,8 +1080,11 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 
 	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
 				  request == PTRACE_INTERRUPT);
-	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/sched/core.c b/kernel/sched/core.c
index 257002c13bb..26058d0bebb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1523,7 +1523,8 @@ out:
  */
 int wake_up_process(struct task_struct *p)
 {
-	return try_to_wake_up(p, TASK_ALL, 0);
+	WARN_ON(task_is_stopped_or_traced(p));
+	return try_to_wake_up(p, TASK_NORMAL, 0);
 }
 EXPORT_SYMBOL(wake_up_process);
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 53cd5c4d117..3d09cf6cde7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -680,23 +680,17 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
  * No need to set need_resched since signal event passing
  * goes through ->blocked
  */
-void signal_wake_up(struct task_struct *t, int resume)
+void signal_wake_up_state(struct task_struct *t, unsigned int state)
 {
-	unsigned int mask;
-
 	set_tsk_thread_flag(t, TIF_SIGPENDING);
-
 	/*
-	 * For SIGKILL, we want to wake it up in the stopped/traced/killable
+	 * TASK_WAKEKILL also means wake it up in the stopped/traced/killable
 	 * case. We don't check t->state here because there is a race with it
 	 * executing another processor and just now entering stopped state.
 	 * By using wake_up_state, we ensure the process will wake up and
 	 * handle its death signal.
 	 */
-	mask = TASK_INTERRUPTIBLE;
-	if (resume)
-		mask |= TASK_WAKEKILL;
-	if (!wake_up_state(t, mask))
+	if (!wake_up_state(t, state | TASK_INTERRUPTIBLE))
 		kick_process(t);
 }
 
@@ -844,7 +838,7 @@ static void ptrace_trap_notify(struct task_struct *t)
 	assert_spin_locked(&t->sighand->siglock);
 
 	task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY);
-	signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
+	ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
 }
 
 /*
@@ -1800,6 +1794,10 @@ 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))
@@ -1925,6 +1923,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 		if (gstop_done)
 			do_notify_parent_cldstop(current, false, why);
 
+		/* tasklist protects us from ptrace_freeze_traced() */
 		__set_current_state(TASK_RUNNING);
 		if (clear_code)
 			current->exit_code = 0;