[RFC] ptrace: Don't change __state

diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index fa067de9f1a9..4e154ad8205f 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,6 +19,7 @@  struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
+#define JOBCTL_DELAY_WAKEKILL_BIT	24	/* delay killable wakeups */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,6 +29,7 @@  struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
+#define JOBCTL_DELAY_WAKEKILL	(1UL << JOBCTL_DELAY_WAKEKILL_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 4f78d0d5940c..a55320a0e8e3 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -197,7 +197,8 @@  static bool ptrace_freeze_traced(struct task_struct *task)
 	spin_lock_irq(&task->sighand->siglock);
 	if (task_is_traced(task) && !looks_like_a_spurious_pid(task) &&
 	    !__fatal_signal_pending(task)) {
-		WRITE_ONCE(task->__state, __TASK_TRACED);
+		//WARN_ON((task->jobctl & JOBCTL_DELAY_WAKEKILL));
+		task->jobctl |= JOBCTL_DELAY_WAKEKILL;
 		ret = true;
 	}
 	spin_unlock_irq(&task->sighand->siglock);
@@ -207,7 +208,7 @@  static bool ptrace_freeze_traced(struct task_struct *task)
 
 static void ptrace_unfreeze_traced(struct task_struct *task)
 {
-	if (READ_ONCE(task->__state) != __TASK_TRACED)
+	if (!task_is_traced(task))
 		return;
 
 	WARN_ON(!task->ptrace || task->parent != current);
@@ -216,13 +217,11 @@  static void ptrace_unfreeze_traced(struct task_struct *task)
 	 * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
 	 * Recheck state under the lock to close this race.
 	 */
-	spin_lock_irq(&task->sighand->siglock);
-	if (READ_ONCE(task->__state) == __TASK_TRACED) {
-		if (__fatal_signal_pending(task))
-			wake_up_state(task, __TASK_TRACED);
-		else
-			WRITE_ONCE(task->__state, TASK_TRACED);
-	}
+	spin_unlock_irq(&task->sighand->siglock);
+	WARN_ON(!(task->jobctl & JOBCTL_DELAY_WAKEKILL));
+	task->jobctl &= ~JOBCTL_DELAY_WAKEKILL;
+	if (fatal_signal_pending(task))
+		wake_up_state(task, TASK_WAKEKILL);
 	spin_unlock_irq(&task->sighand->siglock);
 }
 
@@ -256,7 +255,7 @@  static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	 */
 	read_lock(&tasklist_lock);
 	if (child->ptrace && child->parent == current) {
-		WARN_ON(READ_ONCE(child->__state) == __TASK_TRACED);
+		WARN_ON(child->jobctl & JOBCTL_DELAY_WAKEKILL);
 		/*
 		 * child->sighand can't be NULL, release_task()
 		 * does ptrace_unlink() before __exit_signal().
@@ -267,13 +266,13 @@  static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	read_unlock(&tasklist_lock);
 
 	if (!ret && !ignore_state) {
-		if (!wait_task_inactive(child, __TASK_TRACED)) {
+		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.
+			 * so we should not worry about leaking JOBCTL_DELAY_WAKEKILL.
 			 */
-			WARN_ON(READ_ONCE(child->__state) == __TASK_TRACED);
+			WARN_ON(!(child->jobctl & JOBCTL_DELAY_WAKEKILL));
 			ret = -ESRCH;
 		}
 	}
@@ -892,7 +891,6 @@  static int ptrace_resume(struct task_struct *child, long request,
 	 * status and clears the code too; this can't race with the tracee, it
 	 * takes siglock after resume.
 	 */
-	need_siglock = data && !thread_group_empty(current);
 	if (need_siglock)
 		spin_lock_irq(&child->sighand->siglock);
 	child->exit_code = data;
@@ -1325,8 +1323,7 @@  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);
+	ptrace_unfreeze_traced(child);
 
  out_put_task_struct:
 	put_task_struct(child);
@@ -1468,8 +1465,7 @@  COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
 				  request == PTRACE_INTERRUPT);
 	if (!ret) {
 		ret = compat_arch_ptrace(child, request, addr, data);
-		if (ret || request != PTRACE_DETACH)
-			ptrace_unfreeze_traced(child);
+		ptrace_unfreeze_traced(child);
 	}
 
  out_put_task_struct:
diff --git a/kernel/signal.c b/kernel/signal.c
index 30cd1ca43bcd..a1277580c92e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -762,6 +762,10 @@  static int dequeue_synchronous_signal(kernel_siginfo_t *info)
  */
 void signal_wake_up_state(struct task_struct *t, unsigned int state)
 {
+	/* Suppress wakekill? */
+	if (t->jobctl & JOBCTL_DELAY_WAKEKILL)
+		state &= ~TASK_WAKEKILL;
+
 	set_tsk_thread_flag(t, TIF_SIGPENDING);
 	/*
 	 * TASK_WAKEKILL also means wake it up in the stopped/traced/killable
@@ -2328,6 +2332,7 @@  static int ptrace_stop(int exit_code, int why, int clear_code,
 
 	/* LISTENING can be set only during STOP traps, clear it */
 	current->jobctl &= ~JOBCTL_LISTENING;
+	current->jobctl &= ~JOBCTL_DELAY_WAKEKILL;
 
 	/*
 	 * Queued signals ignored us while we were stopped for tracing.