task_work: teach task_work_add() to do signal_wake_up()

So that the target task will exit the wait_event_interruptible-like
loop and call task_work_run() asap.

The patch turns "bool notify" into 0,TWA_RESUME,TWA_SIGNAL enum, the
new TWA_SIGNAL flag implies signal_wake_up().  However, it needs to
avoid the race with recalc_sigpending(), so the patch also adds the
new JOBCTL_TASK_WORK bit included in JOBCTL_PENDING_MASK.

TODO: once this patch is merged we need to change all current users
of task_work_add(notify = true) to use TWA_RESUME.

Cc: [email protected] # v5.7
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Oleg Nesterov <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

Author: oleg-nesterov

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_TASK_WORK_BIT	24	/* set by TWA_SIGNAL */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,9 +29,10 @@ 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_TASK_WORK	(1UL << JOBCTL_TASK_WORK_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
-#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
+#define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK | JOBCTL_TASK_WORK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);

include/linux/task_work.h

@@ -13,7 +13,10 @@ init_task_work(struct callback_head *twork, task_work_func_t func)
 	twork->func = func;
 }
 
-int task_work_add(struct task_struct *task, struct callback_head *twork, bool);
+#define TWA_RESUME	1
+#define TWA_SIGNAL	2
+int task_work_add(struct task_struct *task, struct callback_head *twork, int);
+
 struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
 void task_work_run(void);
 

kernel/signal.c

@@ -2529,9 +2529,6 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
-	if (unlikely(current->task_works))
-		task_work_run();
-
 	if (unlikely(uprobe_deny_signal()))
 		return false;
 
@@ -2544,6 +2541,13 @@ bool get_signal(struct ksignal *ksig)
 
 relock:
 	spin_lock_irq(&sighand->siglock);
+	current->jobctl &= ~JOBCTL_TASK_WORK;
+	if (unlikely(current->task_works)) {
+		spin_unlock_irq(&sighand->siglock);
+		task_work_run();
+		goto relock;
+	}
+
 	/*
 	 * Every stopped thread goes here after wakeup. Check to see if
 	 * we should notify the parent, prepare_signal(SIGCONT) encodes

kernel/task_work.c

@@ -25,9 +25,10 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * 0 if succeeds or -ESRCH.
  */
 int
-task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
+task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 {
 	struct callback_head *head;
+	unsigned long flags;
 
 	do {
 		head = READ_ONCE(task->task_works);
@@ -36,8 +37,19 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
 		work->next = head;
 	} while (cmpxchg(&task->task_works, head, work) != head);
 
-	if (notify)
+	switch (notify) {
+	case TWA_RESUME:
 		set_notify_resume(task);
+		break;
+	case TWA_SIGNAL:
+		if (lock_task_sighand(task, &flags)) {
+			task->jobctl |= JOBCTL_TASK_WORK;
+			signal_wake_up(task, 0);
+			unlock_task_sighand(task, &flags);
+		}
+		break;
+	}
+
 	return 0;
 }