Re: [PATCH v2 1/1] sched: watchdog: Touch kernel watchdog with sched count

[Peter Zijlstra]

On Wed, Oct 21, 2020 at 12:12:57PM +0200, Peter Zijlstra wrote:
> On Tue, Oct 20, 2020 at 01:57:04PM -0700, Xi Wang wrote:
> 
> > +	if (watchdog_touch_with_sched) {
> > +		/* Trigger reschedule for the next round */
> > +		set_tsk_need_resched(current);
> > +		set_preempt_need_resched();
> 
> Blergh.. that's gross. This relies on this being in IRQ context and
> either: PREEMPT=y *OR* this always being from userspace. Otherwise
> there's no guarantee the return-from-interrupt will actually schedule.

*compeltely* untested.

---
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 996884dcc9fd..f3913a6ed5e1 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -745,8 +745,7 @@ static void pfault_interrupt(struct ext_code ext_code,
 			 * is no kernel task state to trample. Rely on the
 			 * return to userspace schedule() to block. */
 			__set_current_state(TASK_UNINTERRUPTIBLE);
-			set_tsk_need_resched(tsk);
-			set_preempt_need_resched();
+			resched_current_from_IRQ();
 		}
 	}
 out:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8583b15dbc83..e5447b8473d1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1832,6 +1832,8 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+extern void resched_current_from_IRQ(void);
+
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index aa897c3f2e92..a21c16089452 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -70,8 +70,7 @@ void rcu_sched_clock_irq(int user)
 	if (user) {
 		rcu_qs();
 	} else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
-		set_tsk_need_resched(current);
-		set_preempt_need_resched();
+		resched_current_from_IRQ();
 	}
 }
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index edeabc232c21..39aae3663bea 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2558,8 +2558,7 @@ void rcu_sched_clock_irq(int user)
 	if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
 		/* Idle and userspace execution already are quiescent states. */
 		if (!rcu_is_cpu_rrupt_from_idle() && !user) {
-			set_tsk_need_resched(current);
-			set_preempt_need_resched();
+			resched_current_from_IRQ();
 		}
 		__this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	}
@@ -2687,8 +2686,7 @@ static __latent_entropy void rcu_core(void)
 	if (!(preempt_count() & PREEMPT_MASK)) {
 		rcu_preempt_deferred_qs(current);
 	} else if (rcu_preempt_need_deferred_qs(current)) {
-		set_tsk_need_resched(current);
-		set_preempt_need_resched();
+		resched_current_from_IRQ();
 	}
 
 	/* Update RCU state based on any recent quiescent states. */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 8760b6ead770..fbafc3aba268 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -656,8 +656,7 @@ static void rcu_exp_handler(void *unused)
 			rcu_report_exp_rdp(rdp);
 		} else {
 			rdp->exp_deferred_qs = true;
-			set_tsk_need_resched(t);
-			set_preempt_need_resched();
+			resched_current_from_IRQ();
 		}
 		return;
 	}
@@ -725,8 +724,7 @@ static void rcu_exp_need_qs(void)
 	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
 	/* Store .exp before .rcu_urgent_qs. */
 	smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true);
-	set_tsk_need_resched(current);
-	set_preempt_need_resched();
+	resched_current_from_IRQ();
 }
 
 /* Invoked on each online non-idle CPU for expedited quiescent state. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index fd8a52e9a887..b98294585c56 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -625,8 +625,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			// Enabling BH or preempt does reschedule, so...
 			// Also if no expediting, slow is OK.
 			// Plus nohz_full CPUs eventually get tick enabled.
-			set_tsk_need_resched(current);
-			set_preempt_need_resched();
+			resched_current_from_IRQ();
 			if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
 			    !rdp->defer_qs_iw_pending && exp) {
 				// Get scheduler to re-evaluate and call hooks.
@@ -689,8 +688,7 @@ static void rcu_flavor_sched_clock_irq(int user)
 	    (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) {
 		/* No QS, force context switch if deferred. */
 		if (rcu_preempt_need_deferred_qs(t)) {
-			set_tsk_need_resched(t);
-			set_preempt_need_resched();
+			resched_current_from_IRQ();
 		}
 	} else if (rcu_preempt_need_deferred_qs(t)) {
 		rcu_preempt_deferred_qs(t); /* Report deferred QS. */
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 0fde39b8daab..74973ab3c14d 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -566,8 +566,7 @@ static void print_cpu_stall(unsigned long gps)
 	 * progress and it could be we're stuck in kernel space without context
 	 * switches for an entirely unreasonable amount of time.
 	 */
-	set_tsk_need_resched(current);
-	set_preempt_need_resched();
+	resched_current_from_IRQ();
 }
 
 static void check_cpu_stall(struct rcu_data *rdp)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4a51461a2708..79c4ee72c9b6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -641,6 +641,17 @@ void resched_cpu(int cpu)
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
+void resched_current_from_IRQ(void)
+{
+	struct pt_regs *regs = get_irq_regs();
+
+	WARN_ON_ONCE(!in_irq());
+	WARN_ON_ONCE(user_mode(regs) || IS_ENABLED(CONFIG_PREEMPTION));
+
+	set_tsk_need_resched(tsk);
+	set_preempt_need_resched();
+}
+
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ_COMMON
 /*