sched: Replace rq::wake_list

The recent commit: 90b5363acd47 ("sched: Clean up scheduler_ipi()")
got smp_call_function_single_async() subtly wrong. Even though it will
return -EBUSY when trying to re-use a csd, that condition is not
atomic and still requires external serialization.

The change in ttwu_queue_remote() got this wrong.

While on first reading ttwu_queue_remote() has an atomic test-and-set
that appears to serialize the use, the matching 'release' is not in
the right place to actually guarantee this serialization.

The actual race is vs the sched_ttwu_pending() call in the idle loop;
that can run the wakeup-list without consuming the CSD.

Instead of trying to chain the lists, merge them.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200526161908.129371594@infradead.org

4 files changed, 47 insertions, 34 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b71ed5ee97fd..b3c64c6b4d2e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1538,7 +1538,7 @@ static int migration_cpu_stop(void *data)
 	 * __migrate_task() such that we will not miss enforcing cpus_ptr
 	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
 	 */
-	sched_ttwu_pending();
+	flush_smp_call_function_from_idle();
 
 	raw_spin_lock(&p->pi_lock);
 	rq_lock(rq, &rf);
@@ -2272,14 +2272,13 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 }
 
 #ifdef CONFIG_SMP
-void sched_ttwu_pending(void)
+void sched_ttwu_pending(void *arg)
 {
+	struct llist_node *llist = arg;
 	struct rq *rq = this_rq();
-	struct llist_node *llist;
 	struct task_struct *p, *t;
 	struct rq_flags rf;
 
-	llist = llist_del_all(&rq->wake_list);
 	if (!llist)
 		return;
 
@@ -2299,11 +2298,6 @@ void sched_ttwu_pending(void)
 	rq_unlock_irqrestore(rq, &rf);
 }
 
-static void wake_csd_func(void *info)
-{
-	sched_ttwu_pending();
-}
-
 void send_call_function_single_ipi(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -2327,12 +2321,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
 	WRITE_ONCE(rq->ttwu_pending, 1);
-	if (llist_add(&p->wake_entry, &rq->wake_list)) {
-		if (!set_nr_if_polling(rq->idle))
-			smp_call_function_single_async(cpu, &rq->wake_csd);
-		else
-			trace_sched_wake_idle_without_ipi(cpu);
-	}
+	__smp_call_single_queue(cpu, &p->wake_entry);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2772,6 +2761,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->capture_control = NULL;
 #endif
 	init_numa_balancing(clone_flags, p);
+#ifdef CONFIG_SMP
+	p->wake_entry_type = CSD_TYPE_TTWU;
+#endif
 }
 
 DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
@@ -6564,7 +6556,6 @@ int sched_cpu_dying(unsigned int cpu)
 	struct rq_flags rf;
 
 	/* Handle pending wakeups and then migrate everything off */
-	sched_ttwu_pending();
 	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
@@ -6763,8 +6754,6 @@ void __init sched_init(void)
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
 		rq->max_idle_balance_cost = sysctl_sched_migration_cost;
 
-		rq_csd_init(rq, &rq->wake_csd, wake_csd_func);
-
 		INIT_LIST_HEAD(&rq->cfs_tasks);
 
 		rq_attach_root(rq, &def_root_domain);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 387fd75ee6f7..05deb81bb3e3 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -294,7 +294,6 @@ static void do_idle(void)
 	 * critical section.
 	 */
 	flush_smp_call_function_from_idle();
-	sched_ttwu_pending();
 	schedule_idle();
 
 	if (unlikely(klp_patch_pending(current)))
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c86fc94c54e5..1d4e94c1e5fe 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1023,11 +1023,6 @@ struct rq {
 	unsigned int		ttwu_local;
 #endif
 
-#ifdef CONFIG_SMP
-	call_single_data_t	wake_csd;
-	struct llist_head	wake_list;
-#endif
-
 #ifdef CONFIG_CPU_IDLE
 	/* Must be inspected within a rcu lock section */
 	struct cpuidle_state	*idle_state;
@@ -1371,8 +1366,6 @@ queue_balance_callback(struct rq *rq,
 	rq->balance_callback = head;
 }
 
-extern void sched_ttwu_pending(void);
-
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
 			      lockdep_is_held(&sched_domains_mutex))
@@ -1512,7 +1505,6 @@ extern void flush_smp_call_function_from_idle(void);
 
 #else /* !CONFIG_SMP: */
 static inline void flush_smp_call_function_from_idle(void) { }
-static inline void sched_ttwu_pending(void) { }
 #endif
 
 #include "stats.h"
diff --git a/kernel/smp.c b/kernel/smp.c
index 856562b80794..0d61dc060b01 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -196,6 +196,7 @@ void generic_smp_call_function_single_interrupt(void)
 	flush_smp_call_function_queue(true);
 }
 
+extern void sched_ttwu_pending(void *);
 extern void irq_work_single(void *);
 
 /**
@@ -244,6 +245,10 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 					csd->func);
 				break;
 
+			case CSD_TYPE_TTWU:
+				pr_warn("IPI task-wakeup sent to offline CPU\n");
+				break;
+
 			default:
 				pr_warn("IPI callback, unknown type %d, sent to offline CPU\n",
 					CSD_TYPE(csd));
@@ -275,22 +280,43 @@ static void flush_smp_call_function_queue(bool warn_cpu_offline)
 		}
 	}
 
+	if (!entry)
+		return;
+
 	/*
 	 * Second; run all !SYNC callbacks.
 	 */
+	prev = NULL;
 	llist_for_each_entry_safe(csd, csd_next, entry, llist) {
 		int type = CSD_TYPE(csd);
 
-		if (type == CSD_TYPE_ASYNC) {
-			smp_call_func_t func = csd->func;
-			void *info = csd->info;
+		if (type != CSD_TYPE_TTWU) {
+			if (prev) {
+				prev->next = &csd_next->llist;
+			} else {
+				entry = &csd_next->llist;
+			}
 
-			csd_unlock(csd);
-			func(info);
-		} else if (type == CSD_TYPE_IRQ_WORK) {
-			irq_work_single(csd);
+			if (type == CSD_TYPE_ASYNC) {
+				smp_call_func_t func = csd->func;
+				void *info = csd->info;
+
+				csd_unlock(csd);
+				func(info);
+			} else if (type == CSD_TYPE_IRQ_WORK) {
+				irq_work_single(csd);
+			}
+
+		} else {
+			prev = &csd->llist;
 		}
 	}
+
+	/*
+	 * Third; only CSD_TYPE_TTWU is left, issue those.
+	 */
+	if (entry)
+		sched_ttwu_pending(entry);
 }
 
 void flush_smp_call_function_from_idle(void)
@@ -659,6 +685,13 @@ void __init smp_init(void)
 	BUILD_BUG_ON(offsetof(struct irq_work, flags) !=
 		     offsetof(struct __call_single_data, flags));
 
+	/*
+	 * Assert the CSD_TYPE_TTWU layout is similar enough
+	 * for task_struct to be on the @call_single_queue.
+	 */
+	BUILD_BUG_ON(offsetof(struct task_struct, wake_entry_type) - offsetof(struct task_struct, wake_entry) !=
+		     offsetof(struct __call_single_data, flags) - offsetof(struct __call_single_data, llist));
+
 	idle_threads_init();
 	cpuhp_threads_init();