Merge branch 'sched/warnings' into sched/core, to pick up WARN_ON_ONCE() conversion commit

Merge in the BUG_ON() => WARN_ON_ONCE() conversion commit.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

9 files changed, 94 insertions, 46 deletions

diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c
index 4ebaf97f7bd8..991fc9002535 100644
--- a/kernel/sched/autogroup.c
+++ b/kernel/sched/autogroup.c
@@ -161,7 +161,8 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 	struct task_struct *t;
 	unsigned long flags;
 
-	BUG_ON(!lock_task_sighand(p, &flags));
+	if (WARN_ON_ONCE(!lock_task_sighand(p, &flags)))
+		return;
 
 	prev = p->signal->autogroup;
 	if (prev == ag) {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 603a80ec9b0e..7d289d87acf7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -91,7 +91,7 @@
 #include "stats.h"
 
 #include "../workqueue_internal.h"
-#include "../../fs/io-wq.h"
+#include "../../io_uring/io-wq.h"
 #include "../smpboot.h"
 
 /*
@@ -2327,7 +2327,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 	rq = cpu_rq(new_cpu);
 
 	rq_lock(rq, rf);
-	BUG_ON(task_cpu(p) != new_cpu);
+	WARN_ON_ONCE(task_cpu(p) != new_cpu);
 	activate_task(rq, p, 0);
 	check_preempt_curr(rq, p, 0);
 
@@ -3801,7 +3801,7 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
-static inline bool ttwu_queue_cond(int cpu)
+static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
 	/*
 	 * Do not complicate things with the async wake_list while the CPU is
@@ -3810,6 +3810,10 @@ static inline bool ttwu_queue_cond(int cpu)
 	if (!cpu_active(cpu))
 		return false;
 
+	/* Ensure the task will still be allowed to run on the CPU. */
+	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+		return false;
+
 	/*
 	 * If the CPU does not share cache, then queue the task on the
 	 * remote rqs wakelist to avoid accessing remote data.
@@ -3839,7 +3843,7 @@ static inline bool ttwu_queue_cond(int cpu)
 
 static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
-	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu)) {
+	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
@@ -4262,6 +4266,38 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
 }
 
 /**
+ * cpu_curr_snapshot - Return a snapshot of the currently running task
+ * @cpu: The CPU on which to snapshot the task.
+ *
+ * Returns the task_struct pointer of the task "currently" running on
+ * the specified CPU.  If the same task is running on that CPU throughout,
+ * the return value will be a pointer to that task's task_struct structure.
+ * If the CPU did any context switches even vaguely concurrently with the
+ * execution of this function, the return value will be a pointer to the
+ * task_struct structure of a randomly chosen task that was running on
+ * that CPU somewhere around the time that this function was executing.
+ *
+ * If the specified CPU was offline, the return value is whatever it
+ * is, perhaps a pointer to the task_struct structure of that CPU's idle
+ * task, but there is no guarantee.  Callers wishing a useful return
+ * value must take some action to ensure that the specified CPU remains
+ * online throughout.
+ *
+ * This function executes full memory barriers before and after fetching
+ * the pointer, which permits the caller to confine this function's fetch
+ * with respect to the caller's accesses to other shared variables.
+ */
+struct task_struct *cpu_curr_snapshot(int cpu)
+{
+	struct task_struct *t;
+
+	smp_mb(); /* Pairing determined by caller's synchronization design. */
+	t = rcu_dereference(cpu_curr(cpu));
+	smp_mb(); /* Pairing determined by caller's synchronization design. */
+	return t;
+}
+
+/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -6562,7 +6598,7 @@ void __sched schedule_idle(void)
 	} while (need_resched());
 }
 
-#if defined(CONFIG_CONTEXT_TRACKING) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK)
+#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK)
 asmlinkage __visible void __sched schedule_user(void)
 {
 	/*
@@ -8979,7 +9015,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 }
 
 int task_can_attach(struct task_struct *p,
-		    const struct cpumask *cs_cpus_allowed)
+		    const struct cpumask *cs_effective_cpus)
 {
 	int ret = 0;
 
@@ -8998,9 +9034,11 @@ int task_can_attach(struct task_struct *p,
 	}
 
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_cpus_allowed)) {
-		int cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
+					      cs_effective_cpus)) {
+		int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
 
+		if (unlikely(cpu >= nr_cpu_ids))
+			return -EINVAL;
 		ret = dl_cpu_busy(cpu, p);
 	}
 
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index fa9ce9d83683..a286e726eb4b 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -147,7 +147,7 @@ int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
 	int task_pri = convert_prio(p->prio);
 	int idx, cpu;
 
-	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
+	WARN_ON_ONCE(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 4cbdc0c560da..d116d2b9d2f9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -310,7 +310,7 @@ static void dl_change_utilization(struct task_struct *p, u64 new_bw)
 {
 	struct rq *rq;
 
-	BUG_ON(p->dl.flags & SCHED_FLAG_SUGOV);
+	WARN_ON_ONCE(p->dl.flags & SCHED_FLAG_SUGOV);
 
 	if (task_on_rq_queued(p))
 		return;
@@ -607,7 +607,7 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
 {
 	struct rb_node *leftmost;
 
-	BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+	WARN_ON_ONCE(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
 
 	leftmost = rb_add_cached(&p->pushable_dl_tasks,
 				 &rq->dl.pushable_dl_tasks_root,
@@ -684,7 +684,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 			 * Failed to find any suitable CPU.
 			 * The task will never come back!
 			 */
-			BUG_ON(dl_bandwidth_enabled());
+			WARN_ON_ONCE(dl_bandwidth_enabled());
 
 			/*
 			 * If admission control is disabled we
@@ -830,7 +830,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
-	BUG_ON(pi_of(dl_se)->dl_runtime <= 0);
+	WARN_ON_ONCE(pi_of(dl_se)->dl_runtime <= 0);
 
 	/*
 	 * This could be the case for a !-dl task that is boosted.
@@ -1612,7 +1612,7 @@ static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 
-	BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+	WARN_ON_ONCE(!RB_EMPTY_NODE(&dl_se->rb_node));
 
 	rb_add_cached(&dl_se->rb_node, &dl_rq->root, __dl_less);
 
@@ -1636,7 +1636,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
 static void
 enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 {
-	BUG_ON(on_dl_rq(dl_se));
+	WARN_ON_ONCE(on_dl_rq(dl_se));
 
 	update_stats_enqueue_dl(dl_rq_of_se(dl_se), dl_se, flags);
 
@@ -2013,7 +2013,7 @@ static struct task_struct *pick_task_dl(struct rq *rq)
 		return NULL;
 
 	dl_se = pick_next_dl_entity(dl_rq);
-	BUG_ON(!dl_se);
+	WARN_ON_ONCE(!dl_se);
 	p = dl_task_of(dl_se);
 
 	return p;
@@ -2273,12 +2273,12 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
 
 	p = __node_2_pdl(rb_first_cached(&rq->dl.pushable_dl_tasks_root));
 
-	BUG_ON(rq->cpu != task_cpu(p));
-	BUG_ON(task_current(rq, p));
-	BUG_ON(p->nr_cpus_allowed <= 1);
+	WARN_ON_ONCE(rq->cpu != task_cpu(p));
+	WARN_ON_ONCE(task_current(rq, p));
+	WARN_ON_ONCE(p->nr_cpus_allowed <= 1);
 
-	BUG_ON(!task_on_rq_queued(p));
-	BUG_ON(!dl_task(p));
+	WARN_ON_ONCE(!task_on_rq_queued(p));
+	WARN_ON_ONCE(!dl_task(p));
 
 	return p;
 }
@@ -2488,7 +2488,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	struct root_domain *src_rd;
 	struct rq *rq;
 
-	BUG_ON(!dl_task(p));
+	WARN_ON_ONCE(!dl_task(p));
 
 	rq = task_rq(p);
 	src_rd = rq->rd;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e8c1b889dcbb..efceb670e755 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2596,7 +2596,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 	if (!join)
 		return;
 
-	BUG_ON(irqs_disabled());
+	WARN_ON_ONCE(irqs_disabled());
 	double_lock_irq(&my_grp->lock, &grp->lock);
 
 	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
@@ -7280,7 +7280,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		return;
 
 	find_matching_se(&se, &pse);
-	BUG_ON(!pse);
+	WARN_ON_ONCE(!pse);
 
 	cse_is_idle = se_is_idle(se);
 	pse_is_idle = se_is_idle(pse);
@@ -8160,7 +8160,7 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 {
 	lockdep_assert_rq_held(rq);
 
-	BUG_ON(task_rq(p) != rq);
+	WARN_ON_ONCE(task_rq(p) != rq);
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	check_preempt_curr(rq, p, 0);
 }
@@ -10135,7 +10135,7 @@ redo:
 		goto out_balanced;
 	}
 
-	BUG_ON(busiest == env.dst_rq);
+	WARN_ON_ONCE(busiest == env.dst_rq);
 
 	schedstat_add(sd->lb_imbalance[idle], env.imbalance);
 
@@ -10431,7 +10431,7 @@ static int active_load_balance_cpu_stop(void *data)
 	 * we need to fix it. Originally reported by
 	 * Bjorn Helgaas on a 128-CPU setup.
 	 */
-	BUG_ON(busiest_rq == target_rq);
+	WARN_ON_ONCE(busiest_rq == target_rq);
 
 	/* Search for an sd spanning us and the target CPU. */
 	rcu_read_lock();
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 328cccbee444..f26ab2675f7d 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -53,14 +53,14 @@ static noinline int __cpuidle cpu_idle_poll(void)
 {
 	trace_cpu_idle(0, smp_processor_id());
 	stop_critical_timings();
-	rcu_idle_enter();
+	ct_idle_enter();
 	local_irq_enable();
 
 	while (!tif_need_resched() &&
 	       (cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
 
-	rcu_idle_exit();
+	ct_idle_exit();
 	start_critical_timings();
 	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 
@@ -98,12 +98,12 @@ void __cpuidle default_idle_call(void)
 		 *
 		 * Trace IRQs enable here, then switch off RCU, and have
 		 * arch_cpu_idle() use raw_local_irq_enable(). Note that
-		 * rcu_idle_enter() relies on lockdep IRQ state, so switch that
+		 * ct_idle_enter() relies on lockdep IRQ state, so switch that
 		 * last -- this is very similar to the entry code.
 		 */
 		trace_hardirqs_on_prepare();
 		lockdep_hardirqs_on_prepare();
-		rcu_idle_enter();
+		ct_idle_enter();
 		lockdep_hardirqs_on(_THIS_IP_);
 
 		arch_cpu_idle();
@@ -116,7 +116,7 @@ void __cpuidle default_idle_call(void)
 		 */
 		raw_local_irq_disable();
 		lockdep_hardirqs_off(_THIS_IP_);
-		rcu_idle_exit();
+		ct_idle_exit();
 		lockdep_hardirqs_on(_THIS_IP_);
 		raw_local_irq_enable();
 
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index a337f3e35997..ec66b40bdd40 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -957,10 +957,16 @@ int psi_cgroup_alloc(struct cgroup *cgroup)
 	if (static_branch_likely(&psi_disabled))
 		return 0;
 
-	cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu);
-	if (!cgroup->psi.pcpu)
+	cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL);
+	if (!cgroup->psi)
 		return -ENOMEM;
-	group_init(&cgroup->psi);
+
+	cgroup->psi->pcpu = alloc_percpu(struct psi_group_cpu);
+	if (!cgroup->psi->pcpu) {
+		kfree(cgroup->psi);
+		return -ENOMEM;
+	}
+	group_init(cgroup->psi);
 	return 0;
 }
 
@@ -969,10 +975,11 @@ void psi_cgroup_free(struct cgroup *cgroup)
 	if (static_branch_likely(&psi_disabled))
 		return;
 
-	cancel_delayed_work_sync(&cgroup->psi.avgs_work);
-	free_percpu(cgroup->psi.pcpu);
+	cancel_delayed_work_sync(&cgroup->psi->avgs_work);
+	free_percpu(cgroup->psi->pcpu);
 	/* All triggers must be removed by now */
-	WARN_ONCE(cgroup->psi.poll_states, "psi: trigger leak\n");
+	WARN_ONCE(cgroup->psi->poll_states, "psi: trigger leak\n");
+	kfree(cgroup->psi);
 }
 
 /**
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4bc84a1135db..27e694cf3e37 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -843,7 +843,7 @@ static void __disable_runtime(struct rq *rq)
 		 * We cannot be left wanting - that would mean some runtime
 		 * leaked out of the system.
 		 */
-		BUG_ON(want);
+		WARN_ON_ONCE(want);
 balanced:
 		/*
 		 * Disable all the borrow logic by pretending we have inf
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index da17be6f27fd..b75ac74986fb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -27,6 +27,7 @@
 #include <linux/capability.h>
 #include <linux/cgroup_api.h>
 #include <linux/cgroup.h>
+#include <linux/context_tracking.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask_api.h>
 #include <linux/ctype.h>
@@ -465,9 +466,6 @@ extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
 extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
 
-extern void unregister_rt_sched_group(struct task_group *tg);
-extern void free_rt_sched_group(struct task_group *tg);
-extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent);
@@ -505,6 +503,10 @@ struct cfs_bandwidth { };
 
 #endif	/* CONFIG_CGROUP_SCHED */
 
+extern void unregister_rt_sched_group(struct task_group *tg);
+extern void free_rt_sched_group(struct task_group *tg);
+extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
+
 /*
  * u64_u32_load/u64_u32_store
  *
@@ -2695,8 +2697,8 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
 	__acquires(rq1->lock)
 	__acquires(rq2->lock)
 {
-	BUG_ON(!irqs_disabled());
-	BUG_ON(rq1 != rq2);
+	WARN_ON_ONCE(!irqs_disabled());
+	WARN_ON_ONCE(rq1 != rq2);
 	raw_spin_rq_lock(rq1);
 	__acquire(rq2->lock);	/* Fake it out ;) */
 	double_rq_clock_clear_update(rq1, rq2);
@@ -2712,7 +2714,7 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 	__releases(rq1->lock)
 	__releases(rq2->lock)
 {
-	BUG_ON(rq1 != rq2);
+	WARN_ON_ONCE(rq1 != rq2);
 	raw_spin_rq_unlock(rq1);
 	__release(rq2->lock);
 }