1 files changed, 115 insertions, 12 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e99d326fa569..4511532b08b8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -36,7 +36,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
+#ifdef CONFIG_SCHED_DEBUG
 /*
  * Debugging: various feature bits
  *
@@ -794,6 +794,26 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
 
+/*
+ * This static key is used to reduce the uclamp overhead in the fast path. It
+ * primarily disables the call to uclamp_rq_{inc, dec}() in
+ * enqueue/dequeue_task().
+ *
+ * This allows users to continue to enable uclamp in their kernel config with
+ * minimum uclamp overhead in the fast path.
+ *
+ * As soon as userspace modifies any of the uclamp knobs, the static key is
+ * enabled, since we have an actual users that make use of uclamp
+ * functionality.
+ *
+ * The knobs that would enable this static key are:
+ *
+ *   * A task modifying its uclamp value with sched_setattr().
+ *   * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs.
+ *   * An admin modifying the cgroup cpu.uclamp.{min, max}
+ */
+DEFINE_STATIC_KEY_FALSE(sched_uclamp_used);
+
 /* Integer rounded range for each bucket */
 #define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
 
@@ -990,10 +1010,38 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 
 	lockdep_assert_held(&rq->lock);
 
+	/*
+	 * If sched_uclamp_used was enabled after task @p was enqueued,
+	 * we could end up with unbalanced call to uclamp_rq_dec_id().
+	 *
+	 * In this case the uc_se->active flag should be false since no uclamp
+	 * accounting was performed at enqueue time and we can just return
+	 * here.
+	 *
+	 * Need to be careful of the following enqeueue/dequeue ordering
+	 * problem too
+	 *
+	 *	enqueue(taskA)
+	 *	// sched_uclamp_used gets enabled
+	 *	enqueue(taskB)
+	 *	dequeue(taskA)
+	 *	// Must not decrement bukcet->tasks here
+	 *	dequeue(taskB)
+	 *
+	 * where we could end up with stale data in uc_se and
+	 * bucket[uc_se->bucket_id].
+	 *
+	 * The following check here eliminates the possibility of such race.
+	 */
+	if (unlikely(!uc_se->active))
+		return;
+
 	bucket = &uc_rq->bucket[uc_se->bucket_id];
+
 	SCHED_WARN_ON(!bucket->tasks);
 	if (likely(bucket->tasks))
 		bucket->tasks--;
+
 	uc_se->active = false;
 
 	/*
@@ -1021,6 +1069,15 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1036,6 +1093,15 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 {
 	enum uclamp_id clamp_id;
 
+	/*
+	 * Avoid any overhead until uclamp is actually used by the userspace.
+	 *
+	 * The condition is constructed such that a NOP is generated when
+	 * sched_uclamp_used is disabled.
+	 */
+	if (!static_branch_unlikely(&sched_uclamp_used))
+		return;
+
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
 
@@ -1145,8 +1211,10 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 		update_root_tg = true;
 	}
 
-	if (update_root_tg)
+	if (update_root_tg) {
+		static_branch_enable(&sched_uclamp_used);
 		uclamp_update_root_tg();
+	}
 
 	/*
 	 * We update all RUNNABLE tasks only when task groups are in use.
@@ -1181,6 +1249,15 @@ static int uclamp_validate(struct task_struct *p,
 	if (upper_bound > SCHED_CAPACITY_SCALE)
 		return -EINVAL;
 
+	/*
+	 * We have valid uclamp attributes; make sure uclamp is enabled.
+	 *
+	 * We need to do that here, because enabling static branches is a
+	 * blocking operation which obviously cannot be done while holding
+	 * scheduler locks.
+	 */
+	static_branch_enable(&sched_uclamp_used);
+
 	return 0;
 }
 
@@ -1238,6 +1315,20 @@ static void uclamp_fork(struct task_struct *p)
 	}
 }
 
+static void __init init_uclamp_rq(struct rq *rq)
+{
+	enum uclamp_id clamp_id;
+	struct uclamp_rq *uc_rq = rq->uclamp;
+
+	for_each_clamp_id(clamp_id) {
+		uc_rq[clamp_id] = (struct uclamp_rq) {
+			.value = uclamp_none(clamp_id)
+		};
+	}
+
+	rq->uclamp_flags = 0;
+}
+
 static void __init init_uclamp(void)
 {
 	struct uclamp_se uc_max = {};
@@ -1246,11 +1337,8 @@ static void __init init_uclamp(void)
 
 	mutex_init(&uclamp_mutex);
 
-	for_each_possible_cpu(cpu) {
-		memset(&cpu_rq(cpu)->uclamp, 0,
-				sizeof(struct uclamp_rq)*UCLAMP_CNT);
-		cpu_rq(cpu)->uclamp_flags = 0;
-	}
+	for_each_possible_cpu(cpu)
+		init_uclamp_rq(cpu_rq(cpu));
 
 	for_each_clamp_id(clamp_id) {
 		uclamp_se_set(&init_task.uclamp_req[clamp_id],
@@ -1649,7 +1737,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
@@ -2889,6 +2977,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -2953,6 +3042,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -4109,7 +4199,8 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * it wants to wake up a task to maintain concurrency.
 	 * As this function is called inside the schedule() context,
 	 * we disable preemption to avoid it calling schedule() again
-	 * in the possible wakeup of a kworker.
+	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
+	 * requires it.
 	 */
 	if (tsk->flags & PF_WQ_WORKER) {
 		preempt_disable();
@@ -4447,7 +4538,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
@@ -6177,13 +6269,14 @@ void idle_task_exit(void)
 	struct mm_struct *mm = current->active_mm;
 
 	BUG_ON(cpu_online(smp_processor_id()));
+	BUG_ON(current != this_rq()->idle);
 
 	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
-		current->active_mm = &init_mm;
 		finish_arch_post_lock_switch();
 	}
-	mmdrop(mm);
+
+	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
 /*
@@ -7279,6 +7372,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	if (req.ret)
 		return req.ret;
 
+	static_branch_enable(&sched_uclamp_used);
+
 	mutex_lock(&uclamp_mutex);
 	rcu_read_lock();
 
@@ -7373,6 +7468,8 @@ static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
 static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+/* More than 203 days if BW_SHIFT equals 20. */
+static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -7401,6 +7498,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 		return -EINVAL;
 
 	/*
+	 * Bound quota to defend quota against overflow during bandwidth shift.
+	 */
+	if (quota != RUNTIME_INF && quota > max_cfs_runtime)
+		return -EINVAL;
+
+	/*
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */