1 files changed, 574 insertions, 143 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 20ffcc044134..59bea523c84b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -13,7 +13,7 @@
 #include "sched.h"
 
 #include <linux/nospec.h>
-
+#include <linux/blkdev.h>
 #include <linux/kcov.h>
 #include <linux/scs.h>
 
@@ -237,9 +237,30 @@ static DEFINE_MUTEX(sched_core_mutex);
 static atomic_t sched_core_count;
 static struct cpumask sched_core_mask;
 
+static void sched_core_lock(int cpu, unsigned long *flags)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+	int t, i = 0;
+
+	local_irq_save(*flags);
+	for_each_cpu(t, smt_mask)
+		raw_spin_lock_nested(&cpu_rq(t)->__lock, i++);
+}
+
+static void sched_core_unlock(int cpu, unsigned long *flags)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+	int t;
+
+	for_each_cpu(t, smt_mask)
+		raw_spin_unlock(&cpu_rq(t)->__lock);
+	local_irq_restore(*flags);
+}
+
 static void __sched_core_flip(bool enabled)
 {
-	int cpu, t, i;
+	unsigned long flags;
+	int cpu, t;
 
 	cpus_read_lock();
 
@@ -250,19 +271,12 @@ static void __sched_core_flip(bool enabled)
 	for_each_cpu(cpu, &sched_core_mask) {
 		const struct cpumask *smt_mask = cpu_smt_mask(cpu);
 
-		i = 0;
-		local_irq_disable();
-		for_each_cpu(t, smt_mask) {
-			/* supports up to SMT8 */
-			raw_spin_lock_nested(&cpu_rq(t)->__lock, i++);
-		}
+		sched_core_lock(cpu, &flags);
 
 		for_each_cpu(t, smt_mask)
 			cpu_rq(t)->core_enabled = enabled;
 
-		for_each_cpu(t, smt_mask)
-			raw_spin_unlock(&cpu_rq(t)->__lock);
-		local_irq_enable();
+		sched_core_unlock(cpu, &flags);
 
 		cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask);
 	}
@@ -993,6 +1007,7 @@ int get_nohz_timer_target(void)
 {
 	int i, cpu = smp_processor_id(), default_cpu = -1;
 	struct sched_domain *sd;
+	const struct cpumask *hk_mask;
 
 	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
 		if (!idle_cpu(cpu))
@@ -1000,10 +1015,11 @@ int get_nohz_timer_target(void)
 		default_cpu = cpu;
 	}
 
+	hk_mask = housekeeping_cpumask(HK_FLAG_TIMER);
+
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu_and(i, sched_domain_span(sd),
-			housekeeping_cpumask(HK_FLAG_TIMER)) {
+		for_each_cpu_and(i, sched_domain_span(sd), hk_mask) {
 			if (cpu == i)
 				continue;
 
@@ -1619,6 +1635,23 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
 
+static inline void uclamp_rq_reinc_id(struct rq *rq, struct task_struct *p,
+				      enum uclamp_id clamp_id)
+{
+	if (!p->uclamp[clamp_id].active)
+		return;
+
+	uclamp_rq_dec_id(rq, p, clamp_id);
+	uclamp_rq_inc_id(rq, p, clamp_id);
+
+	/*
+	 * Make sure to clear the idle flag if we've transiently reached 0
+	 * active tasks on rq.
+	 */
+	if (clamp_id == UCLAMP_MAX && (rq->uclamp_flags & UCLAMP_FLAG_IDLE))
+		rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
+}
+
 static inline void
 uclamp_update_active(struct task_struct *p)
 {
@@ -1642,12 +1675,8 @@ uclamp_update_active(struct task_struct *p)
 	 * affecting a valid clamp bucket, the next time it's enqueued,
 	 * it will already see the updated clamp bucket value.
 	 */
-	for_each_clamp_id(clamp_id) {
-		if (p->uclamp[clamp_id].active) {
-			uclamp_rq_dec_id(rq, p, clamp_id);
-			uclamp_rq_inc_id(rq, p, clamp_id);
-		}
-	}
+	for_each_clamp_id(clamp_id)
+		uclamp_rq_reinc_id(rq, p, clamp_id);
 
 	task_rq_unlock(rq, p, &rf);
 }
@@ -2161,7 +2190,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 
 	/* Non kernel threads are not allowed during either online or offline. */
 	if (!(p->flags & PF_KTHREAD))
-		return cpu_active(cpu);
+		return cpu_active(cpu) && task_cpu_possible(cpu, p);
 
 	/* KTHREAD_IS_PER_CPU is always allowed. */
 	if (kthread_is_per_cpu(p))
@@ -2468,6 +2497,34 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	__do_set_cpus_allowed(p, new_mask, 0);
 }
 
+int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
+		      int node)
+{
+	if (!src->user_cpus_ptr)
+		return 0;
+
+	dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+	if (!dst->user_cpus_ptr)
+		return -ENOMEM;
+
+	cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+	return 0;
+}
+
+static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
+{
+	struct cpumask *user_mask = NULL;
+
+	swap(p->user_cpus_ptr, user_mask);
+
+	return user_mask;
+}
+
+void release_user_cpus_ptr(struct task_struct *p)
+{
+	kfree(clear_user_cpus_ptr(p));
+}
+
 /*
  * This function is wildly self concurrent; here be dragons.
  *
@@ -2685,28 +2742,26 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 }
 
 /*
- * Change a given task's CPU affinity. Migrate the thread to a
- * proper CPU and schedule it away if the CPU it's executing on
- * is removed from the allowed bitmask.
- *
- * NOTE: the caller must have a valid reference to the task, the
- * task must not exit() & deallocate itself prematurely. The
- * call is not atomic; no spinlocks may be held.
+ * Called with both p->pi_lock and rq->lock held; drops both before returning.
  */
-static int __set_cpus_allowed_ptr(struct task_struct *p,
-				  const struct cpumask *new_mask,
-				  u32 flags)
+static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
+					 const struct cpumask *new_mask,
+					 u32 flags,
+					 struct rq *rq,
+					 struct rq_flags *rf)
+	__releases(rq->lock)
+	__releases(p->pi_lock)
 {
+	const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
 	const struct cpumask *cpu_valid_mask = cpu_active_mask;
+	bool kthread = p->flags & PF_KTHREAD;
+	struct cpumask *user_mask = NULL;
 	unsigned int dest_cpu;
-	struct rq_flags rf;
-	struct rq *rq;
 	int ret = 0;
 
-	rq = task_rq_lock(p, &rf);
 	update_rq_clock(rq);
 
-	if (p->flags & PF_KTHREAD || is_migration_disabled(p)) {
+	if (kthread || is_migration_disabled(p)) {
 		/*
 		 * Kernel threads are allowed on online && !active CPUs,
 		 * however, during cpu-hot-unplug, even these might get pushed
@@ -2720,6 +2775,11 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		cpu_valid_mask = cpu_online_mask;
 	}
 
+	if (!kthread && !cpumask_subset(new_mask, cpu_allowed_mask)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	/*
 	 * Must re-check here, to close a race against __kthread_bind(),
 	 * sched_setaffinity() is not guaranteed to observe the flag.
@@ -2754,20 +2814,178 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 
 	__do_set_cpus_allowed(p, new_mask, flags);
 
-	return affine_move_task(rq, p, &rf, dest_cpu, flags);
+	if (flags & SCA_USER)
+		user_mask = clear_user_cpus_ptr(p);
+
+	ret = affine_move_task(rq, p, rf, dest_cpu, flags);
+
+	kfree(user_mask);
+
+	return ret;
 
 out:
-	task_rq_unlock(rq, p, &rf);
+	task_rq_unlock(rq, p, rf);
 
 	return ret;
 }
 
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+static int __set_cpus_allowed_ptr(struct task_struct *p,
+				  const struct cpumask *new_mask, u32 flags)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &rf);
+	return __set_cpus_allowed_ptr_locked(p, new_mask, flags, rq, &rf);
+}
+
 int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
 	return __set_cpus_allowed_ptr(p, new_mask, 0);
 }
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
+/*
+ * Change a given task's CPU affinity to the intersection of its current
+ * affinity mask and @subset_mask, writing the resulting mask to @new_mask
+ * and pointing @p->user_cpus_ptr to a copy of the old mask.
+ * If the resulting mask is empty, leave the affinity unchanged and return
+ * -EINVAL.
+ */
+static int restrict_cpus_allowed_ptr(struct task_struct *p,
+				     struct cpumask *new_mask,
+				     const struct cpumask *subset_mask)
+{
+	struct cpumask *user_mask = NULL;
+	struct rq_flags rf;
+	struct rq *rq;
+	int err;
+
+	if (!p->user_cpus_ptr) {
+		user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
+		if (!user_mask)
+			return -ENOMEM;
+	}
+
+	rq = task_rq_lock(p, &rf);
+
+	/*
+	 * Forcefully restricting the affinity of a deadline task is
+	 * likely to cause problems, so fail and noisily override the
+	 * mask entirely.
+	 */
+	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
+		err = -EPERM;
+		goto err_unlock;
+	}
+
+	if (!cpumask_and(new_mask, &p->cpus_mask, subset_mask)) {
+		err = -EINVAL;
+		goto err_unlock;
+	}
+
+	/*
+	 * We're about to butcher the task affinity, so keep track of what
+	 * the user asked for in case we're able to restore it later on.
+	 */
+	if (user_mask) {
+		cpumask_copy(user_mask, p->cpus_ptr);
+		p->user_cpus_ptr = user_mask;
+	}
+
+	return __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf);
+
+err_unlock:
+	task_rq_unlock(rq, p, &rf);
+	kfree(user_mask);
+	return err;
+}
+
+/*
+ * Restrict the CPU affinity of task @p so that it is a subset of
+ * task_cpu_possible_mask() and point @p->user_cpu_ptr to a copy of the
+ * old affinity mask. If the resulting mask is empty, we warn and walk
+ * up the cpuset hierarchy until we find a suitable mask.
+ */
+void force_compatible_cpus_allowed_ptr(struct task_struct *p)
+{
+	cpumask_var_t new_mask;
+	const struct cpumask *override_mask = task_cpu_possible_mask(p);
+
+	alloc_cpumask_var(&new_mask, GFP_KERNEL);
+
+	/*
+	 * __migrate_task() can fail silently in the face of concurrent
+	 * offlining of the chosen destination CPU, so take the hotplug
+	 * lock to ensure that the migration succeeds.
+	 */
+	cpus_read_lock();
+	if (!cpumask_available(new_mask))
+		goto out_set_mask;
+
+	if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
+		goto out_free_mask;
+
+	/*
+	 * We failed to find a valid subset of the affinity mask for the
+	 * task, so override it based on its cpuset hierarchy.
+	 */
+	cpuset_cpus_allowed(p, new_mask);
+	override_mask = new_mask;
+
+out_set_mask:
+	if (printk_ratelimit()) {
+		printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
+				task_pid_nr(p), p->comm,
+				cpumask_pr_args(override_mask));
+	}
+
+	WARN_ON(set_cpus_allowed_ptr(p, override_mask));
+out_free_mask:
+	cpus_read_unlock();
+	free_cpumask_var(new_mask);
+}
+
+static int
+__sched_setaffinity(struct task_struct *p, const struct cpumask *mask);
+
+/*
+ * Restore the affinity of a task @p which was previously restricted by a
+ * call to force_compatible_cpus_allowed_ptr(). This will clear (and free)
+ * @p->user_cpus_ptr.
+ *
+ * It is the caller's responsibility to serialise this with any calls to
+ * force_compatible_cpus_allowed_ptr(@p).
+ */
+void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
+{
+	struct cpumask *user_mask = p->user_cpus_ptr;
+	unsigned long flags;
+
+	/*
+	 * Try to restore the old affinity mask. If this fails, then
+	 * we free the mask explicitly to avoid it being inherited across
+	 * a subsequent fork().
+	 */
+	if (!user_mask || !__sched_setaffinity(p, user_mask))
+		return;
+
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	user_mask = clear_user_cpus_ptr(p);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	kfree(user_mask);
+}
+
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
 #ifdef CONFIG_SCHED_DEBUG
@@ -3112,9 +3330,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 
 		/* Look for allowed, online CPU in same node. */
 		for_each_cpu(dest_cpu, nodemask) {
-			if (!cpu_active(dest_cpu))
-				continue;
-			if (cpumask_test_cpu(dest_cpu, p->cpus_ptr))
+			if (is_cpu_allowed(p, dest_cpu))
 				return dest_cpu;
 		}
 	}
@@ -3131,8 +3347,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		/* No more Mr. Nice Guy. */
 		switch (state) {
 		case cpuset:
-			if (IS_ENABLED(CONFIG_CPUSETS)) {
-				cpuset_cpus_allowed_fallback(p);
+			if (cpuset_cpus_allowed_fallback(p)) {
 				state = possible;
 				break;
 			}
@@ -3144,10 +3359,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 			 *
 			 * More yuck to audit.
 			 */
-			do_set_cpus_allowed(p, cpu_possible_mask);
+			do_set_cpus_allowed(p, task_cpu_possible_mask(p));
 			state = fail;
 			break;
-
 		case fail:
 			BUG();
 			break;
@@ -3562,6 +3776,55 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 }
 
 /*
+ * Invoked from try_to_wake_up() to check whether the task can be woken up.
+ *
+ * The caller holds p::pi_lock if p != current or has preemption
+ * disabled when p == current.
+ *
+ * The rules of PREEMPT_RT saved_state:
+ *
+ *   The related locking code always holds p::pi_lock when updating
+ *   p::saved_state, which means the code is fully serialized in both cases.
+ *
+ *   The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other
+ *   bits set. This allows to distinguish all wakeup scenarios.
+ */
+static __always_inline
+bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
+		WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
+			     state != TASK_RTLOCK_WAIT);
+	}
+
+	if (READ_ONCE(p->__state) & state) {
+		*success = 1;
+		return true;
+	}
+
+#ifdef CONFIG_PREEMPT_RT
+	/*
+	 * Saved state preserves the task state across blocking on
+	 * an RT lock.  If the state matches, set p::saved_state to
+	 * TASK_RUNNING, but do not wake the task because it waits
+	 * for a lock wakeup. Also indicate success because from
+	 * the regular waker's point of view this has succeeded.
+	 *
+	 * After acquiring the lock the task will restore p::__state
+	 * from p::saved_state which ensures that the regular
+	 * wakeup is not lost. The restore will also set
+	 * p::saved_state to TASK_RUNNING so any further tests will
+	 * not result in false positives vs. @success
+	 */
+	if (p->saved_state & state) {
+		p->saved_state = TASK_RUNNING;
+		*success = 1;
+	}
+#endif
+	return false;
+}
+
+/*
  * Notes on Program-Order guarantees on SMP systems.
  *
  *  MIGRATION
@@ -3700,10 +3963,9 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
-		if (!(READ_ONCE(p->__state) & state))
+		if (!ttwu_state_match(p, state, &success))
 			goto out;
 
-		success = 1;
 		trace_sched_waking(p);
 		WRITE_ONCE(p->__state, TASK_RUNNING);
 		trace_sched_wakeup(p);
@@ -3718,14 +3980,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
-	if (!(READ_ONCE(p->__state) & state))
+	if (!ttwu_state_match(p, state, &success))
 		goto unlock;
 
 	trace_sched_waking(p);
 
-	/* We're going to change ->state: */
-	success = 1;
-
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
@@ -5660,11 +5919,9 @@ static bool try_steal_cookie(int this, int that)
 		if (p->core_occupation > dst->idle->core_occupation)
 			goto next;
 
-		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src, p, 0);
 		set_task_cpu(p, this);
 		activate_task(dst, p, 0);
-		p->on_rq = TASK_ON_RQ_QUEUED;
 
 		resched_curr(dst);
 
@@ -5736,35 +5993,109 @@ void queue_core_balance(struct rq *rq)
 	queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance);
 }
 
-static inline void sched_core_cpu_starting(unsigned int cpu)
+static void sched_core_cpu_starting(unsigned int cpu)
 {
 	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
-	struct rq *rq, *core_rq = NULL;
-	int i;
+	struct rq *rq = cpu_rq(cpu), *core_rq = NULL;
+	unsigned long flags;
+	int t;
 
-	core_rq = cpu_rq(cpu)->core;
+	sched_core_lock(cpu, &flags);
 
-	if (!core_rq) {
-		for_each_cpu(i, smt_mask) {
-			rq = cpu_rq(i);
-			if (rq->core && rq->core == rq)
-				core_rq = rq;
+	WARN_ON_ONCE(rq->core != rq);
+
+	/* if we're the first, we'll be our own leader */
+	if (cpumask_weight(smt_mask) == 1)
+		goto unlock;
+
+	/* find the leader */
+	for_each_cpu(t, smt_mask) {
+		if (t == cpu)
+			continue;
+		rq = cpu_rq(t);
+		if (rq->core == rq) {
+			core_rq = rq;
+			break;
 		}
+	}
 
-		if (!core_rq)
-			core_rq = cpu_rq(cpu);
+	if (WARN_ON_ONCE(!core_rq)) /* whoopsie */
+		goto unlock;
 
-		for_each_cpu(i, smt_mask) {
-			rq = cpu_rq(i);
+	/* install and validate core_rq */
+	for_each_cpu(t, smt_mask) {
+		rq = cpu_rq(t);
 
-			WARN_ON_ONCE(rq->core && rq->core != core_rq);
+		if (t == cpu)
 			rq->core = core_rq;
-		}
+
+		WARN_ON_ONCE(rq->core != core_rq);
+	}
+
+unlock:
+	sched_core_unlock(cpu, &flags);
+}
+
+static void sched_core_cpu_deactivate(unsigned int cpu)
+{
+	const struct cpumask *smt_mask = cpu_smt_mask(cpu);
+	struct rq *rq = cpu_rq(cpu), *core_rq = NULL;
+	unsigned long flags;
+	int t;
+
+	sched_core_lock(cpu, &flags);
+
+	/* if we're the last man standing, nothing to do */
+	if (cpumask_weight(smt_mask) == 1) {
+		WARN_ON_ONCE(rq->core != rq);
+		goto unlock;
+	}
+
+	/* if we're not the leader, nothing to do */
+	if (rq->core != rq)
+		goto unlock;
+
+	/* find a new leader */
+	for_each_cpu(t, smt_mask) {
+		if (t == cpu)
+			continue;
+		core_rq = cpu_rq(t);
+		break;
 	}
+
+	if (WARN_ON_ONCE(!core_rq)) /* impossible */
+		goto unlock;
+
+	/* copy the shared state to the new leader */
+	core_rq->core_task_seq      = rq->core_task_seq;
+	core_rq->core_pick_seq      = rq->core_pick_seq;
+	core_rq->core_cookie        = rq->core_cookie;
+	core_rq->core_forceidle     = rq->core_forceidle;
+	core_rq->core_forceidle_seq = rq->core_forceidle_seq;
+
+	/* install new leader */
+	for_each_cpu(t, smt_mask) {
+		rq = cpu_rq(t);
+		rq->core = core_rq;
+	}
+
+unlock:
+	sched_core_unlock(cpu, &flags);
 }
+
+static inline void sched_core_cpu_dying(unsigned int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	if (rq->core != rq)
+		rq->core = rq;
+}
+
 #else /* !CONFIG_SCHED_CORE */
 
 static inline void sched_core_cpu_starting(unsigned int cpu) {}
+static inline void sched_core_cpu_deactivate(unsigned int cpu) {}
+static inline void sched_core_cpu_dying(unsigned int cpu) {}
 
 static struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
@@ -5775,6 +6106,24 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 #endif /* CONFIG_SCHED_CORE */
 
 /*
+ * Constants for the sched_mode argument of __schedule().
+ *
+ * The mode argument allows RT enabled kernels to differentiate a
+ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
+ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
+ * optimize the AND operation out and just check for zero.
+ */
+#define SM_NONE			0x0
+#define SM_PREEMPT		0x1
+#define SM_RTLOCK_WAIT		0x2
+
+#ifndef CONFIG_PREEMPT_RT
+# define SM_MASK_PREEMPT	(~0U)
+#else
+# define SM_MASK_PREEMPT	SM_PREEMPT
+#endif
+
+/*
  * __schedule() is the main scheduler function.
  *
  * The main means of driving the scheduler and thus entering this function are:
@@ -5813,7 +6162,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  *
  * WARNING: must be called with preemption disabled!
  */
-static void __sched notrace __schedule(bool preempt)
+static void __sched notrace __schedule(unsigned int sched_mode)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
@@ -5826,13 +6175,13 @@ static void __sched notrace __schedule(bool preempt)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev, preempt);
+	schedule_debug(prev, !!sched_mode);
 
 	if (sched_feat(HRTICK) || sched_feat(HRTICK_DL))
 		hrtick_clear(rq);
 
 	local_irq_disable();
-	rcu_note_context_switch(preempt);
+	rcu_note_context_switch(!!sched_mode);
 
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
@@ -5866,7 +6215,7 @@ static void __sched notrace __schedule(bool preempt)
 	 *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
 	 */
 	prev_state = READ_ONCE(prev->__state);
-	if (!preempt && prev_state) {
+	if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
 		if (signal_pending_state(prev_state, prev)) {
 			WRITE_ONCE(prev->__state, TASK_RUNNING);
 		} else {
@@ -5932,7 +6281,7 @@ static void __sched notrace __schedule(bool preempt)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(preempt, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
@@ -5953,7 +6302,7 @@ void __noreturn do_task_dead(void)
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
 
-	__schedule(false);
+	__schedule(SM_NONE);
 	BUG();
 
 	/* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
@@ -5994,7 +6343,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * make sure to submit it to avoid deadlocks.
 	 */
 	if (blk_needs_flush_plug(tsk))
-		blk_schedule_flush_plug(tsk);
+		blk_flush_plug(tsk->plug, true);
 }
 
 static void sched_update_worker(struct task_struct *tsk)
@@ -6014,7 +6363,7 @@ asmlinkage __visible void __sched schedule(void)
 	sched_submit_work(tsk);
 	do {
 		preempt_disable();
-		__schedule(false);
+		__schedule(SM_NONE);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
 	sched_update_worker(tsk);
@@ -6042,7 +6391,7 @@ void __sched schedule_idle(void)
 	 */
 	WARN_ON_ONCE(current->__state);
 	do {
-		__schedule(false);
+		__schedule(SM_NONE);
 	} while (need_resched());
 }
 
@@ -6077,6 +6426,18 @@ void __sched schedule_preempt_disabled(void)
 	preempt_disable();
 }
 
+#ifdef CONFIG_PREEMPT_RT
+void __sched notrace schedule_rtlock(void)
+{
+	do {
+		preempt_disable();
+		__schedule(SM_RTLOCK_WAIT);
+		sched_preempt_enable_no_resched();
+	} while (need_resched());
+}
+NOKPROBE_SYMBOL(schedule_rtlock);
+#endif
+
 static void __sched notrace preempt_schedule_common(void)
 {
 	do {
@@ -6095,7 +6456,7 @@ static void __sched notrace preempt_schedule_common(void)
 		 */
 		preempt_disable_notrace();
 		preempt_latency_start(1);
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		preempt_latency_stop(1);
 		preempt_enable_no_resched_notrace();
 
@@ -6174,7 +6535,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 		 * an infinite recursion.
 		 */
 		prev_ctx = exception_enter();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		exception_exit(prev_ctx);
 
 		preempt_latency_stop(1);
@@ -6323,7 +6684,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	do {
 		preempt_disable();
 		local_irq_enable();
-		__schedule(true);
+		__schedule(SM_PREEMPT);
 		local_irq_disable();
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
@@ -7300,6 +7661,16 @@ err_size:
 	return -E2BIG;
 }
 
+static void get_params(struct task_struct *p, struct sched_attr *attr)
+{
+	if (task_has_dl_policy(p))
+		__getparam_dl(p, attr);
+	else if (task_has_rt_policy(p))
+		attr->sched_priority = p->rt_priority;
+	else
+		attr->sched_nice = task_nice(p);
+}
+
 /**
  * sys_sched_setscheduler - set/change the scheduler policy and RT priority
  * @pid: the pid in question.
@@ -7361,6 +7732,8 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	rcu_read_unlock();
 
 	if (likely(p)) {
+		if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
+			get_params(p, &attr);
 		retval = sched_setattr(p, &attr);
 		put_task_struct(p);
 	}
@@ -7509,12 +7882,8 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	kattr.sched_policy = p->policy;
 	if (p->sched_reset_on_fork)
 		kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-	if (task_has_dl_policy(p))
-		__getparam_dl(p, &kattr);
-	else if (task_has_rt_policy(p))
-		kattr.sched_priority = p->rt_priority;
-	else
-		kattr.sched_nice = task_nice(p);
+	get_params(p, &kattr);
+	kattr.sched_flags &= SCHED_FLAG_ALL;
 
 #ifdef CONFIG_UCLAMP_TASK
 	/*
@@ -7535,9 +7904,76 @@ out_unlock:
 	return retval;
 }
 
-long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+#ifdef CONFIG_SMP
+int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
+{
+	int ret = 0;
+
+	/*
+	 * If the task isn't a deadline task or admission control is
+	 * disabled then we don't care about affinity changes.
+	 */
+	if (!task_has_dl_policy(p) || !dl_bandwidth_enabled())
+		return 0;
+
+	/*
+	 * Since bandwidth control happens on root_domain basis,
+	 * if admission test is enabled, we only admit -deadline
+	 * tasks allowed to run on all the CPUs in the task's
+	 * root_domain.
+	 */
+	rcu_read_lock();
+	if (!cpumask_subset(task_rq(p)->rd->span, mask))
+		ret = -EBUSY;
+	rcu_read_unlock();
+	return ret;
+}
+#endif
+
+static int
+__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
 {
+	int retval;
 	cpumask_var_t cpus_allowed, new_mask;
+
+	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_free_cpus_allowed;
+	}
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	cpumask_and(new_mask, mask, cpus_allowed);
+
+	retval = dl_task_check_affinity(p, new_mask);
+	if (retval)
+		goto out_free_new_mask;
+again:
+	retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER);
+	if (retval)
+		goto out_free_new_mask;
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	if (!cpumask_subset(new_mask, cpus_allowed)) {
+		/*
+		 * We must have raced with a concurrent cpuset update.
+		 * Just reset the cpumask to the cpuset's cpus_allowed.
+		 */
+		cpumask_copy(new_mask, cpus_allowed);
+		goto again;
+	}
+
+out_free_new_mask:
+	free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+	free_cpumask_var(cpus_allowed);
+	return retval;
+}
+
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+{
 	struct task_struct *p;
 	int retval;
 
@@ -7557,68 +7993,22 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 		retval = -EINVAL;
 		goto out_put_task;
 	}
-	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
-		retval = -ENOMEM;
-		goto out_put_task;
-	}
-	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
-		retval = -ENOMEM;
-		goto out_free_cpus_allowed;
-	}
-	retval = -EPERM;
+
 	if (!check_same_owner(p)) {
 		rcu_read_lock();
 		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
 			rcu_read_unlock();
-			goto out_free_new_mask;
+			retval = -EPERM;
+			goto out_put_task;
 		}
 		rcu_read_unlock();
 	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
-		goto out_free_new_mask;
-
-
-	cpuset_cpus_allowed(p, cpus_allowed);
-	cpumask_and(new_mask, in_mask, cpus_allowed);
-
-	/*
-	 * Since bandwidth control happens on root_domain basis,
-	 * if admission test is enabled, we only admit -deadline
-	 * tasks allowed to run on all the CPUs in the task's
-	 * root_domain.
-	 */
-#ifdef CONFIG_SMP
-	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
-		rcu_read_lock();
-		if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
-			retval = -EBUSY;
-			rcu_read_unlock();
-			goto out_free_new_mask;
-		}
-		rcu_read_unlock();
-	}
-#endif
-again:
-	retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK);
+		goto out_put_task;
 
-	if (!retval) {
-		cpuset_cpus_allowed(p, cpus_allowed);
-		if (!cpumask_subset(new_mask, cpus_allowed)) {
-			/*
-			 * We must have raced with a concurrent cpuset
-			 * update. Just reset the cpus_allowed to the
-			 * cpuset's cpus_allowed
-			 */
-			cpumask_copy(new_mask, cpus_allowed);
-			goto again;
-		}
-	}
-out_free_new_mask:
-	free_cpumask_var(new_mask);
-out_free_cpus_allowed:
-	free_cpumask_var(cpus_allowed);
+	retval = __sched_setaffinity(p, in_mask);
 out_put_task:
 	put_task_struct(p);
 	return retval;
@@ -7761,6 +8151,17 @@ int __sched __cond_resched(void)
 		preempt_schedule_common();
 		return 1;
 	}
+	/*
+	 * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
+	 * whether the current CPU is in an RCU read-side critical section,
+	 * so the tick can report quiescent states even for CPUs looping
+	 * in kernel context.  In contrast, in non-preemptible kernels,
+	 * RCU readers leave no in-memory hints, which means that CPU-bound
+	 * processes executing in kernel context might never report an
+	 * RCU quiescent state.  Therefore, the following code causes
+	 * cond_resched() to report a quiescent state, but only when RCU
+	 * is in urgent need of one.
+	 */
 #ifndef CONFIG_PREEMPT_RCU
 	rcu_all_qs();
 #endif
@@ -7953,7 +8354,8 @@ int io_schedule_prepare(void)
 	int old_iowait = current->in_iowait;
 
 	current->in_iowait = 1;
-	blk_schedule_flush_plug(current);
+	if (current->plug)
+		blk_flush_plug(current->plug, true);
 
 	return old_iowait;
 }
@@ -8394,6 +8796,7 @@ void idle_task_exit(void)
 		finish_arch_post_lock_switch();
 	}
 
+	scs_task_reset(current);
 	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
@@ -8435,7 +8838,6 @@ static void balance_push(struct rq *rq)
 	struct task_struct *push_task = rq->curr;
 
 	lockdep_assert_rq_held(rq);
-	SCHED_WARN_ON(rq->cpu != smp_processor_id());
 
 	/*
 	 * Ensure the thing is persistent until balance_push_set(.on = false);
@@ -8443,9 +8845,10 @@ static void balance_push(struct rq *rq)
 	rq->balance_callback = &balance_push_callback;
 
 	/*
-	 * Only active while going offline.
+	 * Only active while going offline and when invoked on the outgoing
+	 * CPU.
 	 */
-	if (!cpu_dying(rq->cpu))
+	if (!cpu_dying(rq->cpu) || rq != this_rq())
 		return;
 
 	/*
@@ -8707,6 +9110,8 @@ int sched_cpu_deactivate(unsigned int cpu)
 	 */
 	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
 		static_branch_dec_cpuslocked(&sched_smt_present);
+
+	sched_core_cpu_deactivate(cpu);
 #endif
 
 	if (!sched_smp_initialized)
@@ -8811,6 +9216,7 @@ int sched_cpu_dying(unsigned int cpu)
 	calc_load_migrate(rq);
 	update_max_interval();
 	hrtick_clear(rq);
+	sched_core_cpu_dying(cpu);
 	return 0;
 }
 #endif
@@ -9022,7 +9428,7 @@ void __init sched_init(void)
 		atomic_set(&rq->nr_iowait, 0);
 
 #ifdef CONFIG_SCHED_CORE
-		rq->core = NULL;
+		rq->core = rq;
 		rq->core_pick = NULL;
 		rq->core_enabled = 0;
 		rq->core_tree = RB_ROOT;
@@ -9804,7 +10210,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	mutex_lock(&cfs_constraints_mutex);
 	ret = __cfs_schedulable(tg, period, quota);
 	if (ret)
@@ -9848,7 +10254,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 		cfs_bandwidth_usage_dec();
 out_unlock:
 	mutex_unlock(&cfs_constraints_mutex);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -10099,6 +10505,20 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
+			       struct cftype *cft)
+{
+	return css_tg(css)->idle;
+}
+
+static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
+				struct cftype *cft, s64 idle)
+{
+	return sched_group_set_idle(css_tg(css), idle);
+}
+#endif
+
 static struct cftype cpu_legacy_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	{
@@ -10106,6 +10526,11 @@ static struct cftype cpu_legacy_files[] = {
 		.read_u64 = cpu_shares_read_u64,
 		.write_u64 = cpu_shares_write_u64,
 	},
+	{
+		.name = "idle",
+		.read_s64 = cpu_idle_read_s64,
+		.write_s64 = cpu_idle_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{
@@ -10313,6 +10738,12 @@ static struct cftype cpu_files[] = {
 		.read_s64 = cpu_weight_nice_read_s64,
 		.write_s64 = cpu_weight_nice_write_s64,
 	},
+	{
+		.name = "idle",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_s64 = cpu_idle_read_s64,
+		.write_s64 = cpu_idle_write_s64,
+	},
 #endif
 #ifdef CONFIG_CFS_BANDWIDTH
 	{