Merge tag 'sched-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
"Load-balancing improvements:

   - Improve NUMA balancing on AMD Zen systems for affine workloads.

   - Improve the handling of reduced-capacity CPUs in load-balancing.

   - Energy Model improvements: fix & refine all the energy fairness
     metrics (PELT), and remove the conservative threshold requiring 6%
     energy savings to migrate a task. Doing this improves power
     efficiency for most workloads, and also increases the reliability
     of energy-efficiency scheduling.

   - Optimize/tweak select_idle_cpu() to spend (much) less time
     searching for an idle CPU on overloaded systems. There's reports of
     several milliseconds spent there on large systems with large
     workloads ...

     [ Since the search logic changed, there might be behavioral side
       effects. ]

   - Improve NUMA imbalance behavior. On certain systems with spare
     capacity, initial placement of tasks is non-deterministic, and such
     an artificial placement imbalance can persist for a long time,
     hurting (and sometimes helping) performance.

     The fix is to make fork-time task placement consistent with runtime
     NUMA balancing placement.

     Note that some performance regressions were reported against this,
     caused by workloads that are not memory bandwith limited, which
     benefit from the artificial locality of the placement bug(s). Mel
     Gorman's conclusion, with which we concur, was that consistency is
     better than random workload benefits from non-deterministic bugs:

        "Given there is no crystal ball and it's a tradeoff, I think
         it's better to be consistent and use similar logic at both fork
         time and runtime even if it doesn't have universal benefit."

   - Improve core scheduling by fixing a bug in
     sched_core_update_cookie() that caused unnecessary forced idling.

   - Improve wakeup-balancing by allowing same-LLC wakeup of idle CPUs
     for newly woken tasks.

   - Fix a newidle balancing bug that introduced unnecessary wakeup
     latencies.

  ABI improvements/fixes:

   - Do not check capabilities and do not issue capability check denial
     messages when a scheduler syscall doesn't require privileges. (Such
     as increasing niceness.)

   - Add forced-idle accounting to cgroups too.

   - Fix/improve the RSEQ ABI to not just silently accept unknown flags.
     (No existing tooling is known to have learned to rely on the
     previous behavior.)

   - Depreciate the (unused) RSEQ_CS_FLAG_NO_RESTART_ON_* flags.

  Optimizations:

   - Optimize & simplify leaf_cfs_rq_list()

   - Micro-optimize set_nr_{and_not,if}_polling() via try_cmpxchg().

  Misc fixes & cleanups:

   - Fix the RSEQ self-tests on RISC-V and Glibc 2.35 systems.

   - Fix a full-NOHZ bug that can in some cases result in the tick not
     being re-enabled when the last SCHED_RT task is gone from a
     runqueue but there's still SCHED_OTHER tasks around.

   - Various PREEMPT_RT related fixes.

   - Misc cleanups & smaller fixes"

* tag 'sched-core-2022-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  rseq: Kill process when unknown flags are encountered in ABI structures
  rseq: Deprecate RSEQ_CS_FLAG_NO_RESTART_ON_* flags
  sched/core: Fix the bug that task won't enqueue into core tree when update cookie
  nohz/full, sched/rt: Fix missed tick-reenabling bug in dequeue_task_rt()
  sched/core: Always flush pending blk_plug
  sched/fair: fix case with reduced capacity CPU
  sched/core: Use try_cmpxchg in set_nr_{and_not,if}_polling
  sched/core: add forced idle accounting for cgroups
  sched/fair: Remove the energy margin in feec()
  sched/fair: Remove task_util from effective utilization in feec()
  sched/fair: Use the same cpumask per-PD throughout find_energy_efficient_cpu()
  sched/fair: Rename select_idle_mask to select_rq_mask
  sched, drivers: Remove max param from effective_cpu_util()/sched_cpu_util()
  sched/fair: Decay task PELT values during wakeup migration
  sched/fair: Provide u64 read for 32-bits arch helper
  sched/fair: Introduce SIS_UTIL to search idle CPU based on sum of util_avg
  sched: only perform capability check on privileged operation
  sched: Remove unused function group_first_cpu()
  sched/fair: Remove redundant word " *"
  selftests/rseq: check if libc rseq support is registered
  ...

13 files changed, 837 insertions, 448 deletions

diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 24b5c2ab5598..feb59380c896 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -310,6 +310,9 @@ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat,
 	dst_bstat->cputime.utime += src_bstat->cputime.utime;
 	dst_bstat->cputime.stime += src_bstat->cputime.stime;
 	dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime;
+#ifdef CONFIG_SCHED_CORE
+	dst_bstat->forceidle_sum += src_bstat->forceidle_sum;
+#endif
 }
 
 static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
@@ -318,6 +321,9 @@ static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
 	dst_bstat->cputime.utime -= src_bstat->cputime.utime;
 	dst_bstat->cputime.stime -= src_bstat->cputime.stime;
 	dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime;
+#ifdef CONFIG_SCHED_CORE
+	dst_bstat->forceidle_sum -= src_bstat->forceidle_sum;
+#endif
 }
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)
@@ -398,6 +404,11 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
 	case CPUTIME_SOFTIRQ:
 		rstatc->bstat.cputime.stime += delta_exec;
 		break;
+#ifdef CONFIG_SCHED_CORE
+	case CPUTIME_FORCEIDLE:
+		rstatc->bstat.forceidle_sum += delta_exec;
+		break;
+#endif
 	default:
 		break;
 	}
@@ -411,8 +422,9 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
  * with how it is done by __cgroup_account_cputime_field for each bit of
  * cpu time attributed to a cgroup.
  */
-static void root_cgroup_cputime(struct task_cputime *cputime)
+static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
 {
+	struct task_cputime *cputime = &bstat->cputime;
 	int i;
 
 	cputime->stime = 0;
@@ -438,6 +450,10 @@ static void root_cgroup_cputime(struct task_cputime *cputime)
 		cputime->sum_exec_runtime += user;
 		cputime->sum_exec_runtime += sys;
 		cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL];
+
+#ifdef CONFIG_SCHED_CORE
+		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
+#endif
 	}
 }
 
@@ -445,27 +461,43 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
 	u64 usage, utime, stime;
-	struct task_cputime cputime;
+	struct cgroup_base_stat bstat;
+#ifdef CONFIG_SCHED_CORE
+	u64 forceidle_time;
+#endif
 
 	if (cgroup_parent(cgrp)) {
 		cgroup_rstat_flush_hold(cgrp);
 		usage = cgrp->bstat.cputime.sum_exec_runtime;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
 			       &utime, &stime);
+#ifdef CONFIG_SCHED_CORE
+		forceidle_time = cgrp->bstat.forceidle_sum;
+#endif
 		cgroup_rstat_flush_release();
 	} else {
-		root_cgroup_cputime(&cputime);
-		usage = cputime.sum_exec_runtime;
-		utime = cputime.utime;
-		stime = cputime.stime;
+		root_cgroup_cputime(&bstat);
+		usage = bstat.cputime.sum_exec_runtime;
+		utime = bstat.cputime.utime;
+		stime = bstat.cputime.stime;
+#ifdef CONFIG_SCHED_CORE
+		forceidle_time = bstat.forceidle_sum;
+#endif
 	}
 
 	do_div(usage, NSEC_PER_USEC);
 	do_div(utime, NSEC_PER_USEC);
 	do_div(stime, NSEC_PER_USEC);
+#ifdef CONFIG_SCHED_CORE
+	do_div(forceidle_time, NSEC_PER_USEC);
+#endif
 
 	seq_printf(seq, "usage_usec %llu\n"
 		   "user_usec %llu\n"
 		   "system_usec %llu\n",
 		   usage, utime, stime);
+
+#ifdef CONFIG_SCHED_CORE
+	seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time);
+#endif
 }
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 97ac20b4f738..bda8175f8f99 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -18,8 +18,9 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/rseq.h>
 
-#define RSEQ_CS_PREEMPT_MIGRATE_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE | \
-				       RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT)
+#define RSEQ_CS_NO_RESTART_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT | \
+				  RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \
+				  RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE)
 
 /*
  *
@@ -175,23 +176,15 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	u32 flags, event_mask;
 	int ret;
 
+	if (WARN_ON_ONCE(cs_flags & RSEQ_CS_NO_RESTART_FLAGS) || cs_flags)
+		return -EINVAL;
+
 	/* Get thread flags. */
 	ret = get_user(flags, &t->rseq->flags);
 	if (ret)
 		return ret;
 
-	/* Take critical section flags into account. */
-	flags |= cs_flags;
-
-	/*
-	 * Restart on signal can only be inhibited when restart on
-	 * preempt and restart on migrate are inhibited too. Otherwise,
-	 * a preempted signal handler could fail to restart the prior
-	 * execution context on sigreturn.
-	 */
-	if (unlikely((flags & RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL) &&
-		     (flags & RSEQ_CS_PREEMPT_MIGRATE_FLAGS) !=
-		     RSEQ_CS_PREEMPT_MIGRATE_FLAGS))
+	if (WARN_ON_ONCE(flags & RSEQ_CS_NO_RESTART_FLAGS) || flags)
 		return -EINVAL;
 
 	/*
@@ -203,7 +196,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	t->rseq_event_mask = 0;
 	preempt_enable();
 
-	return !!(event_mask & ~flags);
+	return !!event_mask;
 }
 
 static int clear_rseq_cs(struct task_struct *t)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index da0bf6fe9ecd..5555e49c4e12 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -873,15 +873,11 @@ static inline void hrtick_rq_init(struct rq *rq)
 	({								\
 		typeof(ptr) _ptr = (ptr);				\
 		typeof(mask) _mask = (mask);				\
-		typeof(*_ptr) _old, _val = *_ptr;			\
+		typeof(*_ptr) _val = *_ptr;				\
 									\
-		for (;;) {						\
-			_old = cmpxchg(_ptr, _val, _val | _mask);	\
-			if (_old == _val)				\
-				break;					\
-			_val = _old;					\
-		}							\
-	_old;								\
+		do {							\
+		} while (!try_cmpxchg(_ptr, &_val, _val | _mask));	\
+	_val;								\
 })
 
 #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
@@ -890,7 +886,7 @@ static inline void hrtick_rq_init(struct rq *rq)
  * this avoids any races wrt polling state changes and thereby avoids
  * spurious IPIs.
  */
-static bool set_nr_and_not_polling(struct task_struct *p)
+static inline bool set_nr_and_not_polling(struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
 	return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
@@ -905,30 +901,28 @@ static bool set_nr_and_not_polling(struct task_struct *p)
 static bool set_nr_if_polling(struct task_struct *p)
 {
 	struct thread_info *ti = task_thread_info(p);
-	typeof(ti->flags) old, val = READ_ONCE(ti->flags);
+	typeof(ti->flags) val = READ_ONCE(ti->flags);
 
 	for (;;) {
 		if (!(val & _TIF_POLLING_NRFLAG))
 			return false;
 		if (val & _TIF_NEED_RESCHED)
 			return true;
-		old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED);
-		if (old == val)
+		if (try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED))
 			break;
-		val = old;
 	}
 	return true;
 }
 
 #else
-static bool set_nr_and_not_polling(struct task_struct *p)
+static inline bool set_nr_and_not_polling(struct task_struct *p)
 {
 	set_tsk_need_resched(p);
 	return true;
 }
 
 #ifdef CONFIG_SMP
-static bool set_nr_if_polling(struct task_struct *p)
+static inline bool set_nr_if_polling(struct task_struct *p)
 {
 	return false;
 }
@@ -3808,7 +3802,7 @@ 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, int wake_flags)
+static inline bool ttwu_queue_cond(int cpu)
 {
 	/*
 	 * Do not complicate things with the async wake_list while the CPU is
@@ -3824,13 +3818,21 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 	if (!cpus_share_cache(smp_processor_id(), cpu))
 		return true;
 
+	if (cpu == smp_processor_id())
+		return false;
+
 	/*
-	 * If the task is descheduling and the only running task on the
-	 * CPU then use the wakelist to offload the task activation to
-	 * the soon-to-be-idle CPU as the current CPU is likely busy.
-	 * nr_running is checked to avoid unnecessary task stacking.
+	 * If the wakee cpu is idle, or the task is descheduling and the
+	 * only running task on the CPU, then use the wakelist to offload
+	 * the task activation to the idle (or soon-to-be-idle) CPU as
+	 * the current CPU is likely busy. nr_running is checked to
+	 * avoid unnecessary task stacking.
+	 *
+	 * Note that we can only get here with (wakee) p->on_rq=0,
+	 * p->on_cpu can be whatever, we've done the dequeue, so
+	 * the wakee has been accounted out of ->nr_running.
 	 */
-	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
+	if (!cpu_rq(cpu)->nr_running)
 		return true;
 
 	return false;
@@ -3838,10 +3840,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 
 static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
-	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
-		if (WARN_ON_ONCE(cpu == smp_processor_id()))
-			return false;
-
+	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu)) {
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
@@ -4163,7 +4162,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * scheduling.
 	 */
 	if (smp_load_acquire(&p->on_cpu) &&
-	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
 		goto unlock;
 
 	/*
@@ -4753,7 +4752,8 @@ static inline void prepare_task(struct task_struct *next)
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
 	 *
-	 * See the ttwu() WF_ON_CPU case and its ordering comment.
+	 * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
+	 * its ordering comment.
 	 */
 	WRITE_ONCE(next->on_cpu, 1);
 #endif
@@ -6500,8 +6500,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 			io_wq_worker_sleeping(tsk);
 	}
 
-	if (tsk_is_pi_blocked(tsk))
-		return;
+	/*
+	 * spinlock and rwlock must not flush block requests.  This will
+	 * deadlock if the callback attempts to acquire a lock which is
+	 * already acquired.
+	 */
+	SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
 
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
@@ -6998,17 +7002,29 @@ out_unlock:
 EXPORT_SYMBOL(set_user_nice);
 
 /*
- * can_nice - check if a task can reduce its nice value
+ * is_nice_reduction - check if nice value is an actual reduction
+ *
+ * Similar to can_nice() but does not perform a capability check.
+ *
  * @p: task
  * @nice: nice value
  */
-int can_nice(const struct task_struct *p, const int nice)
+static bool is_nice_reduction(const struct task_struct *p, const int nice)
 {
 	/* Convert nice value [19,-20] to rlimit style value [1,40]: */
 	int nice_rlim = nice_to_rlimit(nice);
 
-	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
-		capable(CAP_SYS_NICE));
+	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));
+}
+
+/*
+ * can_nice - check if a task can reduce its nice value
+ * @p: task
+ * @nice: nice value
+ */
+int can_nice(const struct task_struct *p, const int nice)
+{
+	return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);
 }
 
 #ifdef __ARCH_WANT_SYS_NICE
@@ -7137,12 +7153,14 @@ struct task_struct *idle_task(int cpu)
  * required to meet deadlines.
  */
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
-				 unsigned long max, enum cpu_util_type type,
+				 enum cpu_util_type type,
 				 struct task_struct *p)
 {
-	unsigned long dl_util, util, irq;
+	unsigned long dl_util, util, irq, max;
 	struct rq *rq = cpu_rq(cpu);
 
+	max = arch_scale_cpu_capacity(cpu);
+
 	if (!uclamp_is_used() &&
 	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
 		return max;
@@ -7222,10 +7240,9 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 	return min(max, util);
 }
 
-unsigned long sched_cpu_util(int cpu, unsigned long max)
+unsigned long sched_cpu_util(int cpu)
 {
-	return effective_cpu_util(cpu, cpu_util_cfs(cpu), max,
-				  ENERGY_UTIL, NULL);
+	return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL);
 }
 #endif /* CONFIG_SMP */
 
@@ -7287,6 +7304,69 @@ static bool check_same_owner(struct task_struct *p)
 	return match;
 }
 
+/*
+ * Allow unprivileged RT tasks to decrease priority.
+ * Only issue a capable test if needed and only once to avoid an audit
+ * event on permitted non-privileged operations:
+ */
+static int user_check_sched_setscheduler(struct task_struct *p,
+					 const struct sched_attr *attr,
+					 int policy, int reset_on_fork)
+{
+	if (fair_policy(policy)) {
+		if (attr->sched_nice < task_nice(p) &&
+		    !is_nice_reduction(p, attr->sched_nice))
+			goto req_priv;
+	}
+
+	if (rt_policy(policy)) {
+		unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
+
+		/* Can't set/change the rt policy: */
+		if (policy != p->policy && !rlim_rtprio)
+			goto req_priv;
+
+		/* Can't increase priority: */
+		if (attr->sched_priority > p->rt_priority &&
+		    attr->sched_priority > rlim_rtprio)
+			goto req_priv;
+	}
+
+	/*
+	 * Can't set/change SCHED_DEADLINE policy at all for now
+	 * (safest behavior); in the future we would like to allow
+	 * unprivileged DL tasks to increase their relative deadline
+	 * or reduce their runtime (both ways reducing utilization)
+	 */
+	if (dl_policy(policy))
+		goto req_priv;
+
+	/*
+	 * Treat SCHED_IDLE as nice 20. Only allow a switch to
+	 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
+	 */
+	if (task_has_idle_policy(p) && !idle_policy(policy)) {
+		if (!is_nice_reduction(p, task_nice(p)))
+			goto req_priv;
+	}
+
+	/* Can't change other user's priorities: */
+	if (!check_same_owner(p))
+		goto req_priv;
+
+	/* Normal users shall not reset the sched_reset_on_fork flag: */
+	if (p->sched_reset_on_fork && !reset_on_fork)
+		goto req_priv;
+
+	return 0;
+
+req_priv:
+	if (!capable(CAP_SYS_NICE))
+		return -EPERM;
+
+	return 0;
+}
+
 static int __sched_setscheduler(struct task_struct *p,
 				const struct sched_attr *attr,
 				bool user, bool pi)
@@ -7328,58 +7408,11 @@ recheck:
 	    (rt_policy(policy) != (attr->sched_priority != 0)))
 		return -EINVAL;
 
-	/*
-	 * Allow unprivileged RT tasks to decrease priority:
-	 */
-	if (user && !capable(CAP_SYS_NICE)) {
-		if (fair_policy(policy)) {
-			if (attr->sched_nice < task_nice(p) &&
-			    !can_nice(p, attr->sched_nice))
-				return -EPERM;
-		}
-
-		if (rt_policy(policy)) {
-			unsigned long rlim_rtprio =
-					task_rlimit(p, RLIMIT_RTPRIO);
-
-			/* Can't set/change the rt policy: */
-			if (policy != p->policy && !rlim_rtprio)
-				return -EPERM;
-
-			/* Can't increase priority: */
-			if (attr->sched_priority > p->rt_priority &&
-			    attr->sched_priority > rlim_rtprio)
-				return -EPERM;
-		}
-
-		 /*
-		  * Can't set/change SCHED_DEADLINE policy at all for now
-		  * (safest behavior); in the future we would like to allow
-		  * unprivileged DL tasks to increase their relative deadline
-		  * or reduce their runtime (both ways reducing utilization)
-		  */
-		if (dl_policy(policy))
-			return -EPERM;
-
-		/*
-		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
-		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
-		 */
-		if (task_has_idle_policy(p) && !idle_policy(policy)) {
-			if (!can_nice(p, task_nice(p)))
-				return -EPERM;
-		}
-
-		/* Can't change other user's priorities: */
-		if (!check_same_owner(p))
-			return -EPERM;
-
-		/* Normal users shall not reset the sched_reset_on_fork flag: */
-		if (p->sched_reset_on_fork && !reset_on_fork)
-			return -EPERM;
-	}
-
 	if (user) {
+		retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork);
+		if (retval)
+			return retval;
+
 		if (attr->sched_flags & SCHED_FLAG_SUGOV)
 			return -EINVAL;
 
@@ -9531,7 +9564,7 @@ static struct kmem_cache *task_group_cache __read_mostly;
 #endif
 
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
-DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
+DECLARE_PER_CPU(cpumask_var_t, select_rq_mask);
 
 void __init sched_init(void)
 {
@@ -9580,7 +9613,7 @@ void __init sched_init(void)
 	for_each_possible_cpu(i) {
 		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
 			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
-		per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node(
+		per_cpu(select_rq_mask, i) = (cpumask_var_t)kzalloc_node(
 			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
 	}
 #endif /* CONFIG_CPUMASK_OFFSTACK */
diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c
index 38a2cec21014..93878cb2a46d 100644
--- a/kernel/sched/core_sched.c
+++ b/kernel/sched/core_sched.c
@@ -56,7 +56,6 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
 	unsigned long old_cookie;
 	struct rq_flags rf;
 	struct rq *rq;
-	bool enqueued;
 
 	rq = task_rq_lock(p, &rf);
 
@@ -68,14 +67,16 @@ static unsigned long sched_core_update_cookie(struct task_struct *p,
 	 */
 	SCHED_WARN_ON((p->core_cookie || cookie) && !sched_core_enabled(rq));
 
-	enqueued = sched_core_enqueued(p);
-	if (enqueued)
+	if (sched_core_enqueued(p))
 		sched_core_dequeue(rq, p, DEQUEUE_SAVE);
 
 	old_cookie = p->core_cookie;
 	p->core_cookie = cookie;
 
-	if (enqueued)
+	/*
+	 * Consider the cases: !prev_cookie and !cookie.
+	 */
+	if (cookie && task_on_rq_queued(p))
 		sched_core_enqueue(rq, p);
 
 	/*
@@ -277,7 +278,11 @@ void __sched_core_account_forceidle(struct rq *rq)
 		if (p == rq_i->idle)
 			continue;
 
-		__schedstat_add(p->stats.core_forceidle_sum, delta);
+		/*
+		 * Note: this will account forceidle to the current cpu, even
+		 * if it comes from our SMT sibling.
+		 */
+		__account_forceidle_time(p, delta);
 	}
 }
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3dbf351d12d5..1207c78f85c1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -157,11 +157,10 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 static void sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);
 
-	sg_cpu->max = max;
+	sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
-	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), max,
+	sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),
 					  FREQUENCY_UTIL, NULL);
 }
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 78a233d43757..95fc77853743 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -226,6 +226,21 @@ void account_idle_time(u64 cputime)
 		cpustat[CPUTIME_IDLE] += cputime;
 }
 
+
+#ifdef CONFIG_SCHED_CORE
+/*
+ * Account for forceidle time due to core scheduling.
+ *
+ * REQUIRES: schedstat is enabled.
+ */
+void __account_forceidle_time(struct task_struct *p, u64 delta)
+{
+	__schedstat_add(p->stats.core_forceidle_sum, delta);
+
+	task_group_account_field(p, CPUTIME_FORCEIDLE, delta);
+}
+#endif
+
 /*
  * When a guest is interrupted for a longer amount of time, missed clock
  * ticks are not redelivered later. Due to that, this function may on
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7bf561262cb8..0ab79d819a0d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -30,14 +30,16 @@ static struct ctl_table sched_dl_sysctls[] = {
 		.data           = &sysctl_sched_dl_period_max,
 		.maxlen         = sizeof(unsigned int),
 		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
+		.proc_handler   = proc_douintvec_minmax,
+		.extra1         = (void *)&sysctl_sched_dl_period_min,
 	},
 	{
 		.procname       = "sched_deadline_period_min_us",
 		.data           = &sysctl_sched_dl_period_min,
 		.maxlen         = sizeof(unsigned int),
 		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
+		.proc_handler   = proc_douintvec_minmax,
+		.extra2         = (void *)&sysctl_sched_dl_period_max,
 	},
 	{}
 };
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 77b2048a9326..914096c5b1ae 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -612,11 +612,8 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
 	}
 
 	/* ensure we never gain time by being placed backwards. */
-	cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
-#ifndef CONFIG_64BIT
-	smp_wmb();
-	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
-#endif
+	u64_u32_store(cfs_rq->min_vruntime,
+		      max_vruntime(cfs_rq->min_vruntime, vruntime));
 }
 
 static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
@@ -1055,6 +1052,33 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
+#ifdef CONFIG_NUMA
+#define NUMA_IMBALANCE_MIN 2
+
+static inline long
+adjust_numa_imbalance(int imbalance, int dst_running, int imb_numa_nr)
+{
+	/*
+	 * Allow a NUMA imbalance if busy CPUs is less than the maximum
+	 * threshold. Above this threshold, individual tasks may be contending
+	 * for both memory bandwidth and any shared HT resources.  This is an
+	 * approximation as the number of running tasks may not be related to
+	 * the number of busy CPUs due to sched_setaffinity.
+	 */
+	if (dst_running > imb_numa_nr)
+		return imbalance;
+
+	/*
+	 * Allow a small imbalance based on a simple pair of communicating
+	 * tasks that remain local when the destination is lightly loaded.
+	 */
+	if (imbalance <= NUMA_IMBALANCE_MIN)
+		return 0;
+
+	return imbalance;
+}
+#endif /* CONFIG_NUMA */
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * Approximate time to scan a full NUMA task in ms. The task scan period is
@@ -1548,8 +1572,6 @@ struct task_numa_env {
 
 static unsigned long cpu_load(struct rq *rq);
 static unsigned long cpu_runnable(struct rq *rq);
-static inline long adjust_numa_imbalance(int imbalance,
-					int dst_running, int imb_numa_nr);
 
 static inline enum
 numa_type numa_classify(unsigned int imbalance_pct,
@@ -1790,6 +1812,15 @@ static bool task_numa_compare(struct task_numa_env *env,
 	 */
 	cur_ng = rcu_dereference(cur->numa_group);
 	if (cur_ng == p_ng) {
+		/*
+		 * Do not swap within a group or between tasks that have
+		 * no group if there is spare capacity. Swapping does
+		 * not address the load imbalance and helps one task at
+		 * the cost of punishing another.
+		 */
+		if (env->dst_stats.node_type == node_has_spare)
+			goto unlock;
+
 		imp = taskimp + task_weight(cur, env->src_nid, dist) -
 		      task_weight(cur, env->dst_nid, dist);
 		/*
@@ -2885,6 +2916,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 	p->node_stamp			= 0;
 	p->numa_scan_seq		= mm ? mm->numa_scan_seq : 0;
 	p->numa_scan_period		= sysctl_numa_balancing_scan_delay;
+	p->numa_migrate_retry		= 0;
 	/* Protect against double add, see task_tick_numa and task_numa_work */
 	p->numa_work.next		= &p->numa_work;
 	p->numa_faults			= NULL;
@@ -3144,6 +3176,8 @@ void reweight_task(struct task_struct *p, int prio)
 	load->inv_weight = sched_prio_to_wmult[prio];
 }
 
+static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
 /*
@@ -3254,8 +3288,6 @@ static long calc_group_shares(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_SMP */
 
-static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
-
 /*
  * Recomputes the group entity based on the current state of its group
  * runqueue.
@@ -3313,6 +3345,34 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 }
 
 #ifdef CONFIG_SMP
+static inline bool load_avg_is_decayed(struct sched_avg *sa)
+{
+	if (sa->load_sum)
+		return false;
+
+	if (sa->util_sum)
+		return false;
+
+	if (sa->runnable_sum)
+		return false;
+
+	/*
+	 * _avg must be null when _sum are null because _avg = _sum / divider
+	 * Make sure that rounding and/or propagation of PELT values never
+	 * break this.
+	 */
+	SCHED_WARN_ON(sa->load_avg ||
+		      sa->util_avg ||
+		      sa->runnable_avg);
+
+	return true;
+}
+
+static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
+{
+	return u64_u32_load_copy(cfs_rq->avg.last_update_time,
+				 cfs_rq->last_update_time_copy);
+}
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /*
  * Because list_add_leaf_cfs_rq always places a child cfs_rq on the list
@@ -3345,27 +3405,12 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
 	if (cfs_rq->load.weight)
 		return false;
 
-	if (cfs_rq->avg.load_sum)
-		return false;
-
-	if (cfs_rq->avg.util_sum)
-		return false;
-
-	if (cfs_rq->avg.runnable_sum)
+	if (!load_avg_is_decayed(&cfs_rq->avg))
 		return false;
 
 	if (child_cfs_rq_on_list(cfs_rq))
 		return false;
 
-	/*
-	 * _avg must be null when _sum are null because _avg = _sum / divider
-	 * Make sure that rounding and/or propagation of PELT values never
-	 * break this.
-	 */
-	SCHED_WARN_ON(cfs_rq->avg.load_avg ||
-		      cfs_rq->avg.util_avg ||
-		      cfs_rq->avg.runnable_avg);
-
 	return true;
 }
 
@@ -3423,27 +3468,9 @@ void set_task_rq_fair(struct sched_entity *se,
 	if (!(se->avg.last_update_time && prev))
 		return;
 
-#ifndef CONFIG_64BIT
-	{
-		u64 p_last_update_time_copy;
-		u64 n_last_update_time_copy;
-
-		do {
-			p_last_update_time_copy = prev->load_last_update_time_copy;
-			n_last_update_time_copy = next->load_last_update_time_copy;
-
-			smp_rmb();
-
-			p_last_update_time = prev->avg.last_update_time;
-			n_last_update_time = next->avg.last_update_time;
+	p_last_update_time = cfs_rq_last_update_time(prev);
+	n_last_update_time = cfs_rq_last_update_time(next);
 
-		} while (p_last_update_time != p_last_update_time_copy ||
-			 n_last_update_time != n_last_update_time_copy);
-	}
-#else
-	p_last_update_time = prev->avg.last_update_time;
-	n_last_update_time = next->avg.last_update_time;
-#endif
 	__update_load_avg_blocked_se(p_last_update_time, se);
 	se->avg.last_update_time = n_last_update_time;
 }
@@ -3722,6 +3749,89 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
+#ifdef CONFIG_NO_HZ_COMMON
+static inline void migrate_se_pelt_lag(struct sched_entity *se)
+{
+	u64 throttled = 0, now, lut;
+	struct cfs_rq *cfs_rq;
+	struct rq *rq;
+	bool is_idle;
+
+	if (load_avg_is_decayed(&se->avg))
+		return;
+
+	cfs_rq = cfs_rq_of(se);
+	rq = rq_of(cfs_rq);
+
+	rcu_read_lock();
+	is_idle = is_idle_task(rcu_dereference(rq->curr));
+	rcu_read_unlock();
+
+	/*
+	 * The lag estimation comes with a cost we don't want to pay all the
+	 * time. Hence, limiting to the case where the source CPU is idle and
+	 * we know we are at the greatest risk to have an outdated clock.
+	 */
+	if (!is_idle)
+		return;
+
+	/*
+	 * Estimated "now" is: last_update_time + cfs_idle_lag + rq_idle_lag, where:
+	 *
+	 *   last_update_time (the cfs_rq's last_update_time)
+	 *	= cfs_rq_clock_pelt()@cfs_rq_idle
+	 *      = rq_clock_pelt()@cfs_rq_idle
+	 *        - cfs->throttled_clock_pelt_time@cfs_rq_idle
+	 *
+	 *   cfs_idle_lag (delta between rq's update and cfs_rq's u