Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - introduce and use task_rcu_dereference()/try_get_task_struct() to fix
   and generalize task_struct handling (Oleg Nesterov)

 - do various per entity load tracking (PELT) fixes and optimizations
   (Peter Zijlstra)

 - cputime virt-steal time accounting enhancements/fixes (Wanpeng Li)

 - introduce consolidated cputime output file cpuacct.usage_all and
   related refactorings (Zhao Lei)

 - ... plus misc fixes and enhancements

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/core: Panic on scheduling while atomic bugs if kernel.panic_on_warn is set
  sched/cpuacct: Introduce cpuacct.usage_all to show all CPU stats together
  sched/cpuacct: Use loop to consolidate code in cpuacct_stats_show()
  sched/cpuacct: Merge cpuacct_usage_index and cpuacct_stat_index enums
  sched/fair: Rework throttle_count sync
  sched/core: Fix sched_getaffinity() return value kerneldoc comment
  sched/fair: Reorder cgroup creation code
  sched/fair: Apply more PELT fixes
  sched/fair: Fix PELT integrity for new tasks
  sched/cgroup: Fix cpu_cgroup_fork() handling
  sched/fair: Fix PELT integrity for new groups
  sched/fair: Fix and optimize the fork() path
  sched/cputime: Add steal time support to full dynticks CPU time accounting
  sched/cputime: Fix prev steal time accouting during CPU hotplug
  KVM: Fix steal clock warp during guest CPU hotplug
  sched/debug: Always show 'nr_migrations'
  sched/fair: Use task_rcu_dereference()
  sched/api: Introduce task_rcu_dereference() and try_get_task_struct()
  sched/idle: Optimize the generic idle loop
  sched/fair: Fix the wrong throttled clock time for cfs_rq_clock_task()
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index eea2a6f..1ef5e48 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -301,8 +301,6 @@
 	if (!has_steal_clock)
 		return;
 
-	memset(st, 0, sizeof(*st));
-
 	wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
 	pr_info("kvm-stealtime: cpu %d, msr %llx\n",
 		cpu, (unsigned long long) slow_virt_to_phys(st));
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 253538f..d99218a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -219,9 +219,10 @@
 #define TASK_WAKING		256
 #define TASK_PARKED		512
 #define TASK_NOLOAD		1024
-#define TASK_STATE_MAX		2048
+#define TASK_NEW		2048
+#define TASK_STATE_MAX		4096
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn"
 
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -2139,6 +2140,9 @@
 		__put_task_struct(t);
 }
 
+struct task_struct *task_rcu_dereference(struct task_struct **ptask);
+struct task_struct *try_get_task_struct(struct task_struct **ptask);
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void task_cputime(struct task_struct *t,
 			 cputime_t *utime, cputime_t *stime);
diff --git a/kernel/exit.c b/kernel/exit.c
index 0b40791..84ae830 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -211,6 +211,82 @@
 }
 
 /*
+ * Note that if this function returns a valid task_struct pointer (!NULL)
+ * task->usage must remain >0 for the duration of the RCU critical section.
+ */
+struct task_struct *task_rcu_dereference(struct task_struct **ptask)
+{
+	struct sighand_struct *sighand;
+	struct task_struct *task;
+
+	/*
+	 * We need to verify that release_task() was not called and thus
+	 * delayed_put_task_struct() can't run and drop the last reference
+	 * before rcu_read_unlock(). We check task->sighand != NULL,
+	 * but we can read the already freed and reused memory.
+	 */
+retry:
+	task = rcu_dereference(*ptask);
+	if (!task)
+		return NULL;
+
+	probe_kernel_address(&task->sighand, sighand);
+
+	/*
+	 * Pairs with atomic_dec_and_test() in put_task_struct(). If this task
+	 * was already freed we can not miss the preceding update of this
+	 * pointer.
+	 */
+	smp_rmb();
+	if (unlikely(task != READ_ONCE(*ptask)))
+		goto retry;
+
+	/*
+	 * We've re-checked that "task == *ptask", now we have two different
+	 * cases:
+	 *
+	 * 1. This is actually the same task/task_struct. In this case
+	 *    sighand != NULL tells us it is still alive.
+	 *
+	 * 2. This is another task which got the same memory for task_struct.
+	 *    We can't know this of course, and we can not trust
+	 *    sighand != NULL.
+	 *
+	 *    In this case we actually return a random value, but this is
+	 *    correct.
+	 *
+	 *    If we return NULL - we can pretend that we actually noticed that
+	 *    *ptask was updated when the previous task has exited. Or pretend
+	 *    that probe_slab_address(&sighand) reads NULL.
+	 *
+	 *    If we return the new task (because sighand is not NULL for any
+	 *    reason) - this is fine too. This (new) task can't go away before
+	 *    another gp pass.
+	 *
+	 *    And note: We could even eliminate the false positive if re-read
+	 *    task->sighand once again to avoid the falsely NULL. But this case
+	 *    is very unlikely so we don't care.
+	 */
+	if (!sighand)
+		return NULL;
+
+	return task;
+}
+
+struct task_struct *try_get_task_struct(struct task_struct **ptask)
+{
+	struct task_struct *task;
+
+	rcu_read_lock();
+	task = task_rcu_dereference(ptask);
+	if (task)
+		get_task_struct(task);
+	rcu_read_unlock();
+
+	return task;
+}
+
+/*
  * Determine if a process group is "orphaned", according to the POSIX
  * definition in 2.2.2.52.  Orphaned process groups are not to be affected
  * by terminal-generated stop signals.  Newly orphaned process groups are
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index af0ef74..5c883fe 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2342,11 +2342,11 @@
 
 	__sched_fork(clone_flags, p);
 	/*
-	 * We mark the process as running here. This guarantees that
+	 * We mark the process as NEW here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
 	 * event cannot wake it up and insert it on the runqueue either.
 	 */
-	p->state = TASK_RUNNING;
+	p->state = TASK_NEW;
 
 	/*
 	 * Make sure we do not leak PI boosting priority to the child.
@@ -2383,8 +2383,7 @@
 		p->sched_class = &fair_sched_class;
 	}
 
-	if (p->sched_class->task_fork)
-		p->sched_class->task_fork(p);
+	init_entity_runnable_average(&p->se);
 
 	/*
 	 * The child is not yet in the pid-hash so no cgroup attach races,
@@ -2394,7 +2393,13 @@
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	set_task_cpu(p, cpu);
+	/*
+	 * We're setting the cpu for the first time, we don't migrate,
+	 * so use __set_task_cpu().
+	 */
+	__set_task_cpu(p, cpu);
+	if (p->sched_class->task_fork)
+		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 #ifdef CONFIG_SCHED_INFO
@@ -2526,16 +2531,18 @@
 	struct rq_flags rf;
 	struct rq *rq;
 
-	/* Initialize new task's runnable average */
-	init_entity_runnable_average(&p->se);
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
+	p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
+	 *
+	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
+	 * as we're not fully set-up yet.
 	 */
-	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
+	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
 	post_init_entity_util_avg(&p->se);
@@ -3161,6 +3168,9 @@
 		pr_cont("\n");
 	}
 #endif
+	if (panic_on_warn)
+		panic("scheduling while atomic\n");
+
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
@@ -4752,7 +4762,8 @@
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to hold the current cpu mask
  *
- * Return: 0 on success. An error code otherwise.
+ * Return: size of CPU mask copied to user_mask_ptr on success. An
+ * error code otherwise.
  */
 SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 		unsigned long __user *, user_mask_ptr)
@@ -7233,7 +7244,6 @@
 	struct rq *rq = cpu_rq(cpu);
 
 	rq->calc_load_update = calc_load_update;
-	account_reset_rq(rq);
 	update_max_interval();
 }
 
@@ -7713,6 +7723,8 @@
 	INIT_LIST_HEAD(&tg->children);
 	list_add_rcu(&tg->siblings, &parent->children);
 	spin_unlock_irqrestore(&task_group_lock, flags);
+
+	online_fair_sched_group(tg);
 }
 
 /* rcu callback to free various structures associated with a task group */
@@ -7741,14 +7753,37 @@
 	spin_unlock_irqrestore(&task_group_lock, flags);
 }
 
-/* change task's runqueue when it moves between groups.
- *	The caller of this function should have put the task in its new group
- *	by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
- *	reflect its new group.
+static void sched_change_group(struct task_struct *tsk, int type)
+{
+	struct task_group *tg;
+
+	/*
+	 * All callers are synchronized by task_rq_lock(); we do not use RCU
+	 * which is pointless here. Thus, we pass "true" to task_css_check()
+	 * to prevent lockdep warnings.
+	 */
+	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
+			  struct task_group, css);
+	tg = autogroup_task_group(tsk, tg);
+	tsk->sched_task_group = tg;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	if (tsk->sched_class->task_change_group)
+		tsk->sched_class->task_change_group(tsk, type);
+	else
+#endif
+		set_task_rq(tsk, task_cpu(tsk));
+}
+
+/*
+ * Change task's runqueue when it moves between groups.
+ *
+ * The caller of this function should have put the task in its new group by
+ * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
+ * its new group.
  */
 void sched_move_task(struct task_struct *tsk)
 {
-	struct task_group *tg;
 	int queued, running;
 	struct rq_flags rf;
 	struct rq *rq;
@@ -7763,22 +7798,7 @@
 	if (unlikely(running))
 		put_prev_task(rq, tsk);
 
-	/*
-	 * All callers are synchronized by task_rq_lock(); we do not use RCU
-	 * which is pointless here. Thus, we pass "true" to task_css_check()
-	 * to prevent lockdep warnings.
-	 */
-	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
-			  struct task_group, css);
-	tg = autogroup_task_group(tsk, tg);
-	tsk->sched_task_group = tg;
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	if (tsk->sched_class->task_move_group)
-		tsk->sched_class->task_move_group(tsk);
-	else
-#endif
-		set_task_rq(tsk, task_cpu(tsk));
+	sched_change_group(tsk, TASK_MOVE_GROUP);
 
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
@@ -8206,15 +8226,27 @@
 	sched_free_group(tg);
 }
 
+/*
+ * This is called before wake_up_new_task(), therefore we really only
+ * have to set its group bits, all the other stuff does not apply.
+ */
 static void cpu_cgroup_fork(struct task_struct *task)
 {
-	sched_move_task(task);
+	struct rq_flags rf;
+	struct rq *rq;
+
+	rq = task_rq_lock(task, &rf);
+
+	sched_change_group(task, TASK_SET_GROUP);
+
+	task_rq_unlock(rq, task, &rf);
 }
 
 static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
 	struct cgroup_subsys_state *css;
+	int ret = 0;
 
 	cgroup_taskset_for_each(task, css, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -8225,8 +8257,24 @@
 		if (task->sched_class != &fair_sched_class)
 			return -EINVAL;
 #endif
+		/*
+		 * Serialize against wake_up_new_task() such that if its
+		 * running, we're sure to observe its full state.
+		 */
+		raw_spin_lock_irq(&task->pi_lock);
+		/*
+		 * Avoid calling sched_move_task() before wake_up_new_task()
+		 * has happened. This would lead to problems with PELT, due to
+		 * move wanting to detach+attach while we're not attached yet.
+		 */
+		if (task->state == TASK_NEW)
+			ret = -EINVAL;
+		raw_spin_unlock_irq(&task->pi_lock);
+
+		if (ret)
+			break;
 	}
-	return 0;
+	return ret;
 }
 
 static void cpu_cgroup_attach(struct cgroup_taskset *tset)
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 41f85c4..bc0b309c 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -25,15 +25,13 @@
 	CPUACCT_STAT_NSTATS,
 };
 
-enum cpuacct_usage_index {
-	CPUACCT_USAGE_USER,	/* ... user mode */
-	CPUACCT_USAGE_SYSTEM,	/* ... kernel mode */
-
-	CPUACCT_USAGE_NRUSAGE,
+static const char * const cpuacct_stat_desc[] = {
+	[CPUACCT_STAT_USER] = "user",
+	[CPUACCT_STAT_SYSTEM] = "system",
 };
 
 struct cpuacct_usage {
-	u64	usages[CPUACCT_USAGE_NRUSAGE];
+	u64	usages[CPUACCT_STAT_NSTATS];
 };
 
 /* track cpu usage of a group of tasks and its child groups */
@@ -108,16 +106,16 @@
 }
 
 static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu,
-				 enum cpuacct_usage_index index)
+				 enum cpuacct_stat_index index)
 {
 	struct cpuacct_usage *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
 	u64 data;
 
 	/*
-	 * We allow index == CPUACCT_USAGE_NRUSAGE here to read
+	 * We allow index == CPUACCT_STAT_NSTATS here to read
 	 * the sum of suages.
 	 */
-	BUG_ON(index > CPUACCT_USAGE_NRUSAGE);
+	BUG_ON(index > CPUACCT_STAT_NSTATS);
 
 #ifndef CONFIG_64BIT
 	/*
@@ -126,11 +124,11 @@
 	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
 #endif
 
-	if (index == CPUACCT_USAGE_NRUSAGE) {
+	if (index == CPUACCT_STAT_NSTATS) {
 		int i = 0;
 
 		data = 0;
-		for (i = 0; i < CPUACCT_USAGE_NRUSAGE; i++)
+		for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
 			data += cpuusage->usages[i];
 	} else {
 		data = cpuusage->usages[index];
@@ -155,7 +153,7 @@
 	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
 #endif
 
-	for (i = 0; i < CPUACCT_USAGE_NRUSAGE; i++)
+	for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
 		cpuusage->usages[i] = val;
 
 #ifndef CONFIG_64BIT
@@ -165,7 +163,7 @@
 
 /* return total cpu usage (in nanoseconds) of a group */
 static u64 __cpuusage_read(struct cgroup_subsys_state *css,
-			   enum cpuacct_usage_index index)
+			   enum cpuacct_stat_index index)
 {
 	struct cpuacct *ca = css_ca(css);
 	u64 totalcpuusage = 0;
@@ -180,18 +178,18 @@
 static u64 cpuusage_user_read(struct cgroup_subsys_state *css,
 			      struct cftype *cft)
 {
-	return __cpuusage_read(css, CPUACCT_USAGE_USER);
+	return __cpuusage_read(css, CPUACCT_STAT_USER);
 }
 
 static u64 cpuusage_sys_read(struct cgroup_subsys_state *css,
 			     struct cftype *cft)
 {
-	return __cpuusage_read(css, CPUACCT_USAGE_SYSTEM);
+	return __cpuusage_read(css, CPUACCT_STAT_SYSTEM);
 }
 
 static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
-	return __cpuusage_read(css, CPUACCT_USAGE_NRUSAGE);
+	return __cpuusage_read(css, CPUACCT_STAT_NSTATS);
 }
 
 static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
@@ -213,7 +211,7 @@
 }
 
 static int __cpuacct_percpu_seq_show(struct seq_file *m,
-				     enum cpuacct_usage_index index)
+				     enum cpuacct_stat_index index)
 {
 	struct cpuacct *ca = css_ca(seq_css(m));
 	u64 percpu;
@@ -229,48 +227,78 @@
 
 static int cpuacct_percpu_user_seq_show(struct seq_file *m, void *V)
 {
-	return __cpuacct_percpu_seq_show(m, CPUACCT_USAGE_USER);
+	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_USER);
 }
 
 static int cpuacct_percpu_sys_seq_show(struct seq_file *m, void *V)
 {
-	return __cpuacct_percpu_seq_show(m, CPUACCT_USAGE_SYSTEM);
+	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_SYSTEM);
 }
 
 static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
 {
-	return __cpuacct_percpu_seq_show(m, CPUACCT_USAGE_NRUSAGE);
+	return __cpuacct_percpu_seq_show(m, CPUACCT_STAT_NSTATS);
 }
 
-static const char * const cpuacct_stat_desc[] = {
-	[CPUACCT_STAT_USER] = "user",
-	[CPUACCT_STAT_SYSTEM] = "system",
-};
+static int cpuacct_all_seq_show(struct seq_file *m, void *V)
+{
+	struct cpuacct *ca = css_ca(seq_css(m));
+	int index;
+	int cpu;
+
+	seq_puts(m, "cpu");
+	for (index = 0; index < CPUACCT_STAT_NSTATS; index++)
+		seq_printf(m, " %s", cpuacct_stat_desc[index]);
+	seq_puts(m, "\n");
+
+	for_each_possible_cpu(cpu) {
+		struct cpuacct_usage *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+
+		seq_printf(m, "%d", cpu);
+
+		for (index = 0; index < CPUACCT_STAT_NSTATS; index++) {
+#ifndef CONFIG_64BIT
+			/*
+			 * Take rq->lock to make 64-bit read safe on 32-bit
+			 * platforms.
+			 */
+			raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+#endif
+
+			seq_printf(m, " %llu", cpuusage->usages[index]);
+
+#ifndef CONFIG_64BIT
+			raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+#endif
+		}
+		seq_puts(m, "\n");
+	}
+	return 0;
+}
 
 static int cpuacct_stats_show(struct seq_file *sf, void *v)
 {
 	struct cpuacct *ca = css_ca(seq_css(sf));
+	s64 val[CPUACCT_STAT_NSTATS];
 	int cpu;
-	s64 val = 0;
+	int stat;
 
+	memset(val, 0, sizeof(val));
 	for_each_possible_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_USER];
-		val += kcpustat->cpustat[CPUTIME_NICE];
-	}
-	val = cputime64_to_clock_t(val);
-	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
+		u64 *cpustat = per_cpu_ptr(ca->cpustat, cpu)->cpustat;
 
-	val = 0;
-	for_each_possible_cpu(cpu) {
-		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
-		val += kcpustat->cpustat[CPUTIME_SYSTEM];
-		val += kcpustat->cpustat[CPUTIME_IRQ];
-		val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
+		val[CPUACCT_STAT_USER]   += cpustat[CPUTIME_USER];
+		val[CPUACCT_STAT_USER]   += cpustat[CPUTIME_NICE];
+		val[CPUACCT_STAT_SYSTEM] += cpustat[CPUTIME_SYSTEM];
+		val[CPUACCT_STAT_SYSTEM] += cpustat[CPUTIME_IRQ];
+		val[CPUACCT_STAT_SYSTEM] += cpustat[CPUTIME_SOFTIRQ];
 	}
 
-	val = cputime64_to_clock_t(val);
-	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+	for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) {
+		seq_printf(sf, "%s %lld\n",
+			   cpuacct_stat_desc[stat],
+			   cputime64_to_clock_t(val[stat]));
+	}
 
 	return 0;
 }
@@ -302,6 +330,10 @@
 		.seq_show = cpuacct_percpu_sys_seq_show,
 	},
 	{
+		.name = "usage_all",
+		.seq_show = cpuacct_all_seq_show,
+	},
+	{
 		.name = "stat",
 		.seq_show = cpuacct_stats_show,
 	},
@@ -316,11 +348,11 @@
 void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
 	struct cpuacct *ca;
-	int index = CPUACCT_USAGE_SYSTEM;
+	int index = CPUACCT_STAT_SYSTEM;
 	struct pt_regs *regs = task_pt_regs(tsk);
 
 	if (regs && user_mode(regs))
-		index = CPUACCT_USAGE_USER;
+		index = CPUACCT_STAT_USER;
 
 	rcu_read_lock();
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 75f98c5..3d60e5d 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -257,7 +257,7 @@
 		cpustat[CPUTIME_IDLE] += (__force u64) cputime;
 }
 
-static __always_inline bool steal_account_process_tick(void)
+static __always_inline unsigned long steal_account_process_tick(unsigned long max_jiffies)
 {
 #ifdef CONFIG_PARAVIRT
 	if (static_key_false(&paravirt_steal_enabled)) {
@@ -272,14 +272,14 @@
 		 * time in jiffies. Lets cast the result to jiffies
 		 * granularity and account the rest on the next rounds.
 		 */
-		steal_jiffies = nsecs_to_jiffies(steal);
+		steal_jiffies = min(nsecs_to_jiffies(steal), max_jiffies);
 		this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies);
 
 		account_steal_time(jiffies_to_cputime(steal_jiffies));
 		return steal_jiffies;
 	}
 #endif
-	return false;
+	return 0;
 }
 
 /*
@@ -346,7 +346,7 @@
 	u64 cputime = (__force u64) cputime_one_jiffy;
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
-	if (steal_account_process_tick())
+	if (steal_account_process_tick(ULONG_MAX))
 		return;
 
 	cputime *= ticks;
@@ -477,7 +477,7 @@
 		return;
 	}
 
-	if (steal_account_process_tick())
+	if (steal_account_process_tick(ULONG_MAX))
 		return;
 
 	if (user_tick)
@@ -681,12 +681,14 @@
 static cputime_t get_vtime_delta(struct task_struct *tsk)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	unsigned long delta = now - tsk->vtime_snap;
+	unsigned long delta_jiffies, steal_jiffies;
 
+	delta_jiffies = now - tsk->vtime_snap;
+	steal_jiffies = steal_account_process_tick(delta_jiffies);
 	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
 	tsk->vtime_snap = now;
 
-	return jiffies_to_cputime(delta);
+	return jiffies_to_cputime(delta_jiffies - steal_jiffies);
 }
 
 static void __vtime_account_system(struct task_struct *tsk)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 0368c39..2a0a999 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -879,9 +879,9 @@
 
 	nr_switches = p->nvcsw + p->nivcsw;
 
-#ifdef CONFIG_SCHEDSTATS
 	P(se.nr_migrations);
 
+#ifdef CONFIG_SCHEDSTATS
 	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c8c5d2d..4088eed 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -690,6 +690,11 @@
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
+static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
+static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq);
+static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force);
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
 /*
  * With new tasks being created, their initial util_avgs are extrapolated
  * based on the cfs_rq's current util_avg:
@@ -720,6 +725,8 @@
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct sched_avg *sa = &se->avg;
 	long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+	u64 now = cfs_rq_clock_task(cfs_rq);
+	int tg_update;
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
@@ -733,16 +740,42 @@
 		}
 		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	}
+
+	if (entity_is_task(se)) {
+		struct task_struct *p = task_of(se);
+		if (p->sched_class != &fair_sched_class) {
+			/*
+			 * For !fair tasks do:
+			 *
+			update_cfs_rq_load_avg(now, cfs_rq, false);
+			attach_entity_load_avg(cfs_rq, se);
+			switched_from_fair(rq, p);
+			 *
+			 * such that the next switched_to_fair() has the
+			 * expected state.
+			 */
+			se->avg.last_update_time = now;
+			return;
+		}
+	}
+
+	tg_update = update_cfs_rq_load_avg(now, cfs_rq, false);
+	attach_entity_load_avg(cfs_rq, se);
+	if (tg_update)
+		update_tg_load_avg(cfs_rq, false);
 }
 
-#else
+#else /* !CONFIG_SMP */
 void init_entity_runnable_average(struct sched_entity *se)
 {
 }
 void post_init_entity_util_avg(struct sched_entity *se)
 {
 }
-#endif
+static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+{
+}
+#endif /* CONFIG_SMP */
 
 /*
  * Update the current task's runtime statistics.
@@ -1303,6 +1336,8 @@
 {
 	if (env->best_task)
 		put_task_struct(env->best_task);
+	if (p)
+		get_task_struct(p);
 
 	env->best_task = p;
 	env->best_imp = imp;
@@ -1370,31 +1405,11 @@
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
 	int dist = env->dist;
-	bool assigned = false;
 
 	rcu_read_lock();
-
-	raw_spin_lock_irq(&dst_rq->lock);
-	cur = dst_rq->curr;
-	/*
-	 * No need to move the exiting task or idle task.
-	 */
-	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
+	cur = task_rcu_dereference(&dst_rq->curr);
+	if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
 		cur = NULL;
-	else {
-		/*
-		 * The task_struct must be protected here to protect the
-		 * p->numa_faults access in the task_weight since the
-		 * numa_faults could already be freed in the following path:
-		 * finish_task_switch()
-		 *     --> put_task_struct()
-		 *         --> __put_task_struct()
-		 *             --> task_numa_free()
-		 */
-		get_task_struct(cur);
-	}
-
-	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
 	 * Because we have preemption enabled we can get migrated around and
@@ -1477,7 +1492,6 @@
 		 */
 		if (!load_too_imbalanced(src_load, dst_load, env)) {
 			imp = moveimp - 1;
-			put_task_struct(cur);
 			cur = NULL;
 			goto assign;
 		}
@@ -1503,16 +1517,9 @@
 		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
-	assigned = true;
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
-	/*
-	 * The dst_rq->curr isn't assigned. The protection for task_struct is
-	 * finished.
-	 */
-	if (cur && !assigned)
-		put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
@@ -2866,8 +2873,6 @@
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
-
 static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
@@ -2914,7 +2919,23 @@
 	WRITE_ONCE(*ptr, res);					\
 } while (0)
 
-/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
+/**
+ * update_cfs_rq_load_avg - update the cfs_rq's load/util averages
+ * @now: current time, as per cfs_rq_clock_task()
+ * @cfs_rq: cfs_rq to update
+ * @update_freq: should we call cfs_rq_util_change() or will the call do so
+ *
+ * The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
+ * avg. The immediate corollary is that all (fair) tasks must be attached, see
+ * post_init_entity_util_avg().
+ *
+ * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
+ *
+ * Returns true if the load decayed or we removed utilization. It is expected
+ * that one calls update_tg_load_avg() on this condition, but after you've
+ * modified the cfs_rq avg (attach/detach), such that we propagate the new
+ * avg up.
+ */
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 {
@@ -2969,6 +2990,14 @@
 		update_tg_load_avg(cfs_rq, 0);
 }
 
+/**
+ * attach_entity_load_avg - attach this entity to its cfs_rq load avg
+ * @cfs_rq: cfs_rq to attach to
+ * @se: sched_entity to attach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (!sched_feat(ATTACH_AGE_LOAD))
@@ -2977,6 +3006,8 @@
 	/*
 	 * If we got migrated (either between CPUs or between cgroups) we'll
 	 * have aged the average right before clearing @last_update_time.
+	 *
+	 * Or we're fresh through post_init_entity_util_avg().
 	 */
 	if (se->avg.last_update_time) {
 		__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
@@ -2998,6 +3029,14 @@
 	cfs_rq_util_change(cfs_rq);
 }
 
+/**
+ * detach_entity_load_avg - detach this entity from its cfs_rq load avg
+ * @cfs_rq: cfs_rq to detach from
+ * @se: sched_entity to detach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
@@ -3082,11 +3121,14 @@
 	u64 last_update_time;
 
 	/*
-	 * Newly created task or never used group entity should not be removed
-	 * from its (source) cfs_rq
+	 * tasks cannot exit without having gone through wake_up_new_task() ->
+	 * post_init_entity_util_avg() which will have added things to the
+	 * cfs_rq, so we can remove unconditionally.
+	 *
+	 * Similarly for groups, they will have passed through
+	 * post_init_entity_util_avg() before unregister_sched_fair_group()
+	 * calls this.
 	 */
-	if (se->avg.last_update_time == 0)
-		return;
 
 	last_update_time = cfs_rq_last_update_time(cfs_rq);
 
@@ -3109,6 +3151,12 @@
 
 #else /* CONFIG_SMP */
 
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
+{
+	return 0;
+}
+
 static inline void update_load_avg(struct sched_entity *se, int not_used)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -3698,7 +3746,7 @@
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 {
 	if (unlikely(cfs_rq->throttle_count))
-		return cfs_rq->throttled_clock_task;
+		return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time;
 
 	return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
 }
@@ -3836,13 +3884,11 @@
 	struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
 	cfs_rq->throttle_count--;
-#ifdef CONFIG_SMP
 	if (!cfs_rq->throttle_count) {
 		/* adjust cfs_rq_clock_task() */
 		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
 	}
-#endif
 
 	return 0;
 }
@@ -4195,26 +4241,6 @@
 	if (!cfs_bandwidth_used())
 		return;
 
-	/* Synchronize hierarchical throttle counter: */
-	if (unlikely(!cfs_rq->throttle_uptodate)) {
-		struct rq *rq = rq_of(cfs_rq);
-		struct cfs_rq *pcfs_rq;
-		struct task_group *tg;
-
-		cfs_rq->throttle_uptodate = 1;
-
-		/* Get closest up-to-date node, because leaves go first: */
-		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
-			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
-			if (pcfs_rq->throttle_uptodate)
-				break;
-		}
-		if (tg) {
-			cfs_rq->throttle_count = pcfs_rq->throttle_count;
-			cfs_rq->throttled_clock_task = rq_clock_task(rq);
-		}
-	}
-
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
@@ -4229,6 +4255,23 @@
 		throttle_cfs_rq(cfs_rq);
 }
 
+static void sync_throttle(struct task_group *tg, int cpu)
+{
+	struct cfs_rq *pcfs_rq, *cfs_rq;
+
+	if (!cfs_bandwidth_used())
+		return;
+
+	if (!tg->parent)
+		return;
+
+	cfs_rq = tg->cfs_rq[cpu];
+	pcfs_rq = tg->parent->cfs_rq[cpu];
+
+	cfs_rq->throttle_count = pcfs_rq->throttle_count;
+	pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+}
+
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
@@ -4368,6 +4411,7 @@
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
+static inline void sync_throttle(struct task_group *tg, int cpu) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
@@ -4476,7 +4520,7 @@
 		 *
 		 * note: in the case of encountering a throttled cfs_rq we will
 		 * post the final h_nr_running increment below.
-		*/
+		 */
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 		cfs_rq->h_nr_running++;
@@ -8317,31 +8361,17 @@
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se, *curr;
-	int this_cpu = smp_processor_id();
 	struct rq *rq = this_rq();
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
-
+	raw_spin_lock(&rq->lock);
 	update_rq_clock(rq);
 
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
-
-	/*
-	 * Not only the cpu but also the task_group of the parent might have
-	 * been changed after parent->se.parent,cfs_rq were copied to
-	 * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
-	 * of child point to valid ones.
-	 */
-	rcu_read_lock();
-	__set_task_cpu(p, this_cpu);
-	rcu_read_unlock();
-
-	update_curr(cfs_rq);
-
-	if (curr)
+	if (curr) {
+		update_curr(cfs_rq);
 		se->vruntime = curr->vruntime;
+	}
 	place_entity(cfs_rq, se, 1);
 
 	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
@@ -8354,8 +8384,7 @@
 	}
 
 	se->vruntime -= cfs_rq->min_vruntime;
-
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_unlock(&rq->lock);
 }
 
 /*
@@ -8411,6 +8440,8 @@
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 now = cfs_rq_clock_task(cfs_rq);
+	int tg_update;
 
 	if (!vruntime_normalized(p)) {
 		/*
@@ -8422,13 +8453,18 @@
 	}
 
 	/* Catch up with the cfs_rq and remove our load when we leave */
+	tg_update = update_cfs_rq_load_avg(now, cfs_rq, false);
 	detach_entity_load_avg(cfs_rq, se);
+	if (tg_update)
+		update_tg_load_avg(cfs_rq, false);
 }
 
 static void attach_task_cfs_rq(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 now = cfs_rq_clock_task(cfs_rq);
+	int tg_update;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
@@ -8439,7 +8475,10 @@
 #endif
 
 	/* Synchronize task with its cfs_rq */
+	tg_update = update_cfs_rq_load_avg(now, cfs_rq, false);
 	attach_entity_load_avg(cfs_rq, se);
+	if (tg_update)
+		update_tg_load_avg(cfs_rq, false);
 
 	if (!vruntime_normalized(p))
 		se->vruntime += cfs_rq->min_vruntime;
@@ -8499,6 +8538,14 @@
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+static void task_set_group_fair(struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+
+	set_task_rq(p, task_cpu(p));
+	se->depth = se->parent ? se->parent->depth + 1 : 0;
+}
+
 static void task_move_group_fair(struct task_struct *p)
 {
 	detach_task_cfs_rq(p);
@@ -8511,6 +8558,19 @@
 	attach_task_cfs_rq(p);
 }
 
+static void task_change_group_fair(struct task_struct *p, int type)
+{
+	switch (type) {
+	case TASK_SET_GROUP:
+		task_set_group_fair(p);
+		break;
+
+	case TASK_MOVE_GROUP:
+		task_move_group_fair(p);
+		break;
+	}
+}
+
 void free_fair_sched_group(struct task_group *tg)
 {
 	int i;
@@ -8562,10 +8622,6 @@
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
-
-		raw_spin_lock_irq(&rq->lock);
-		post_init_entity_util_avg(se);
-		raw_spin_unlock_irq(&rq->lock);
 	}
 
 	return 1;
@@ -8576,6 +8632,23 @@
 	return 0;
 }
 
+void online_fair_sched_group(struct task_group *tg)
+{
+	struct sched_entity *se;
+	struct rq *rq;
+	int i;
+
+	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+		se = tg->se[i];
+
+		raw_spin_lock_irq(&rq->lock);
+		post_init_entity_util_avg(se);
+		sync_throttle(tg, i);
+		raw_spin_unlock_irq(&rq->lock);
+	}
+}
+
 void unregister_fair_sched_group(struct task_group *tg)
 {
 	unsigned long flags;
@@ -8680,6 +8753,8 @@
 	return 1;
 }
 
+void online_fair_sched_group(struct task_group *tg) { }
+
 void unregister_fair_sched_group(struct task_group *tg) { }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -8739,7 +8814,7 @@
 	.update_curr		= update_curr_fair,
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	.task_move_group	= task_move_group_fair,
+	.task_change_group	= task_change_group_fair,
 #endif
 };
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index c5aeedf..9fb873c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -201,6 +201,8 @@
  */
 static void cpu_idle_loop(void)
 {
+	int cpu = smp_processor_id();
+
 	while (1) {
 		/*
 		 * If the arch has a polling bit, we maintain an invariant:
@@ -219,7 +221,7 @@
 			check_pgt_cache();
 			rmb();
 
-			if (cpu_is_offline(smp_processor_id())) {
+			if (cpu_is_offline(cpu)) {
 				cpuhp_report_idle_dead();
 				arch_cpu_idle_dead();
 			}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8128359..c64fc51 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -321,6 +321,7 @@
 
 extern void free_fair_sched_group(struct task_group *tg);
 extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
+extern void online_fair_sched_group(struct task_group *tg);
 extern void unregister_fair_sched_group(struct task_group *tg);
 extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 			struct sched_entity *se, int cpu,
@@ -437,7 +438,7 @@
 
 	u64 throttled_clock, throttled_clock_task;
 	u64 throttled_clock_task_time;
-	int throttled, throttle_count, throttle_uptodate;
+	int throttled, throttle_count;
 	struct list_head throttled_list;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -1246,8 +1247,11 @@
 
 	void (*update_curr) (struct rq *rq);
 
+#define TASK_SET_GROUP  0
+#define TASK_MOVE_GROUP	1
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	void (*task_move_group) (struct task_struct *p);
+	void (*task_change_group) (struct task_struct *p, int type);
 #endif
 };
 
@@ -1809,16 +1813,3 @@
 #else /* arch_scale_freq_capacity */
 #define arch_scale_freq_invariant()	(false)
 #endif
-
-static inline void account_reset_rq(struct rq *rq)
-{
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-	rq->prev_irq_time = 0;
-#endif
-#ifdef CONFIG_PARAVIRT
-	rq->prev_steal_time = 0;
-#endif
-#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-	rq->prev_steal_time_rq = 0;
-#endif
-}