Merge branch 'sched/core' into core/mm

Pull the migrate disable mechanics which is a prerequisite for preemptible
kmap_local().

Documentation/scheduler/sched-domains.rst

@@ -65,21 +65,17 @@ of the SMP domain will span the entire machine, with each group having the
 cpumask of a node. Or, you could do multi-level NUMA or Opteron, for example,
 might have just one domain covering its one NUMA level.
 
-The implementor should read comments in include/linux/sched.h:
-struct sched_domain fields, SD_FLAG_*, SD_*_INIT to get an idea of
-the specifics and what to tune.
+The implementor should read comments in include/linux/sched/sd_flags.h:
+SD_* to get an idea of the specifics and what to tune for the SD flags
+of a sched_domain.
 
-Architectures may retain the regular override the default SD_*_INIT flags
-while using the generic domain builder in kernel/sched/core.c if they wish to
-retain the traditional SMT->SMP->NUMA topology (or some subset of that). This
-can be done by #define'ing ARCH_HASH_SCHED_TUNE.
-
-Alternatively, the architecture may completely override the generic domain
-builder by #define'ing ARCH_HASH_SCHED_DOMAIN, and exporting your
-arch_init_sched_domains function. This function will attach domains to all
-CPUs using cpu_attach_domain.
+Architectures may override the generic domain builder and the default SD flags
+for a given topology level by creating a sched_domain_topology_level array and
+calling set_sched_topology() with this array as the parameter.
 
 The sched-domains debugging infrastructure can be enabled by enabling
-CONFIG_SCHED_DEBUG. This enables an error checking parse of the sched domains
-which should catch most possible errors (described above). It also prints out
-the domain structure in a visual format.
+CONFIG_SCHED_DEBUG and adding 'sched_debug' to your cmdline. If you forgot to
+tweak your cmdline, you can also flip the /sys/kernel/debug/sched_debug
+knob. This enables an error checking parse of the sched domains which should
+catch most possible errors (described above). It also prints out the domain
+structure in a visual format.

arch/arm64/kernel/topology.c

@@ -213,6 +213,7 @@ static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
 
 static int __init init_amu_fie(void)
 {
+	bool invariance_status = topology_scale_freq_invariant();
 	cpumask_var_t valid_cpus;
 	bool have_policy = false;
 	int ret = 0;
@@ -255,6 +256,15 @@ static int __init init_amu_fie(void)
 	if (!topology_scale_freq_invariant())
 		static_branch_disable(&amu_fie_key);
 
+	/*
+	 * Task scheduler behavior depends on frequency invariance support,
+	 * either cpufreq or counter driven. If the support status changes as
+	 * a result of counter initialisation and use, retrigger the build of
+	 * scheduling domains to ensure the information is propagated properly.
+	 */
+	if (invariance_status != topology_scale_freq_invariant())
+		rebuild_sched_domains_energy();
+
 free_valid_mask:
 	free_cpumask_var(valid_cpus);
 

fs/proc/array.c

@@ -382,9 +382,9 @@ static inline void task_context_switch_counts(struct seq_file *m,
 static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 {
 	seq_printf(m, "Cpus_allowed:\t%*pb\n",
-		   cpumask_pr_args(task->cpus_ptr));
+		   cpumask_pr_args(&task->cpus_mask));
 	seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
-		   cpumask_pr_args(task->cpus_ptr));
+		   cpumask_pr_args(&task->cpus_mask));
 }
 
 static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)

include/linux/cpuhotplug.h

@@ -152,6 +152,7 @@ enum cpuhp_state {
 	CPUHP_AP_ONLINE,
 	CPUHP_TEARDOWN_CPU,
 	CPUHP_AP_ONLINE_IDLE,
+	CPUHP_AP_SCHED_WAIT_EMPTY,
 	CPUHP_AP_SMPBOOT_THREADS,
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_IRQ_AFFINITY_ONLINE,

include/linux/cpumask.h

@@ -199,6 +199,11 @@ static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
 	return cpumask_next_and(-1, src1p, src2p);
 }
 
+static inline int cpumask_any_distribute(const struct cpumask *srcp)
+{
+	return cpumask_first(srcp);
+}
+
 #define for_each_cpu(cpu, mask)			\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
 #define for_each_cpu_not(cpu, mask)		\
@@ -252,6 +257,7 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
 unsigned int cpumask_local_spread(unsigned int i, int node);
 int cpumask_any_and_distribute(const struct cpumask *src1p,
 			       const struct cpumask *src2p);
+int cpumask_any_distribute(const struct cpumask *srcp);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask

include/linux/kernel.h

@@ -204,6 +204,7 @@ extern int _cond_resched(void);
 extern void ___might_sleep(const char *file, int line, int preempt_offset);
 extern void __might_sleep(const char *file, int line, int preempt_offset);
 extern void __cant_sleep(const char *file, int line, int preempt_offset);
+extern void __cant_migrate(const char *file, int line);
 
 /**
  * might_sleep - annotation for functions that can sleep
@@ -227,6 +228,18 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 # define cant_sleep() \
 	do { __cant_sleep(__FILE__, __LINE__, 0); } while (0)
 # define sched_annotate_sleep()	(current->task_state_change = 0)
+
+/**
+ * cant_migrate - annotation for functions that cannot migrate
+ *
+ * Will print a stack trace if executed in code which is migratable
+ */
+# define cant_migrate()							\
+	do {								\
+		if (IS_ENABLED(CONFIG_SMP))				\
+			__cant_migrate(__FILE__, __LINE__);		\
+	} while (0)
+
 /**
  * non_block_start - annotate the start of section where sleeping is prohibited
  *
@@ -251,6 +264,7 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
 # define cant_sleep() do { } while (0)
+# define cant_migrate()		do { } while (0)
 # define sched_annotate_sleep() do { } while (0)
 # define non_block_start() do { } while (0)
 # define non_block_end() do { } while (0)
@@ -258,13 +272,6 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
 
-#ifndef CONFIG_PREEMPT_RT
-# define cant_migrate()		cant_sleep()
-#else
-  /* Placeholder for now */
-# define cant_migrate()		do { } while (0)
-#endif
-
 /**
  * abs - return absolute value of an argument
  * @x: the value.  If it is unsigned type, it is converted to signed type first.

include/linux/preempt.h

@@ -322,34 +322,71 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 
 #endif
 
-/**
- * migrate_disable - Prevent migration of the current task
+#ifdef CONFIG_SMP
+
+/*
+ * Migrate-Disable and why it is undesired.
  *
- * Maps to preempt_disable() which also disables preemption. Use
- * migrate_disable() to annotate that the intent is to prevent migration,
- * but not necessarily preemption.
+ * When a preempted task becomes elegible to run under the ideal model (IOW it
+ * becomes one of the M highest priority tasks), it might still have to wait
+ * for the preemptee's migrate_disable() section to complete. Thereby suffering
+ * a reduction in bandwidth in the exact duration of the migrate_disable()
+ * section.
  *
- * Can be invoked nested like preempt_disable() and needs the corresponding
- * number of migrate_enable() invocations.
- */
-static __always_inline void migrate_disable(void)
-{
-	preempt_disable();
-}
-
-/**
- * migrate_enable - Allow migration of the current task
+ * Per this argument, the change from preempt_disable() to migrate_disable()
+ * gets us:
+ *
+ * - a higher priority tasks gains reduced wake-up latency; with preempt_disable()
+ *   it would have had to wait for the lower priority task.
+ *
+ * - a lower priority tasks; which under preempt_disable() could've instantly
+ *   migrated away when another CPU becomes available, is now constrained
+ *   by the ability to push the higher priority task away, which might itself be
+ *   in a migrate_disable() section, reducing it's available bandwidth.
+ *
+ * IOW it trades latency / moves the interference term, but it stays in the
+ * system, and as long as it remains unbounded, the system is not fully
+ * deterministic.
+ *
+ *
+ * The reason we have it anyway.
  *
- * Counterpart to migrate_disable().
+ * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a
+ * number of primitives into becoming preemptible, they would also allow
+ * migration. This turns out to break a bunch of per-cpu usage. To this end,
+ * all these primitives employ migirate_disable() to restore this implicit
+ * assumption.
  *
- * As migrate_disable() can be invoked nested, only the outermost invocation
- * reenables migration.
+ * This is a 'temporary' work-around at best. The correct solution is getting
+ * rid of the above assumptions and reworking the code to employ explicit
+ * per-cpu locking or short preempt-disable regions.
+ *
+ * The end goal must be to get rid of migrate_disable(), alternatively we need
+ * a schedulability theory that does not depend on abritrary migration.
+ *
+ *
+ * Notes on the implementation.
+ *
+ * The implementation is particularly tricky since existing code patterns
+ * dictate neither migrate_disable() nor migrate_enable() is allowed to block.
+ * This means that it cannot use cpus_read_lock() to serialize against hotplug,
+ * nor can it easily migrate itself into a pending affinity mask change on
+ * migrate_enable().
+ *
+ *
+ * Note: even non-work-conserving schedulers like semi-partitioned depends on
+ *       migration, so migrate_disable() is not only a problem for
+ *       work-conserving schedulers.
  *
- * Currently mapped to preempt_enable().
  */
-static __always_inline void migrate_enable(void)
-{
-	preempt_enable();
-}
+extern void migrate_disable(void);
+extern void migrate_enable(void);
+
+#else
+
+static inline void migrate_disable(void) { }
+static inline void migrate_enable(void) { }
+
+#endif /* CONFIG_SMP */
 
 #endif /* __LINUX_PREEMPT_H */

include/linux/sched.h

@@ -714,6 +714,11 @@ struct task_struct {
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			cpus_mask;
+	void				*migration_pending;
+#ifdef CONFIG_SMP
+	unsigned short			migration_disabled;
+#endif
+	unsigned short			migration_flags;
 
 #ifdef CONFIG_PREEMPT_RCU
 	int				rcu_read_lock_nesting;

include/linux/sched/hotplug.h

@@ -11,8 +11,10 @@ extern int sched_cpu_activate(unsigned int cpu);
 extern int sched_cpu_deactivate(unsigned int cpu);
 
 #ifdef CONFIG_HOTPLUG_CPU
+extern int sched_cpu_wait_empty(unsigned int cpu);
 extern int sched_cpu_dying(unsigned int cpu);
 #else
+# define sched_cpu_wait_empty	NULL
 # define sched_cpu_dying	NULL
 #endif
 

include/linux/sched/mm.h

@@ -347,6 +347,8 @@ static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 
 extern void membarrier_exec_mmap(struct mm_struct *mm);
 
+extern void membarrier_update_current_mm(struct mm_struct *next_mm);
+
 #else
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
 static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
@@ -361,6 +363,9 @@ static inline void membarrier_exec_mmap(struct mm_struct *mm)
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
 }
+static inline void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+}
 #endif
 
 #endif /* _LINUX_SCHED_MM_H */

include/linux/sched/topology.h

@@ -225,6 +225,14 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 
 #endif	/* !CONFIG_SMP */
 
+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
+extern void rebuild_sched_domains_energy(void);
+#else
+static inline void rebuild_sched_domains_energy(void)
+{
+}
+#endif
+
 #ifndef arch_scale_cpu_capacity
 /**
  * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.

include/linux/stop_machine.h

@@ -24,6 +24,7 @@ typedef int (*cpu_stop_fn_t)(void *arg);
 struct cpu_stop_work {
 	struct list_head	list;		/* cpu_stopper->works */
 	cpu_stop_fn_t		fn;
+	unsigned long		caller;
 	void			*arg;
 	struct cpu_stop_done	*done;
 };
@@ -36,6 +37,8 @@ void stop_machine_park(int cpu);
 void stop_machine_unpark(int cpu);
 void stop_machine_yield(const struct cpumask *cpumask);
 
+extern void print_stop_info(const char *log_lvl, struct task_struct *task);
+
 #else	/* CONFIG_SMP */
 
 #include <linux/workqueue.h>
@@ -80,6 +83,8 @@ static inline bool stop_one_cpu_nowait(unsigned int cpu,
 	return false;
 }
 
+static inline void print_stop_info(const char *log_lvl, struct task_struct *task) { }
+
 #endif	/* CONFIG_SMP */
 
 /*

include/uapi/linux/sched/types.h

@@ -96,6 +96,8 @@ struct sched_param {
  * on a CPU with a capacity big enough to fit the specified value.
  * A task with a max utilization value smaller than 1024 is more likely
  * scheduled on a CPU with no more capacity than the specified value.
+ *
+ * A task utilization boundary can be reset by setting the attribute to -1.
  */
 struct sched_attr {
 	__u32 size;

kernel/cgroup/cpuset.c

@@ -983,25 +983,48 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
  */
 static void rebuild_sched_domains_locked(void)
 {
+	struct cgroup_subsys_state *pos_css;
 	struct sched_domain_attr *attr;
 	cpumask_var_t *doms;
+	struct cpuset *cs;
 	int ndoms;
 
 	lockdep_assert_cpus_held();
 	percpu_rwsem_assert_held(&cpuset_rwsem);
 
 	/*
-	 * We have raced with CPU hotplug. Don't do anything to avoid
+	 * If we have raced with CPU hotplug, return early to avoid
 	 * passing doms with offlined cpu to partition_sched_domains().
-	 * Anyways, hotplug work item will rebuild sched domains.
+	 * Anyways, cpuset_hotplug_workfn() will rebuild sched domains.
+	 *
+	 * With no CPUs in any subpartitions, top_cpuset's effective CPUs
+	 * should be the same as the active CPUs, so checking only top_cpuset
+	 * is enough to detect racing CPU offlines.
 	 */
 	if (!top_cpuset.nr_subparts_cpus &&
 	    !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
 		return;
 
-	if (top_cpuset.nr_subparts_cpus &&
-	   !cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask))
-		return;
+	/*
+	 * With subpartition CPUs, however, the effective CPUs of a partition
+	 * root should be only a subset of the active CPUs.  Since a CPU in any
+	 * partition root could be offlined, all must be checked.
+	 */
+	if (top_cpuset.nr_subparts_cpus) {
+		rcu_read_lock();
+		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
+			if (!is_partition_root(cs)) {
+				pos_css = css_rightmost_descendant(pos_css);
+				continue;
+			}
+			if (!cpumask_subset(cs->effective_cpus,
+					    cpu_active_mask)) {
+				rcu_read_unlock();
+				return;
+			}
+		}
+		rcu_read_unlock();
+	}
 
 	/* Generate domain masks and attrs */
 	ndoms = generate_sched_domains(&doms, &attr);

kernel/cpu.c

@@ -1602,7 +1602,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.name			= "ap:online",
 	},
 	/*
-	 * Handled on controll processor until the plugged processor manages
+	 * Handled on control processor until the plugged processor manages
 	 * this itself.
 	 */
 	[CPUHP_TEARDOWN_CPU] = {
@@ -1611,6 +1611,13 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.teardown.single	= takedown_cpu,
 		.cant_stop		= true,
 	},
+
+	[CPUHP_AP_SCHED_WAIT_EMPTY] = {
+		.name			= "sched:waitempty",
+		.startup.single		= NULL,
+		.teardown.single	= sched_cpu_wait_empty,
+	},
+
 	/* Handle smpboot threads park/unpark */
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",

kernel/exit.c

@@ -475,10 +475,24 @@ static void exit_mm(void)
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
 	task_lock(current);
+	/*
+	 * When a thread stops operating on an address space, the loop
+	 * in membarrier_private_expedited() may not observe that
+	 * tsk->mm, and the loop in membarrier_global_expedited() may
+	 * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED
+	 * rq->membarrier_state, so those would not issue an IPI.
+	 * Membarrier requires a memory barrier after accessing
+	 * user-space memory, before clearing tsk->mm or the
+	 * rq->membarrier_state.
+	 */
+	smp_mb__after_spinlock();
+	local_irq_disable();
 	current->mm = NULL;
-	mmap_read_unlock(mm);
+	membarrier_update_current_mm(NULL);
 	enter_lazy_tlb(mm, current);
+	local_irq_enable();
 	task_unlock(current);
+	mmap_read_unlock(mm);
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))

kernel/kthread.c

@@ -1248,6 +1248,7 @@ void kthread_use_mm(struct mm_struct *mm)
 		tsk->active_mm = mm;
 	}
 	tsk->mm = mm;
+	membarrier_update_current_mm(mm);
 	switch_mm_irqs_off(active_mm, mm, tsk);
 	local_irq_enable();
 	task_unlock(tsk);
@@ -1255,8 +1256,19 @@ void kthread_use_mm(struct mm_struct *mm)
 	finish_arch_post_lock_switch();
 #endif
 
+	/*
+	 * When a kthread starts operating on an address space, the loop
+	 * in membarrier_{private,global}_expedited() may not observe
+	 * that tsk->mm, and not issue an IPI. Membarrier requires a
+	 * memory barrier after storing to tsk->mm, before accessing
+	 * user-space memory. A full memory barrier for membarrier
+	 * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by
+	 * mmdrop(), or explicitly with smp_mb().
+	 */
 	if (active_mm != mm)
 		mmdrop(active_mm);
+	else
+		smp_mb();
 
 	to_kthread(tsk)->oldfs = force_uaccess_begin();
 }
@@ -1276,9 +1288,18 @@ void kthread_unuse_mm(struct mm_struct *mm)
 	force_uaccess_end(to_kthread(tsk)->oldfs);
 
 	task_lock(tsk);
+	/*
+	 * When a kthread stops operating on an address space, the loop
+	 * in membarrier_{private,global}_expedited() may not observe
+	 * that tsk->mm, and not issue an IPI. Membarrier requires a
+	 * memory barrier after accessing user-space memory, before
+	 * clearing tsk->mm.
+	 */
+	smp_mb__after_spinlock();
 	sync_mm_rss(mm);
 	local_irq_disable();
 	tsk->mm = NULL;
+	membarrier_update_current_mm(NULL);
 	/* active_mm is still 'mm' */
 	enter_lazy_tlb(mm, tsk);
 	local_irq_enable();

kernel/sched/cpudeadline.c

@@ -120,7 +120,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	const struct sched_dl_entity *dl_se = &p->dl;
 
 	if (later_mask &&
-	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
+	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_mask)) {
 		unsigned long cap, max_cap = 0;
 		int cpu, max_cpu = -1;
 
@@ -151,7 +151,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 
 		WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
-		if (cpumask_test_cpu(best_cpu, p->cpus_ptr) &&
+		if (cpumask_test_cpu(best_cpu, &p->cpus_mask) &&
 		    dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
 			if (later_mask)
 				cpumask_set_cpu(best_cpu, later_mask);

kernel/sched/cpufreq_schedutil.c

@@ -901,16 +901,9 @@ struct cpufreq_governor *cpufreq_default_governor(void)
 cpufreq_governor_init(schedutil_gov);
 
 #ifdef CONFIG_ENERGY_MODEL
-extern bool sched_energy_update;
-extern struct mutex sched_energy_mutex;
-
 static void rebuild_sd_workfn(struct work_struct *work)
 {
-	mutex_lock(&sched_energy_mutex);
-	sched_energy_update = true;
-	rebuild_sched_domains();
-	sched_energy_update = false;
-	mutex_unlock(&sched_energy_mutex);
+	rebuild_sched_domains_energy();
 }
 static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);
 

kernel/sched/cpupri.c

@@ -11,7 +11,7 @@
  *  This code tracks the priority of each CPU so that global migration
  *  decisions are easy to calculate.  Each CPU can be in a state as follows:
  *
- *                 (INVALID), IDLE, NORMAL, RT1, ... RT99
+ *                 (INVALID), NORMAL, RT1, ... RT99, HIGHER
  *
  *  going from the lowest priority to the highest.  CPUs in the INVALID state
  *  are not eligible for routing.  The system maintains this state with
@@ -19,24 +19,48 @@
  *  in that class).  Therefore a typical application without affinity
  *  restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
  *  searches).  For tasks with affinity restrictions, the algorithm has a
- *  worst case complexity of O(min(102, nr_domcpus)), though the scenario that
+ *  worst case complexity of O(min(101, nr_domcpus)), though the scenario that
  *  yields the worst case search is fairly contrived.
  */
 #include "sched.h"
 
-/* Convert between a 140 based task->prio, and our 102 based cpupri */
+/*
+ * p->rt_priority   p->prio   newpri   cpupri
+ *
+ *				  -1       -1 (CPUPRI_INVALID)
+ *
+ *				  99        0 (CPUPRI_NORMAL)
+ *
+ *		1        98       98        1
+ *	      ...
+ *	       49        50       50       49
+ *	       50        49       49       50
+ *	      ...
+ *	       99         0        0       99
+ *
+ *				 100	  100 (CPUPRI_HIGHER)
+ */
 static int convert_prio(int prio)
 {
 	int cpupri;
 
-	if (prio == CPUPRI_INVALID)
-		cpupri = CPUPRI_INVALID;
-	else if (prio == MAX_PRIO)
-		cpupri = CPUPRI_IDLE;
-	else if (prio >= MAX_RT_PRIO)
-		cpupri = CPUPRI_NORMAL;
-	else
-		cpupri = MAX_RT_PRIO - prio + 1;
+	switch (prio) {
+	case CPUPRI_INVALID:
+		cpupri = CPUPRI_INVALID;	/* -1 */
+		break;
+
+	case 0 ... 98:
+		cpupri = MAX_RT_PRIO-1 - prio;	/* 1 ... 99 */
+		break;
+
+	case MAX_RT_PRIO-1:
+		cpupri = CPUPRI_NORMAL;		/*  0 */
+		break;
+
+	case MAX_RT_PRIO:
+		cpupri = CPUPRI_HIGHER;		/* 100 */
+		break;
+	}
 
 	return cpupri;
 }
@@ -73,11 +97,11 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
 	if (skip)
 		return 0;
 
-	if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
+	if (cpumask_any_and(&p->cpus_mask, vec->mask) >= nr_cpu_ids)
 		return 0;
 
 	if (lowest_mask) {
-		cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
+		cpumask_and(lowest_mask, &p->cpus_mask, vec->mask);
 
 		/*
 		 * We have to ensure that we have at least one bit
@@ -177,7 +201,7 @@ int cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
  * cpupri_set - update the CPU priority setting
  * @cp: The cpupri context
  * @cpu: The target CPU
- * @newpri: The priority (INVALID-RT99) to assign to this CPU
+ * @newpri: The priority (INVALID,NORMAL,RT1-RT99,HIGHER) to assign to this CPU
  *
  * Note: Assumes cpu_rq(cpu)->lock is locked
  *

kernel/sched/cpupri.h

 /* SPDX-License-Identifier: GPL-2.0 */
 
-#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO + 2)
+#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO+1)
 
 #define CPUPRI_INVALID		-1
-#define CPUPRI_IDLE		 0
-#define CPUPRI_NORMAL		 1
-/* values 2-101 are RT priorities 0-99 */
+#define CPUPRI_NORMAL		 0
+/* values 1-99 are for RT1-RT99 priorities */
+#define CPUPRI_HIGHER		100
 
 struct cpupri_vec {
 	atomic_t		count;

kernel/sched/deadline.c

@@ -97,6 +97,17 @@ static inline unsigned long dl_bw_capacity(int i)
 		return __dl_bw_capacity(i);
 	}
 }
+
+static inline bool dl_bw_visited(int cpu, u64 gen)
+{
+	struct root_domain *rd = cpu_rq(cpu)->rd;
+
+	if (rd->visit_gen == gen)
+		return true;
+
+	rd->visit_gen = gen;
+	return false;
+}
 #else
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -112,6 +123,11 @@ static inline unsigned long dl_bw_capacity(int i)
 {
 	return SCHED_CAPACITY_SCALE;
 }
+
+static inline bool dl_bw_visited(int cpu, u64 gen)
+{
+	return false;
+}
 #endif
 
 static inline
@@ -543,7 +559,7 @@ static int push_dl_task(struct rq *rq);
 
 static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
 {
-	return dl_task(prev);
+	return rq->online && dl_task(prev);
 }
 
 static DEFINE_PER_CPU(struct callback_head, dl_push_head);
@@ -1378,6 +1394,8 @@ static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 
 	if (dl_rq->earliest_dl.curr == 0 ||
 	    dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+		if (dl_rq->earliest_dl.curr == 0)
+			cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_HIGHER);
 		dl_rq->earliest_dl.curr = deadline;
 		cpudl_set(&rq->rd->cpudl, rq->cpu, deadline);
 	}
@@ -1395,6 +1413,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 		dl_rq->earliest_dl.curr = 0;
 		dl_rq->earliest_dl.next = 0;
 		cpudl_clear(&rq->rd->cpudl, rq->cpu);
+		cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
 	} else {
 		struct rb_node *leftmost = dl_rq->root.rb_leftmost;
 		struct sched_dl_entity *entry;
@@ -1664,13 +1683,13 @@ static void yield_task_dl(struct rq *rq)
 static int find_later_rq(struct task_struct *task);
 
 static int
-select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_dl(struct task_struct *p, int cpu, int flags)
 {
 	struct task_struct *curr;
 	bool select_rq;
 	struct rq *rq;
 
-	if (sd_flag != SD_BALANCE_WAKE)
+	if (!(flags & WF_TTWU))
 		goto out;
 
 	rq = cpu_rq(cpu);
@@ -1912,7 +1931,7 @@ static void task_fork_dl(struct task_struct *p)
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, p->cpus_ptr))
+	    cpumask_test_cpu(cpu, &p->cpus_mask))
 		return 1;
 	return 0;
 }
@@ -2002,8 +2021,8 @@ static int find_later_rq(struct task_struct *task)
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(later_mask,
-							sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(later_mask,
+							      sched_domain_span(sd));
 			/*
 			 * Last chance: if a CPU being in both later_mask
 			 * and current sd span is valid, that becomes our
@@ -2025,7 +2044,7 @@ static int find_later_rq(struct task_struct *task)
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(later_mask);
+	cpu = cpumask_any_distribute(later_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
@@ -2062,7 +2081,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 		/* Retry if something changed. */
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) ||
+				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) ||
 				     task_running(rq, task) ||
 				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
@@ -2129,6 +2148,9 @@ static int push_dl_task(struct rq *rq)
 		return 0;
 
 retry:
+	if (is_migration_disabled(next_task))
+		return 0;
+
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
@@ -2206,7 +2228,7 @@ static void push_dl_tasks(struct rq *rq)
 static void pull_dl_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, cpu;
-	struct task_struct *p;
+	struct task_struct *p, *push_task;
 	bool resched = false;
 	struct rq *src_rq;
 	u64 dmin = LONG_MAX;
@@ -2236,6 +2258,7 @@ static void pull_dl_task(struct rq *this_rq)
 			continue;
 
 		/* Might drop this_rq->lock */
+		push_task = NULL;
 		double_lock_balance(this_rq, src_rq);
 
 		/*
@@ -2267,17 +2290,27 @@ static void pull_dl_task(struct rq *this_rq)
 					   src_rq->curr->dl.deadline))
 				goto skip;
 
-			resched = true;
-
-			deactivate_task(src_rq, p, 0);
-			set_task_cpu(p, this_cpu);
-			activate_task(this_rq, p, 0);
-			dmin = p->dl.deadline;
+			if (is_migration_disabled(p)) {
+				push_task = get_push_task(src_rq);
+			} else {
+				deactivate_task(src_rq, p, 0);
+				set_task_cpu(p, this_cpu);
+				activate_task(this_rq, p, 0);
+				dmin = p->dl.deadline;
+				resched = true;
+			}
 
 			/* Is there any other task even earlier? */
 		}
 skip:
 		double_unlock_balance(this_rq, src_rq);
+
+		if (push_task) {
+			raw_spin_unlock(&this_rq->lock);
+			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
+					    push_task, &src_rq->push_work);
+			raw_spin_lock(&this_rq->lock);
+		}
 	}
 
 	if (resched)
@@ -2301,7 +2334,8 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 }
 
 static void set_cpus_allowed_dl(struct task_struct *p,
-				const struct cpumask *new_mask)
+				const struct cpumask *new_mask,
+				u32 flags)
 {
 	struct root_domain *src_rd;
 	struct rq *rq;
@@ -2330,7 +2364,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
-	set_cpus_allowed_common(p, new_mask);
+	set_cpus_allowed_common(p, new_mask, flags);
 }
 
 /* Assumes rq->lock is held */
@@ -2503,8 +2537,8 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 	}
 }
 
-const struct sched_class dl_sched_class
-	__section("__dl_sched_class") = {
+DEFINE_SCHED_CLASS(dl) = {
+
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
@@ -2523,6 +2557,7 @@ const struct sched_class dl_sched_class
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
 	.task_woken		= task_woken_dl,
+	.find_lock_rq		= find_lock_later_rq,
 #endif
 
 	.task_tick		= task_tick_dl,
@@ -2535,33 +2570,39 @@ const struct sched_class dl_sched_class
 	.update_curr		= update_curr_dl,
 };
 
+/* Used for dl_bw check and update, used under sched_rt_handler()::mutex */
+static u64 dl_generation;
+
 int sched_dl_global_validate(void)
 {
 	u64 runtime = global_rt_runtime();
 	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
+	u64 gen = ++dl_generation;
 	struct dl_bw *dl_b;
-	int cpu, ret = 0;
+	int cpu, cpus, ret = 0;
 	unsigned long flags;
 
 	/*
 	 * Here we want to check the bandwidth not being set to some
 	 * value smaller than the currently allocated bandwidth in
 	 * any of the root_domains.
-	 *
-	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
-	 * cycling on root_domains... Discussion on different/better
-	 * solutions is welcome!
 	 */
 	for_each_possible_cpu(cpu) {
 		rcu_read_lock_sched();
+
+		if (dl_bw_visited(cpu, gen))
+			goto next;
+
 		dl_b = dl_bw_of(cpu);
+		cpus = dl_bw_cpus(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		if (new_bw < dl_b->total_bw)
+		if (new_bw * cpus < dl_b->total_bw)
 			ret = -EBUSY;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
+next:
 		rcu_read_unlock_sched();
 
 		if (ret)
@@ -2587,6 +2628,7 @@ static void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
 void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
+	u64 gen = ++dl_generation;
 	struct dl_bw *dl_b;
 	int cpu;
 	unsigned long flags;
@@ -2597,11 +2639,14 @@ void sched_dl_do_global(void)
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
-	/*
-	 * FIXME: As above...
-	 */
 	for_each_possible_cpu(cpu) {
 		rcu_read_lock_sched();
+
+		if (dl_bw_visited(cpu, gen)) {
+			rcu_read_unlock_sched();
+			continue;
+		}
+
 		dl_b = dl_bw_of(cpu);
 
 		raw_spin_lock_irqsave(&dl_b->lock, flags);

kernel/sched/fair.c

@@ -906,6 +906,15 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (!schedstat_enabled())
 		return;
 
+	/*
+	 * When the sched_schedstat changes from 0 to 1, some sched se
+	 * maybe already in the runqueue, the se->statistics.wait_start
+	 * will be 0.So it will let the delta wrong. We need to avoid this
+	 * scenario.
+	 */
+	if (unlikely(!schedstat_val(se->statistics.wait_start)))
+		return;
+
 	delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start);
 
 	if (entity_is_task(se)) {
@@ -4779,25 +4788,37 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
 		/* throttled entity or throttle-on-deactivate */
 		if (!se->on_rq)
-			break;
+			goto done;
 
-		if (dequeue) {
-			dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
-		} else {
-			update_load_avg(qcfs_rq, se, 0);
-			se_update_runnable(se);
-		}
+		dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
 
 		qcfs_rq->h_nr_running -= task_delta;
 		qcfs_rq->idle_h_nr_running -= idle_task_delta;
 
-		if (qcfs_rq->load.weight)
-			dequeue = 0;
+		if (qcfs_rq->load.weight) {
+			/* Avoid re-evaluating load for this entity: */
+			se = parent_entity(se);
+			break;
+		}
 	}
 
-	if (!se)
-		sub_nr_running(rq, task_delta);
+	for_each_sched_entity(se) {
+		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
+		/* throttled entity or throttle-on-deactivate */
+		if (!se->on_rq)
+			goto done;
+
+		update_load_avg(qcfs_rq, se, 0);
+		se_update_runnable(se);
 
+		qcfs_rq->h_nr_running -= task_delta;
+		qcfs_rq->idle_h_nr_running -= idle_task_delta;
+	}
+
+	/* At this point se is NULL and we are at root level*/
+	sub_nr_running(rq, task_delta);
+
+done:
 	/*
 	 * Note: distribution will already see us throttled via the
 	 * throttled-list.  rq->lock protects completion.
@@ -5105,9 +5126,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 		return;
 
 	distribute_cfs_runtime(cfs_b);
-
-	raw_spin_lock_irqsave(&cfs_b->lock, flags);
-	raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
 }
 
 /*
@@ -5804,6 +5822,9 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	if (sync && cpu_rq(this_cpu)->nr_running == 1)
 		return this_cpu;
 
+	if (available_idle_cpu(prev_cpu))
+		return prev_cpu;
+
 	return nr_cpumask_bits;
 }
 
@@ -6663,7 +6684,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
 
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
- * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
+ * that have the relevant SD flag set. In practice, this is SD_BALANCE_WAKE,
  * SD_BALANCE_FORK, or SD_BALANCE_EXEC.
  *
  * Balances load by selecting the idlest CPU in the idlest group, or under
@@ -6674,15 +6695,17 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
  * preempt must be disabled.
  */
 static int
-select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
 {
+	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
 	struct sched_domain *tmp, *sd = NULL;
 	int cpu = smp_processor_id();
 	int new_cpu = prev_cpu;
 	int want_affine = 0;
-	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
+	/* SD_flags and WF_flags share the first nibble */
+	int sd_flag = wake_flags & 0xF;
 
-	if (sd_flag & SD_BALANCE_WAKE) {
+	if (wake_flags & WF_TTWU) {
 		record_wakee(p);
 
 		if (sched_energy_enabled()) {
@@ -6719,9 +6742,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	if (unlikely(sd)) {
 		/* Slow path */
 		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
-	} else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
+	} else if (wake_flags & WF_TTWU) { /* XXX always ? */
 		/* Fast path */
-
 		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
 		if (want_affine)
@@ -10047,6 +10069,10 @@ static inline int find_new_ilb(void)
 
 	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
 			      housekeeping_cpumask(HK_FLAG_MISC)) {
+
+		if (ilb == smp_processor_id())
+			continue;
+
 		if (idle_cpu(ilb))
 			return ilb;
 	}
@@ -11158,8 +11184,8 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task
 /*
  * All the scheduling class methods:
  */
-const struct sched_class fair_sched_class
-	__section("__fair_sched_class") = {
+DEFINE_SCHED_CLASS(fair) = {
+
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,

kernel/sched/idle.c

@@ -338,6 +338,7 @@ void play_idle_precise(u64 duration_ns, u64 latency_ns)
 	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
 	WARN_ON_ONCE(!duration_ns);
+	WARN_ON_ONCE(current->mm);
 
 	rcu_sleep_check();
 	preempt_disable();
@@ -375,7 +376,7 @@ void cpu_startup_entry(enum cpuhp_state state)
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_idle(struct task_struct *p, int cpu, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
@@ -457,8 +458,8 @@ static void update_curr_idle(struct rq *rq)
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
-const struct sched_class idle_sched_class
-	__section("__idle_sched_class") = {
+DEFINE_SCHED_CLASS(idle) = {
+
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */

kernel/sched/membarrier.c

@@ -6,6 +6,134 @@
  */
 #include "sched.h"
 
+/*
+ * For documentation purposes, here are some membarrier ordering
+ * scenarios to keep in mind:
+ *
+ * A) Userspace thread execution after IPI vs membarrier's memory
+ *    barrier before sending the IPI
+ *
+ * Userspace variables:
+ *
+ * int x = 0, y = 0;
+ *
+ * The memory barrier at the start of membarrier() on CPU0 is necessary in
+ * order to enforce the guarantee that any writes occurring on CPU0 before
+ * the membarrier() is executed will be visible to any code executing on
+ * CPU1 after the IPI-induced memory barrier:
+ *
+ *         CPU0                              CPU1
+ *
+ *         x = 1
+ *         membarrier():
+ *           a: smp_mb()
+ *           b: send IPI                       IPI-induced mb
+ *           c: smp_mb()
+ *         r2 = y
+ *                                           y = 1
+ *                                           barrier()
+ *                                           r1 = x
+ *
+ *                     BUG_ON(r1 == 0 && r2 == 0)
+ *
+ * The write to y and load from x by CPU1 are unordered by the hardware,
+ * so it's possible to have "r1 = x" reordered before "y = 1" at any
+ * point after (b).  If the memory barrier at (a) is omitted, then "x = 1"
+ * can be reordered after (a) (although not after (c)), so we get r1 == 0
+ * and r2 == 0.  This violates the guarantee that membarrier() is
+ * supposed by provide.
+ *
+ * The timing of the memory barrier at (a) has to ensure that it executes
+ * before the IPI-induced memory barrier on CPU1.
+ *
+ * B) Userspace thread execution before IPI vs membarrier's memory
+ *    barrier after completing the IPI
+ *
+ * Userspace variables:
+ *
+ * int x = 0, y = 0;
+ *
+ * The memory barrier at the end of membarrier() on CPU0 is necessary in
+ * order to enforce the guarantee that any writes occurring on CPU1 before
+ * the membarrier() is executed will be visible to any code executing on
+ * CPU0 after the membarrier():
+ *
+ *         CPU0                              CPU1
+ *
+ *                                           x = 1
+ *                                           barrier()
+ *                                           y = 1
+ *         r2 = y
+ *         membarrier():
+ *           a: smp_mb()
+ *           b: send IPI                       IPI-induced mb
+ *           c: smp_mb()
+ *         r1 = x
+ *         BUG_ON(r1 == 0 && r2 == 1)
+ *
+ * The writes to x and y are unordered by the hardware, so it's possible to
+ * have "r2 = 1" even though the write to x doesn't execute until (b).  If
+ * the memory barrier at (c) is omitted then "r1 = x" can be reordered
+ * before (b) (although not before (a)), so we get "r1 = 0".  This violates
+ * the guarantee that membarrier() is supposed to provide.
+ *
+ * The timing of the memory barrier at (c) has to ensure that it executes
+ * after the IPI-induced memory barrier on CPU1.
+ *
+ * C) Scheduling userspace thread -> kthread -> userspace thread vs membarrier
+ *
+ *           CPU0                            CPU1
+ *
+ *           membarrier():
+ *           a: smp_mb()
+ *                                           d: switch to kthread (includes mb)
+ *           b: read rq->curr->mm == NULL
+ *                                           e: switch to user (includes mb)
+ *           c: smp_mb()
+ *
+ * Using the scenario from (A), we can show that (a) needs to be paired
+ * with (e). Using the scenario from (B), we can show that (c) needs to
+ * be paired with (d).
+ *
+ * D) exit_mm vs membarrier
+ *
+ * Two thread groups are created, A and B.  Thread group B is created by
+ * issuing clone from group A with flag CLONE_VM set, but not CLONE_THREAD.
+ * Let's assume we have a single thread within each thread group (Thread A
+ * and Thread B).  Thread A runs on CPU0, Thread B runs on CPU1.
+ *
+ *           CPU0                            CPU1
+ *
+ *           membarrier():
+ *             a: smp_mb()
+ *                                           exit_mm():
+ *                                             d: smp_mb()
+ *                                             e: current->mm = NULL
+ *             b: read rq->curr->mm == NULL
+ *             c: smp_mb()
+ *
+ * Using scenario (B), we can show that (c) needs to be paired with (d).
+ *
+ * E) kthread_{use,unuse}_mm vs membarrier
+ *
+ *           CPU0                            CPU1
+ *
+ *           membarrier():
+ *           a: smp_mb()
+ *                                           kthread_unuse_mm()
+ *                                             d: smp_mb()
+ *                                             e: current->mm = NULL
+ *           b: read rq->curr->mm == NULL
+ *                                           kthread_use_mm()
+ *                                             f: current->mm = mm
+ *                                             g: smp_mb()
+ *           c: smp_mb()
+ *
+ * Using the scenario from (A), we can show that (a) needs to be paired
+ * with (g). Using the scenario from (B), we can show that (c) needs to
+ * be paired with (d).
+ */
+
 /*
  * Bitmask made from a "or" of all commands within enum membarrier_cmd,
  * except MEMBARRIER_CMD_QUERY.
@@ -76,6 +204,18 @@ void membarrier_exec_mmap(struct mm_struct *mm)
 	this_cpu_write(runqueues.membarrier_state, 0);
 }
 
+void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+	struct rq *rq = this_rq();
+	int membarrier_state = 0;
+
+	if (next_mm)
+		membarrier_state = atomic_read(&next_mm->membarrier_state);
+	if (READ_ONCE(rq->membarrier_state) == membarrier_state)
+		return;
+	WRITE_ONCE(rq->membarrier_state, membarrier_state);
+}
+
 static int membarrier_global_expedited(void)
 {
 	int cpu;
@@ -114,12 +254,11 @@ static int membarrier_global_expedited(void)
 			continue;
 
 		/*
-		 * Skip the CPU if it runs a kernel thread. The scheduler
-		 * leaves the prior task mm in place as an optimization when
-		 * scheduling a kthread.
+		 * Skip the CPU if it runs a kernel thread which is not using
+		 * a task mm.
 		 */
 		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p->flags & PF_KTHREAD)
+		if (!p->mm)
 			continue;
 
 		__cpumask_set_cpu(cpu, tmpmask);

kernel/sched/rt.c

@@ -89,8 +89,8 @@ void init_rt_rq(struct rt_rq *rt_rq)
 	__set_bit(MAX_RT_PRIO, array->bitmap);
 
 #if defined CONFIG_SMP
-	rt_rq->highest_prio.curr = MAX_RT_PRIO;
-	rt_rq->highest_prio.next = MAX_RT_PRIO;
+	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
+	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
 	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
@@ -161,7 +161,7 @@ void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 {
 	struct rq *rq = cpu_rq(cpu);
 
-	rt_rq->highest_prio.curr = MAX_RT_PRIO;
+	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
 	rt_rq->rt_nr_boosted = 0;
 	rt_rq->rq = rq;
 	rt_rq->tg = tg;
@@ -265,7 +265,7 @@ static void pull_rt_task(struct rq *this_rq);
 static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev)
 {
 	/* Try to pull RT tasks here if we lower this rq's prio */
-	return rq->rt.highest_prio.curr > prev->prio;
+	return rq->online && rq->rt.highest_prio.curr > prev->prio;
 }
 
 static inline int rt_overloaded(struct rq *rq)
@@ -393,8 +393,9 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 		p = plist_first_entry(&rq->rt.pushable_tasks,
 				      struct task_struct, pushable_tasks);
 		rq->rt.highest_prio.next = p->prio;
-	} else
-		rq->rt.highest_prio.next = MAX_RT_PRIO;
+	} else {
+		rq->rt.highest_prio.next = MAX_RT_PRIO-1;
+	}
 }
 
 #else
@@ -1147,8 +1148,9 @@ dec_rt_prio(struct rt_rq *rt_rq, int prio)
 				sched_find_first_bit(array->bitmap);
 		}
 
-	} else
-		rt_rq->highest_prio.curr = MAX_RT_PRIO;
+	} else {
+		rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
+	}
 
 	dec_rt_prio_smp(rt_rq, prio, prev_prio);
 }
@@ -1428,14 +1430,14 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int cpu, int flags)
 {
 	struct task_struct *curr;
 	struct rq *rq;
 	bool test;
 
 	/* For anything but wake ups, just return the task_cpu */
-	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+	if (!(flags & (WF_TTWU | WF_FORK)))
 		goto out;
 
 	rq = cpu_rq(cpu);
@@ -1658,7 +1660,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, p->cpus_ptr))
+	    cpumask_test_cpu(cpu, &p->cpus_mask))
 		return 1;
 
 	return 0;
@@ -1752,8 +1754,8 @@ static int find_lowest_rq(struct task_struct *task)
 				return this_cpu;
 			}
 
-			best_cpu = cpumask_first_and(lowest_mask,
-						     sched_domain_span(sd));
+			best_cpu = cpumask_any_and_distribute(lowest_mask,
+							      sched_domain_span(sd));
 			if (best_cpu < nr_cpu_ids) {
 				rcu_read_unlock();
 				return best_cpu;
@@ -1770,7 +1772,7 @@ static int find_lowest_rq(struct task_struct *task)
 	if (this_cpu != -1)
 		return this_cpu;
 
-	cpu = cpumask_any(lowest_mask);
+	cpu = cpumask_any_distribute(lowest_mask);
 	if (cpu < nr_cpu_ids)
 		return cpu;
 
@@ -1811,7 +1813,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * Also make sure that it wasn't scheduled on its rq.
 			 */
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) ||
+				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
 				     task_running(rq, task) ||
 				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
@@ -1859,7 +1861,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
  * running task can migrate over to a CPU that is running a task
  * of lesser priority.
  */
-static int push_rt_task(struct rq *rq)
+static int push_rt_task(struct rq *rq, bool pull)
 {
 	struct task_struct *next_task;
 	struct rq *lowest_rq;
@@ -1873,6 +1875,34 @@ static int push_rt_task(struct rq *rq)
 		return 0;
 
 retry:
+	if (is_migration_disabled(next_task)) {
+		struct task_struct *push_task = NULL;
+		int cpu;
+
+		if (!pull || rq->push_busy)
+			return 0;
+
+		cpu = find_lowest_rq(rq->curr);
+		if (cpu == -1 || cpu == rq->cpu)
+			return 0;
+
+		/*
+		 * Given we found a CPU with lower priority than @next_task,
+		 * therefore it should be running. However we cannot migrate it
+		 * to this other CPU, instead attempt to push the current
+		 * running task on this CPU away.
+		 */
+		push_task = get_push_task(rq);
+		if (push_task) {
+			raw_spin_unlock(&rq->lock);
+			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
+					    push_task, &rq->push_work);
+			raw_spin_lock(&rq->lock);
+		}
+
+		return 0;
+	}
+
 	if (WARN_ON(next_task == rq->curr))
 		return 0;
 
@@ -1927,12 +1957,10 @@ static int push_rt_task(struct rq *rq)
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, lowest_rq->cpu);
 	activate_task(lowest_rq, next_task, 0);
-	ret = 1;
-
 	resched_curr(lowest_rq);
+	ret = 1;
 
 	double_unlock_balance(rq, lowest_rq);
-
 out:
 	put_task_struct(next_task);
 
@@ -1942,7 +1970,7 @@ static int push_rt_task(struct rq *rq)
 static void push_rt_tasks(struct rq *rq)
 {
 	/* push_rt_task will return true if it moved an RT */
-	while (push_rt_task(rq))
+	while (push_rt_task(rq, false))
 		;
 }
 
@@ -2095,7 +2123,8 @@ void rto_push_irq_work_func(struct irq_work *work)
 	 */
 	if (has_pushable_tasks(rq)) {
 		raw_spin_lock(&rq->lock);
-		push_rt_tasks(rq);
+		while (push_rt_task(rq, true))
+			;
 		raw_spin_unlock(&rq->lock);
 	}
 
@@ -2120,7 +2149,7 @@ static void pull_rt_task(struct rq *this_rq)
 {
 	int this_cpu = this_rq->cpu, cpu;
 	bool resched = false;
-	struct task_struct *p;
+	struct task_struct *p, *push_task;
 	struct rq *src_rq;
 	int rt_overload_count = rt_overloaded(this_rq);
 
@@ -2167,6 +2196,7 @@ static void pull_rt_task(struct rq *this_rq)
 		 * double_lock_balance, and another CPU could
 		 * alter this_rq
 		 */
+		push_task = NULL;
 		double_lock_balance(this_rq, src_rq);
 
 		/*
@@ -2194,11 +2224,14 @@ static void pull_rt_task(struct rq *this_rq)
 			if (p->prio < src_rq->curr->prio)
 				goto skip;
 
-			resched = true;
-
-			deactivate_task(src_rq, p, 0);
-			set_task_cpu(p, this_cpu);
-			activate_task(this_rq, p, 0);
+			if (is_migration_disabled(p)) {
+				push_task = get_push_task(src_rq);
+			} else {
+				deactivate_task(src_rq, p, 0);
+				set_task_cpu(p, this_cpu);
+				activate_task(this_rq, p, 0);
+				resched = true;
+			}
 			/*
 			 * We continue with the search, just in
 			 * case there's an even higher prio task
@@ -2208,6 +2241,13 @@ static void pull_rt_task(struct rq *this_rq)
 		}
 skip:
 		double_unlock_balance(this_rq, src_rq);
+
+		if (push_task) {
+			raw_spin_unlock(&this_rq->lock);
+			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
+					    push_task, &src_rq->push_work);
+			raw_spin_lock(&this_rq->lock);
+		}
 	}
 
 	if (resched)
@@ -2429,8 +2469,8 @@ static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 		return 0;
 }
 
-const struct sched_class rt_sched_class
-	__section("__rt_sched_class") = {
+DEFINE_SCHED_CLASS(rt) = {
+
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
@@ -2449,6 +2489,7 @@ const struct sched_class rt_sched_class
 	.rq_offline             = rq_offline_rt,
 	.task_woken		= task_woken_rt,
 	.switched_from		= switched_from_rt,
+	.find_lock_rq		= find_lock_lowest_rq,
 #endif
 
 	.task_tick		= task_tick_rt,

kernel/sched/sched.h

@@ -67,7 +67,6 @@
 #include <linux/tsacct_kern.h>
 
 #include <asm/tlb.h>
-#include <asm-generic/vmlinux.lds.h>
 
 #ifdef CONFIG_PARAVIRT
 # include <asm/paravirt.h>
@@ -257,30 +256,6 @@ struct rt_bandwidth {
 
 void __dl_clear_params(struct task_struct *p);
 
-/*
- * To keep the bandwidth of -deadline tasks and groups under control
- * we need some place where:
- *  - store the maximum -deadline bandwidth of the system (the group);
- *  - cache the fraction of that bandwidth that is currently allocated.
- *
- * This is all done in the data structure below. It is similar to the
- * one used for RT-throttling (rt_bandwidth), with the main difference
- * that, since here we are only interested in admission control, we
- * do not decrease any runtime while the group "executes", neither we
- * need a timer to replenish it.
- *
- * With respect to SMP, the bandwidth is given on a per-CPU basis,
- * meaning that:
- *  - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
- *  - dl_total_bw array contains, in the i-eth element, the currently
- *    allocated bandwidth on the i-eth CPU.
- * Moreover, groups consume bandwidth on each CPU, while tasks only
- * consume bandwidth on the CPU they're running on.
- * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
- * that will be shown the next time the proc or cgroup controls will
- * be red. It on its turn can be changed by writing on its own
- * control.
- */
 struct dl_bandwidth {
 	raw_spinlock_t		dl_runtime_lock;
 	u64			dl_runtime;
@@ -292,6 +267,24 @@ static inline int dl_bandwidth_enabled(void)
 	return sysctl_sched_rt_runtime >= 0;
 }
 
+/*
+ * To keep the bandwidth of -deadline tasks under control
+ * we need some place where:
+ *  - store the maximum -deadline bandwidth of each cpu;
+ *  - cache the fraction of bandwidth that is currently allocated in
+ *    each root domain;
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, bandwidth is given on a per root domain basis,
+ * meaning that:
+ *  - bw (< 100%) is the deadline bandwidth of each CPU;
+ *  - total_bw is the currently allocated bandwidth in each root domain;
+ */
 struct dl_bw {
 	raw_spinlock_t		lock;
 	u64			bw;
@@ -801,6 +794,15 @@ struct root_domain {
 	struct dl_bw		dl_bw;
 	struct cpudl		cpudl;
 
+	/*
+	 * Indicate whether a root_domain's dl_bw has been checked or
+	 * updated. It's monotonously increasing value.
+	 *
+	 * Also, some corner cases, like 'wrap around' is dangerous, but given
+	 * that u64 is 'big enough'. So that shouldn't be a concern.
+	 */
+	u64 visit_gen;
+
 #ifdef HAVE_RT_PUSH_IPI
 	/*
 	 * For IPI pull requests, loop across the rto_mask.
@@ -973,6 +975,7 @@ struct rq {
 	unsigned long		cpu_capacity_orig;
 
 	struct callback_head	*balance_callback;
+	unsigned char		balance_flags;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;
@@ -1003,6 +1006,10 @@ struct rq {
 
 	/* This is used to determine avg_idle's max value */
 	u64			max_idle_balance_cost;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	struct rcuwait		hotplug_wait;
+#endif
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -1048,6 +1055,12 @@ struct rq {
 	/* Must be inspected within a rcu lock section */
 	struct cpuidle_state	*idle_state;
 #endif
+
+#ifdef CONFIG_SMP
+	unsigned int		nr_pinned;
+#endif
+	unsigned int		push_busy;
+	struct cpu_stop_work	push_work;
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1075,6 +1088,16 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
+#define MDF_PUSH	0x01
+
+static inline bool is_migration_disabled(struct task_struct *p)
+{
+#ifdef CONFIG_SMP
+	return p->migration_disabled;
+#else
+	return false;
+#endif
+}
 
 #ifdef CONFIG_SCHED_SMT
 extern void __update_idle_core(struct rq *rq);
@@ -1221,6 +1244,9 @@ static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
 	rf->clock_update_flags = 0;
 #endif
+#ifdef CONFIG_SMP
+	SCHED_WARN_ON(rq->balance_callback);
+#endif
 }
 
 static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
@@ -1382,6 +1408,9 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 #ifdef CONFIG_SMP
 
+#define BALANCE_WORK	0x01
+#define BALANCE_PUSH	0x02
+
 static inline void
 queue_balance_callback(struct rq *rq,
 		       struct callback_head *head,
@@ -1389,12 +1418,13 @@ queue_balance_callback(struct rq *rq,
 {
 	lockdep_assert_held(&rq->lock);
 
-	if (unlikely(head->next))
+	if (unlikely(head->next || (rq->balance_flags & BALANCE_PUSH)))
 		return;
 
 	head->func = (void (*)(struct callback_head *))func;
 	head->next = rq->balance_callback;
 	rq->balance_callback = head;
+	rq->balance_flags |= BALANCE_WORK;
 }
 
 #define rcu_dereference_check_sched_domain(p) \
@@ -1714,13 +1744,20 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 	return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
 }
 
-/*
- * wake flags
- */
-#define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
-#define WF_FORK			0x02		/* Child wakeup after fork */
-#define WF_MIGRATED		0x04		/* Internal use, task got migrated */
-#define WF_ON_CPU		0x08		/* Wakee is on_cpu */
+/* Wake flags. The first three directly map to some SD flag value */
+#define WF_EXEC     0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
+#define WF_FORK     0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
+#define WF_TTWU     0x08 /* Wakeup;            maps to SD_BALANCE_WAKE */
+
+#define WF_SYNC     0x10 /* Waker goes to sleep after wakeup */
+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
+#define WF_ON_CPU   0x40 /* Wakee is on_cpu */
+
+#ifdef CONFIG_SMP
+static_assert(WF_EXEC == SD_BALANCE_EXEC);
+static_assert(WF_FORK == SD_BALANCE_FORK);
+static_assert(WF_TTWU == SD_BALANCE_WAKE);
+#endif
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
@@ -1796,16 +1833,19 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
 	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
-	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
+	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
 	void (*task_woken)(struct rq *this_rq, struct task_struct *task);
 
 	void (*set_cpus_allowed)(struct task_struct *p,
-				 const struct cpumask *newmask);
+				 const struct cpumask *newmask,
+				 u32 flags);
 
 	void (*rq_online)(struct rq *rq);
 	void (*rq_offline)(struct rq *rq);
+
+	struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
 #endif
 
 	void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
@@ -1833,7 +1873,7 @@ struct sched_class {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*task_change_group)(struct task_struct *p, int type);
 #endif
-} __aligned(STRUCT_ALIGNMENT); /* STRUCT_ALIGN(), vmlinux.lds.h */
+};
 
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
@@ -1847,6 +1887,20 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
 	next->sched_class->set_next_task(rq, next, false);
 }
 
+
+/*
+ * Helper to define a sched_class instance; each one is placed in a separate
+ * section which is ordered by the linker script:
+ *
+ *   include/asm-generic/vmlinux.lds.h
+ *
+ * Also enforce alignment on the instance, not the type, to guarantee layout.
+ */
+#define DEFINE_SCHED_CLASS(name) \
+const struct sched_class name##_sched_class \
+	__aligned(__alignof__(struct sched_class)) \
+	__section("__" #name "_sched_class")
+
 /* Defined in include/asm-generic/vmlinux.lds.h */
 extern struct sched_class __begin_sched_classes[];
 extern struct sched_class __end_sched_classes[];
@@ -1889,13 +1943,35 @@ static inline bool sched_fair_runnable(struct rq *rq)
 extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 extern struct task_struct *pick_next_task_idle(struct rq *rq);
 
+#define SCA_CHECK		0x01
+#define SCA_MIGRATE_DISABLE	0x02
+#define SCA_MIGRATE_ENABLE	0x04
+
 #ifdef CONFIG_SMP
 
 extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
 
-extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
+extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+
+static inline struct task_struct *get_push_task(struct rq *rq)
+{
+	struct task_struct *p = rq->curr;
+
+	lockdep_assert_held(&rq->lock);
+
+	if (rq->push_busy)
+		return NULL;
+
+	if (p->nr_cpus_allowed == 1)
+		return NULL;
+
+	rq->push_busy = true;
+	return get_task_struct(p);
+}
+
+extern int push_cpu_stop(void *arg);
 
 #endif
 

kernel/sched/stop_task.c

@@ -11,7 +11,7 @@
 
 #ifdef CONFIG_SMP
 static int
-select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
+select_task_rq_stop(struct task_struct *p, int cpu, int flags)
 {
 	return task_cpu(p); /* stop tasks as never migrate */
 }
@@ -109,8 +109,7 @@ static void update_curr_stop(struct rq *rq)
 /*
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
-const struct sched_class stop_sched_class
-	__section("__stop_sched_class") = {
+DEFINE_SCHED_CLASS(stop) = {
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,

kernel/sched/topology.c

@@ -211,6 +211,15 @@ unsigned int sysctl_sched_energy_aware = 1;
 DEFINE_MUTEX(sched_energy_mutex);
 bool sched_energy_update;
 
+void rebuild_sched_domains_energy(void)
+{
+	mutex_lock(&sched_energy_mutex);
+	sched_energy_update = true;
+	rebuild_sched_domains();
+	sched_energy_update = false;
+	mutex_unlock(&sched_energy_mutex);
+}
+
 #ifdef CONFIG_PROC_SYSCTL
 int sched_energy_aware_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
@@ -223,13 +232,8 @@ int sched_energy_aware_handler(struct ctl_table *table, int write,
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (!ret && write) {
 		state = static_branch_unlikely(&sched_energy_present);
-		if (state != sysctl_sched_energy_aware) {
-			mutex_lock(&sched_energy_mutex);
-			sched_energy_update = 1;
-			rebuild_sched_domains();
-			sched_energy_update = 0;
-			mutex_unlock(&sched_energy_mutex);
-		}
+		if (state != sysctl_sched_energy_aware)
+			rebuild_sched_domains_energy();
 	}
 
 	return ret;
@@ -324,6 +328,7 @@ static void sched_energy_set(bool has_eas)
  *    3. no SMT is detected.
  *    4. the EM complexity is low enough to keep scheduling overheads low;
  *    5. schedutil is driving the frequency of all CPUs of the rd;
+ *    6. frequency invariance support is present;
  *
  * The complexity of the Energy Model is defined as:
  *
@@ -372,6 +377,14 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
 		goto free;
 	}
 
+	if (!arch_scale_freq_invariant()) {
+		if (sched_debug()) {
+			pr_warn("rd %*pbl: Disabling EAS: frequency-invariant load tracking not yet supported",
+				cpumask_pr_args(cpu_map));
+		}
+		goto free;
+	}
+
 	for_each_cpu(i, cpu_map) {
 		/* Skip already covered CPUs. */
 		if (find_pd(pd, i))
@@ -516,6 +529,7 @@ static int init_rootdomain(struct root_domain *rd)
 	init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
 #endif
 
+	rd->visit_gen = 0;
 	init_dl_bw(&rd->dl_bw);
 	if (cpudl_init(&rd->cpudl) != 0)
 		goto free_rto_mask;
@@ -674,6 +688,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct sched_domain *tmp;
+	int numa_distance = 0;
 
 	/* Remove the sched domains which do not contribute to scheduling. */
 	for (tmp = sd; tmp; ) {
@@ -705,6 +720,38 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 			sd->child = NULL;
 	}
 
+	for (tmp = sd; tmp; tmp = tmp->parent)
+		numa_distance += !!(tmp->flags & SD_NUMA);
+
+	/*
+	 * FIXME: Diameter >=3 is misrepresented.
+	 *
+	 * Smallest diameter=3 topology is:
+	 *
+	 *   node   0   1   2   3
+	 *     0:  10  20  30  40
+	 *     1:  20  10  20  30
+	 *     2:  30  20  10  20
+	 *     3:  40  30  20  10
+	 *
+	 *   0 --- 1 --- 2 --- 3
+	 *
+	 * NUMA-3	0-3		N/A		N/A		0-3
+	 *  groups:	{0-2},{1-3}					{1-3},{0-2}
+	 *
+	 * NUMA-2	0-2		0-3		0-3		1-3
+	 *  groups:	{0-1},{1-3}	{0-2},{2-3}	{1-3},{0-1}	{2-3},{0-2}
+	 *
+	 * NUMA-1	0-1		0-2		1-3		2-3
+	 *  groups:	{0},{1}		{1},{2},{0}	{2},{3},{1}	{3},{2}
+	 *
+	 * NUMA-0	0		1		2		3
+	 *
+	 * The NUMA-2 groups for nodes 0 and 3 are obviously buggered, as the
+	 * group span isn't a subset of the domain span.
+	 */
+	WARN_ONCE(numa_distance > 2, "Shortest NUMA path spans too many nodes\n");
+
 	sched_domain_debug(sd, cpu);
 
 	rq_attach_root(rq, rd);

kernel/stop_machine.c

@@ -42,11 +42,27 @@ struct cpu_stopper {
 	struct list_head	works;		/* list of pending works */
 
 	struct cpu_stop_work	stop_work;	/* for stop_cpus */
+	unsigned long		caller;
+	cpu_stop_fn_t		fn;
 };
 
 static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
 static bool stop_machine_initialized = false;
 
+void print_stop_info(const char *log_lvl, struct task_struct *task)
+{
+	/*
+	 * If @task is a stopper task, it cannot migrate and task_cpu() is
+	 * stable.
+	 */
+	struct cpu_stopper *stopper = per_cpu_ptr(&cpu_stopper, task_cpu(task));
+
+	if (task != stopper->thread)
+		return;
+
+	printk("%sStopper: %pS <- %pS\n", log_lvl, stopper->fn, (void *)stopper->caller);
+}
+
 /* static data for stop_cpus */
 static DEFINE_MUTEX(stop_cpus_mutex);
 static bool stop_cpus_in_progress;
@@ -123,7 +139,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
 {
 	struct cpu_stop_done done;
-	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
+	struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done, .caller = _RET_IP_ };
 
 	cpu_stop_init_done(&done, 1);
 	if (!cpu_stop_queue_work(cpu, &work))
@@ -331,7 +347,8 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 	work1 = work2 = (struct cpu_stop_work){
 		.fn = multi_cpu_stop,
 		.arg = &msdata,
-		.done = &done
+		.done = &done,
+		.caller = _RET_IP_,
 	};
 
 	cpu_stop_init_done(&done, 2);
@@ -367,7 +384,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			struct cpu_stop_work *work_buf)
 {
-	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
+	*work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, .caller = _RET_IP_, };
 	return cpu_stop_queue_work(cpu, work_buf);
 }
 
@@ -487,6 +504,8 @@ static void cpu_stopper_thread(unsigned int cpu)
 		int ret;
 
 		/* cpu stop callbacks must not sleep, make in_atomic() == T */
+		stopper->caller = work->caller;
+		stopper->fn = fn;
 		preempt_count_inc();
 		ret = fn(arg);
 		if (done) {
@@ -495,6 +514,8 @@ static void cpu_stopper_thread(unsigned int cpu)
 			cpu_stop_signal_done(done);
 		}
 		preempt_count_dec();
+		stopper->fn = NULL;
+		stopper->caller = 0;
 		WARN_ONCE(preempt_count(),
 			  "cpu_stop: %ps(%p) leaked preempt count\n", fn, arg);
 		goto repeat;

kernel/workqueue.c

@@ -4908,6 +4908,10 @@ static void unbind_workers(int cpu)
 		pool->flags |= POOL_DISASSOCIATED;
 
 		raw_spin_unlock_irq(&pool->lock);
+
+		for_each_pool_worker(worker, pool)
+			WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_active_mask) < 0);
+
 		mutex_unlock(&wq_pool_attach_mutex);
 
 		/*

lib/cpumask.c

@@ -267,3 +267,21 @@ int cpumask_any_and_distribute(const struct cpumask *src1p,
 	return next;
 }
 EXPORT_SYMBOL(cpumask_any_and_distribute);
+
+int cpumask_any_distribute(const struct cpumask *srcp)
+{
+	int next, prev;
+
+	/* NOTE: our first selection will skip 0. */
+	prev = __this_cpu_read(distribute_cpu_mask_prev);
+
+	next = cpumask_next(prev, srcp);
+	if (next >= nr_cpu_ids)
+		next = cpumask_first(srcp);
+
+	if (next < nr_cpu_ids)
+		__this_cpu_write(distribute_cpu_mask_prev, next);
+
+	return next;
+}
+EXPORT_SYMBOL(cpumask_any_distribute);

lib/dump_stack.c

@@ -12,6 +12,7 @@
 #include <linux/atomic.h>
 #include <linux/kexec.h>
 #include <linux/utsname.h>
+#include <linux/stop_machine.h>
 
 static char dump_stack_arch_desc_str[128];
 
@@ -57,6 +58,7 @@ void dump_stack_print_info(const char *log_lvl)
 		       log_lvl, dump_stack_arch_desc_str);
 
 	print_worker_info(log_lvl, current);
+	print_stop_info(log_lvl, current);
 }
 
 /**

lib/smp_processor_id.c

@@ -26,6 +26,11 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2)
 	if (current->nr_cpus_allowed == 1)
 		goto out;
 
+#ifdef CONFIG_SMP
+	if (current->migration_disabled)
+		goto out;
+#endif
+
 	/*
 	 * It is valid to assume CPU-locality during early bootup:
 	 */