Merge tag 'sched-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - The biggest change in this cycle is scheduler support for asymmetric
   scheduling affinity, to support the execution of legacy 32-bit tasks
   on AArch32 systems that also have 64-bit-only CPUs.

   Architectures can fill in this functionality by defining their own
   task_cpu_possible_mask(p). When this is done, the scheduler will make
   sure the task will only be scheduled on CPUs that support it.

   (The actual arm64 specific changes are not part of this tree.)

   For other architectures there will be no change in functionality.

 - Add cgroup SCHED_IDLE support

 - Increase node-distance flexibility & delay determining it until a CPU
   is brought online. (This enables platforms where node distance isn't
   final until the CPU is only.)

 - Deadline scheduler enhancements & fixes

 - Misc fixes & cleanups.

* tag 'sched-core-2021-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  eventfd: Make signal recursion protection a task bit
  sched/fair: Mark tg_is_idle() an inline in the !CONFIG_FAIR_GROUP_SCHED case
  sched: Introduce dl_task_check_affinity() to check proposed affinity
  sched: Allow task CPU affinity to be restricted on asymmetric systems
  sched: Split the guts of sched_setaffinity() into a helper function
  sched: Introduce task_struct::user_cpus_ptr to track requested affinity
  sched: Reject CPU affinity changes based on task_cpu_possible_mask()
  cpuset: Cleanup cpuset_cpus_allowed_fallback() use in select_fallback_rq()
  cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus()
  cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1
  sched: Introduce task_cpu_possible_mask() to limit fallback rq selection
  sched: Cgroup SCHED_IDLE support
  sched/topology: Skip updating masks for non-online nodes
  sched: Replace deprecated CPU-hotplug functions.
  sched: Skip priority checks with SCHED_FLAG_KEEP_PARAMS
  sched: Fix UCLAMP_FLAG_IDLE setting
  sched/deadline: Fix missing clock update in migrate_task_rq_dl()
  sched/fair: Avoid a second scan of target in select_idle_cpu
  sched/fair: Use prev instead of new target as recent_used_cpu
  sched: Don't report SCHED_FLAG_SUGOV in sched_getattr()
  ...

fs/aio.c

@@ -1695,7 +1695,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 		list_del(&iocb->ki_list);
 		iocb->ki_res.res = mangle_poll(mask);
 		req->done = true;
-		if (iocb->ki_eventfd && eventfd_signal_count()) {
+		if (iocb->ki_eventfd && eventfd_signal_allowed()) {
 			iocb = NULL;
 			INIT_WORK(&req->work, aio_poll_put_work);
 			schedule_work(&req->work);

fs/eventfd.c

@@ -25,8 +25,6 @@
 #include <linux/idr.h>
 #include <linux/uio.h>
 
-DEFINE_PER_CPU(int, eventfd_wake_count);
-
 static DEFINE_IDA(eventfd_ida);
 
 struct eventfd_ctx {
@@ -67,21 +65,21 @@ __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
 	 * Deadlock or stack overflow issues can happen if we recurse here
 	 * through waitqueue wakeup handlers. If the caller users potentially
 	 * nested waitqueues with custom wakeup handlers, then it should
-	 * check eventfd_signal_count() before calling this function. If
-	 * it returns true, the eventfd_signal() call should be deferred to a
+	 * check eventfd_signal_allowed() before calling this function. If
+	 * it returns false, the eventfd_signal() call should be deferred to a
 	 * safe context.
 	 */
-	if (WARN_ON_ONCE(this_cpu_read(eventfd_wake_count)))
+	if (WARN_ON_ONCE(current->in_eventfd_signal))
 		return 0;
 
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
-	this_cpu_inc(eventfd_wake_count);
+	current->in_eventfd_signal = 1;
 	if (ULLONG_MAX - ctx->count < n)
 		n = ULLONG_MAX - ctx->count;
 	ctx->count += n;
 	if (waitqueue_active(&ctx->wqh))
 		wake_up_locked_poll(&ctx->wqh, EPOLLIN);
-	this_cpu_dec(eventfd_wake_count);
+	current->in_eventfd_signal = 0;
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 
 	return n;

include/linux/cpuset.h

@@ -15,6 +15,7 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/mm.h>
+#include <linux/mmu_context.h>
 #include <linux/jump_label.h>
 
 #ifdef CONFIG_CPUSETS
@@ -58,7 +59,7 @@ extern void cpuset_wait_for_hotplug(void);
 extern void cpuset_read_lock(void);
 extern void cpuset_read_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
-extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
@@ -184,11 +185,12 @@ static inline void cpuset_read_unlock(void) { }
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
-	cpumask_copy(mask, cpu_possible_mask);
+	cpumask_copy(mask, task_cpu_possible_mask(p));
 }
 
-static inline void cpuset_cpus_allowed_fallback(struct task_struct *p)
+static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
+	return false;
 }
 
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)

include/linux/eventfd.h

@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/percpu-defs.h>
 #include <linux/percpu.h>
+#include <linux/sched.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
@@ -43,11 +44,9 @@ int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *w
 				  __u64 *cnt);
 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
 
-DECLARE_PER_CPU(int, eventfd_wake_count);
-
-static inline bool eventfd_signal_count(void)
+static inline bool eventfd_signal_allowed(void)
 {
-	return this_cpu_read(eventfd_wake_count);
+	return !current->in_eventfd_signal;
 }
 
 #else /* CONFIG_EVENTFD */
@@ -78,9 +77,9 @@ static inline int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx,
 	return -ENOSYS;
 }
 
-static inline bool eventfd_signal_count(void)
+static inline bool eventfd_signal_allowed(void)
 {
-	return false;
+	return true;
 }
 
 static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)

include/linux/mmu_context.h

@@ -14,4 +14,18 @@
 static inline void leave_mm(int cpu) { }
 #endif
 
+/*
+ * CPUs that are capable of running user task @p. Must contain at least one
+ * active CPU. It is assumed that the kernel can run on all CPUs, so calling
+ * this for a kernel thread is pointless.
+ *
+ * By default, we assume a sane, homogeneous system.
+ */
+#ifndef task_cpu_possible_mask
+# define task_cpu_possible_mask(p)	cpu_possible_mask
+# define task_cpu_possible(cpu, p)	true
+#else
+# define task_cpu_possible(cpu, p)	cpumask_test_cpu((cpu), task_cpu_possible_mask(p))
+#endif
+
 #endif

include/linux/sched.h

@@ -748,6 +748,7 @@ struct task_struct {
 	unsigned int			policy;
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
+	cpumask_t			*user_cpus_ptr;
 	cpumask_t			cpus_mask;
 	void				*migration_pending;
 #ifdef CONFIG_SMP
@@ -863,6 +864,10 @@ struct task_struct {
 	/* Used by page_owner=on to detect recursion in page tracking. */
 	unsigned			in_page_owner:1;
 #endif
+#ifdef CONFIG_EVENTFD
+	/* Recursion prevention for eventfd_signal() */
+	unsigned			in_eventfd_signal:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -1705,6 +1710,11 @@ extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
 extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
+extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node);
+extern void release_user_cpus_ptr(struct task_struct *p);
+extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask);
+extern void force_compatible_cpus_allowed_ptr(struct task_struct *p);
+extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p);
 #else
 static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
@@ -1715,6 +1725,21 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpuma
 		return -EINVAL;
 	return 0;
 }
+static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node)
+{
+	if (src->user_cpus_ptr)
+		return -EINVAL;
+	return 0;
+}
+static inline void release_user_cpus_ptr(struct task_struct *p)
+{
+	WARN_ON(p->user_cpus_ptr);
+}
+
+static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
+{
+	return 0;
+}
 #endif
 
 extern int yield_to(struct task_struct *p, bool preempt);

include/linux/sched/sysctl.h

@@ -28,30 +28,12 @@ enum { sysctl_hung_task_timeout_secs = 0 };
 
 extern unsigned int sysctl_sched_child_runs_first;
 
-extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_min_granularity;
-extern unsigned int sysctl_sched_wakeup_granularity;
-
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
 	SCHED_TUNABLESCALING_LOG,
 	SCHED_TUNABLESCALING_LINEAR,
 	SCHED_TUNABLESCALING_END,
 };
-extern unsigned int sysctl_sched_tunable_scaling;
-
-extern unsigned int sysctl_numa_balancing_scan_delay;
-extern unsigned int sysctl_numa_balancing_scan_period_min;
-extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_size;
-
-#ifdef CONFIG_SCHED_DEBUG
-extern __read_mostly unsigned int sysctl_sched_migration_cost;
-extern __read_mostly unsigned int sysctl_sched_nr_migrate;
-
-extern int sysctl_resched_latency_warn_ms;
-extern int sysctl_resched_latency_warn_once;
-#endif
 
 /*
  *  control realtime throttling:

include/linux/wait.h

@@ -56,7 +56,7 @@ struct task_struct;
 
 #define __WAIT_QUEUE_HEAD_INITIALIZER(name) {					\
 	.lock		= __SPIN_LOCK_UNLOCKED(name.lock),			\
-	.head		= { &(name).head, &(name).head } }
+	.head		= LIST_HEAD_INIT(name.head) }
 
 #define DECLARE_WAIT_QUEUE_HEAD(name) \
 	struct wait_queue_head name = __WAIT_QUEUE_HEAD_INITIALIZER(name)

init/init_task.c

@@ -80,6 +80,7 @@ struct task_struct init_task
 	.normal_prio	= MAX_PRIO - 20,
 	.policy		= SCHED_NORMAL,
 	.cpus_ptr	= &init_task.cpus_mask,
+	.user_cpus_ptr	= NULL,
 	.cpus_mask	= CPU_MASK_ALL,
 	.nr_cpus_allowed= NR_CPUS,
 	.mm		= NULL,

kernel/cgroup/cpuset.c

@@ -372,18 +372,29 @@ static inline bool is_in_v2_mode(void)
 }
 
 /*
- * Return in pmask the portion of a cpusets's cpus_allowed that
- * are online.  If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus.
+ * Return in pmask the portion of a task's cpusets's cpus_allowed that
+ * are online and are capable of running the task.  If none are found,
+ * walk up the cpuset hierarchy until we find one that does have some
+ * appropriate cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
  *
  * Call with callback_lock or cpuset_mutex held.
  */
-static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
+static void guarantee_online_cpus(struct task_struct *tsk,
+				  struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
+	const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+	struct cpuset *cs;
+
+	if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask)))
+		cpumask_copy(pmask, cpu_online_mask);
+
+	rcu_read_lock();
+	cs = task_cs(tsk);
+
+	while (!cpumask_intersects(cs->effective_cpus, pmask)) {
 		cs = parent_cs(cs);
 		if (unlikely(!cs)) {
 			/*
@@ -393,11 +404,13 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 			 * cpuset's effective_cpus is on its way to be
 			 * identical to cpu_online_mask.
 			 */
-			cpumask_copy(pmask, cpu_online_mask);
-			return;
+			goto out_unlock;
 		}
 	}
-	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
+	cpumask_and(pmask, pmask, cs->effective_cpus);
+
+out_unlock:
+	rcu_read_unlock();
 }
 
 /*
@@ -2199,15 +2212,13 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 
 	percpu_down_write(&cpuset_rwsem);
 
-	/* prepare for attach */
-	if (cs == &top_cpuset)
-		cpumask_copy(cpus_attach, cpu_possible_mask);
-	else
-		guarantee_online_cpus(cs, cpus_attach);
-
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
 	cgroup_taskset_for_each(task, css, tset) {
+		if (cs != &top_cpuset)
+			guarantee_online_cpus(task, cpus_attach);
+		else
+			cpumask_copy(cpus_attach, task_cpu_possible_mask(task));
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
@@ -3302,9 +3313,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 	unsigned long flags;
 
 	spin_lock_irqsave(&callback_lock, flags);
-	rcu_read_lock();
-	guarantee_online_cpus(task_cs(tsk), pmask);
-	rcu_read_unlock();
+	guarantee_online_cpus(tsk, pmask);
 	spin_unlock_irqrestore(&callback_lock, flags);
 }
 
@@ -3318,13 +3327,22 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
  * which will not contain a sane cpumask during cases such as cpu hotplugging.
  * This is the absolute last resort for the scheduler and it is only used if
  * _every_ other avenue has been traveled.
+ *
+ * Returns true if the affinity of @tsk was changed, false otherwise.
  **/
 
-void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+bool cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
+	const struct cpumask *possible_mask = task_cpu_possible_mask(tsk);
+	const struct cpumask *cs_mask;
+	bool changed = false;
+
 	rcu_read_lock();
-	do_set_cpus_allowed(tsk, is_in_v2_mode() ?
-		task_cs(tsk)->cpus_allowed : cpu_possible_mask);
+	cs_mask = task_cs(tsk)->cpus_allowed;
+	if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) {
+		do_set_cpus_allowed(tsk, cs_mask);
+		changed = true;
+	}
 	rcu_read_unlock();
 
 	/*
@@ -3344,6 +3362,7 @@ void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	 * select_fallback_rq() will fix things ups and set cpu_possible_mask
 	 * if required.
 	 */
+	return changed;
 }
 
 void __init cpuset_init_current_mems_allowed(void)

kernel/fork.c

@@ -446,6 +446,7 @@ void put_task_stack(struct task_struct *tsk)
 
 void free_task(struct task_struct *tsk)
 {
+	release_user_cpus_ptr(tsk);
 	scs_release(tsk);
 
 #ifndef CONFIG_THREAD_INFO_IN_TASK
@@ -924,6 +925,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #endif
 	if (orig->cpus_ptr == &orig->cpus_mask)
 		tsk->cpus_ptr = &tsk->cpus_mask;
+	dup_user_cpus_ptr(tsk, orig, node);
 
 	/*
 	 * One for the user space visible state that goes away when reaped.

kernel/sched/deadline.c

@@ -1733,6 +1733,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 	 */
 	raw_spin_rq_lock(rq);
 	if (p->dl.dl_non_contending) {
+		update_rq_clock(rq);
 		sub_running_bw(&p->dl, &rq->dl);
 		p->dl.dl_non_contending = 0;
 		/*
@@ -2741,7 +2742,7 @@ void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_runtime = attr->sched_runtime;
 	dl_se->dl_deadline = attr->sched_deadline;
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
-	dl_se->flags = attr->sched_flags;
+	dl_se->flags = attr->sched_flags & SCHED_DL_FLAGS;
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
 	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
 }
@@ -2754,7 +2755,8 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 	attr->sched_runtime = dl_se->dl_runtime;
 	attr->sched_deadline = dl_se->dl_deadline;
 	attr->sched_period = dl_se->dl_period;
-	attr->sched_flags = dl_se->flags;
+	attr->sched_flags &= ~SCHED_DL_FLAGS;
+	attr->sched_flags |= dl_se->flags;
 }
 
 /*
@@ -2851,7 +2853,7 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 	if (dl_se->dl_runtime != attr->sched_runtime ||
 	    dl_se->dl_deadline != attr->sched_deadline ||
 	    dl_se->dl_period != attr->sched_period ||
-	    dl_se->flags != attr->sched_flags)
+	    dl_se->flags != (attr->sched_flags & SCHED_DL_FLAGS))
 		return true;
 
 	return false;

kernel/sched/debug.c

@@ -388,6 +388,13 @@ void update_sched_domain_debugfs(void)
 {
 	int cpu, i;
 
+	/*
+	 * This can unfortunately be invoked before sched_debug_init() creates
+	 * the debug directory. Don't touch sd_sysctl_cpus until then.
+	 */
+	if (!debugfs_sched)
+		return;
+
 	if (!cpumask_available(sd_sysctl_cpus)) {
 		if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL))
 			return;
@@ -600,6 +607,9 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running);
+	SEQ_printf(m, "  .%-30s: %d\n", "idle_h_nr_running",
+			cfs_rq->idle_h_nr_running);
 	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_SMP
 	SEQ_printf(m, "  .%-30s: %lu\n", "load_avg",

kernel/sched/sched.h

@@ -227,6 +227,8 @@ static inline void update_avg(u64 *avg, u64 sample)
  */
 #define SCHED_FLAG_SUGOV	0x10000000
 
+#define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV)
+
 static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se)
 {
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
@@ -394,6 +396,9 @@ struct task_group {
 	struct cfs_rq		**cfs_rq;
 	unsigned long		shares;
 
+	/* A positive value indicates that this is a SCHED_IDLE group. */
+	int			idle;
+
 #ifdef	CONFIG_SMP
 	/*
 	 * load_avg can be heavily contended at clock tick time, so put
@@ -503,6 +508,8 @@ extern void sched_move_task(struct task_struct *tsk);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
+extern int sched_group_set_idle(struct task_group *tg, long idle);
+
 #ifdef CONFIG_SMP
 extern void set_task_rq_fair(struct sched_entity *se,
 			     struct cfs_rq *prev, struct cfs_rq *next);
@@ -599,6 +606,9 @@ struct cfs_rq {
 	struct list_head	leaf_cfs_rq_list;
 	struct task_group	*tg;	/* group that "owns" this runqueue */
 
+	/* Locally cached copy of our task_group's idle value */
+	int			idle;
+
 #ifdef CONFIG_CFS_BANDWIDTH
 	int			runtime_enabled;
 	s64			runtime_remaining;
@@ -2234,6 +2244,7 @@ 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
+#define SCA_USER		0x08
 
 #ifdef CONFIG_SMP
 
@@ -2388,6 +2399,21 @@ extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
+#ifdef CONFIG_SCHED_DEBUG
+extern unsigned int sysctl_sched_latency;
+extern unsigned int sysctl_sched_min_granularity;
+extern unsigned int sysctl_sched_wakeup_granularity;
+extern int sysctl_resched_latency_warn_ms;
+extern int sysctl_resched_latency_warn_once;
+
+extern unsigned int sysctl_sched_tunable_scaling;
+
+extern unsigned int sysctl_numa_balancing_scan_delay;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_size;
+#endif
+
 #ifdef CONFIG_SCHED_HRTICK
 
 /*

kernel/sched/topology.c

@@ -1482,6 +1482,8 @@ int				sched_max_numa_distance;
 static int			*sched_domains_numa_distance;
 static struct cpumask		***sched_domains_numa_masks;
 int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
+
+static unsigned long __read_mostly *sched_numa_onlined_nodes;
 #endif
 
 /*
@@ -1833,6 +1835,16 @@ void sched_init_numa(void)
 			sched_domains_numa_masks[i][j] = mask;
 
 			for_each_node(k) {
+				/*
+				 * Distance information can be unreliable for
+				 * offline nodes, defer building the node
+				 * masks to its bringup.
+				 * This relies on all unique distance values
+				 * still being visible at init time.
+				 */
+				if (!node_online(j))
+					continue;
+
 				if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
 					sched_numa_warn("Node-distance not symmetric");
 
@@ -1886,6 +1898,53 @@ void sched_init_numa(void)
 	sched_max_numa_distance = sched_domains_numa_distance[nr_levels - 1];
 
 	init_numa_topology_type();
+
+	sched_numa_onlined_nodes = bitmap_alloc(nr_node_ids, GFP_KERNEL);
+	if (!sched_numa_onlined_nodes)
+		return;
+
+	bitmap_zero(sched_numa_onlined_nodes, nr_node_ids);
+	for_each_online_node(i)
+		bitmap_set(sched_numa_onlined_nodes, i, 1);
+}
+
+static void __sched_domains_numa_masks_set(unsigned int node)
+{
+	int i, j;
+
+	/*
+	 * NUMA masks are not built for offline nodes in sched_init_numa().
+	 * Thus, when a CPU of a never-onlined-before node gets plugged in,
+	 * adding that new CPU to the right NUMA masks is not sufficient: the
+	 * masks of that CPU's node must also be updated.
+	 */
+	if (test_bit(node, sched_numa_onlined_nodes))
+		return;
+
+	bitmap_set(sched_numa_onlined_nodes, node, 1);
+
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		for (j = 0; j < nr_node_ids; j++) {
+			if (!node_online(j) || node == j)
+				continue;
+
+			if (node_distance(j, node) > sched_domains_numa_distance[i])
+				continue;
+
+			/* Add remote nodes in our masks */
+			cpumask_or(sched_domains_numa_masks[i][node],
+				   sched_domains_numa_masks[i][node],
+				   sched_domains_numa_masks[0][j]);
+		}
+	}
+
+	/*
+	 * A new node has been brought up, potentially changing the topology
+	 * classification.
+	 *
+	 * Note that this is racy vs any use of sched_numa_topology_type :/
+	 */
+	init_numa_topology_type();
 }
 
 void sched_domains_numa_masks_set(unsigned int cpu)
@@ -1893,8 +1952,14 @@ void sched_domains_numa_masks_set(unsigned int cpu)
 	int node = cpu_to_node(cpu);
 	int i, j;
 
+	__sched_domains_numa_masks_set(node);
+
 	for (i = 0; i < sched_domains_numa_levels; i++) {
 		for (j = 0; j < nr_node_ids; j++) {
+			if (!node_online(j))
+				continue;
+
+			/* Set ourselves in the remote node's masks */
 			if (node_distance(j, node) <= sched_domains_numa_distance[i])
 				cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
 		}