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

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle are:

   - Make schedstats a runtime tunable (disabled by default) and
     optimize it via static keys.

     As most distributions enable CONFIG_SCHEDSTATS=y due to its
     instrumentation value, this is a nice performance enhancement.
     (Mel Gorman)

   - Implement 'simple waitqueues' (swait): these are just pure
     waitqueues without any of the more complex features of full-blown
     waitqueues (callbacks, wake flags, wake keys, etc.).  Simple
     waitqueues have less memory overhead and are faster.

     Use simple waitqueues in the RCU code (in 4 different places) and
     for handling KVM vCPU wakeups.

     (Peter Zijlstra, Daniel Wagner, Thomas Gleixner, Paul Gortmaker,
     Marcelo Tosatti)

   - sched/numa enhancements (Rik van Riel)

   - NOHZ performance enhancements (Rik van Riel)

   - Various sched/deadline enhancements (Steven Rostedt)

   - Various fixes (Peter Zijlstra)

   - ... and a number of other fixes, cleanups and smaller enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  sched/cputime: Fix steal_account_process_tick() to always return jiffies
  sched/deadline: Remove dl_new from struct sched_dl_entity
  Revert "kbuild: Add option to turn incompatible pointer check into error"
  sched/deadline: Remove superfluous call to switched_to_dl()
  sched/debug: Fix preempt_disable_ip recording for preempt_disable()
  sched, time: Switch VIRT_CPU_ACCOUNTING_GEN to jiffy granularity
  time, acct: Drop irq save & restore from __acct_update_integrals()
  acct, time: Change indentation in __acct_update_integrals()
  sched, time: Remove non-power-of-two divides from __acct_update_integrals()
  sched/rt: Kick RT bandwidth timer immediately on start up
  sched/debug: Add deadline scheduler bandwidth ratio to /proc/sched_debug
  sched/debug: Move sched_domain_sysctl to debug.c
  sched/debug: Move the /sys/kernel/debug/sched_features file setup into debug.c
  sched/rt: Fix PI handling vs. sched_setscheduler()
  sched/core: Remove duplicated sched_group_set_shares() prototype
  sched/fair: Consolidate nohz CPU load update code
  sched/fair: Avoid using decay_load_missed() with a negative value
  sched/deadline: Always calculate end of period on sched_yield()
  sched/cgroup: Fix cgroup entity load tracking tear-down
  rcu: Use simple wait queues where possible in rcutree
  ...

Documentation/kernel-parameters.txt

@@ -3532,6 +3532,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	sched_debug	[KNL] Enables verbose scheduler debug messages.
 
+	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
+			Allowed values are enable and disable. This feature
+			incurs a small amount of overhead in the scheduler
+			but is useful for debugging and performance tuning.
+
 	skew_tick=	[KNL] Offset the periodic timer tick per cpu to mitigate
 			xtime_lock contention on larger systems, and/or RCU lock
 			contention on all systems with CONFIG_MAXSMP set.

Documentation/sysctl/kernel.txt

@@ -773,6 +773,14 @@ rtsig-nr shows the number of RT signals currently queued.
 
 ==============================================================
 
+sched_schedstats:
+
+Enables/disables scheduler statistics. Enabling this feature
+incurs a small amount of overhead in the scheduler but is
+useful for debugging and performance tuning.
+
+==============================================================
+
 sg-big-buff:
 
 This file shows the size of the generic SCSI (sg) buffer.

arch/arm/kvm/arm.c

@@ -506,18 +506,18 @@ static void kvm_arm_resume_guest(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+		struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
 		vcpu->arch.pause = false;
-		wake_up_interruptible(wq);
+		swake_up(wq);
 	}
 }
 
 static void vcpu_sleep(struct kvm_vcpu *vcpu)
 {
-	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
-	wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
 }
 

arch/arm/kvm/psci.c

@@ -70,7 +70,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu = NULL;
-	wait_queue_head_t *wq;
+	struct swait_queue_head *wq;
 	unsigned long cpu_id;
 	unsigned long context_id;
 	phys_addr_t target_pc;
@@ -119,7 +119,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	wake_up_interruptible(wq);
+	swake_up(wq);
 
 	return PSCI_RET_SUCCESS;
 }

arch/mips/kvm/mips.c

@@ -445,8 +445,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 
 	dvcpu->arch.wait = 0;
 
-	if (waitqueue_active(&dvcpu->wq))
-		wake_up_interruptible(&dvcpu->wq);
+	if (swait_active(&dvcpu->wq))
+		swake_up(&dvcpu->wq);
 
 	return 0;
 }
@@ -1174,8 +1174,8 @@ static void kvm_mips_comparecount_func(unsigned long data)
 	kvm_mips_callbacks->queue_timer_int(vcpu);
 
 	vcpu->arch.wait = 0;
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
+	if (swait_active(&vcpu->wq))
+		swake_up(&vcpu->wq);
 }
 
 /* low level hrtimer wake routine */

arch/powerpc/include/asm/kvm_host.h

@@ -289,7 +289,7 @@ struct kvmppc_vcore {
 	struct list_head runnable_threads;
 	struct list_head preempt_list;
 	spinlock_t lock;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
 	u64 stolen_tb;
 	u64 preempt_tb;
@@ -629,7 +629,7 @@ struct kvm_vcpu_arch {
 	u8 prodded;
 	u32 last_inst;
 
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 	struct kvmppc_vcore *vcore;
 	int ret;
 	int trap;

arch/powerpc/kvm/book3s_hv.c

@@ -114,11 +114,11 @@ static bool kvmppc_ipi_thread(int cpu)
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int cpu;
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (waitqueue_active(wqp)) {
-		wake_up_interruptible(wqp);
+	if (swait_active(wqp)) {
+		swake_up(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -701,8 +701,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		tvcpu->arch.prodded = 1;
 		smp_mb();
 		if (vcpu->arch.ceded) {
-			if (waitqueue_active(&vcpu->wq)) {
-				wake_up_interruptible(&vcpu->wq);
+			if (swait_active(&vcpu->wq)) {
+				swake_up(&vcpu->wq);
 				vcpu->stat.halt_wakeup++;
 			}
 		}
@@ -1459,7 +1459,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	INIT_LIST_HEAD(&vcore->runnable_threads);
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
-	init_waitqueue_head(&vcore->wq);
+	init_swait_queue_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = core * threads_per_subcore;
@@ -2531,10 +2531,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
 	struct kvm_vcpu *vcpu;
 	int do_sleep = 1;
+	DECLARE_SWAITQUEUE(wait);
 
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	/*
 	 * Check one last time for pending exceptions and ceded state after
@@ -2548,7 +2547,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	}
 
 	if (!do_sleep) {
-		finish_wait(&vc->wq, &wait);
+		finish_swait(&vc->wq, &wait);
 		return;
 	}
 
@@ -2556,7 +2555,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
 	schedule();
-	finish_wait(&vc->wq, &wait);
+	finish_swait(&vc->wq, &wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
@@ -2612,7 +2611,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			wake_up(&vc->wq);
+			swake_up(&vc->wq);
 		}
 
 	}

arch/s390/include/asm/kvm_host.h

@@ -467,7 +467,7 @@ struct kvm_s390_irq_payload {
 struct kvm_s390_local_interrupt {
 	spinlock_t lock;
 	struct kvm_s390_float_interrupt *float_int;
-	wait_queue_head_t *wq;
+	struct swait_queue_head *wq;
 	atomic_t *cpuflags;
 	DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
 	struct kvm_s390_irq_payload irq;

arch/s390/kvm/interrupt.c

@@ -966,13 +966,13 @@ no_timer:
 
 void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 {
-	if (waitqueue_active(&vcpu->wq)) {
+	if (swait_active(&vcpu->wq)) {
 		/*
 		 * The vcpu gave up the cpu voluntarily, mark it as a good
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		wake_up_interruptible(&vcpu->wq);
+		swake_up(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 }

arch/x86/kvm/lapic.c

@@ -1195,7 +1195,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
-	wait_queue_head_t *q = &vcpu->wq;
+	struct swait_queue_head *q = &vcpu->wq;
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 
 	if (atomic_read(&apic->lapic_timer.pending))
@@ -1204,8 +1204,8 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	atomic_inc(&apic->lapic_timer.pending);
 	kvm_set_pending_timer(vcpu);
 
-	if (waitqueue_active(q))
-		wake_up_interruptible(q);
+	if (swait_active(q))
+		swake_up(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;

include/linux/ftrace.h

@@ -713,6 +713,18 @@ static inline void __ftrace_enabled_restore(int enabled)
 #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
 #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
 
+static inline unsigned long get_lock_parent_ip(void)
+{
+	unsigned long addr = CALLER_ADDR0;
+
+	if (!in_lock_functions(addr))
+		return addr;
+	addr = CALLER_ADDR1;
+	if (!in_lock_functions(addr))
+		return addr;
+	return CALLER_ADDR2;
+}
+
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
   extern void time_hardirqs_off(unsigned long a0, unsigned long a1);

include/linux/kvm_host.h

@@ -25,6 +25,7 @@
 #include <linux/irqflags.h>
 #include <linux/context_tracking.h>
 #include <linux/irqbypass.h>
+#include <linux/swait.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -218,7 +219,7 @@ struct kvm_vcpu {
 	int fpu_active;
 	int guest_fpu_loaded, guest_xcr0_loaded;
 	unsigned char fpu_counter;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	struct pid *pid;
 	int sigset_active;
 	sigset_t sigset;
@@ -782,7 +783,7 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
 }
 #endif
 
-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
 {
 #ifdef __KVM_HAVE_ARCH_WQP
 	return vcpu->arch.wqp;

include/linux/latencytop.h

@@ -37,6 +37,9 @@ account_scheduler_latency(struct task_struct *task, int usecs, int inter)
 
 void clear_all_latency_tracing(struct task_struct *p);
 
+extern int sysctl_latencytop(struct ctl_table *table, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos);
+
 #else
 
 static inline void

include/linux/sched.h

@@ -182,8 +182,6 @@ extern void update_cpu_load_nohz(int active);
 static inline void update_cpu_load_nohz(int active) { }
 #endif
 
-extern unsigned long get_parent_ip(unsigned long addr);
-
 extern void dump_cpu_task(int cpu);
 
 struct seq_file;
@@ -920,6 +918,10 @@ static inline int sched_info_on(void)
 #endif
 }
 
+#ifdef CONFIG_SCHEDSTATS
+void force_schedstat_enabled(void);
+#endif
+
 enum cpu_idle_type {
 	CPU_IDLE,
 	CPU_NOT_IDLE,
@@ -1289,6 +1291,8 @@ struct sched_rt_entity {
 	unsigned long timeout;
 	unsigned long watchdog_stamp;
 	unsigned int time_slice;
+	unsigned short on_rq;
+	unsigned short on_list;
 
 	struct sched_rt_entity *back;
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -1329,10 +1333,6 @@ struct sched_dl_entity {
 	 * task has to wait for a replenishment to be performed at the
 	 * next firing of dl_timer.
 	 *
-	 * @dl_new tells if a new instance arrived. If so we must
-	 * start executing it with full runtime and reset its absolute
-	 * deadline;
-	 *
 	 * @dl_boosted tells if we are boosted due to DI. If so we are
 	 * outside bandwidth enforcement mechanism (but only until we
 	 * exit the critical section);
@@ -1340,7 +1340,7 @@ struct sched_dl_entity {
 	 * @dl_yielded tells if task gave up the cpu before consuming
 	 * all its available runtime during the last job.
 	 */
-	int dl_throttled, dl_new, dl_boosted, dl_yielded;
+	int dl_throttled, dl_boosted, dl_yielded;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its

include/linux/sched/sysctl.h

@@ -95,4 +95,8 @@ extern int sysctl_numa_balancing(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp,
 				 loff_t *ppos);
 
+extern int sysctl_schedstats(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos);
+
 #endif /* _SCHED_SYSCTL_H */

include/linux/swait.h

@@ -0,0 +1,172 @@
+#ifndef _LINUX_SWAIT_H
+#define _LINUX_SWAIT_H
+
+#include <linux/list.h>
+#include <linux/stddef.h>
+#include <linux/spinlock.h>
+#include <asm/current.h>
+
+/*
+ * Simple wait queues
+ *
+ * While these are very similar to the other/complex wait queues (wait.h) the
+ * most important difference is that the simple waitqueue allows for
+ * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold
+ * times.
+ *
+ * In order to make this so, we had to drop a fair number of features of the
+ * other waitqueue code; notably:
+ *
+ *  - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue;
+ *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
+ *    sleeper state.
+ *
+ *  - the exclusive mode; because this requires preserving the list order
+ *    and this is hard.
+ *
+ *  - custom wake functions; because you cannot give any guarantees about
+ *    random code.
+ *
+ * As a side effect of this; the data structures are slimmer.
+ *
+ * One would recommend using this wait queue where possible.
+ */
+
+struct task_struct;
+
+struct swait_queue_head {
+	raw_spinlock_t		lock;
+	struct list_head	task_list;
+};
+
+struct swait_queue {
+	struct task_struct	*task;
+	struct list_head	task_list;
+};
+
+#define __SWAITQUEUE_INITIALIZER(name) {				\
+	.task		= current,					\
+	.task_list	= LIST_HEAD_INIT((name).task_list),		\
+}
+
+#define DECLARE_SWAITQUEUE(name)					\
+	struct swait_queue name = __SWAITQUEUE_INITIALIZER(name)
+
+#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) {				\
+	.lock		= __RAW_SPIN_LOCK_UNLOCKED(name.lock),		\
+	.task_list	= LIST_HEAD_INIT((name).task_list),		\
+}
+
+#define DECLARE_SWAIT_QUEUE_HEAD(name)					\
+	struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name)
+
+extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
+				    struct lock_class_key *key);
+
+#define init_swait_queue_head(q)				\
+	do {							\
+		static struct lock_class_key __key;		\
+		__init_swait_queue_head((q), #q, &__key);	\
+	} while (0)
+
+#ifdef CONFIG_LOCKDEP
+# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name)			\
+	({ init_swait_queue_head(&name); name; })
+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name)			\
+	struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name)
+#else
+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name)			\
+	DECLARE_SWAIT_QUEUE_HEAD(name)
+#endif
+
+static inline int swait_active(struct swait_queue_head *q)
+{
+	return !list_empty(&q->task_list);
+}
+
+extern void swake_up(struct swait_queue_head *q);
+extern void swake_up_all(struct swait_queue_head *q);
+extern void swake_up_locked(struct swait_queue_head *q);
+
+extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
+extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
+
+extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
+
+/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+#define ___swait_event(wq, condition, state, ret, cmd)			\
+({									\
+	struct swait_queue __wait;					\
+	long __ret = ret;						\
+									\
+	INIT_LIST_HEAD(&__wait.task_list);				\
+	for (;;) {							\
+		long __int = prepare_to_swait_event(&wq, &__wait, state);\
+									\
+		if (condition)						\
+			break;						\
+									\
+		if (___wait_is_interruptible(state) && __int) {		\
+			__ret = __int;					\
+			break;						\
+		}							\
+									\
+		cmd;							\
+	}								\
+	finish_swait(&wq, &__wait);					\
+	__ret;								\
+})
+
+#define __swait_event(wq, condition)					\
+	(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,	\
+			    schedule())
+
+#define swait_event(wq, condition)					\
+do {									\
+	if (condition)							\
+		break;							\
+	__swait_event(wq, condition);					\
+} while (0)
+
+#define __swait_event_timeout(wq, condition, timeout)			\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_UNINTERRUPTIBLE, timeout,			\
+		      __ret = schedule_timeout(__ret))
+
+#define swait_event_timeout(wq, condition, timeout)			\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_timeout(wq, condition, timeout);	\
+	__ret;								\
+})
+
+#define __swait_event_interruptible(wq, condition)			\
+	___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0,		\
+		      schedule())
+
+#define swait_event_interruptible(wq, condition)			\
+({									\
+	int __ret = 0;							\
+	if (!(condition))						\
+		__ret = __swait_event_interruptible(wq, condition);	\
+	__ret;								\
+})
+
+#define __swait_event_interruptible_timeout(wq, condition, timeout)	\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_INTERRUPTIBLE, timeout,			\
+		      __ret = schedule_timeout(__ret))
+
+#define swait_event_interruptible_timeout(wq, condition, timeout)	\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_interruptible_timeout(wq,		\
+						condition, timeout);	\
+	__ret;								\
+})
+
+#endif /* _LINUX_SWAIT_H */

include/linux/wait.h

@@ -338,7 +338,7 @@ do {									\
 			    schedule(); try_to_freeze())
 
 /**
- * wait_event - sleep (or freeze) until a condition gets true
+ * wait_event_freezable - sleep (or freeze) until a condition gets true
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *

kernel/latencytop.c

@@ -47,12 +47,12 @@
  * of times)
  */
 
-#include <linux/latencytop.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
 #include <linux/proc_fs.h>
+#include <linux/latencytop.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/list.h>
@@ -289,4 +289,16 @@ static int __init init_lstats_procfs(void)
 	proc_create("latency_stats", 0644, NULL, &lstats_fops);
 	return 0;
 }
+
+int sysctl_latencytop(struct ctl_table *table, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int err;
+
+	err = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (latencytop_enabled)
+		force_schedstat_enabled();
+
+	return err;
+}
 device_initcall(init_lstats_procfs);

kernel/profile.c

@@ -59,6 +59,7 @@ int profile_setup(char *str)
 
 	if (!strncmp(str, sleepstr, strlen(sleepstr))) {
 #ifdef CONFIG_SCHEDSTATS
+		force_schedstat_enabled();
 		prof_on = SLEEP_PROFILING;
 		if (str[strlen(sleepstr)] == ',')
 			str += strlen(sleepstr) + 1;

kernel/rcu/tree.c

@@ -1614,7 +1614,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 	int needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
-	rcu_nocb_gp_cleanup(rsp, rnp);
 	rnp->need_future_gp[c & 0x1] = 0;
 	needmore = rnp->need_future_gp[(c + 1) & 0x1];
 	trace_rcu_future_gp(rnp, rdp, c,
@@ -1635,7 +1634,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
-	wake_up(&rsp->gp_wq);
+	swake_up(&rsp->gp_wq);
 }
 
 /*
@@ -2010,6 +2009,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	int nocb = 0;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
+	struct swait_queue_head *sq;
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
 	raw_spin_lock_irq_rcu_node(rnp);
@@ -2046,7 +2046,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
 		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
+		sq = rcu_nocb_gp_get(rnp);
 		raw_spin_unlock_irq(&rnp->lock);
+		rcu_nocb_gp_cleanup(sq);
 		cond_resched_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 		rcu_gp_slow(rsp, gp_cleanup_delay);
@@ -2092,7 +2094,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
-			wait_event_interruptible(rsp->gp_wq,
+			swait_event_interruptible(rsp->gp_wq,
 						 READ_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
 			rsp->gp_state = RCU_GP_DONE_GPS;
@@ -2122,7 +2124,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
-			ret = wait_event_interruptible_timeout(rsp->gp_wq,
+			ret = swait_event_interruptible_timeout(rsp->gp_wq,
 					rcu_gp_fqs_check_wake(rsp, &gf), j);
 			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */
@@ -2246,7 +2248,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
 	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
 	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
-	rcu_gp_kthread_wake(rsp);
+	swake_up(&rsp->gp_wq);  /* Memory barrier implied by swake_up() path. */
 }
 
 /*
@@ -2900,7 +2902,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	}
 	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
 	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
-	rcu_gp_kthread_wake(rsp);
+	swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */
 }
 
 /*
@@ -3529,7 +3531,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				wake_up(&rsp->expedited_wq);
+				swake_up(&rsp->expedited_wq);
 			}
 			break;
 		}
@@ -3780,7 +3782,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	jiffies_start = jiffies;
 
 	for (;;) {
-		ret = wait_event_interruptible_timeout(
+		ret = swait_event_timeout(
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done(rnp_root),
 				jiffies_stall);
@@ -3788,7 +3790,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 			return;
 		if (ret < 0) {
 			/* Hit a signal, disable CPU stall warnings. */
-			wait_event(rsp->expedited_wq,
+			swait_event(rsp->expedited_wq,
 				   sync_rcu_preempt_exp_done(rnp_root));
 			return;
 		}
@@ -4482,8 +4484,8 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 		}
 	}
 
-	init_waitqueue_head(&rsp->gp_wq);
-	init_waitqueue_head(&rsp->expedited_wq);
+	init_swait_queue_head(&rsp->gp_wq);
+	init_swait_queue_head(&rsp->expedited_wq);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)