scheduler changes for v4.3

index c99e259469f7..12ebfcc1d539 100644
@@ -10,7 +10,9 @@
  * CPU.
  */
 #if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
-#define finish_arch_switch(prev)	dsb(ish)
+#define __complete_pending_tlbi()	dsb(ish)
+#else
+#define __complete_pending_tlbi()
 #endif
 
 /*

@@ -22,6 +24,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
 
 #define switch_to(prev,next,last)					\
 do {									\
+	__complete_pending_tlbi();					\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
 

index 9a8e9d5208d4..6f00581c3d4f 100644
@@ -15,11 +15,13 @@
  */
 #ifdef CONFIG_OWNERSHIP_TRACE
 #include <asm/ocd.h>
-#define finish_arch_switch(prev)			\
+#define ocd_switch(prev, next)				\
 	do {						\
 		ocd_write(PID, prev->pid);		\
-		ocd_write(PID, current->pid);		\
+		ocd_write(PID, next->pid);		\
 	} while(0)
+#else
+#define ocd_switch(prev, next)
 #endif
 
 /*

@@ -38,6 +40,7 @@ extern struct task_struct *__switch_to(struct task_struct *,
 				       struct cpu_context *);
 #define switch_to(prev, next, last)					\
 	do {								\
+		ocd_switch(prev, next);					\
 		last = __switch_to(prev, &prev->thread.cpu_context + 1,	\
 				   &next->thread.cpu_context);		\
 	} while (0)

68 lines not on this page · raw message

index 68d067ad4222..a9f753fb73a8 100644
@@ -2178,7 +2178,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		vc->runner = vcpu;
 		if (n_ceded == vc->n_runnable) {
 			kvmppc_vcore_blocked(vc);
-		} else if (should_resched()) {
+		} else if (need_resched()) {
 			vc->vcore_state = VCORE_PREEMPT;
 			/* Let something else run */
 			cond_resched_lock(&vc->lock);

index 031756b59ece..fda3f83308d2 100644
@@ -8,6 +8,4 @@ do {								\
 	(last) = resume(prev, next, task_thread_info(next));	\
 } while (0)
 
-#define finish_arch_switch(prev)	do {} while (0)
-
 #endif /* _ASM_SCORE_SWITCH_TO_H */

index 0c065513e7ac..7661b4ba8259 100644
@@ -78,6 +78,8 @@ do {								\
 								\
 	if (is_dsp_enabled(prev))				\
 		__save_dsp(prev);				\
+	if (is_dsp_enabled(next))				\
+		__restore_dsp(next);				\
 								\
 	__ts1 = (u32 *)&prev->thread.sp;			\
 	__ts2 = (u32 *)&prev->thread.pc;			\

@@ -125,10 +127,4 @@ do {								\
 	last = __last;						\
 } while (0)
 
-#define finish_arch_switch(prev)				\
-do {								\
-	if (is_dsp_enabled(prev))				\
-		__restore_dsp(prev);				\
-} while (0)
-
 #endif /* __ASM_SH_SWITCH_TO_32_H */

index 50e7b626afe8..c5113c7ce2fd 100644
@@ -333,11 +333,11 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	childregs = (struct pt_regs *) (new_stack + STACKFRAME_SZ);
 
 	/*
-	 * A new process must start with interrupts closed in 2.5,
-	 * because this is how Mingo's scheduler works (see schedule_tail
-	 * and finish_arch_switch). If we do not do it, a timer interrupt hits
-	 * before we unlock, attempts to re-take the rq->lock, and then we die.
-	 * Thus, kpsr|=PSR_PIL.
+	 * A new process must start with interrupts disabled, see schedule_tail()
+	 * and finish_task_switch(). (If we do not do it and if a timer interrupt
+	 * hits before we unlock and attempts to take the rq->lock, we deadlock.)
+	 *
+	 * Thus, kpsr |= PSR_PIL.
 	 */
 	ti->ksp = (unsigned long) new_stack;
 	p->thread.kregs = childregs;

index b8f888cbe6b0..34ee72705521 100644
@@ -53,15 +53,13 @@ extern unsigned long get_switch_to_pc(void);
  * Kernel threads can check to see if they need to migrate their
  * stack whenever they return from a context switch; for user
  * threads, we defer until they are returning to user-space.
+ * We defer homecache migration until the runqueue lock is released.
  */
-#define finish_arch_switch(prev) do {                                     \
-	if (unlikely((prev)->state == TASK_DEAD))                         \
-		__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_EXIT |       \
-			((prev)->pid << _SIM_CONTROL_OPERATOR_BITS));     \
+#define finish_arch_post_lock_switch() do {                               \
 	__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_SWITCH |             \
 		(current->pid << _SIM_CONTROL_OPERATOR_BITS));            \
 	if (current->mm == NULL && !kstack_hash &&                        \
-	    current_thread_info()->homecache_cpu != smp_processor_id())   \
+	    current_thread_info()->homecache_cpu != raw_smp_processor_id()) \
 		homecache_migrate_kthread();                              \
 } while (0)
 

index a45213781ad0..7d5769310bef 100644
@@ -446,6 +446,11 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
 	hardwall_switch_tasks(prev, next);
 #endif
 
+	/* Notify the simulator of task exit. */
+	if (unlikely(prev->state == TASK_DEAD))
+		__insn_mtspr(SPR_SIM_CONTROL, SIM_CONTROL_OS_EXIT |
+			     (prev->pid << _SIM_CONTROL_OPERATOR_BITS));
+
 	/*
 	 * Switch kernel SP, PC, and callee-saved registers.
 	 * In the context of the new task, return the old task pointer

index dca71714f860..b12f81022a6b 100644
@@ -90,9 +90,9 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!raw_cpu_read_4(__preempt_count));
+	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPT

index e8e2775c3821..a5d9f2e470ea 100644
@@ -118,6 +118,7 @@ static void enter_freeze_proper(struct cpuidle_driver *drv,
 	 * cpuidle mechanism enables interrupts and doing that with timekeeping
 	 * suspended is generally unsafe.
 	 */
+	stop_critical_timings();
 	drv->states[index].enter_freeze(dev, drv, index);
 	WARN_ON(!irqs_disabled());
 	/*

@@ -126,6 +127,7 @@ static void enter_freeze_proper(struct cpuidle_driver *drv,
 	 * critical sections, so tell RCU about that.
 	 */
 	RCU_NONIDLE(tick_unfreeze());
+	start_critical_timings();
 }
 
 /**

@@ -190,7 +192,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	trace_cpu_idle_rcuidle(index, dev->cpu);
 	time_start = ktime_get();
 
+	stop_critical_timings();
 	entered_state = target_state->enter(dev, drv, index);
+	start_critical_timings();
 
 	time_end = ktime_get();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);

index a1800c150839..08cb419eb4e6 100644
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
 asmlinkage __visible void xen_maybe_preempt_hcall(void)
 {
 	if (unlikely(__this_cpu_read(xen_in_preemptible_hcall)
-		     && should_resched())) {
+		     && need_resched())) {
 		/*
 		 * Clear flag as we may be rescheduled on a different
 		 * cpu.

index d0a7a4753db2..0bec580a4885 100644
@@ -71,9 +71,10 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!preempt_count() && tif_need_resched());
+	return unlikely(preempt_count() == preempt_offset &&
+			tif_need_resched());
 }
 
 #ifdef CONFIG_PREEMPT

index e8493fee8160..d0b380ee7d67 100644
@@ -32,6 +32,14 @@ extern struct fs_struct init_fs;
 #define INIT_CPUSET_SEQ(tsk)
 #endif
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+#define INIT_PREV_CPUTIME(x)	.prev_cputime = {			\
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(x.prev_cputime.lock),		\
+},
+#else
+#define INIT_PREV_CPUTIME(x)
+#endif
+
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
 	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\

@@ -46,6 +54,7 @@ extern struct fs_struct init_fs;
 		.cputime_atomic	= INIT_CPUTIME_ATOMIC,			\
 		.running	= 0,					\
 	},								\
+	INIT_PREV_CPUTIME(sig)						\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
 }

@@ -246,6 +255,7 @@ extern struct task_group root_task_group;
 	INIT_TASK_RCU_TASKS(tsk)					\
 	INIT_CPUSET_SEQ(tsk)						\
 	INIT_RT_MUTEXES(tsk)						\
+	INIT_PREV_CPUTIME(tsk)						\
 	INIT_VTIME(tsk)							\
 	INIT_NUMA_BALANCING(tsk)					\
 	INIT_KASAN(tsk)							\

index 13d55206ccf6..869b21dcf503 100644
@@ -38,6 +38,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 })
 
 void kthread_bind(struct task_struct *k, unsigned int cpu);
+void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask);
 int kthread_stop(struct task_struct *k);
 bool kthread_should_stop(void);
 bool kthread_should_park(void);

index 84991f185173..bea8dd8ff5e0 100644
@@ -84,13 +84,21 @@
  */
 #define in_nmi()	(preempt_count() & NMI_MASK)
 
+/*
+ * The preempt_count offset after preempt_disable();
+ */
 #if defined(CONFIG_PREEMPT_COUNT)
-# define PREEMPT_DISABLE_OFFSET 1
+# define PREEMPT_DISABLE_OFFSET	PREEMPT_OFFSET
 #else
-# define PREEMPT_DISABLE_OFFSET 0
+# define PREEMPT_DISABLE_OFFSET	0
 #endif
 
 /*
+ * The preempt_count offset after spin_lock()
+ */
+#define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+
+/*
  * The preempt_count offset needed for things like:
  *
  *  spin_lock_bh()

@@ -103,7 +111,7 @@
  *
  * Work as expected.
  */
-#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET)
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET)
 
 /*
  * Are we running in atomic context?  WARNING: this macro cannot

@@ -124,7 +132,8 @@
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
 extern void preempt_count_sub(int val);
-#define preempt_count_dec_and_test() ({ preempt_count_sub(1); should_resched(); })
+#define preempt_count_dec_and_test() \
+	({ preempt_count_sub(1); should_resched(0); })
 #else
 #define preempt_count_add(val)	__preempt_count_add(val)
 #define preempt_count_sub(val)	__preempt_count_sub(val)

@@ -184,7 +193,7 @@ do { \
 
 #define preempt_check_resched() \
 do { \
-	if (should_resched()) \
+	if (should_resched(0)) \
 		__preempt_schedule(); \
 } while (0)
 

170 lines not on this page · raw message

index d2abbdb8c6aa..414d924318ce 100644
@@ -112,25 +112,13 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  *
  * This can be thought of as a very heavy write lock, equivalent to
  * grabbing every spinlock in the kernel. */
-int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
+int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
-/**
- * __stop_machine: freeze the machine on all CPUs and run this function
- * @fn: the function to run
- * @data: the data ptr for the @fn
- * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
- *
- * Description: This is a special version of the above, which assumes cpus
- * won't come or go while it's being called.  Used by hotplug cpu.
- */
-int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
-
-int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
+int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
-
 #else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
 
-static inline int __stop_machine(int (*fn)(void *), void *data,
+static inline int stop_machine(cpu_stop_fn_t fn, void *data,
 				 const struct cpumask *cpus)
 {
 	unsigned long flags;

@@ -141,16 +129,10 @@ static inline int __stop_machine(int (*fn)(void *), void *data,
 	return ret;
 }
 
-static inline int stop_machine(int (*fn)(void *), void *data,
-			       const struct cpumask *cpus)
-{
-	return __stop_machine(fn, data, cpus);
-}
-
-static inline int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
+static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 						 const struct cpumask *cpus)
 {
-	return __stop_machine(fn, data, cpus);
+	return stop_machine(fn, data, cpus);
 }
 
 #endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */

index d57a575fe31f..539d6bc3216a 100644
@@ -55,9 +55,9 @@ TRACE_EVENT(sched_kthread_stop_ret,
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-	TP_PROTO(struct task_struct *p, int success),
+	TP_PROTO(struct task_struct *p),
 
-	TP_ARGS(__perf_task(p), success),
+	TP_ARGS(__perf_task(p)),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)

@@ -71,25 +71,37 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->success	= success;
+		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
 
-	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
+	TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success, __entry->target_cpu)
+		  __entry->target_cpu)
 );
 
+/*
+ * Tracepoint called when waking a task; this tracepoint is guaranteed to be
+ * called from the waking context.
+ */
+DEFINE_EVENT(sched_wakeup_template, sched_waking,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
+
+/*
+ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
+ * It it not always called from the waking context.
+ */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 /*
  * Tracepoint for waking up a new task:
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
 static inline long __trace_sched_switch_state(struct task_struct *p)

index 9c9c9fab16cc..664ce5299334 100644
@@ -395,7 +395,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
 
-	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
+	err = stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);

index 1bfefc6f96a4..6e8f807c5716 100644
@@ -1067,6 +1067,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 	rcu_assign_pointer(tsk->sighand, sig);
 	if (!sig)
 		return -ENOMEM;
+
 	atomic_set(&sig->count, 1);
 	memcpy(sig->action, current->sighand->action, sizeof(sig->action));
 	return 0;

@@ -1128,6 +1129,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
 	seqlock_init(&sig->stats_lock);
+	prev_cputime_init(&sig->prev_cputime);
 
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sig->real_timer.function = it_real_fn;

@@ -1335,9 +1337,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	p->prev_cputime.utime = p->prev_cputime.stime = 0;
-#endif
+	prev_cputime_init(&p->prev_cputime);
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 	seqlock_init(&p->vtime_seqlock);
 	p->vtime_snap = 0;

index 10e489c448fe..7c40a189becc 100644
@@ -325,16 +325,30 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
-static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
+static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state)
 {
-	/* Must have done schedule() in kthread() before we set_task_cpu */
+	unsigned long flags;
+
 	if (!wait_task_inactive(p, state)) {
 		WARN_ON(1);
 		return;
 	}
+
 	/* It's safe because the task is inactive. */
-	do_set_cpus_allowed(p, cpumask_of(cpu));
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	do_set_cpus_allowed(p, mask);
 	p->flags |= PF_NO_SETAFFINITY;
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+}
+
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
+{
+	__kthread_bind_mask(p, cpumask_of(cpu), state);
+}
+
+void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask)
+{
+	__kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE);
 }
 
 /**

225 lines not on this page · raw message

130 lines not on this page · raw message

index 0a17af35670a..fc8f01083527 100644
@@ -953,7 +953,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 
 	/*
 	 * Use the scheduling parameters of the top pi-waiter
-	 * task if we have one and its (relative) deadline is
+	 * task if we have one and its (absolute) deadline is
 	 * smaller than our one... OTW we keep our runtime and
 	 * deadline.
 	 */

@@ -1563,7 +1563,7 @@ static int push_dl_task(struct rq *rq)
 
 static void push_dl_tasks(struct rq *rq)
 {
-	/* Terminates as it moves a -deadline task */
+	/* push_dl_task() will return true if it moved a -deadline task */
 	while (push_dl_task(rq))
 		;
 }

@@ -1657,7 +1657,6 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 {
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
-	    has_pushable_dl_tasks(rq) &&
 	    p->nr_cpus_allowed > 1 &&
 	    dl_task(rq->curr) &&
 	    (rq->curr->nr_cpus_allowed < 2 ||

@@ -1669,9 +1668,8 @@ 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)
 {
-	struct rq *rq;
 	struct root_domain *src_rd;
-	int weight;
+	struct rq *rq;
 
 	BUG_ON(!dl_task(p));
 

@@ -1697,37 +1695,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
-	/*
-	 * Update only if the task is actually running (i.e.,
-	 * it is on the rq AND it is not throttled).
-	 */
-	if (!on_dl_rq(&p->dl))
-		return;
-
-	weight = cpumask_weight(new_mask);
-
-	/*
-	 * Only update if the process changes its state from whether it
-	 * can migrate or not.
-	 */
-	if ((p->nr_cpus_allowed > 1) == (weight > 1))
-		return;
-
-	/*
-	 * The process used to be able to migrate OR it can now migrate
-	 */
-	if (weight <= 1) {
-		if (!task_current(rq, p))
-			dequeue_pushable_dl_task(rq, p);
-		BUG_ON(!rq->dl.dl_nr_migratory);
-		rq->dl.dl_nr_migratory--;
-	} else {
-		if (!task_current(rq, p))
-			enqueue_pushable_dl_task(rq, p);
-		rq->dl.dl_nr_migratory++;
-	}
-
-	update_dl_migration(&rq->dl);
+	set_cpus_allowed_common(p, new_mask);
 }
 
 /* Assumes rq->lock is held */

77 lines not on this page · raw message

1,447 lines not on this page · raw message

index 91e33cd485f6..83a50e7ca533 100644
@@ -79,20 +79,12 @@ SCHED_FEAT(LB_MIN, false)
  * numa_balancing=
  */
 #ifdef CONFIG_NUMA_BALANCING
-SCHED_FEAT(NUMA,	false)
 
 /*
- * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a
- * higher number of hinting faults are recorded during active load
- * balancing.
+ * NUMA will favor moving tasks towards nodes where a higher number of
+ * hinting faults are recorded during active load balancing. It will
+ * resist moving tasks towards nodes where a lower number of hinting
+ * faults have been recorded.
  */
-SCHED_FEAT(NUMA_FAVOUR_HIGHER, true)
-
-/*
- * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a
- * lower number of hinting faults have been recorded. As this has
- * the potential to prevent a task ever migrating to a new node
- * due to CPU overload it is disabled by default.
- */
-SCHED_FEAT(NUMA_RESIST_LOWER, false)
+SCHED_FEAT(NUMA,	true)
 #endif

index 594275ed2620..8f177c73ae19 100644
@@ -83,10 +83,13 @@ void __weak arch_cpu_idle(void)
  */
 void default_idle_call(void)
 {
-	if (current_clr_polling_and_test())
+	if (current_clr_polling_and_test()) {
 		local_irq_enable();
-	else
+	} else {
+		stop_critical_timings();
 		arch_cpu_idle();
+		start_critical_timings();
+	}
 }
 
 static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,

@@ -141,12 +144,6 @@ static void cpuidle_idle_call(void)
 	}
 
 	/*
-	 * During the idle period, stop measuring the disabled irqs
-	 * critical sections latencies
-	 */
-	stop_critical_timings();
-
-	/*
 	 * Tell the RCU framework we are entering an idle section,
 	 * so no more rcu read side critical sections and one more
 	 * step to the grace period

@@ -198,7 +195,6 @@ static void cpuidle_idle_call(void)
 		local_irq_enable();
 
 	rcu_idle_exit();
-	start_critical_timings();
 }
 
 DEFINE_PER_CPU(bool, cpu_dead_idle);

index c65dac8c97cd..c4ae0f1fdf9b 100644
@@ -96,6 +96,7 @@ const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
+	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,

60 lines not on this page · raw message

index 84d48790bb6d..68cda117574c 100644
@@ -245,7 +245,6 @@ struct task_group {
 
 #ifdef	CONFIG_SMP
 	atomic_long_t load_avg;
-	atomic_t runnable_avg;
 #endif
 #endif
 

@@ -366,27 +365,20 @@ struct cfs_rq {
 
 #ifdef CONFIG_SMP
 	/*
-	 * CFS Load tracking
-	 * Under CFS, load is tracked on a per-entity basis and aggregated up.
-	 * This allows for the description of both thread and group usage (in
-	 * the FAIR_GROUP_SCHED case).
-	 * runnable_load_avg is the sum of the load_avg_contrib of the
-	 * sched_entities on the rq.
-	 * blocked_load_avg is similar to runnable_load_avg except that its
-	 * the blocked sched_entities on the rq.
-	 * utilization_load_avg is the sum of the average running time of the
-	 * sched_entities on the rq.
+	 * CFS load tracking
 	 */
-	unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg;
-	atomic64_t decay_counter;
-	u64 last_decay;
-	atomic_long_t removed_load;
-
+	struct sched_avg avg;
+	u64 runnable_load_sum;
+	unsigned long runnable_load_avg;
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	/* Required to track per-cpu representation of a task_group */
-	u32 tg_runnable_contrib;
-	unsigned long tg_load_contrib;
+	unsigned long tg_load_avg_contrib;
+#endif
+	atomic_long_t removed_load_avg, removed_util_avg;
+#ifndef CONFIG_64BIT
+	u64 load_last_update_time_copy;
+#endif
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
 	 *   h_load = weight * f(tg)
 	 *

@@ -595,8 +587,6 @@ struct rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
 	struct list_head leaf_cfs_rq_list;
-
-	struct sched_avg avg;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 	/*

@@ -1065,9 +1055,6 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #ifndef prepare_arch_switch
 # define prepare_arch_switch(next)	do { } while (0)
 #endif
-#ifndef finish_arch_switch
-# define finish_arch_switch(prev)	do { } while (0)
-#endif
 #ifndef finish_arch_post_lock_switch
 # define finish_arch_post_lock_switch()	do { } while (0)
 #endif

@@ -1268,6 +1255,8 @@ extern void trigger_load_balance(struct rq *rq);
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
 
+extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);
+
 #else
 
 static inline void idle_enter_fair(struct rq *rq) { }

@@ -1319,7 +1308,7 @@ extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 
 unsigned long to_ratio(u64 period, u64 runtime);
 
-extern void init_task_runnable_average(struct task_struct *p);
+extern void init_entity_runnable_average(struct sched_entity *se);
 
 static inline void add_nr_running(struct rq *rq, unsigned count)
 {

index 79ffec45a6ac..cbc67da10954 100644
@@ -123,6 +123,7 @@ const struct sched_class stop_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_stop,
+	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif
 
 	.set_curr_task          = set_curr_task_stop,

132 lines not on this page · raw message

index 419ca37e72c9..f270088e9929 100644
@@ -26,7 +26,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n
 }
 
 static void
-probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 {
 	if (unlikely(!sched_ref))
 		return;

index 9b33dd117f3f..12cbe77b4136 100644
@@ -514,7 +514,7 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-probe_wakeup(void *ignore, struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p)
 {
 	struct trace_array_cpu *data;
 	int cpu = smp_processor_id();

index 4c4f06176f74..f5782d5fd196 100644
@@ -1714,9 +1714,7 @@ static struct worker *create_worker(struct worker_pool *pool)
 		goto fail;
 
 	set_user_nice(worker->task, pool->attrs->nice);
-
-	/* prevent userland from meddling with cpumask of workqueue workers */
-	worker->task->flags |= PF_NO_SETAFFINITY;
+	kthread_bind_mask(worker->task, pool->attrs->cpumask);
 
 	/* successful, attach the worker to the pool */
 	worker_attach_to_pool(worker, pool);

@@ -3856,7 +3854,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 		}
 
 		wq->rescuer = rescuer;
-		rescuer->task->flags |= PF_NO_SETAFFINITY;
+		kthread_bind_mask(rescuer->task, cpu_possible_mask);
 		wake_up_process(rescuer->task);
 	}
 

index 82cf9dff4295..873aa0757b04 100644
@@ -397,12 +397,11 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	 * Prevent irq alloc/free while the dying cpu reorganizes the
 	 * interrupt affinities.
 	 */
-	irq_lock_sparse();
 
 	/*
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
-	err = stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
+	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);

diff --cc kernel/cpu.c
index 3c91a3fdfce5,664ce5299334..82cf9dff4295
@@@ -394,15 -392,10 +394,15 @@@ static int _cpu_down(unsigned int cpu, 
  	smpboot_park_threads(cpu);
  
  	/*
 -	 * So now all preempt/rcu users must observe !cpu_active().
 +	 * Prevent irq alloc/free while the dying cpu reorganizes the
 +	 * interrupt affinities.
  	 */
 +	irq_lock_sparse();
  
 +	/*
 +	 * So now all preempt/rcu users must observe !cpu_active().
 +	 */
- 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
+ 	err = stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
  	if (err) {
  		/* CPU didn't die: tell everyone.  Can't complain. */
  		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);

index 74d825716f4f..3190173a575f 100644
@@ -989,7 +989,7 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
-	build_mtrr2protval();
+//	build_mtrr2protval();
 	return 0;
 
 err:

index 189e464..d9d3a30 100644
@@ -884,6 +884,7 @@ static u8 fallback_mtrr_type(int mtrr)
        case MTRR_TYPE_WRPROT:
                return MTRR_TYPE_UC_MINUS;
        default:
+               printk("BUG in %s, mtrr = %d.\n", __FUNCTION__, mtrr);
                BUG();
        }
 }

@@ -907,6 +908,8 @@ static void build_mtrr2protval(void)
         * guest.
         */
        rdmsrl(MSR_IA32_CR_PAT, pat);
+       printk("KVM PAT: 0x%llx.\n", pat);
+
        for (i = 0; i < 8; i++) {
                u8 mtrr = pat >> (8 * i);
 

@@ -914,10 +917,17 @@ static void build_mtrr2protval(void)
                        mtrr2protval[mtrr] = __cm_idx2pte(i);
        }
 
+       for (i = 0; i < 8; i++)
+               printk("mtrr2protval[%d]:%x.\n", i, mtrr2protval[i]);
+
+
        for (i = 0; i < 8; i++) {
                if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
                        u8 fallback = fallback_mtrr_type(i);
                        mtrr2protval[i] = mtrr2protval[fallback];
+                       if (mtrr2protval[i] == MTRR2PROTVAL_INVALID)
+                               printk("BUG in %s, mtrr2protval[%d] = %x.\n", __FUNCTION__, i, mtrr2protval[i]);
+
                        BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
                }
        }