sched/fair: Remove duplicate code from can_migrate_task()

index 2a1e6ac..420bc98 100644
@@ -5292,24 +5292,12 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	if (!tsk_cache_hot)
 		tsk_cache_hot = migrate_degrades_locality(p, env);
 
-	if (migrate_improves_locality(p, env)) {
-#ifdef CONFIG_SCHEDSTATS
+	if (migrate_improves_locality(p, env) || !tsk_cache_hot ||
+	    env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 		if (tsk_cache_hot) {
 			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
 			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
-#endif
-		return 1;
-	}
-
-	if (!tsk_cache_hot ||
-		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
-
-		if (tsk_cache_hot) {
-			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
-			schedstat_inc(p, se.statistics.nr_forced_migrations);
-		}
-
 		return 1;
 	}
 

index 2a93b87..5b864e9 100644
@@ -1700,15 +1700,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 #ifdef CONFIG_SMP
 	/*
-	 * If the owning (remote) cpu is still in the middle of schedule() with
-	 * this task as prev, wait until its done referencing the task.
+	 * Note, that p is dequeued at the moment. But it still
+	 * may be "prev" in the middle of schedule() on other cpu.
 	 */
-	while (p->on_cpu)
-		cpu_relax();
-	/*
-	 * Pairs with the smp_wmb() in finish_lock_switch().
-	 */
-	smp_rmb();
+	cpu_relax__while_on_cpu(p);
 
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;

index aaa5abb..ea0ba33 100644
@@ -1364,7 +1364,9 @@ static int push_dl_task(struct rq *rq)
 		next_task = task;
 		goto retry;
 	}
-
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+	cpu_relax__while_on_cpu(next_task);
+#endif
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, later_rq->cpu);
 	activate_task(later_rq, next_task, 0);

@@ -1451,6 +1453,9 @@ static int pull_dl_task(struct rq *this_rq)
 
 			ret = 1;
 
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+			cpu_relax__while_on_cpu(p);
+#endif
 			deactivate_task(src_rq, p, 0);
 			set_task_cpu(p, this_cpu);
 			activate_task(this_rq, p, 0);

index 420bc98..80c5064 100644
@@ -5298,6 +5298,9 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 			schedstat_inc(env->sd, lb_hot_gained[env->idle]);
 			schedstat_inc(p, se.statistics.nr_forced_migrations);
 		}
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+		cpu_relax__while_on_cpu(p);
+#endif
 		return 1;
 	}
 

index 2e6a774..de356b0 100644
@@ -1734,7 +1734,9 @@ static int push_rt_task(struct rq *rq)
 		next_task = task;
 		goto retry;
 	}
-
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+	cpu_relax__while_on_cpu(next_task);
+#endif
 	deactivate_task(rq, next_task, 0);
 	set_task_cpu(next_task, lowest_rq->cpu);
 	activate_task(lowest_rq, next_task, 0);

@@ -1823,6 +1825,9 @@ static int pull_rt_task(struct rq *this_rq)
 
 			ret = 1;
 
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+			cpu_relax__while_on_cpu(p);
+#endif
 			deactivate_task(src_rq, p, 0);
 			set_task_cpu(p, this_cpu);
 			activate_task(this_rq, p, 0);

index 1bc6aad..9c07d72 100644
@@ -1034,6 +1034,22 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
+ * If the owning (remote) cpu is still in the middle of schedule() with
+ * this task as prev, wait until its done referencing the task.
+ */
+static inline void cpu_relax__while_on_cpu(struct task_struct *p)
+{
+#ifdef CONFIG_SMP
+	while (p->on_cpu)
+		cpu_relax();
+	/*
+	 * Pairs with the smp_wmb() in finish_lock_switch().
+	 */
+	smp_rmb();
+#endif
+}
+
+/*
  * wake flags
  */
 #define WF_SYNC		0x01		/* waker goes to sleep after wakeup */

index c736713..ce53c50 100644
@@ -19,7 +19,6 @@
 #include <asm/ptrace.h>
 #include <asm/ustack.h>
 
-#define __ARCH_WANT_UNLOCKED_CTXSW
 #define ARCH_HAS_PREFETCH_SWITCH_STACK
 
 #define IA64_NUM_PHYS_STACK_REG	96

index 05f0843..f1df4cb 100644
@@ -397,12 +397,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define ARCH_HAS_PREFETCHW
 #define prefetchw(x) __builtin_prefetch((x), 1, 1)
 
-/*
- * See Documentation/scheduler/sched-arch.txt; prevents deadlock on SMP
- * systems.
- */
-#define __ARCH_WANT_UNLOCKED_CTXSW
-
 #endif
 
 #endif /* _ASM_PROCESSOR_H */

index 2a93b87..ccbafb0 100644
@@ -2304,10 +2304,6 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 */
 	post_schedule(rq);
 
-#ifdef __ARCH_WANT_UNLOCKED_CTXSW
-	/* In this case, finish_task_switch does not reenable preemption */
-	preempt_enable();
-#endif
 	if (current->set_child_tid)
 		put_user(task_pid_vnr(current), current->set_child_tid);
 }

@@ -2350,9 +2346,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 * of the scheduler it's an obvious special-case), so we
 	 * do an early lockdep release here:
 	 */
-#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
-#endif
 
 	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */

index 1bc6aad..d87f122 100644
@@ -966,7 +966,6 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 # define finish_arch_post_lock_switch()	do { } while (0)
 #endif
 
-#ifndef __ARCH_WANT_UNLOCKED_CTXSW
 static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
 {
 #ifdef CONFIG_SMP

@@ -1004,35 +1003,6 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	raw_spin_unlock_irq(&rq->lock);
 }
 
-#else /* __ARCH_WANT_UNLOCKED_CTXSW */
-static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * We can optimise this out completely for !SMP, because the
-	 * SMP rebalancing from interrupt is the only thing that cares
-	 * here.
-	 */
-	next->on_cpu = 1;
-#endif
-	raw_spin_unlock(&rq->lock);
-}
-
-static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
-	 * We must ensure this doesn't happen until the switch is completely
-	 * finished.
-	 */
-	smp_wmb();
-	prev->on_cpu = 0;
-#endif
-	local_irq_enable();
-}
-#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
-
 /*
  * wake flags
  */

index 5b864e9..a300fce 100644
@@ -1989,6 +1989,8 @@ unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_SMP
 inline struct dl_bw *dl_bw_of(int i)
 {
+	rcu_lockdep_assert(rcu_read_lock_sched_held(),
+			   "sched RCU must be held");
 	return &cpu_rq(i)->rd->dl_bw;
 }
 

@@ -1997,6 +1999,8 @@ static inline int dl_bw_cpus(int i)
 	struct root_domain *rd = cpu_rq(i)->rd;
 	int cpus = 0;
 
+	rcu_lockdep_assert(rcu_read_lock_sched_held(),
+			   "sched RCU must be held");
 	for_each_cpu_and(i, rd->span, cpu_active_mask)
 		cpus++;
 

@@ -7623,6 +7627,8 @@ static int sched_dl_global_constraints(void)
 	int cpu, ret = 0;
 	unsigned long flags;
 
+	rcu_read_lock();
+
 	/*
 	 * Here we want to check the bandwidth not being set to some
 	 * value smaller than the currently allocated bandwidth in

@@ -7644,6 +7650,8 @@ static int sched_dl_global_constraints(void)
 			break;
 	}
 
+	rcu_read_unlock();
+
 	return ret;
 }
 

@@ -7659,6 +7667,7 @@ static void sched_dl_do_global(void)
 	if (global_rt_runtime() != RUNTIME_INF)
 		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
 
+	rcu_read_lock();
 	/*
 	 * FIXME: As above...
 	 */

@@ -7669,6 +7678,7 @@ static void sched_dl_do_global(void)
 		dl_b->bw = new_bw;
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	}
+	rcu_read_unlock();
 }
 
 static int sched_rt_global_validate(void)

index a300fce..3b07710 100644
@@ -4003,14 +4003,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 		rcu_read_lock();
 		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
 			rcu_read_unlock();
-			goto out_unlock;
+			goto out_free_new_mask;
 		}
 		rcu_read_unlock();
 	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
-		goto out_unlock;
+		goto out_free_new_mask;
 
 
 	cpuset_cpus_allowed(p, cpus_allowed);

@@ -4028,7 +4028,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 
 		if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
 			retval = -EBUSY;
-			goto out_unlock;
+			goto out_free_new_mask;
 		}
 	}
 #endif

@@ -4047,7 +4047,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 			goto again;
 		}
 	}
-out_unlock:
+out_free_new_mask:
 	free_cpumask_var(new_mask);
 out_free_cpus_allowed:
 	free_cpumask_var(cpus_allowed);

index 3b07710..643ee99 100644
@@ -4023,13 +4023,14 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	 * root_domain.
 	 */
 #ifdef CONFIG_SMP
-	if (task_has_dl_policy(p)) {
-		const struct cpumask *span = task_rq(p)->rd->span;
-
-		if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
+	if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
+		rcu_read_lock();
+		if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
 			retval = -EBUSY;
+			rcu_read_unlock();
 			goto out_free_new_mask;
 		}
+		rcu_read_unlock();
 	}
 #endif
 again:

index de356b0..c322071 100644
@@ -2077,7 +2077,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	for_each_sched_rt_entity(rt_se) {
 		if (rt_se->run_list.prev != rt_se->run_list.next) {
 			requeue_task_rt(rq, p, 0);
-			set_tsk_need_resched(p);
+			resched_curr(rq);
 			return;
 		}
 	}