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

Pull RCU updates from Ingo Molnad:
 "The main RCU related changes in this cycle were:

   - Removal of spin_unlock_wait()
   - SRCU updates
   - RCU torture-test updates
   - RCU Documentation updates
   - Extend the sys_membarrier() ABI with the MEMBARRIER_CMD_PRIVATE_EXPEDITED variant
   - Miscellaneous RCU fixes
   - CPU-hotplug fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  arch: Remove spin_unlock_wait() arch-specific definitions
  locking: Remove spin_unlock_wait() generic definitions
  drivers/ata: Replace spin_unlock_wait() with lock/unlock pair
  ipc: Replace spin_unlock_wait() with lock/unlock pair
  exit: Replace spin_unlock_wait() with lock/unlock pair
  completion: Replace spin_unlock_wait() with lock/unlock pair
  doc: Set down RCU's scheduling-clock-interrupt needs
  doc: No longer allowed to use rcu_dereference on non-pointers
  doc: Add RCU files to docbook-generation files
  doc: Update memory-barriers.txt for read-to-write dependencies
  doc: Update RCU documentation
  membarrier: Provide expedited private command
  rcu: Remove exports from rcu_idle_exit() and rcu_idle_enter()
  rcu: Add warning to rcu_idle_enter() for irqs enabled
  rcu: Make rcu_idle_enter() rely on callers disabling irqs
  rcu: Add assertions verifying blocked-tasks list
  rcu/tracing: Set disable_rcu_irq_enter on rcu_eqs_exit()
  rcu: Add TPS() protection for _rcu_barrier_trace strings
  rcu: Use idle versions of swait to make idle-hack clear
  swait: Add idle variants which don't contribute to load average
  ...

1 files changed, 34 insertions, 4 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0869b20fba81..e053c31d96da 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -951,8 +951,13 @@ struct migration_arg {
 static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 				 struct task_struct *p, int dest_cpu)
 {
-	if (unlikely(!cpu_active(dest_cpu)))
-		return rq;
+	if (p->flags & PF_KTHREAD) {
+		if (unlikely(!cpu_online(dest_cpu)))
+			return rq;
+	} else {
+		if (unlikely(!cpu_active(dest_cpu)))
+			return rq;
+	}
 
 	/* Affinity changed (again). */
 	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
@@ -2635,6 +2640,16 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	prev_state = prev->state;
 	vtime_task_switch(prev);
 	perf_event_task_sched_in(prev, current);
+	/*
+	 * The membarrier system call requires a full memory barrier
+	 * after storing to rq->curr, before going back to user-space.
+	 *
+	 * TODO: This smp_mb__after_unlock_lock can go away if PPC end
+	 * up adding a full barrier to switch_mm(), or we should figure
+	 * out if a smp_mb__after_unlock_lock is really the proper API
+	 * to use.
+	 */
+	smp_mb__after_unlock_lock();
 	finish_lock_switch(rq, prev);
 	finish_arch_post_lock_switch();
 
@@ -3324,6 +3339,21 @@ static void __sched notrace __schedule(bool preempt)
 	if (likely(prev != next)) {
 		rq->nr_switches++;
 		rq->curr = next;
+		/*
+		 * The membarrier system call requires each architecture
+		 * to have a full memory barrier after updating
+		 * rq->curr, before returning to user-space. For TSO
+		 * (e.g. x86), the architecture must provide its own
+		 * barrier in switch_mm(). For weakly ordered machines
+		 * for which spin_unlock() acts as a full memory
+		 * barrier, finish_lock_switch() in common code takes
+		 * care of this barrier. For weakly ordered machines for
+		 * which spin_unlock() acts as a RELEASE barrier (only
+		 * arm64 and PowerPC), arm64 has a full barrier in
+		 * switch_to(), and PowerPC has
+		 * smp_mb__after_unlock_lock() before
+		 * finish_lock_switch().
+		 */
 		++*switch_count;
 
 		trace_sched_switch(preempt, prev, next);
@@ -3352,8 +3382,8 @@ void __noreturn do_task_dead(void)
 	 * To avoid it, we have to wait for releasing tsk->pi_lock which
 	 * is held by try_to_wake_up()
 	 */
-	smp_mb();
-	raw_spin_unlock_wait(&current->pi_lock);
+	raw_spin_lock_irq(&current->pi_lock);
+	raw_spin_unlock_irq(&current->pi_lock);
 
 	/* Causes final put_task_struct in finish_task_switch(): */
 	__set_current_state(TASK_DEAD);