[GIT pull] scheduler fixes for 4.4

[Thomas Gleixner]

Linus,

please pull the latest sched-urgent-for-linus git tree from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

This updates contains the following changes:

 - Fix a signal handling regression in the bit wait functions.

 - Avoid false positive warnings in the wakeup path.

 - Initialize the scheduler root domain properly.

 - Handle gtime calculations in proc/$PID/stat proper.

 - Add more documentation for the barriers in try_to_wake_up().

 - Fix a subtle race in try_to_wake_up() which might cause a task to
   be scheduled on two cpus

 - Compile static helper function only when it is used.


Thanks,

	tglx

------------------>
Arnd Bergmann (1):
      sched/rt: Hide the push_irq_work_func() declaration

Hiroshi Shimamoto (1):
      sched/cputime: Fix invalid gtime in proc

Peter Zijlstra (3):
      sched/wait: Fix signal handling in bit wait helpers
      sched/core: Better document the try_to_wake_up() barriers
      sched/core: Fix an SMP ordering race in try_to_wake_up() vs. schedule()

Sasha Levin (1):
      sched/core: Remove false-positive warning from wake_up_process()

Xunlei Pang (1):
      sched/core: Clear the root_domain cpumasks in init_rootdomain()


 kernel/sched/core.c    | 36 ++++++++++++++++++++++++++++++------
 kernel/sched/cputime.c |  3 +++
 kernel/sched/rt.c      |  2 +-
 kernel/sched/sched.h   |  3 +++
 kernel/sched/wait.c    | 16 ++++++++--------
 5 files changed, 45 insertions(+), 15 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4d568ac9319e..7063c6a07440 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1947,13 +1947,38 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 #ifdef CONFIG_SMP
 	/*
+	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
+	 * possible to, falsely, observe p->on_cpu == 0.
+	 *
+	 * One must be running (->on_cpu == 1) in order to remove oneself
+	 * from the runqueue.
+	 *
+	 *  [S] ->on_cpu = 1;	[L] ->on_rq
+	 *      UNLOCK rq->lock
+	 *			RMB
+	 *      LOCK   rq->lock
+	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 *
+	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
+	 * from the consecutive calls to schedule(); the first switching to our
+	 * task, the second putting it to sleep.
+	 */
+	smp_rmb();
+
+	/*
 	 * If the owning (remote) cpu is still in the middle of schedule() with
 	 * this task as prev, wait until its done referencing the task.
 	 */
 	while (p->on_cpu)
 		cpu_relax();
 	/*
-	 * Pairs with the smp_wmb() in finish_lock_switch().
+	 * Combined with the control dependency above, we have an effective
+	 * smp_load_acquire() without the need for full barriers.
+	 *
+	 * Pairs with the smp_store_release() in finish_lock_switch().
+	 *
+	 * This ensures that tasks getting woken will be fully ordered against
+	 * their previous state and preserve Program Order.
 	 */
 	smp_rmb();
 
@@ -2039,7 +2064,6 @@ out:
  */
 int wake_up_process(struct task_struct *p)
 {
-	WARN_ON(task_is_stopped_or_traced(p));
 	return try_to_wake_up(p, TASK_NORMAL, 0);
 }
 EXPORT_SYMBOL(wake_up_process);
@@ -5847,13 +5871,13 @@ static int init_rootdomain(struct root_domain *rd)
 {
 	memset(rd, 0, sizeof(*rd));
 
-	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
 		goto out;
-	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
 		goto free_online;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
 		goto free_dlo_mask;
 
 	init_dl_bw(&rd->dl_bw);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 26a54461bf59..05de80b48586 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -788,6 +788,9 @@ cputime_t task_gtime(struct task_struct *t)
 	unsigned int seq;
 	cputime_t gtime;
 
+	if (!context_tracking_is_enabled())
+		return t->gtime;
+
 	do {
 		seq = read_seqbegin(&t->vtime_seqlock);
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index e3cc16312046..8ec86abe0ea1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -64,7 +64,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 	raw_spin_unlock(&rt_b->rt_runtime_lock);
 }
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && defined(HAVE_RT_PUSH_IPI)
 static void push_irq_work_func(struct irq_work *work);
 #endif
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index efd3bfc7e347..b242775bf670 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1073,6 +1073,9 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
 	 *
+	 * In particular, the load of prev->state in finish_task_switch() must
+	 * happen before this.
+	 *
 	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
 	smp_store_release(&prev->on_cpu, 0);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 052e02672d12..f10bd873e684 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -583,18 +583,18 @@ EXPORT_SYMBOL(wake_up_atomic_t);
 
 __sched int bit_wait(struct wait_bit_key *word)
 {
-	if (signal_pending_state(current->state, current))
-		return 1;
 	schedule();
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait);
 
 __sched int bit_wait_io(struct wait_bit_key *word)
 {
-	if (signal_pending_state(current->state, current))
-		return 1;
 	io_schedule();
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL(bit_wait_io);
@@ -602,11 +602,11 @@ EXPORT_SYMBOL(bit_wait_io);
 __sched int bit_wait_timeout(struct wait_bit_key *word)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	if (signal_pending_state(current->state, current))
-		return 1;
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	schedule_timeout(word->timeout - now);
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_timeout);
@@ -614,11 +614,11 @@ EXPORT_SYMBOL_GPL(bit_wait_timeout);
 __sched int bit_wait_io_timeout(struct wait_bit_key *word)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	if (signal_pending_state(current->state, current))
-		return 1;
 	if (time_after_eq(now, word->timeout))
 		return -EAGAIN;
 	io_schedule_timeout(word->timeout - now);
+	if (signal_pending(current))
+		return -EINTR;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bit_wait_io_timeout);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/