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 were:

   - Optimized support for Intel "Cluster-on-Die" (CoD) topologies (Dave
     Hansen)

   - Various sched/idle refinements for better idle handling (Nicolas
     Pitre, Daniel Lezcano, Chuansheng Liu, Vincent Guittot)

   - sched/numa updates and optimizations (Rik van Riel)

   - sysbench speedup (Vincent Guittot)

   - capacity calculation cleanups/refactoring (Vincent Guittot)

   - Various cleanups to thread group iteration (Oleg Nesterov)

   - Double-rq-lock removal optimization and various refactorings
     (Kirill Tkhai)

   - various sched/deadline fixes

  ... and lots of other changes"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  sched/dl: Use dl_bw_of() under rcu_read_lock_sched()
  sched/fair: Delete resched_cpu() from idle_balance()
  sched, time: Fix build error with 64 bit cputime_t on 32 bit systems
  sched: Improve sysbench performance by fixing spurious active migration
  sched/x86: Fix up typo in topology detection
  x86, sched: Add new topology for multi-NUMA-node CPUs
  sched/rt: Use resched_curr() in task_tick_rt()
  sched: Use rq->rd in sched_setaffinity() under RCU read lock
  sched: cleanup: Rename 'out_unlock' to 'out_free_new_mask'
  sched: Use dl_bw_of() under RCU read lock
  sched/fair: Remove duplicate code from can_migrate_task()
  sched, mips, ia64: Remove __ARCH_WANT_UNLOCKED_CTXSW
  sched: print_rq(): Don't use tasklist_lock
  sched: normalize_rt_tasks(): Don't use _irqsave for tasklist_lock, use task_rq_lock()
  sched: Fix the task-group check in tg_has_rt_tasks()
  sched/fair: Leverage the idle state info when choosing the "idlest" cpu
  sched: Let the scheduler see CPU idle states
  sched/deadline: Fix inter- exclusive cpusets migrations
  sched/deadline: Clear dl_entity params when setscheduling to different class
  sched/numa: Kill the wrong/dead TASK_DEAD check in task_numa_fault()
  ...

4 files changed, 37 insertions, 6 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 05a8c00e8339..5e344bbe63ec 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -57,6 +57,7 @@ struct sched_param {
 #include <linux/llist.h>
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
+#include <linux/magic.h>
 
 #include <asm/processor.h>
 
@@ -646,6 +647,7 @@ struct signal_struct {
 	 * Live threads maintain their own counters and add to these
 	 * in __exit_signal, except for the group leader.
 	 */
+	seqlock_t stats_lock;
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
@@ -1024,6 +1026,7 @@ struct sched_domain_topology_level {
 extern struct sched_domain_topology_level *sched_domain_topology;
 
 extern void set_sched_topology(struct sched_domain_topology_level *tl);
+extern void wake_up_if_idle(int cpu);
 
 #ifdef CONFIG_SCHED_DEBUG
 # define SD_INIT_NAME(type)		.name = #type
@@ -2647,6 +2650,8 @@ static inline unsigned long *end_of_stack(struct task_struct *p)
 }
 
 #endif
+#define task_stack_end_corrupted(task) \
+		(*(end_of_stack(task)) != STACK_END_MAGIC)
 
 static inline int object_is_on_stack(void *obj)
 {
@@ -2669,6 +2674,7 @@ static inline unsigned long stack_not_used(struct task_struct *p)
 	return (unsigned long)n - (unsigned long)end_of_stack(p);
 }
 #endif
+extern void set_task_stack_end_magic(struct task_struct *tsk);
 
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index cc359636cfa3..f5df8f687b4d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -456,4 +456,23 @@ read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags)
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
+static inline unsigned long
+read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq)
+{
+	unsigned long flags = 0;
+
+	if (!(*seq & 1))	/* Even */
+		*seq = read_seqbegin(lock);
+	else			/* Odd */
+		read_seqlock_excl_irqsave(lock, flags);
+
+	return flags;
+}
+
+static inline void
+done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags)
+{
+	if (seq & 1)
+		read_sequnlock_excl_irqrestore(lock, flags);
+}
 #endif /* __LINUX_SEQLOCK_H */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 34347f26be9b..93dff5fff524 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -100,6 +100,7 @@ int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait);
 
 void kick_all_cpus_sync(void);
+void wake_up_all_idle_cpus(void);
 
 /*
  * Generic and arch helpers
@@ -148,6 +149,7 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 }
 
 static inline void kick_all_cpus_sync(void) {  }
+static inline void wake_up_all_idle_cpus(void) {  }
 
 #endif /* !SMP */
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 80115bf88671..e4a8eb9312ea 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -281,9 +281,11 @@ do {									\
  * wake_up() has to be called after changing any variable that could
  * change the result of the wait condition.
  *
- * The function returns 0 if the @timeout elapsed, or the remaining
- * jiffies (at least 1) if the @condition evaluated to %true before
- * the @timeout elapsed.
+ * Returns:
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * or the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed.
  */
 #define wait_event_timeout(wq, condition, timeout)			\
 ({									\
@@ -364,9 +366,11 @@ do {									\
  * change the result of the wait condition.
  *
  * Returns:
- * 0 if the @timeout elapsed, -%ERESTARTSYS if it was interrupted by
- * a signal, or the remaining jiffies (at least 1) if the @condition
- * evaluated to %true before the @timeout elapsed.
+ * 0 if the @condition evaluated to %false after the @timeout elapsed,
+ * 1 if the @condition evaluated to %true after the @timeout elapsed,
+ * the remaining jiffies (at least 1) if the @condition evaluated
+ * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was
+ * interrupted by a signal.
  */
 #define wait_event_interruptible_timeout(wq, condition, timeout)	\
 ({									\