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

Pull scheduler updates from Ingo Molnar:

 - Move the nohz kick code out of the scheduler tick to a dedicated IPI,
   from Frederic Weisbecker.

  This necessiated quite some background infrastructure rework,
  including:

   * Clean up some irq-work internals
   * Implement remote irq-work
   * Implement nohz kick on top of remote irq-work
   * Move full dynticks timer enqueue notification to new kick
   * Move multi-task notification to new kick
   * Remove unecessary barriers on multi-task notification

 - Remove proliferation of wait_on_bit() action functions and allow
   wait_on_bit_action() functions to support a timeout.  (Neil Brown)

 - Another round of sched/numa improvements, cleanups and fixes.  (Rik
   van Riel)

 - Implement fast idling of CPUs when the system is partially loaded,
   for better scalability.  (Tim Chen)

 - Restructure and fix the CPU hotplug handling code that may leave
   cfs_rq and rt_rq's throttled when tasks are migrated away from a dead
   cpu.  (Kirill Tkhai)

 - Robustify the sched topology setup code.  (Peterz Zijlstra)

 - Improve sched_feat() handling wrt.  static_keys (Jason Baron)

 - Misc fixes.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  sched/fair: Fix 'make xmldocs' warning caused by missing description
  sched: Use macro for magic number of -1 for setparam
  sched: Robustify topology setup
  sched: Fix sched_setparam() policy == -1 logic
  sched: Allow wait_on_bit_action() functions to support a timeout
  sched: Remove proliferation of wait_on_bit() action functions
  sched/numa: Revert "Use effective_load() to balance NUMA loads"
  sched: Fix static_key race with sched_feat()
  sched: Remove extra static_key*() function indirection
  sched/rt: Fix replenish_dl_entity() comments to match the current upstream code
  sched: Transform resched_task() into resched_curr()
  sched/deadline: Kill task_struct->pi_top_task
  sched: Rework check_for_tasks()
  sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()
  sched/fair: Disable runtime_enabled on dying rq
  sched/numa: Change scan period code to match intent
  sched/numa: Rework best node setting in task_numa_migrate()
  sched/numa: Examine a task move when examining a task swap
  sched/numa: Simplify task_numa_compare()
  sched/numa: Use effective_load() to balance NUMA loads
  ...

6 files changed, 135 insertions, 17 deletions

diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 19ae05d4b8ec..bf9422c3aefe 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -33,6 +33,11 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *))
 #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), }
 
 bool irq_work_queue(struct irq_work *work);
+
+#ifdef CONFIG_SMP
+bool irq_work_queue_on(struct irq_work *work, int cpu);
+#endif
+
 void irq_work_run(void);
 void irq_work_sync(struct irq_work *work);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b39a671cfd59..42cac4dc2157 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1437,8 +1437,6 @@ struct task_struct {
 	struct rb_node *pi_waiters_leftmost;
 	/* Deadlock detection and priority inheritance handling */
 	struct rt_mutex_waiter *pi_blocked_on;
-	/* Top pi_waiters task */
-	struct task_struct *pi_top_task;
 #endif
 
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -2782,7 +2780,7 @@ static inline bool __must_check current_set_polling_and_test(void)
 
 	/*
 	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_task()
+	 * paired by resched_curr()
 	 */
 	smp_mb__after_atomic();
 
@@ -2800,7 +2798,7 @@ static inline bool __must_check current_clr_polling_and_test(void)
 
 	/*
 	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_task()
+	 * paired by resched_curr()
 	 */
 	smp_mb__after_atomic();
 
@@ -2832,7 +2830,7 @@ static inline void current_clr_polling(void)
 	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
 	 * fold.
 	 */
-	smp_mb(); /* paired with resched_task() */
+	smp_mb(); /* paired with resched_curr() */
 
 	preempt_fold_need_resched();
 }
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index ad7dbe2cfecd..1a8959944c5f 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -236,7 +236,7 @@ void *		rpc_malloc(struct rpc_task *, size_t);
 void		rpc_free(void *);
 int		rpciod_up(void);
 void		rpciod_down(void);
-int		__rpc_wait_for_completion_task(struct rpc_task *task, int (*)(void *));
+int		__rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *);
 #ifdef RPC_DEBUG
 struct net;
 void		rpc_show_tasks(struct net *);
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 06cc093ab7ad..059052306831 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -183,7 +183,13 @@ static inline bool tick_nohz_full_cpu(int cpu)
 
 extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
-extern void tick_nohz_full_kick(void);
+extern void tick_nohz_full_kick_cpu(int cpu);
+
+static inline void tick_nohz_full_kick(void)
+{
+	tick_nohz_full_kick_cpu(smp_processor_id());
+}
+
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
@@ -191,6 +197,7 @@ static inline void tick_nohz_init(void) { }
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void __tick_nohz_full_check(void) { }
+static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void tick_nohz_full_kick(void) { }
 static inline void tick_nohz_full_kick_all(void) { }
 static inline void __tick_nohz_task_switch(struct task_struct *tsk) { }
diff --git a/include/linux/wait.h b/include/linux/wait.h
index bd68819f0815..6fb1ba5f9b2f 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -25,6 +25,7 @@ struct wait_bit_key {
 	void			*flags;
 	int			bit_nr;
 #define WAIT_ATOMIC_T_BIT_NR	-1
+	unsigned long		private;
 };
 
 struct wait_bit_queue {
@@ -141,18 +142,19 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 	list_del(&old->task_list);
 }
 
+typedef int wait_bit_action_f(struct wait_bit_key *);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_bit(wait_queue_head_t *, void *, int);
-int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
-int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
+int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
+int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
 void wake_up_bit(void *, int);
 void wake_up_atomic_t(atomic_t *);
-int out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned);
-int out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned);
+int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned);
+int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned);
 int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned);
 wait_queue_head_t *bit_waitqueue(void *, int);
 
@@ -854,11 +856,14 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 		(wait)->flags = 0;					\
 	} while (0)
 
+
+extern int bit_wait(struct wait_bit_key *);
+extern int bit_wait_io(struct wait_bit_key *);
+
 /**
  * wait_on_bit - wait for a bit to be cleared
  * @word: the word being waited on, a kernel virtual address
  * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
  * @mode: the task state to sleep in
  *
  * There is a standard hashed waitqueue table for generic use. This
@@ -867,9 +872,62 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
  * call wait_on_bit() in threads waiting for the bit to clear.
  * One uses wait_on_bit() where one is waiting for the bit to clear,
  * but has no intention of setting it.
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit(void *word, int bit, unsigned mode)
+{
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait,
+				       mode);
+}
+
+/**
+ * wait_on_bit_io - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared.  This is similar to wait_on_bit(), but calls
+ * io_schedule() instead of schedule() for the actual waiting.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit_io(void *word, int bit, unsigned mode)
+{
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait_io,
+				       mode);
+}
+
+/**
+ * wait_on_bit_action - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared, and allow the waiting action to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
  */
 static inline int
-wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode)
+wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
 	if (!test_bit(bit, word))
 		return 0;
@@ -880,7 +938,6 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode)
  * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
  * @word: the word being waited on, a kernel virtual address
  * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
  * @mode: the task state to sleep in
  *
  * There is a standard hashed waitqueue table for generic use. This
@@ -891,9 +948,61 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode)
  * wait_on_bit() in threads waiting to be able to set the bit.
  * One uses wait_on_bit_lock() where one is waiting for the bit to
  * clear with the intention of setting it, and when done, clearing it.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock(void *word, int bit, unsigned mode)
+{
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
+}
+
+/**
+ * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to atomically set it.  This is similar
+ * to wait_on_bit(), but calls io_schedule() instead of schedule()
+ * for the actual waiting.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock_io(void *word, int bit, unsigned mode)
+{
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
+}
+
+/**
+ * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to set it, and allow the waiting action
+ * to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock(void *word, int bit, int (*action)(void *), unsigned mode)
+wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
 	if (!test_and_set_bit(bit, word))
 		return 0;
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 5777c13849ba..a219be961c0a 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -90,7 +90,6 @@ struct writeback_control {
  * fs/fs-writeback.c
  */	
 struct bdi_writeback;
-int inode_wait(void *);
 void writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 							enum wb_reason reason);
@@ -105,7 +104,7 @@ void inode_wait_for_writeback(struct inode *inode);
 static inline void wait_on_inode(struct inode *inode)
 {
 	might_sleep();
-	wait_on_bit(&inode->i_state, __I_NEW, inode_wait, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
 }
 
 /*