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 are:

   - lockless wakeup support for futexes and IPC message queues
     (Davidlohr Bueso, Peter Zijlstra)

   - Replace spinlocks with atomics in thread_group_cputimer(), to
     improve scalability (Jason Low)

   - NUMA balancing improvements (Rik van Riel)

   - SCHED_DEADLINE improvements (Wanpeng Li)

   - clean up and reorganize preemption helpers (Frederic Weisbecker)

   - decouple page fault disabling machinery from the preemption
     counter, to improve debuggability and robustness (David
     Hildenbrand)

   - SCHED_DEADLINE documentation updates (Luca Abeni)

   - topology CPU masks cleanups (Bartosz Golaszewski)

   - /proc/sched_debug improvements (Srikar Dronamraju)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (79 commits)
  sched/deadline: Remove needless parameter in dl_runtime_exceeded()
  sched: Remove superfluous resetting of the p->dl_throttled flag
  sched/deadline: Drop duplicate init_sched_dl_class() declaration
  sched/deadline: Reduce rq lock contention by eliminating locking of non-feasible target
  sched/deadline: Make init_sched_dl_class() __init
  sched/deadline: Optimize pull_dl_task()
  sched/preempt: Add static_key() to preempt_notifiers
  sched/preempt: Fix preempt notifiers documentation about hlist_del() within unsafe iteration
  sched/stop_machine: Fix deadlock between multiple stop_two_cpus()
  sched/debug: Add sum_sleep_runtime to /proc/<pid>/sched
  sched/debug: Replace vruntime with wait_sum in /proc/sched_debug
  sched/debug: Properly format runnable tasks in /proc/sched_debug
  sched/numa: Only consider less busy nodes as numa balancing destinations
  Revert 095bebf61a46 ("sched/numa: Do not move past the balance point if unbalanced")
  sched/fair: Prevent throttling in early pick_next_task_fair()
  preempt: Reorganize the notrace definitions a bit
  preempt: Use preempt_schedule_context() as the official tracing preemption point
  sched: Make preempt_schedule_context() function-tracing safe
  x86: Remove cpu_sibling_mask() and cpu_core_mask()
  x86: Replace cpu_**_mask() with topology_**_cpumask()
  ...

1 files changed, 91 insertions, 27 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 659f5729cacc..d4193d5613cf 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -25,7 +25,7 @@ struct sched_param {
 #include <linux/errno.h>
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
-#include <linux/preempt_mask.h>
+#include <linux/preempt.h>
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -174,7 +174,12 @@ extern unsigned long nr_iowait_cpu(int cpu);
 extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 
 extern void calc_global_load(unsigned long ticks);
+
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
 extern void update_cpu_load_nohz(void);
+#else
+static inline void update_cpu_load_nohz(void) { }
+#endif
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -214,9 +219,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define TASK_WAKEKILL		128
 #define TASK_WAKING		256
 #define TASK_PARKED		512
-#define TASK_STATE_MAX		1024
+#define TASK_NOLOAD		1024
+#define TASK_STATE_MAX		2048
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPN"
 
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -226,6 +232,8 @@ extern char ___assert_task_state[1 - 2*!!(
 #define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
 #define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
 
+#define TASK_IDLE		(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
+
 /* Convenience macros for the sake of wake_up */
 #define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
 #define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
@@ -241,7 +249,8 @@ extern char ___assert_task_state[1 - 2*!!(
 			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-				 (task->flags & PF_FROZEN) == 0)
+				 (task->flags & PF_FROZEN) == 0 && \
+				 (task->state & TASK_NOLOAD) == 0)
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
@@ -568,6 +577,23 @@ struct task_cputime {
 		.sum_exec_runtime = 0,				\
 	}
 
+/*
+ * This is the atomic variant of task_cputime, which can be used for
+ * storing and updating task_cputime statistics without locking.
+ */
+struct task_cputime_atomic {
+	atomic64_t utime;
+	atomic64_t stime;
+	atomic64_t sum_exec_runtime;
+};
+
+#define INIT_CPUTIME_ATOMIC \
+	(struct task_cputime_atomic) {				\
+		.utime = ATOMIC64_INIT(0),			\
+		.stime = ATOMIC64_INIT(0),			\
+		.sum_exec_runtime = ATOMIC64_INIT(0),		\
+	}
+
 #ifdef CONFIG_PREEMPT_COUNT
 #define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
 #else
@@ -585,18 +611,16 @@ struct task_cputime {
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
- * @cputime:		thread group interval timers.
+ * @cputime_atomic:	atomic thread group interval timers.
  * @running:		non-zero when there are timers running and
  * 			@cputime receives updates.
- * @lock:		lock for fields in this struct.
  *
  * This structure contains the version of task_cputime, above, that is
  * used for thread group CPU timer calculations.
  */
 struct thread_group_cputimer {
-	struct task_cputime cputime;
+	struct task_cputime_atomic cputime_atomic;
 	int running;
-	raw_spinlock_t lock;
 };
 
 #include <linux/rwsem.h>
@@ -901,6 +925,50 @@ enum cpu_idle_type {
 #define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
 
 /*
+ * Wake-queues are lists of tasks with a pending wakeup, whose
+ * callers have already marked the task as woken internally,
+ * and can thus carry on. A common use case is being able to
+ * do the wakeups once the corresponding user lock as been
+ * released.
+ *
+ * We hold reference to each task in the list across the wakeup,
+ * thus guaranteeing that the memory is still valid by the time
+ * the actual wakeups are performed in wake_up_q().
+ *
+ * One per task suffices, because there's never a need for a task to be
+ * in two wake queues simultaneously; it is forbidden to abandon a task
+ * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is
+ * already in a wake queue, the wakeup will happen soon and the second
+ * waker can just skip it.
+ *
+ * The WAKE_Q macro declares and initializes the list head.
+ * wake_up_q() does NOT reinitialize the list; it's expected to be
+ * called near the end of a function, where the fact that the queue is
+ * not used again will be easy to see by inspection.
+ *
+ * Note that this can cause spurious wakeups. schedule() callers
+ * must ensure the call is done inside a loop, confirming that the
+ * wakeup condition has in fact occurred.
+ */
+struct wake_q_node {
+	struct wake_q_node *next;
+};
+
+struct wake_q_head {
+	struct wake_q_node *first;
+	struct wake_q_node **lastp;
+};
+
+#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
+
+#define WAKE_Q(name)					\
+	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
+
+extern void wake_q_add(struct wake_q_head *head,
+		       struct task_struct *task);
+extern void wake_up_q(struct wake_q_head *head);
+
+/*
  * sched-domains (multiprocessor balancing) declarations:
  */
 #ifdef CONFIG_SMP
@@ -1335,8 +1403,6 @@ struct task_struct {
 	int rcu_read_lock_nesting;
 	union rcu_special rcu_read_unlock_special;
 	struct list_head rcu_node_entry;
-#endif /* #ifdef CONFIG_PREEMPT_RCU */
-#ifdef CONFIG_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TASKS_RCU
@@ -1367,7 +1433,7 @@ struct task_struct {
 	int exit_state;
 	int exit_code, exit_signal;
 	int pdeath_signal;  /*  The signal sent when the parent dies  */
-	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
+	unsigned long jobctl;	/* JOBCTL_*, siglock protected */
 
 	/* Used for emulating ABI behavior of previous Linux versions */
 	unsigned int personality;
@@ -1513,6 +1579,8 @@ struct task_struct {
 	/* Protection of the PI data structures: */
 	raw_spinlock_t pi_lock;
 
+	struct wake_q_node wake_q;
+
 #ifdef CONFIG_RT_MUTEXES
 	/* PI waiters blocked on a rt_mutex held by this task */
 	struct rb_root pi_waiters;
@@ -1726,6 +1794,7 @@ struct task_struct {
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long	task_state_change;
 #endif
+	int pagefault_disabled;
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -2079,22 +2148,22 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 
-#define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
-#define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
-#define JOBCTL_STOP_CONSUME	(1 << JOBCTL_STOP_CONSUME_BIT)
-#define JOBCTL_TRAP_STOP	(1 << JOBCTL_TRAP_STOP_BIT)
-#define JOBCTL_TRAP_NOTIFY	(1 << JOBCTL_TRAP_NOTIFY_BIT)
-#define JOBCTL_TRAPPING		(1 << JOBCTL_TRAPPING_BIT)
-#define JOBCTL_LISTENING	(1 << JOBCTL_LISTENING_BIT)
+#define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
+#define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
+#define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
+#define JOBCTL_TRAP_STOP	(1UL << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1UL << JOBCTL_TRAP_NOTIFY_BIT)
+#define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
+#define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task,
-				    unsigned int mask);
+				    unsigned long mask);
 extern void task_clear_jobctl_trapping(struct task_struct *task);
 extern void task_clear_jobctl_pending(struct task_struct *task,
-				      unsigned int mask);
+				      unsigned long mask);
 
 static inline void rcu_copy_process(struct task_struct *p)
 {
@@ -2964,11 +3033,6 @@ static __always_inline bool need_resched(void)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
 void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
 
-static inline void thread_group_cputime_init(struct signal_struct *sig)
-{
-	raw_spin_lock_init(&sig->cputimer.lock);
-}
-
 /*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
@@ -3082,13 +3146,13 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 static inline unsigned long task_rlimit(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_cur);
 }
 
 static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
 		unsigned int limit)
 {
-	return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
+	return READ_ONCE(tsk->signal->rlim[limit].rlim_max);
 }
 
 static inline unsigned long rlimit(unsigned int limit)