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

Pull scheduler changes from Ingo Molnar:
 "Bigger changes:

   - sched/idle restructuring: they are WIP preparation for deeper
     integration between the scheduler and idle state selection, by
     Nicolas Pitre.

   - add NUMA scheduling pseudo-interleaving, by Rik van Riel.

   - optimize cgroup context switches, by Peter Zijlstra.

   - RT scheduling enhancements, by Thomas Gleixner.

  The rest is smaller changes, non-urgnt fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (68 commits)
  sched: Clean up the task_hot() function
  sched: Remove double calculation in fix_small_imbalance()
  sched: Fix broken setscheduler()
  sparc64, sched: Remove unused sparc64_multi_core
  sched: Remove unused mc_capable() and smt_capable()
  sched/numa: Move task_numa_free() to __put_task_struct()
  sched/fair: Fix endless loop in idle_balance()
  sched/core: Fix endless loop in pick_next_task()
  sched/fair: Push down check for high priority class task into idle_balance()
  sched/rt: Fix picking RT and DL tasks from empty queue
  trace: Replace hardcoding of 19 with MAX_NICE
  sched: Guarantee task priority in pick_next_task()
  sched/idle: Remove stale old file
  sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED
  cpuidle/arm64: Remove redundant cpuidle_idle_call()
  cpuidle/powernv: Remove redundant cpuidle_idle_call()
  sched, nohz: Exclude isolated cores from load balancing
  sched: Fix select_task_rq_fair() description comments
  workqueue: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  sys: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  ...

3 files changed, 88 insertions, 26 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index a781dec1cd0b..825ed838d4b9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -3,6 +3,8 @@
 
 #include <uapi/linux/sched.h>
 
+#include <linux/sched/prio.h>
+
 
 struct sched_param {
 	int sched_priority;
@@ -1077,6 +1079,7 @@ struct sched_entity {
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+	int			depth;
 	struct sched_entity	*parent;
 	/* rq on which this entity is (to be) queued: */
 	struct cfs_rq		*cfs_rq;
@@ -1460,6 +1463,9 @@ struct task_struct {
 	struct mutex perf_event_mutex;
 	struct list_head perf_event_list;
 #endif
+#ifdef CONFIG_DEBUG_PREEMPT
+	unsigned long preempt_disable_ip;
+#endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
 	short il_next;
@@ -1470,9 +1476,10 @@ struct task_struct {
 	unsigned int numa_scan_period;
 	unsigned int numa_scan_period_max;
 	int numa_preferred_nid;
-	int numa_migrate_deferred;
 	unsigned long numa_migrate_retry;
 	u64 node_stamp;			/* migration stamp  */
+	u64 last_task_numa_placement;
+	u64 last_sum_exec_runtime;
 	struct callback_head numa_work;
 
 	struct list_head numa_entry;
@@ -1483,15 +1490,22 @@ struct task_struct {
 	 * Scheduling placement decisions are made based on the these counts.
 	 * The values remain static for the duration of a PTE scan
 	 */
-	unsigned long *numa_faults;
+	unsigned long *numa_faults_memory;
 	unsigned long total_numa_faults;
 
 	/*
 	 * numa_faults_buffer records faults per node during the current
-	 * scan window. When the scan completes, the counts in numa_faults
-	 * decay and these values are copied.
+	 * scan window. When the scan completes, the counts in
+	 * numa_faults_memory decay and these values are copied.
+	 */
+	unsigned long *numa_faults_buffer_memory;
+
+	/*
+	 * Track the nodes the process was running on when a NUMA hinting
+	 * fault was incurred.
 	 */
-	unsigned long *numa_faults_buffer;
+	unsigned long *numa_faults_cpu;
+	unsigned long *numa_faults_buffer_cpu;
 
 	/*
 	 * numa_faults_locality tracks if faults recorded during the last
@@ -1596,8 +1610,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
 extern void set_numabalancing_state(bool enabled);
 extern void task_numa_free(struct task_struct *p);
-
-extern unsigned int sysctl_numa_balancing_migrate_deferred;
+extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
+					int src_nid, int dst_cpu);
 #else
 static inline void task_numa_fault(int last_node, int node, int pages,
 				   int flags)
@@ -1613,6 +1627,11 @@ static inline void set_numabalancing_state(bool enabled)
 static inline void task_numa_free(struct task_struct *p)
 {
 }
+static inline bool should_numa_migrate_memory(struct task_struct *p,
+				struct page *page, int src_nid, int dst_cpu)
+{
+	return true;
+}
 #endif
 
 static inline struct pid *task_pid(struct task_struct *task)
@@ -2080,7 +2099,16 @@ static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
-extern int task_nice(const struct task_struct *p);
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ *
+ * Return: The nice value [ -20 ... 0 ... 19 ].
+ */
+static inline int task_nice(const struct task_struct *p)
+{
+	return PRIO_TO_NICE((p)->static_prio);
+}
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
new file mode 100644
index 000000000000..ac322583c820
--- /dev/null
+++ b/include/linux/sched/prio.h
@@ -0,0 +1,44 @@
+#ifndef _SCHED_PRIO_H
+#define _SCHED_PRIO_H
+
+#define MAX_NICE	19
+#define MIN_NICE	-20
+#define NICE_WIDTH	(MAX_NICE - MIN_NICE + 1)
+
+/*
+ * Priority of a process goes from 0..MAX_PRIO-1, valid RT
+ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
+ * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
+ * values are inverted: lower p->prio value means higher priority.
+ *
+ * The MAX_USER_RT_PRIO value allows the actual maximum
+ * RT priority to be separate from the value exported to
+ * user-space.  This allows kernel threads to set their
+ * priority to a value higher than any user task. Note:
+ * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ */
+
+#define MAX_USER_RT_PRIO	100
+#define MAX_RT_PRIO		MAX_USER_RT_PRIO
+
+#define MAX_PRIO		(MAX_RT_PRIO + NICE_WIDTH)
+#define DEFAULT_PRIO		(MAX_RT_PRIO + NICE_WIDTH / 2)
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+ * and back.
+ */
+#define NICE_TO_PRIO(nice)	((nice) + DEFAULT_PRIO)
+#define PRIO_TO_NICE(prio)	((prio) - DEFAULT_PRIO)
+
+/*
+ * 'User priority' is the nice value converted to something we
+ * can work with better when scaling various scheduler parameters,
+ * it's a [ 0 ... 39 ] range.
+ */
+#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
+#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
+#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
+
+#endif /* _SCHED_PRIO_H */
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 34e4ebea8fce..6341f5be6e24 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -1,24 +1,7 @@
 #ifndef _SCHED_RT_H
 #define _SCHED_RT_H
 
-/*
- * Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
- * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
- * values are inverted: lower p->prio value means higher priority.
- *
- * The MAX_USER_RT_PRIO value allows the actual maximum
- * RT priority to be separate from the value exported to
- * user-space.  This allows kernel threads to set their
- * priority to a value higher than any user task. Note:
- * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
- */
-
-#define MAX_USER_RT_PRIO	100
-#define MAX_RT_PRIO		MAX_USER_RT_PRIO
-
-#define MAX_PRIO		(MAX_RT_PRIO + 40)
-#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
+#include <linux/sched/prio.h>
 
 static inline int rt_prio(int prio)
 {
@@ -35,6 +18,7 @@ static inline int rt_task(struct task_struct *p)
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
+extern int rt_mutex_check_prio(struct task_struct *task, int newprio);
 extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
@@ -46,6 +30,12 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 {
 	return p->normal_prio;
 }
+
+static inline int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+	return 0;
+}
+
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;