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

Pull scheduler updates from Ingo Molnar:
 "The main scheduling related changes in this cycle were:

   - various sched/numa updates, for better performance

   - tree wide cleanup of open coded nice levels

   - nohz fix related to rq->nr_running use

   - cpuidle changes and continued consolidation to improve the
     kernel/sched/idle.c high level idle scheduling logic.  As part of
     this effort I pulled cpuidle driver changes from Rafael as well.

   - standardized idle polling amongst architectures

   - continued work on preparing better power/energy aware scheduling

   - sched/rt updates

   - misc fixlets and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  sched/numa: Decay ->wakee_flips instead of zeroing
  sched/numa: Update migrate_improves/degrades_locality()
  sched/numa: Allow task switch if load imbalance improves
  sched/rt: Fix 'struct sched_dl_entity' and dl_task_time() comments, to match the current upstream code
  sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice()
  sched: Initialize rq->age_stamp on processor start
  sched, nohz: Change rq->nr_running to always use wrappers
  sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance()
  sched: Use clamp() and clamp_val() to make sys_nice() more readable
  sched: Do not zero sg->cpumask and sg->sgp->power in build_sched_groups()
  sched/numa: Fix initialization of sched_domain_topology for NUMA
  sched: Call select_idle_sibling() when not affine_sd
  sched: Simplify return logic in sched_read_attr()
  sched: Simplify return logic in sched_copy_attr()
  sched: Fix exec_start/task_hot on migrated tasks
  arm64: Remove TIF_POLLING_NRFLAG
  metag: Remove TIF_POLLING_NRFLAG
  sched/idle: Make cpuidle_idle_call() void
  sched/idle: Reflow cpuidle_idle_call()
  sched/idle: Delay clearing the polling bit
  ...

5 files changed, 88 insertions, 181 deletions

diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index b0238cba440b..c51a436135c4 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -120,8 +120,6 @@ struct cpuidle_driver {
 #ifdef CONFIG_CPU_IDLE
 extern void disable_cpuidle(void);
 
-extern int cpuidle_enabled(struct cpuidle_driver *drv,
-			  struct cpuidle_device *dev);
 extern int cpuidle_select(struct cpuidle_driver *drv,
 			  struct cpuidle_device *dev);
 extern int cpuidle_enter(struct cpuidle_driver *drv,
@@ -145,13 +143,11 @@ extern void cpuidle_resume(void);
 extern int cpuidle_enable_device(struct cpuidle_device *dev);
 extern void cpuidle_disable_device(struct cpuidle_device *dev);
 extern int cpuidle_play_dead(void);
+extern void cpuidle_use_deepest_state(bool enable);
 
 extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev);
 #else
 static inline void disable_cpuidle(void) { }
-static inline int cpuidle_enabled(struct cpuidle_driver *drv,
-				  struct cpuidle_device *dev)
-{return -ENODEV; }
 static inline int cpuidle_select(struct cpuidle_driver *drv,
 				 struct cpuidle_device *dev)
 {return -ENODEV; }
@@ -180,6 +176,7 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev)
 {return -ENODEV; }
 static inline void cpuidle_disable_device(struct cpuidle_device *dev) { }
 static inline int cpuidle_play_dead(void) {return -ENODEV; }
+static inline void cpuidle_use_deepest_state(bool enable) {}
 static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
 	struct cpuidle_device *dev) {return NULL; }
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4dce5d844b74..70f67e4e6156 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -870,6 +870,7 @@ enum cpu_idle_type {
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
 #define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
+#define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
 #define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
@@ -877,7 +878,26 @@ enum cpu_idle_type {
 #define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
 #define SD_NUMA			0x4000	/* cross-node balancing */
 
-extern int __weak arch_sd_sibiling_asym_packing(void);
+#ifdef CONFIG_SCHED_SMT
+static inline const int cpu_smt_flags(void)
+{
+	return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+static inline const int cpu_core_flags(void)
+{
+	return SD_SHARE_PKG_RESOURCES;
+}
+#endif
+
+#ifdef CONFIG_NUMA
+static inline const int cpu_numa_flags(void)
+{
+	return SD_NUMA;
+}
+#endif
 
 struct sched_domain_attr {
 	int relax_domain_level;
@@ -985,6 +1005,38 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
 bool cpus_share_cache(int this_cpu, int that_cpu);
 
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
+typedef const int (*sched_domain_flags_f)(void);
+
+#define SDTL_OVERLAP	0x01
+
+struct sd_data {
+	struct sched_domain **__percpu sd;
+	struct sched_group **__percpu sg;
+	struct sched_group_power **__percpu sgp;
+};
+
+struct sched_domain_topology_level {
+	sched_domain_mask_f mask;
+	sched_domain_flags_f sd_flags;
+	int		    flags;
+	int		    numa_level;
+	struct sd_data      data;
+#ifdef CONFIG_SCHED_DEBUG
+	char                *name;
+#endif
+};
+
+extern struct sched_domain_topology_level *sched_domain_topology;
+
+extern void set_sched_topology(struct sched_domain_topology_level *tl);
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(type)		.name = #type
+#else
+# define SD_INIT_NAME(type)
+#endif
+
 #else /* CONFIG_SMP */
 
 struct sched_domain_attr;
@@ -1123,8 +1175,8 @@ struct sched_dl_entity {
 
 	/*
 	 * Original scheduling parameters. Copied here from sched_attr
-	 * during sched_setscheduler2(), they will remain the same until
-	 * the next sched_setscheduler2().
+	 * during sched_setattr(), they will remain the same until
+	 * the next sched_setattr().
 	 */
 	u64 dl_runtime;		/* maximum runtime for each instance	*/
 	u64 dl_deadline;	/* relative deadline of each instance	*/
@@ -2723,51 +2775,9 @@ static inline int spin_needbreak(spinlock_t *lock)
 
 /*
  * Idle thread specific functions to determine the need_resched
- * polling state. We have two versions, one based on TS_POLLING in
- * thread_info.status and one based on TIF_POLLING_NRFLAG in
- * thread_info.flags
+ * polling state.
  */
-#ifdef TS_POLLING
-static inline int tsk_is_polling(struct task_struct *p)
-{
-	return task_thread_info(p)->status & TS_POLLING;
-}
-static inline void __current_set_polling(void)
-{
-	current_thread_info()->status |= TS_POLLING;
-}
-
-static inline bool __must_check current_set_polling_and_test(void)
-{
-	__current_set_polling();
-
-	/*
-	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_task()
-	 */
-	smp_mb();
-
-	return unlikely(tif_need_resched());
-}
-
-static inline void __current_clr_polling(void)
-{
-	current_thread_info()->status &= ~TS_POLLING;
-}
-
-static inline bool __must_check current_clr_polling_and_test(void)
-{
-	__current_clr_polling();
-
-	/*
-	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_task()
-	 */
-	smp_mb();
-
-	return unlikely(tif_need_resched());
-}
-#elif defined(TIF_POLLING_NRFLAG)
+#ifdef TIF_POLLING_NRFLAG
 static inline int tsk_is_polling(struct task_struct *p)
 {
 	return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
index ac322583c820..d9cf5a5762d9 100644
--- a/include/linux/sched/prio.h
+++ b/include/linux/sched/prio.h
@@ -41,4 +41,20 @@
 #define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
 #define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
 
+/*
+ * Convert nice value [19,-20] to rlimit style value [1,40].
+ */
+static inline long nice_to_rlimit(long nice)
+{
+	return (MAX_NICE - nice + 1);
+}
+
+/*
+ * Convert rlimit style value [1,40] to nice value [-20, 19].
+ */
+static inline long rlimit_to_nice(long prio)
+{
+	return (MAX_NICE - prio + 1);
+}
+
 #endif /* _SCHED_PRIO_H */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index fddbe2023a5d..cb0cec94fda3 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -104,20 +104,6 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define test_thread_flag(flag) \
 	test_ti_thread_flag(current_thread_info(), flag)
 
-static inline __deprecated void set_need_resched(void)
-{
-	/*
-	 * Use of this function in deprecated.
-	 *
-	 * As of this writing there are only a few users in the DRM tree left
-	 * all of which are wrong and can be removed without causing too much
-	 * grief.
-	 *
-	 * The DRM people are aware and are working on removing the last few
-	 * instances.
-	 */
-}
-
 #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
 
 #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 7062330a1329..973671ff9e7d 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -66,121 +66,6 @@ int arch_update_cpu_topology(void);
 #define PENALTY_FOR_NODE_WITH_CPUS	(1)
 #endif
 
-/*
- * Below are the 3 major initializers used in building sched_domains:
- * SD_SIBLING_INIT, for SMT domains
- * SD_CPU_INIT, for SMP domains
- *
- * Any architecture that cares to do any tuning to these values should do so
- * by defining their own arch-specific initializer in include/asm/topology.h.
- * A definition there will automagically override these default initializers
- * and allow arch-specific performance tuning of sched_domains.
- * (Only non-zero and non-null fields need be specified.)
- */
-
-#ifdef CONFIG_SCHED_SMT
-/* MCD - Do we really need this?  It is always on if CONFIG_SCHED_SMT is,
- * so can't we drop this in favor of CONFIG_SCHED_SMT?
- */
-#define ARCH_HAS_SCHED_WAKE_IDLE
-/* Common values for SMT siblings */
-#ifndef SD_SIBLING_INIT
-#define SD_SIBLING_INIT (struct sched_domain) {				\
-	.min_interval		= 1,					\
-	.max_interval		= 2,					\
-	.busy_factor		= 64,					\
-	.imbalance_pct		= 110,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 1*SD_SHARE_CPUPOWER			\
-				| 1*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				| 0*SD_PREFER_SIBLING			\
-				| arch_sd_sibling_asym_packing()	\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-	.smt_gain		= 1178,	/* 15% */			\
-	.max_newidle_lb_cost	= 0,					\
-	.next_decay_max_lb_cost	= jiffies,				\
-}
-#endif
-#endif /* CONFIG_SCHED_SMT */
-
-#ifdef CONFIG_SCHED_MC
-/* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */
-#ifndef SD_MC_INIT
-#define SD_MC_INIT (struct sched_domain) {				\
-	.min_interval		= 1,					\
-	.max_interval		= 4,					\
-	.busy_factor		= 64,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 2,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 1*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-	.max_newidle_lb_cost	= 0,					\
-	.next_decay_max_lb_cost	= jiffies,				\
-}
-#endif
-#endif /* CONFIG_SCHED_MC */
-
-/* Common values for CPUs */
-#ifndef SD_CPU_INIT
-#define SD_CPU_INIT (struct sched_domain) {				\
-	.min_interval		= 1,					\
-	.max_interval		= 4,					\
-	.busy_factor		= 64,					\
-	.imbalance_pct		= 125,					\
-	.cache_nice_tries	= 1,					\
-	.busy_idx		= 2,					\
-	.idle_idx		= 1,					\
-	.newidle_idx		= 0,					\
-	.wake_idx		= 0,					\
-	.forkexec_idx		= 0,					\
-									\
-	.flags			= 1*SD_LOAD_BALANCE			\
-				| 1*SD_BALANCE_NEWIDLE			\
-				| 1*SD_BALANCE_EXEC			\
-				| 1*SD_BALANCE_FORK			\
-				| 0*SD_BALANCE_WAKE			\
-				| 1*SD_WAKE_AFFINE			\
-				| 0*SD_SHARE_CPUPOWER			\
-				| 0*SD_SHARE_PKG_RESOURCES		\
-				| 0*SD_SERIALIZE			\
-				| 1*SD_PREFER_SIBLING			\
-				,					\
-	.last_balance		= jiffies,				\
-	.balance_interval	= 1,					\
-	.max_newidle_lb_cost	= 0,					\
-	.next_decay_max_lb_cost	= jiffies,				\
-}
-#endif
-
-#ifdef CONFIG_SCHED_BOOK
-#ifndef SD_BOOK_INIT
-#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
-#endif
-#endif /* CONFIG_SCHED_BOOK */
-
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DECLARE_PER_CPU(int, numa_node);
 
@@ -295,4 +180,17 @@ static inline int cpu_to_mem(int cpu)
 #define topology_core_cpumask(cpu)		cpumask_of(cpu)
 #endif
 
+#ifdef CONFIG_SCHED_SMT
+static inline const struct cpumask *cpu_smt_mask(int cpu)
+{
+	return topology_thread_cpumask(cpu);
+}
+#endif
+
+static inline const struct cpumask *cpu_cpu_mask(int cpu)
+{
+	return cpumask_of_node(cpu_to_node(cpu));
+}
+
+
 #endif /* _LINUX_TOPOLOGY_H */