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 are:

   - Various NUMA scheduling updates: harmonize the load-balancer and
     NUMA placement logic to not work against each other. The intended
     result is better locality, better utilization and fewer migrations.

   - Introduce Thermal Pressure tracking and optimizations, to improve
     task placement on thermally overloaded systems.

   - Implement frequency invariant scheduler accounting on (some) x86
     CPUs. This is done by observing and sampling the 'recent' CPU
     frequency average at ~tick boundaries. The CPU provides this data
     via the APERF/MPERF MSRs. This hopefully makes our capacity
     estimates more precise and keeps tasks on the same CPU better even
     if it might seem overloaded at a lower momentary frequency. (As
     usual, turbo mode is a complication that we resolve by observing
     the maximum frequency and renormalizing to it.)

   - Add asymmetric CPU capacity wakeup scan to improve capacity
     utilization on asymmetric topologies. (big.LITTLE systems)

   - PSI fixes and optimizations.

   - RT scheduling capacity awareness fixes & improvements.

   - Optimize the CONFIG_RT_GROUP_SCHED constraints code.

   - Misc fixes, cleanups and optimizations - see the changelog for
     details"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits)
  threads: Update PID limit comment according to futex UAPI change
  sched/fair: Fix condition of avg_load calculation
  sched/rt: cpupri_find: Trigger a full search as fallback
  kthread: Do not preempt current task if it is going to call schedule()
  sched/fair: Improve spreading of utilization
  sched: Avoid scale real weight down to zero
  psi: Move PF_MEMSTALL out of task->flags
  MAINTAINERS: Add maintenance information for psi
  psi: Optimize switching tasks inside shared cgroups
  psi: Fix cpu.pressure for cpu.max and competing cgroups
  sched/core: Distribute tasks within affinity masks
  sched/fair: Fix enqueue_task_fair warning
  thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code
  sched/rt: Remove unnecessary push for unfit tasks
  sched/rt: Allow pulling unfitting task
  sched/rt: Optimize cpupri_find() on non-heterogenous systems
  sched/rt: Re-instate old behavior in select_task_rq_rt()
  sched/rt: cpupri_find: Implement fallback mechanism for !fit case
  sched/fair: Fix reordering of enqueue/dequeue_task_fair()
  sched/fair: Fix runnable_avg for throttled cfs
  ...

10 files changed, 126 insertions, 40 deletions

diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index c507e9ddd909..8dd9aeb6cdeb 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -30,6 +30,16 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
+DECLARE_PER_CPU(unsigned long, thermal_pressure);
+
+static inline unsigned long topology_get_thermal_pressure(int cpu)
+{
+	return per_cpu(thermal_pressure, cpu);
+}
+
+void arch_set_thermal_pressure(struct cpumask *cpus,
+			       unsigned long th_pressure);
+
 struct cpu_topology {
 	int thread_id;
 	int core_id;
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index d5cc88514aee..f0d895d6ac39 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -194,6 +194,11 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node)
 	return 0;
 }
 
+static inline int cpumask_any_and_distribute(const struct cpumask *src1p,
+					     const struct cpumask *src2p) {
+	return cpumask_next_and(-1, src1p, src2p);
+}
+
 #define for_each_cpu(cpu, mask)			\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
 #define for_each_cpu_not(cpu, mask)		\
@@ -245,6 +250,8 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
 int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
 unsigned int cpumask_local_spread(unsigned int i, int node);
+int cpumask_any_and_distribute(const struct cpumask *src1p,
+			       const struct cpumask *src2p);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 0d9db2a14f44..9b7a8d74a9d6 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -257,6 +257,13 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
 
+#ifndef CONFIG_PREEMPT_RT
+# define cant_migrate()		cant_sleep()
+#else
+  /* Placeholder for now */
+# define cant_migrate()		do { } while (0)
+#endif
+
 /**
  * abs - return absolute value of an argument
  * @x: the value.  If it is unsigned type, it is converted to signed type first.
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index bbb68dba37cc..bc3f1aecaa19 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -322,4 +322,34 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 
 #endif
 
+/**
+ * migrate_disable - Prevent migration of the current task
+ *
+ * Maps to preempt_disable() which also disables preemption. Use
+ * migrate_disable() to annotate that the intent is to prevent migration,
+ * but not necessarily preemption.
+ *
+ * Can be invoked nested like preempt_disable() and needs the corresponding
+ * number of migrate_enable() invocations.
+ */
+static __always_inline void migrate_disable(void)
+{
+	preempt_disable();
+}
+
+/**
+ * migrate_enable - Allow migration of the current task
+ *
+ * Counterpart to migrate_disable().
+ *
+ * As migrate_disable() can be invoked nested, only the outermost invocation
+ * reenables migration.
+ *
+ * Currently mapped to preempt_enable().
+ */
+static __always_inline void migrate_enable(void)
+{
+	preempt_enable();
+}
+
 #endif /* __LINUX_PREEMPT_H */
diff --git a/include/linux/psi.h b/include/linux/psi.h
index 7b3de7321219..7361023f3fdd 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -17,6 +17,8 @@ extern struct psi_group psi_system;
 void psi_init(void);
 
 void psi_task_change(struct task_struct *task, int clear, int set);
+void psi_task_switch(struct task_struct *prev, struct task_struct *next,
+		     bool sleep);
 
 void psi_memstall_tick(struct task_struct *task, int cpu);
 void psi_memstall_enter(unsigned long *flags);
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 07aaf9b82241..4b7258495a04 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -14,13 +14,21 @@ enum psi_task_count {
 	NR_IOWAIT,
 	NR_MEMSTALL,
 	NR_RUNNING,
-	NR_PSI_TASK_COUNTS = 3,
+	/*
+	 * This can't have values other than 0 or 1 and could be
+	 * implemented as a bit flag. But for now we still have room
+	 * in the first cacheline of psi_group_cpu, and this way we
+	 * don't have to special case any state tracking for it.
+	 */
+	NR_ONCPU,
+	NR_PSI_TASK_COUNTS = 4,
 };
 
 /* Task state bitmasks */
 #define TSK_IOWAIT	(1 << NR_IOWAIT)
 #define TSK_MEMSTALL	(1 << NR_MEMSTALL)
 #define TSK_RUNNING	(1 << NR_RUNNING)
+#define TSK_ONCPU	(1 << NR_ONCPU)
 
 /* Resources that workloads could be stalled on */
 enum psi_res {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 933914cdf219..5d0d2fc018e9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -356,28 +356,30 @@ struct util_est {
 } __attribute__((__aligned__(sizeof(u64))));
 
 /*
- * The load_avg/util_avg accumulates an infinite geometric series
- * (see __update_load_avg() in kernel/sched/fair.c).
+ * The load/runnable/util_avg accumulates an infinite geometric series
+ * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c).
  *
  * [load_avg definition]
  *
  *   load_avg = runnable% * scale_load_down(load)
  *
- * where runnable% is the time ratio that a sched_entity is runnable.
- * For cfs_rq, it is the aggregated load_avg of all runnable and
- * blocked sched_entities.
+ * [runnable_avg definition]
+ *
+ *   runnable_avg = runnable% * SCHED_CAPACITY_SCALE
  *
  * [util_avg definition]
  *
  *   util_avg = running% * SCHED_CAPACITY_SCALE
  *
- * where running% is the time ratio that a sched_entity is running on
- * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
- * and blocked sched_entities.
+ * where runnable% is the time ratio that a sched_entity is runnable and
+ * running% the time ratio that a sched_entity is running.
+ *
+ * For cfs_rq, they are the aggregated values of all runnable and blocked
+ * sched_entities.
  *
- * load_avg and util_avg don't direcly factor frequency scaling and CPU
- * capacity scaling. The scaling is done through the rq_clock_pelt that
- * is used for computing those signals (see update_rq_clock_pelt())
+ * The load/runnable/util_avg doesn't direcly factor frequency scaling and CPU
+ * capacity scaling. The scaling is done through the rq_clock_pelt that is used
+ * for computing those signals (see update_rq_clock_pelt())
  *
  * N.B., the above ratios (runnable% and running%) themselves are in the
  * range of [0, 1]. To do fixed point arithmetics, we therefore scale them
@@ -401,11 +403,11 @@ struct util_est {
 struct sched_avg {
 	u64				last_update_time;
 	u64				load_sum;
-	u64				runnable_load_sum;
+	u64				runnable_sum;
 	u32				util_sum;
 	u32				period_contrib;
 	unsigned long			load_avg;
-	unsigned long			runnable_load_avg;
+	unsigned long			runnable_avg;
 	unsigned long			util_avg;
 	struct util_est			util_est;
 } ____cacheline_aligned;
@@ -449,7 +451,6 @@ struct sched_statistics {
 struct sched_entity {
 	/* For load-balancing: */
 	struct load_weight		load;
-	unsigned long			runnable_weight;
 	struct rb_node			run_node;
 	struct list_head		group_node;
 	unsigned int			on_rq;
@@ -470,6 +471,8 @@ struct sched_entity {
 	struct cfs_rq			*cfs_rq;
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq			*my_q;
+	/* cached value of my_q->h_nr_running */
+	unsigned long			runnable_weight;
 #endif
 
 #ifdef CONFIG_SMP
@@ -782,9 +785,12 @@ struct task_struct {
 	unsigned			frozen:1;
 #endif
 #ifdef CONFIG_BLK_CGROUP
-	/* to be used once the psi infrastructure lands upstream. */
 	unsigned			use_memdelay:1;
 #endif
+#ifdef CONFIG_PSI
+	/* Stalled due to lack of memory */
+	unsigned			in_memstall:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -1479,7 +1485,6 @@ extern struct pid *cad_pid;
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
-#define PF_MEMSTALL		0x01000000	/* Stalled due to lack of memory */
 #define PF_UMH			0x02000000	/* I'm an Usermodehelper process */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index f341163fedc9..af9319e4cfb9 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -225,6 +225,14 @@ unsigned long arch_scale_cpu_capacity(int cpu)
 }
 #endif
 
+#ifndef arch_scale_thermal_pressure
+static __always_inline
+unsigned long arch_scale_thermal_pressure(int cpu)
+{
+	return 0;
+}
+#endif
+
 static inline int task_node(const struct task_struct *p)
 {
 	return cpu_to_node(task_cpu(p));
diff --git a/include/linux/threads.h b/include/linux/threads.h
index 3086dba525e2..18d5a74bcc3d 100644
--- a/include/linux/threads.h
+++ b/include/linux/threads.h
@@ -29,7 +29,7 @@
 
 /*
  * A maximum of 4 million PIDs should be enough for a while.
- * [NOTE: PID/TIDs are limited to 2^29 ~= 500+ million, see futex.h.]
+ * [NOTE: PID/TIDs are limited to 2^30 ~= 1 billion, see FUTEX_TID_MASK.]
  */
 #define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \
 	(sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT))
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 420e80e56e55..ed168b0e2c53 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -487,7 +487,11 @@ TRACE_EVENT(sched_process_hang,
 );
 #endif /* CONFIG_DETECT_HUNG_TASK */
 
-DECLARE_EVENT_CLASS(sched_move_task_template,
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes.
+ */
+TRACE_EVENT(sched_move_numa,
 
 	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
 
@@ -519,23 +523,7 @@ DECLARE_EVENT_CLASS(sched_move_task_template,
 			__entry->dst_cpu, __entry->dst_nid)
 );
 
-/*
- * Tracks migration of tasks from one runqueue to another. Can be used to
- * detect if automatic NUMA balancing is bouncing between nodes
- */
-DEFINE_EVENT(sched_move_task_template, sched_move_numa,
-	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
-
-	TP_ARGS(tsk, src_cpu, dst_cpu)
-);
-
-DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
-	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
-
-	TP_ARGS(tsk, src_cpu, dst_cpu)
-);
-
-TRACE_EVENT(sched_swap_numa,
+DECLARE_EVENT_CLASS(sched_numa_pair_template,
 
 	TP_PROTO(struct task_struct *src_tsk, int src_cpu,
 		 struct task_struct *dst_tsk, int dst_cpu),
@@ -561,11 +549,11 @@ TRACE_EVENT(sched_swap_numa,
 		__entry->src_ngid	= task_numa_group_id(src_tsk);
 		__entry->src_cpu	= src_cpu;
 		__entry->src_nid	= cpu_to_node(src_cpu);
-		__entry->dst_pid	= task_pid_nr(dst_tsk);
-		__entry->dst_tgid	= task_tgid_nr(dst_tsk);
-		__entry->dst_ngid	= task_numa_group_id(dst_tsk);
+		__entry->dst_pid	= dst_tsk ? task_pid_nr(dst_tsk) : 0;
+		__entry->dst_tgid	= dst_tsk ? task_tgid_nr(dst_tsk) : 0;
+		__entry->dst_ngid	= dst_tsk ? task_numa_group_id(dst_tsk) : 0;
 		__entry->dst_cpu	= dst_cpu;
-		__entry->dst_nid	= cpu_to_node(dst_cpu);
+		__entry->dst_nid	= dst_cpu >= 0 ? cpu_to_node(dst_cpu) : -1;
 	),
 
 	TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
@@ -575,6 +563,23 @@ TRACE_EVENT(sched_swap_numa,
 			__entry->dst_cpu, __entry->dst_nid)
 );
 
+DEFINE_EVENT(sched_numa_pair_template, sched_stick_numa,
+
+	TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+		 struct task_struct *dst_tsk, int dst_cpu),
+
+	TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu)
+);
+
+DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa,
+
+	TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+		 struct task_struct *dst_tsk, int dst_cpu),
+
+	TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu)
+);
+
+
 /*
  * Tracepoint for waking a polling cpu without an IPI.
  */
@@ -613,6 +618,10 @@ DECLARE_TRACE(pelt_dl_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));
 
+DECLARE_TRACE(pelt_thermal_tp,
+	TP_PROTO(struct rq *rq),
+	TP_ARGS(rq));
+
 DECLARE_TRACE(pelt_irq_tp,
 	TP_PROTO(struct rq *rq),
 	TP_ARGS(rq));