Merge tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Cleanups for SCHED_DEADLINE

 - Tracing updates/fixes

 - CPU Accounting fixes

 - First wave of changes to optimize the overhead of the scheduler
   build, from the fast-headers tree - including placeholder *_api.h
   headers for later header split-ups.

 - Preempt-dynamic using static_branch() for ARM64

 - Isolation housekeeping mask rework; preperatory for further changes

 - NUMA-balancing: deal with CPU-less nodes

 - NUMA-balancing: tune systems that have multiple LLC cache domains per
   node (eg. AMD)

 - Updates to RSEQ UAPI in preparation for glibc usage

 - Lots of RSEQ/selftests, for same

 - Add Suren as PSI co-maintainer

* tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
  sched/headers: ARM needs asm/paravirt_api_clock.h too
  sched/numa: Fix boot crash on arm64 systems
  headers/prep: Fix header to build standalone: <linux/psi.h>
  sched/headers: Only include <linux/entry-common.h> when CONFIG_GENERIC_ENTRY=y
  cgroup: Fix suspicious rcu_dereference_check() usage warning
  sched/preempt: Tell about PREEMPT_DYNAMIC on kernel headers
  sched/topology: Remove redundant variable and fix incorrect type in build_sched_domains
  sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity()
  sched/deadline,rt: Remove unused functions for !CONFIG_SMP
  sched/deadline: Use __node_2_[pdl|dle]() and rb_first_cached() consistently
  sched/deadline: Merge dl_task_can_attach() and dl_cpu_busy()
  sched/deadline: Move bandwidth mgmt and reclaim functions into sched class source file
  sched/deadline: Remove unused def_dl_bandwidth
  sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE
  sched/tracing: Don't re-read p->state when emitting sched_switch event
  sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race
  sched/cpuacct: Remove redundant RCU read lock
  sched/cpuacct: Optimize away RCU read lock
  sched/cpuacct: Fix charge percpu cpuusage
  sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies
  ...

10 files changed, 31 insertions, 25 deletions

diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/affinity.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/cond_resched.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 1aff00b65f3c..7c83d4d5a971 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -6,6 +6,8 @@
  * NORMAL/BATCH tasks.
  */
 
+#include <linux/sched.h>
+
 #define MAX_DL_PRIO		0
 
 static inline int dl_prio(int prio)
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index cc9f393e2a70..8c15abd67aed 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -5,54 +5,55 @@
 #include <linux/init.h>
 #include <linux/tick.h>
 
-enum hk_flags {
-	HK_FLAG_TIMER		= 1,
-	HK_FLAG_RCU		= (1 << 1),
-	HK_FLAG_MISC		= (1 << 2),
-	HK_FLAG_SCHED		= (1 << 3),
-	HK_FLAG_TICK		= (1 << 4),
-	HK_FLAG_DOMAIN		= (1 << 5),
-	HK_FLAG_WQ		= (1 << 6),
-	HK_FLAG_MANAGED_IRQ	= (1 << 7),
-	HK_FLAG_KTHREAD		= (1 << 8),
+enum hk_type {
+	HK_TYPE_TIMER,
+	HK_TYPE_RCU,
+	HK_TYPE_MISC,
+	HK_TYPE_SCHED,
+	HK_TYPE_TICK,
+	HK_TYPE_DOMAIN,
+	HK_TYPE_WQ,
+	HK_TYPE_MANAGED_IRQ,
+	HK_TYPE_KTHREAD,
+	HK_TYPE_MAX
 };
 
 #ifdef CONFIG_CPU_ISOLATION
 DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);
-extern int housekeeping_any_cpu(enum hk_flags flags);
-extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
-extern bool housekeeping_enabled(enum hk_flags flags);
-extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
-extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
+extern int housekeeping_any_cpu(enum hk_type type);
+extern const struct cpumask *housekeeping_cpumask(enum hk_type type);
+extern bool housekeeping_enabled(enum hk_type type);
+extern void housekeeping_affine(struct task_struct *t, enum hk_type type);
+extern bool housekeeping_test_cpu(int cpu, enum hk_type type);
 extern void __init housekeeping_init(void);
 
 #else
 
-static inline int housekeeping_any_cpu(enum hk_flags flags)
+static inline int housekeeping_any_cpu(enum hk_type type)
 {
 	return smp_processor_id();
 }
 
-static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+static inline const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
 	return cpu_possible_mask;
 }
 
-static inline bool housekeeping_enabled(enum hk_flags flags)
+static inline bool housekeeping_enabled(enum hk_type type)
 {
 	return false;
 }
 
 static inline void housekeeping_affine(struct task_struct *t,
-				       enum hk_flags flags) { }
+				       enum hk_type type) { }
 static inline void housekeeping_init(void) { }
 #endif /* CONFIG_CPU_ISOLATION */
 
-static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
+static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 {
 #ifdef CONFIG_CPU_ISOLATION
 	if (static_branch_unlikely(&housekeeping_overridden))
-		return housekeeping_test_cpu(cpu, flags);
+		return housekeeping_test_cpu(cpu, type);
 #endif
 	return true;
 }
diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h
new file mode 100644
index 000000000000..523a381d6c88
--- /dev/null
+++ b/include/linux/sched/posix-timers.h
@@ -0,0 +1 @@
+#include <linux/posix-timers.h>
diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h
new file mode 100644
index 000000000000..cf2af72693e1
--- /dev/null
+++ b/include/linux/sched/rseq_api.h
@@ -0,0 +1 @@
+#include <linux/rseq.h>
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index c19dd5a2c05c..3f2b70f8d32c 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -45,10 +45,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default;
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
 
-#ifdef CONFIG_SCHED_AUTOGROUP
-extern unsigned int sysctl_sched_autogroup_enabled;
-#endif
-
 extern int sysctl_sched_rr_timeslice;
 extern int sched_rr_timeslice;
 
diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h
new file mode 100644
index 000000000000..227f5be81bcd
--- /dev/null
+++ b/include/linux/sched/task_flags.h
@@ -0,0 +1 @@
+#include <linux/sched.h>
diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h
new file mode 100644
index 000000000000..2c60fbc16c08
--- /dev/null
+++ b/include/linux/sched/thread_info_api.h
@@ -0,0 +1 @@
+#include <linux/thread_info.h>
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 8054641c0a7b..56cffe42abbc 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -93,6 +93,7 @@ struct sched_domain {
 	unsigned int busy_factor;	/* less balancing by factor if busy */
 	unsigned int imbalance_pct;	/* No balance until over watermark */
 	unsigned int cache_nice_tries;	/* Leave cache hot tasks for # tries */
+	unsigned int imb_numa_nr;	/* Nr running tasks that allows a NUMA imbalance */
 
 	int nohz_idle;			/* NOHZ IDLE status */
 	int flags;			/* See SD_* */