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
  ...

1 files changed, 33 insertions, 4 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index cabfac22f2fb..17709ac1030a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1293,12 +1293,41 @@ config HAVE_STATIC_CALL_INLINE
 
 config HAVE_PREEMPT_DYNAMIC
 	bool
+
+config HAVE_PREEMPT_DYNAMIC_CALL
+	bool
 	depends on HAVE_STATIC_CALL
-	depends on GENERIC_ENTRY
+	select HAVE_PREEMPT_DYNAMIC
+	help
+	   An architecture should select this if it can handle the preemption
+	   model being selected at boot time using static calls.
+
+	   Where an architecture selects HAVE_STATIC_CALL_INLINE, any call to a
+	   preemption function will be patched directly.
+
+	   Where an architecture does not select HAVE_STATIC_CALL_INLINE, any
+	   call to a preemption function will go through a trampoline, and the
+	   trampoline will be patched.
+
+	   It is strongly advised to support inline static call to avoid any
+	   overhead.
+
+config HAVE_PREEMPT_DYNAMIC_KEY
+	bool
+	depends on HAVE_ARCH_JUMP_LABEL && CC_HAS_ASM_GOTO
+	select HAVE_PREEMPT_DYNAMIC
 	help
-	   Select this if the architecture support boot time preempt setting
-	   on top of static calls. It is strongly advised to support inline
-	   static call to avoid any overhead.
+	   An architecture should select this if it can handle the preemption
+	   model being selected at boot time using static keys.
+
+	   Each preemption function will be given an early return based on a
+	   static key. This should have slightly lower overhead than non-inline
+	   static calls, as this effectively inlines each trampoline into the
+	   start of its callee. This may avoid redundant work, and may
+	   integrate better with CFI schemes.
+
+	   This will have greater overhead than using inline static calls as
+	   the call to the preemption function cannot be entirely elided.
 
 config ARCH_WANT_LD_ORPHAN_WARN
 	bool