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

Pull scheduler updates from Ingo Molnar:

 - MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and
   Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann,
   Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers.

   As perf and the scheduler is getting bigger and more complex,
   document the status quo of current responsibilities and interests,
   and spread the review pain^H^H^H^H fun via an increase in the Cc:
   linecount generated by scripts/get_maintainer.pl. :-)

 - Add another series of patches that brings the -rt (PREEMPT_RT) tree
   closer to mainline: split the monolithic CONFIG_PREEMPT dependencies
   into a new CONFIG_PREEMPTION category that will allow the eventual
   introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches
   to go though.

 - Extend the CPU cgroup controller with uclamp.min and uclamp.max to
   allow the finer shaping of CPU bandwidth usage.

 - Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS).

 - Improve the behavior of high CPU count, high thread count
   applications running under cpu.cfs_quota_us constraints.

 - Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present.

 - Improve CPU isolation housekeeping CPU allocation NUMA locality.

 - Fix deadline scheduler bandwidth calculations and logic when cpusets
   rebuilds the topology, or when it gets deadline-throttled while it's
   being offlined.

 - Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from
   setscheduler() system calls without creating global serialization.
   Add new synchronization between cpuset topology-changing events and
   the deadline acceptance tests in setscheduler(), which were broken
   before.

 - Rework the active_mm state machine to be less confusing and more
   optimal.

 - Rework (simplify) the pick_next_task() slowpath.

 - Improve load-balancing on AMD EPYC systems.

 - ... and misc cleanups, smaller fixes and improvements - please see
   the Git log for more details.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  sched/psi: Correct overly pessimistic size calculation
  sched/fair: Speed-up energy-aware wake-ups
  sched/uclamp: Always use 'enum uclamp_id' for clamp_id values
  sched/uclamp: Update CPU's refcount on TG's clamp changes
  sched/uclamp: Use TG's clamps to restrict TASK's clamps
  sched/uclamp: Propagate system defaults to the root group
  sched/uclamp: Propagate parent clamps
  sched/uclamp: Extend CPU's cgroup controller
  sched/topology: Improve load balancing on AMD EPYC systems
  arch, ia64: Make NUMA select SMP
  sched, perf: MAINTAINERS update, add submaintainers and reviewers
  sched/fair: Use rq_lock/unlock in online_fair_sched_group
  cpufreq: schedutil: fix equation in comment
  sched: Rework pick_next_task() slow-path
  sched: Allow put_prev_task() to drop rq->lock
  sched/fair: Expose newidle_balance()
  sched: Add task_struct pointer to sched_class::set_curr_task
  sched: Rework CPU hotplug task selection
  sched/{rt,deadline}: Fix set_next_task vs pick_next_task
  sched: Fix kerneldoc comment for ia64_set_curr_task
  ...

11 files changed, 24 insertions, 13 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 71d9ae0c0ea1..6baedab10dca 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -106,7 +106,7 @@ config STATIC_KEYS_SELFTEST
 config OPTPROBES
 	def_bool y
 	depends on KPROBES && HAVE_OPTPROBES
-	select TASKS_RCU if PREEMPT
+	select TASKS_RCU if PREEMPTION
 
 config KPROBES_ON_FTRACE
 	def_bool y
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 13d49c232556..9711cf730929 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -311,6 +311,7 @@ config ARCH_DISCONTIGMEM_DEFAULT
 config NUMA
 	bool "NUMA support"
 	depends on !FLATMEM
+	select SMP
 	help
 	  Say Y to compile the kernel to support NUMA (Non-Uniform Memory
 	  Access).  This option is for configuring high-end multiprocessor
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 4f86928246e7..f83ca5aa8b77 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -63,7 +63,7 @@
  * enough to patch inline, increasing performance.
  */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 # define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
 #else
 # define preempt_stop(clobbers)
@@ -1084,7 +1084,7 @@ restore_all:
 	INTERRUPT_RETURN
 
 restore_all_kernel:
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	.Lno_preempt
@@ -1364,7 +1364,7 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:	mov	%esp, %eax
 	call	xen_evtchn_do_upcall
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 	call	xen_maybe_preempt_hcall
 #endif
 	jmp	ret_from_intr
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index be9ca198c581..af077ded1969 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -664,7 +664,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 
 /* Returning to kernel space */
 retint_kernel:
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	/* Interrupts are off */
 	/* Check if we need preemption */
 	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
@@ -1115,7 +1115,7 @@ ENTRY(xen_do_hypervisor_callback)		/* do_hypervisor_callback(struct *pt_regs) */
 	call	xen_evtchn_do_upcall
 	LEAVE_IRQ_STACK
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 	call	xen_maybe_preempt_hcall
 #endif
 	jmp	error_exit
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index cb3464525b37..2713490611a3 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -34,7 +34,7 @@
 	THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
 #endif
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	THUNK ___preempt_schedule, preempt_schedule
 	THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
 	EXPORT_SYMBOL(___preempt_schedule)
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index cc20465b2867..ea5c4167086c 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -46,7 +46,7 @@
 	THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
 #endif
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	THUNK ___preempt_schedule, preempt_schedule
 	THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
 	EXPORT_SYMBOL(___preempt_schedule)
@@ -55,7 +55,7 @@
 
 #if defined(CONFIG_TRACE_IRQFLAGS) \
  || defined(CONFIG_DEBUG_LOCK_ALLOC) \
- || defined(CONFIG_PREEMPT)
+ || defined(CONFIG_PREEMPTION)
 .L_restore:
 	popq %r11
 	popq %r10
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 99a7fa9ab0a3..3d4cb83a8828 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -102,7 +102,7 @@ static __always_inline bool should_resched(int preempt_offset)
 	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
   extern asmlinkage void ___preempt_schedule(void);
 # define __preempt_schedule() \
 	asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 68c363c341bf..7d6e0efcc2db 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -8,6 +8,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <linux/random.h>
+#include <linux/topology.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cacheinfo.h>
@@ -889,6 +890,10 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
 
+#ifdef CONFIG_NUMA
+	node_reclaim_distance = 32;
+#endif
+
 	/*
 	 * Fix erratum 1076: CPB feature bit not being set in CPUID.
 	 * Always set it, except when running under a hypervisor.
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 2b5886401e5f..e07424e19274 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -367,13 +367,18 @@ NOKPROBE_SYMBOL(oops_end);
 
 int __die(const char *str, struct pt_regs *regs, long err)
 {
+	const char *pr = "";
+
 	/* Save the regs of the first oops for the executive summary later. */
 	if (!die_counter)
 		exec_summary_regs = *regs;
 
+	if (IS_ENABLED(CONFIG_PREEMPTION))
+		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
+
 	printk(KERN_DEFAULT
 	       "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
-	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT"         : "",
+	       pr,
 	       IS_ENABLED(CONFIG_SMP)     ? " SMP"             : "",
 	       debug_pagealloc_enabled()  ? " DEBUG_PAGEALLOC" : "",
 	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "",
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0e0b08008b5a..43fc13c831af 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -580,7 +580,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 	if (setup_detour_execution(p, regs, reenter))
 		return;
 
-#if !defined(CONFIG_PREEMPT)
+#if !defined(CONFIG_PREEMPTION)
 	if (p->ainsn.boostable && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		if (!reenter)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4ab377c9fffe..4cc967178bf9 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -311,7 +311,7 @@ static void kvm_guest_cpu_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
 		u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
 #endif
 		pa |= KVM_ASYNC_PF_ENABLED;