Merge tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Improve the scalability of the CFS bandwidth unthrottling logic with
   large number of CPUs.

 - Fix & rework various cpuidle routines, simplify interaction with the
   generic scheduler code. Add __cpuidle methods as noinstr to objtool's
   noinstr detection and fix boatloads of cpuidle bugs & quirks.

 - Add new ABI: introduce MEMBARRIER_CMD_GET_REGISTRATIONS, to query
   previously issued registrations.

 - Limit scheduler slice duration to the sysctl_sched_latency period, to
   improve scheduling granularity with a large number of SCHED_IDLE
   tasks.

 - Debuggability enhancement on sys_exit(): warn about disabled IRQs,
   but also enable them to prevent a cascade of followup problems and
   repeat warnings.

 - Fix the rescheduling logic in prio_changed_dl().

 - Micro-optimize cpufreq and sched-util methods.

 - Micro-optimize ttwu_runnable()

 - Micro-optimize the idle-scanning in update_numa_stats(),
   select_idle_capacity() and steal_cookie_task().

 - Update the RSEQ code & self-tests

 - Constify various scheduler methods

 - Remove unused methods

 - Refine __init tags

 - Documentation updates

 - Misc other cleanups, fixes

* tag 'sched-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
  sched/rt: pick_next_rt_entity(): check list_entry
  sched/deadline: Add more reschedule cases to prio_changed_dl()
  sched/fair: sanitize vruntime of entity being placed
  sched/fair: Remove capacity inversion detection
  sched/fair: unlink misfit task from cpu overutilized
  objtool: mem*() are not uaccess safe
  cpuidle: Fix poll_idle() noinstr annotation
  sched/clock: Make local_clock() noinstr
  sched/clock/x86: Mark sched_clock() noinstr
  x86/pvclock: Improve atomic update of last_value in pvclock_clocksource_read()
  x86/atomics: Always inline arch_atomic64*()
  cpuidle: tracing, preempt: Squash _rcuidle tracing
  cpuidle: tracing: Warn about !rcu_is_watching()
  cpuidle: lib/bug: Disable rcu_is_watching() during WARN/BUG
  cpuidle: drivers: firmware: psci: Dont instrument suspend code
  KVM: selftests: Fix build of rseq test
  exit: Detect and fix irq disabled state in oops
  cpuidle, arm64: Fix the ARM64 cpuidle logic
  cpuidle: mvebu: Fix duplicate flags assignment
  sched/fair: Limit sched slice duration
  ...

2 files changed, 23 insertions, 41 deletions

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c9e40f692650..54a163ae4815 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3128,6 +3128,9 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
 		return;
 	}
 
+	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_GENERIC_ENTRY)))
+		return;
+
 	/*
 	 * When an NMI triggers, RCU is enabled via ct_nmi_enter(),
 	 * but if the above rcu_is_watching() failed, then the NMI
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 1e130da1b742..e37446f7916e 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -15,6 +15,20 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/preemptirq.h>
 
+/*
+ * Use regular trace points on architectures that implement noinstr
+ * tooling: these calls will only happen with RCU enabled, which can
+ * use a regular tracepoint.
+ *
+ * On older architectures, use the rcuidle tracing methods (which
+ * aren't NMI-safe - so exclude NMI contexts):
+ */
+#ifdef CONFIG_ARCH_WANTS_NO_INSTR
+#define trace(point)	trace_##point
+#else
+#define trace(point)	if (!in_nmi()) trace_##point##_rcuidle
+#endif
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 /* Per-cpu variable to prevent redundant calls when IRQs already off */
 static DEFINE_PER_CPU(int, tracing_irq_cpu);
@@ -28,8 +42,7 @@ static DEFINE_PER_CPU(int, tracing_irq_cpu);
 void trace_hardirqs_on_prepare(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
-		if (!in_nmi())
-			trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_enable)(CALLER_ADDR0, CALLER_ADDR1);
 		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
@@ -40,8 +53,7 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
 void trace_hardirqs_on(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
-		if (!in_nmi())
-			trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_enable)(CALLER_ADDR0, CALLER_ADDR1);
 		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
@@ -63,8 +75,7 @@ void trace_hardirqs_off_finish(void)
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
-		if (!in_nmi())
-			trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_disable)(CALLER_ADDR0, CALLER_ADDR1);
 	}
 
 }
@@ -78,56 +89,24 @@ void trace_hardirqs_off(void)
 	if (!this_cpu_read(tracing_irq_cpu)) {
 		this_cpu_write(tracing_irq_cpu, 1);
 		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
-		if (!in_nmi())
-			trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1);
+		trace(irq_disable)(CALLER_ADDR0, CALLER_ADDR1);
 	}
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
 NOKPROBE_SYMBOL(trace_hardirqs_off);
-
-__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
-{
-	if (this_cpu_read(tracing_irq_cpu)) {
-		if (!in_nmi())
-			trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr);
-		tracer_hardirqs_on(CALLER_ADDR0, caller_addr);
-		this_cpu_write(tracing_irq_cpu, 0);
-	}
-
-	lockdep_hardirqs_on_prepare();
-	lockdep_hardirqs_on(caller_addr);
-}
-EXPORT_SYMBOL(trace_hardirqs_on_caller);
-NOKPROBE_SYMBOL(trace_hardirqs_on_caller);
-
-__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
-{
-	lockdep_hardirqs_off(caller_addr);
-
-	if (!this_cpu_read(tracing_irq_cpu)) {
-		this_cpu_write(tracing_irq_cpu, 1);
-		tracer_hardirqs_off(CALLER_ADDR0, caller_addr);
-		if (!in_nmi())
-			trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr);
-	}
-}
-EXPORT_SYMBOL(trace_hardirqs_off_caller);
-NOKPROBE_SYMBOL(trace_hardirqs_off_caller);
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
 #ifdef CONFIG_TRACE_PREEMPT_TOGGLE
 
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-	if (!in_nmi())
-		trace_preempt_enable_rcuidle(a0, a1);
+	trace(preempt_enable)(a0, a1);
 	tracer_preempt_on(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-	if (!in_nmi())
-		trace_preempt_disable_rcuidle(a0, a1);
+	trace(preempt_disable)(a0, a1);
 	tracer_preempt_off(a0, a1);
 }
 #endif