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
  ...

1 files changed, 21 insertions, 10 deletions

diff --git a/drivers/cpuidle/cpuidle-tegra.c b/drivers/cpuidle/cpuidle-tegra.c
index 9845629aeb6d..b203a93deac5 100644
--- a/drivers/cpuidle/cpuidle-tegra.c
+++ b/drivers/cpuidle/cpuidle-tegra.c
@@ -160,8 +160,8 @@ static int tegra_cpuidle_coupled_barrier(struct cpuidle_device *dev)
 	return 0;
 }
 
-static int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
-				     int index, unsigned int cpu)
+static __cpuidle int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
+					       int index, unsigned int cpu)
 {
 	int err;
 
@@ -180,9 +180,11 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
 	}
 
 	local_fiq_disable();
-	RCU_NONIDLE(tegra_pm_set_cpu_in_lp2());
+	tegra_pm_set_cpu_in_lp2();
 	cpu_pm_enter();
 
+	ct_cpuidle_enter();
+
 	switch (index) {
 	case TEGRA_C7:
 		err = tegra_cpuidle_c7_enter();
@@ -197,8 +199,10 @@ static int tegra_cpuidle_state_enter(struct cpuidle_device *dev,
 		break;
 	}
 
+	ct_cpuidle_exit();
+
 	cpu_pm_exit();
-	RCU_NONIDLE(tegra_pm_clear_cpu_in_lp2());
+	tegra_pm_clear_cpu_in_lp2();
 	local_fiq_enable();
 
 	return err ?: index;
@@ -222,10 +226,11 @@ static int tegra_cpuidle_adjust_state_index(int index, unsigned int cpu)
 	return index;
 }
 
-static int tegra_cpuidle_enter(struct cpuidle_device *dev,
-			       struct cpuidle_driver *drv,
-			       int index)
+static __cpuidle int tegra_cpuidle_enter(struct cpuidle_device *dev,
+					 struct cpuidle_driver *drv,
+					 int index)
 {
+	bool do_rcu = drv->states[index].flags & CPUIDLE_FLAG_RCU_IDLE;
 	unsigned int cpu = cpu_logical_map(dev->cpu);
 	int ret;
 
@@ -233,9 +238,13 @@ static int tegra_cpuidle_enter(struct cpuidle_device *dev,
 	if (dev->states_usage[index].disable)
 		return -1;
 
-	if (index == TEGRA_C1)
+	if (index == TEGRA_C1) {
+		if (do_rcu)
+			ct_cpuidle_enter();
 		ret = arm_cpuidle_simple_enter(dev, drv, index);
-	else
+		if (do_rcu)
+			ct_cpuidle_exit();
+	} else
 		ret = tegra_cpuidle_state_enter(dev, index, cpu);
 
 	if (ret < 0) {
@@ -285,7 +294,8 @@ static struct cpuidle_driver tegra_idle_driver = {
 			.exit_latency		= 2000,
 			.target_residency	= 2200,
 			.power_usage		= 100,
-			.flags			= CPUIDLE_FLAG_TIMER_STOP,
+			.flags			= CPUIDLE_FLAG_TIMER_STOP |
+						  CPUIDLE_FLAG_RCU_IDLE,
 			.name			= "C7",
 			.desc			= "CPU core powered off",
 		},
@@ -295,6 +305,7 @@ static struct cpuidle_driver tegra_idle_driver = {
 			.target_residency	= 10000,
 			.power_usage		= 0,
 			.flags			= CPUIDLE_FLAG_TIMER_STOP |
+						  CPUIDLE_FLAG_RCU_IDLE   |
 						  CPUIDLE_FLAG_COUPLED,
 			.name			= "CC6",
 			.desc			= "CPU cluster powered off",