Merge tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Thomas Gleixner:

 - Revert the printk format based wchan() symbol resolution as it can
   leak the raw value in case that the symbol is not resolvable.

 - Make wchan() more robust and work with all kind of unwinders by
   enforcing that the task stays blocked while unwinding is in progress.

 - Prevent sched_fork() from accessing an invalid sched_task_group

 - Improve asymmetric packing logic

 - Extend scheduler statistics to RT and DL scheduling classes and add
   statistics for bandwith burst to the SCHED_FAIR class.

 - Properly account SCHED_IDLE entities

 - Prevent a potential deadlock when initial priority is assigned to a
   newly created kthread. A recent change to plug a race between cpuset
   and __sched_setscheduler() introduced a new lock dependency which is
   now triggered. Break the lock dependency chain by moving the priority
   assignment to the thread function.

 - Fix the idle time reporting in /proc/uptime for NOHZ enabled systems.

 - Improve idle balancing in general and especially for NOHZ enabled
   systems.

 - Provide proper interfaces for live patching so it does not have to
   fiddle with scheduler internals.

 - Add cluster aware scheduling support.

 - A small set of tweaks for RT (irqwork, wait_task_inactive(), various
   scheduler options and delaying mmdrop)

 - The usual small tweaks and improvements all over the place

* tag 'sched-core-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (69 commits)
  sched/fair: Cleanup newidle_balance
  sched/fair: Remove sysctl_sched_migration_cost condition
  sched/fair: Wait before decaying max_newidle_lb_cost
  sched/fair: Skip update_blocked_averages if we are defering load balance
  sched/fair: Account update_blocked_averages in newidle_balance cost
  x86: Fix __get_wchan() for !STACKTRACE
  sched,x86: Fix L2 cache mask
  sched/core: Remove rq_relock()
  sched: Improve wake_up_all_idle_cpus() take #2
  irq_work: Also rcuwait for !IRQ_WORK_HARD_IRQ on PREEMPT_RT
  irq_work: Handle some irq_work in a per-CPU thread on PREEMPT_RT
  irq_work: Allow irq_work_sync() to sleep if irq_work() no IRQ support.
  sched/rt: Annotate the RT balancing logic irqwork as IRQ_WORK_HARD_IRQ
  sched: Add cluster scheduler level for x86
  sched: Add cluster scheduler level in core and related Kconfig for ARM64
  topology: Represent clusters of CPUs within a die
  sched: Disable -Wunused-but-set-variable
  sched: Add wrapper for get_wchan() to keep task blocked
  x86: Fix get_wchan() to support the ORC unwinder
  proc: Use task_is_running() for wchan in /proc/$pid/stat
  ...

4 files changed, 13 insertions, 4 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3d027ce8f7a3..bc8d3702f4ed 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -988,6 +988,15 @@ config SCHED_MC
 	  making when dealing with multi-core CPU chips at a cost of slightly
 	  increased overhead in some places. If unsure say N here.
 
+config SCHED_CLUSTER
+	bool "Cluster scheduler support"
+	help
+	  Cluster scheduler support improves the CPU scheduler's decision
+	  making when dealing with machines that have clusters of CPUs.
+	  Cluster usually means a couple of CPUs which are placed closely
+	  by sharing mid-level caches, last-level cache tags or internal
+	  busses.
+
 config SCHED_SMT
 	bool "SMT scheduler support"
 	help
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ee2bdc1b9f5b..55ca034238ea 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -257,7 +257,7 @@ struct task_struct;
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-unsigned long get_wchan(struct task_struct *p);
+unsigned long __get_wchan(struct task_struct *p);
 
 void update_sctlr_el1(u64 sctlr);
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 40adb8cdbf5a..aacf2f5559a8 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -528,13 +528,11 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	return last;
 }
 
-unsigned long get_wchan(struct task_struct *p)
+unsigned long __get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
 	unsigned long stack_page, ret = 0;
 	int count = 0;
-	if (!p || p == current || task_is_running(p))
-		return 0;
 
 	stack_page = (unsigned long)try_get_task_stack(p);
 	if (!stack_page)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 4dd14a6620c1..9ab78ad826e2 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -103,6 +103,8 @@ int __init parse_acpi_topology(void)
 			cpu_topology[cpu].thread_id  = -1;
 			cpu_topology[cpu].core_id    = topology_id;
 		}
+		topology_id = find_acpi_cpu_topology_cluster(cpu);
+		cpu_topology[cpu].cluster_id = topology_id;
 		topology_id = find_acpi_cpu_topology_package(cpu);
 		cpu_topology[cpu].package_id = topology_id;