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
  ...

3 files changed, 92 insertions, 0 deletions

diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index fe69dc518f31..701f61c01359 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -747,6 +747,73 @@ int find_acpi_cpu_topology_package(unsigned int cpu)
 }
 
 /**
+ * find_acpi_cpu_topology_cluster() - Determine a unique CPU cluster value
+ * @cpu: Kernel logical CPU number
+ *
+ * Determine a topology unique cluster ID for the given CPU/thread.
+ * This ID can then be used to group peers, which will have matching ids.
+ *
+ * The cluster, if present is the level of topology above CPUs. In a
+ * multi-thread CPU, it will be the level above the CPU, not the thread.
+ * It may not exist in single CPU systems. In simple multi-CPU systems,
+ * it may be equal to the package topology level.
+ *
+ * Return: -ENOENT if the PPTT doesn't exist, the CPU cannot be found
+ * or there is no toplogy level above the CPU..
+ * Otherwise returns a value which represents the package for this CPU.
+ */
+
+int find_acpi_cpu_topology_cluster(unsigned int cpu)
+{
+	struct acpi_table_header *table;
+	acpi_status status;
+	struct acpi_pptt_processor *cpu_node, *cluster_node;
+	u32 acpi_cpu_id;
+	int retval;
+	int is_thread;
+
+	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
+	if (ACPI_FAILURE(status)) {
+		acpi_pptt_warn_missing();
+		return -ENOENT;
+	}
+
+	acpi_cpu_id = get_acpi_id_for_cpu(cpu);
+	cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
+	if (cpu_node == NULL || !cpu_node->parent) {
+		retval = -ENOENT;
+		goto put_table;
+	}
+
+	is_thread = cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_IS_THREAD;
+	cluster_node = fetch_pptt_node(table, cpu_node->parent);
+	if (cluster_node == NULL) {
+		retval = -ENOENT;
+		goto put_table;
+	}
+	if (is_thread) {
+		if (!cluster_node->parent) {
+			retval = -ENOENT;
+			goto put_table;
+		}
+		cluster_node = fetch_pptt_node(table, cluster_node->parent);
+		if (cluster_node == NULL) {
+			retval = -ENOENT;
+			goto put_table;
+		}
+	}
+	if (cluster_node->flags & ACPI_PPTT_ACPI_PROCESSOR_ID_VALID)
+		retval = cluster_node->acpi_processor_id;
+	else
+		retval = ACPI_PTR_DIFF(cluster_node, table);
+
+put_table:
+	acpi_put_table(table);
+
+	return retval;
+}
+
+/**
  * find_acpi_cpu_topology_hetero_id() - Get a core architecture tag
  * @cpu: Kernel logical CPU number
  *
diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 43407665918f..fc0836f460fb 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -600,6 +600,11 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	return core_mask;
 }
 
+const struct cpumask *cpu_clustergroup_mask(int cpu)
+{
+	return &cpu_topology[cpu].cluster_sibling;
+}
+
 void update_siblings_masks(unsigned int cpuid)
 {
 	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
@@ -617,6 +622,12 @@ void update_siblings_masks(unsigned int cpuid)
 		if (cpuid_topo->package_id != cpu_topo->package_id)
 			continue;
 
+		if (cpuid_topo->cluster_id == cpu_topo->cluster_id &&
+		    cpuid_topo->cluster_id != -1) {
+			cpumask_set_cpu(cpu, &cpuid_topo->cluster_sibling);
+			cpumask_set_cpu(cpuid, &cpu_topo->cluster_sibling);
+		}
+
 		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
 		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
 
@@ -635,6 +646,9 @@ static void clear_cpu_topology(int cpu)
 	cpumask_clear(&cpu_topo->llc_sibling);
 	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
 
+	cpumask_clear(&cpu_topo->cluster_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->cluster_sibling);
+
 	cpumask_clear(&cpu_topo->core_sibling);
 	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
 	cpumask_clear(&cpu_topo->thread_sibling);
@@ -650,6 +664,7 @@ void __init reset_cpu_topology(void)
 
 		cpu_topo->thread_id = -1;
 		cpu_topo->core_id = -1;
+		cpu_topo->cluster_id = -1;
 		cpu_topo->package_id = -1;
 		cpu_topo->llc_id = -1;
 
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 43c0940643f5..8f2b641d0b8c 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -48,6 +48,9 @@ static DEVICE_ATTR_RO(physical_package_id);
 define_id_show_func(die_id);
 static DEVICE_ATTR_RO(die_id);
 
+define_id_show_func(cluster_id);
+static DEVICE_ATTR_RO(cluster_id);
+
 define_id_show_func(core_id);
 static DEVICE_ATTR_RO(core_id);
 
@@ -63,6 +66,10 @@ define_siblings_read_func(core_siblings, core_cpumask);
 static BIN_ATTR_RO(core_siblings, 0);
 static BIN_ATTR_RO(core_siblings_list, 0);
 
+define_siblings_read_func(cluster_cpus, cluster_cpumask);
+static BIN_ATTR_RO(cluster_cpus, 0);
+static BIN_ATTR_RO(cluster_cpus_list, 0);
+
 define_siblings_read_func(die_cpus, die_cpumask);
 static BIN_ATTR_RO(die_cpus, 0);
 static BIN_ATTR_RO(die_cpus_list, 0);
@@ -94,6 +101,8 @@ static struct bin_attribute *bin_attrs[] = {
 	&bin_attr_thread_siblings_list,
 	&bin_attr_core_siblings,
 	&bin_attr_core_siblings_list,
+	&bin_attr_cluster_cpus,
+	&bin_attr_cluster_cpus_list,
 	&bin_attr_die_cpus,
 	&bin_attr_die_cpus_list,
 	&bin_attr_package_cpus,
@@ -112,6 +121,7 @@ static struct bin_attribute *bin_attrs[] = {
 static struct attribute *default_attrs[] = {
 	&dev_attr_physical_package_id.attr,
 	&dev_attr_die_id.attr,
+	&dev_attr_cluster_id.attr,
 	&dev_attr_core_id.attr,
 #ifdef CONFIG_SCHED_BOOK
 	&dev_attr_book_id.attr,