Merge tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Clean up SCHED_DEBUG: move the decades old mess of sysctl, procfs and
   debugfs interfaces to a unified debugfs interface.

 - Signals: Allow caching one sigqueue object per task, to improve
   performance & latencies.

 - Improve newidle_balance() irq-off latencies on systems with a large
   number of CPU cgroups.

 - Improve energy-aware scheduling

 - Improve the PELT metrics for certain workloads

 - Reintroduce select_idle_smt() to improve load-balancing locality -
   but without the previous regressions

 - Add 'scheduler latency debugging': warn after long periods of pending
   need_resched. This is an opt-in feature that requires the enabling of
   the LATENCY_WARN scheduler feature, or the use of the
   resched_latency_warn_ms=xx boot parameter.

 - CPU hotplug fixes for HP-rollback, and for the 'fail' interface. Fix
   remaining balance_push() vs. hotplug holes/races

 - PSI fixes, plus allow /proc/pressure/ files to be written by
   CAP_SYS_RESOURCE tasks as well

 - Fix/improve various load-balancing corner cases vs. capacity margins

 - Fix sched topology on systems with NUMA diameter of 3 or above

 - Fix PF_KTHREAD vs to_kthread() race

 - Minor rseq optimizations

 - Misc cleanups, optimizations, fixes and smaller updates

* tag 'sched-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  cpumask/hotplug: Fix cpu_dying() state tracking
  kthread: Fix PF_KTHREAD vs to_kthread() race
  sched/debug: Fix cgroup_path[] serialization
  sched,psi: Handle potential task count underflow bugs more gracefully
  sched: Warn on long periods of pending need_resched
  sched/fair: Move update_nohz_stats() to the CONFIG_NO_HZ_COMMON block to simplify the code & fix an unused function warning
  sched/debug: Rename the sched_debug parameter to sched_verbose
  sched,fair: Alternative sched_slice()
  sched: Move /proc/sched_debug to debugfs
  sched,debug: Convert sysctl sched_domains to debugfs
  debugfs: Implement debugfs_create_str()
  sched,preempt: Move preempt_dynamic to debug.c
  sched: Move SCHED_DEBUG sysctl to debugfs
  sched: Don't make LATENCYTOP select SCHED_DEBUG
  sched: Remove sched_schedstats sysctl out from under SCHED_DEBUG
  sched/numa: Allow runtime enabling/disabling of NUMA balance without SCHED_DEBUG
  sched: Use cpu_dying() to fix balance_push vs hotplug-rollback
  cpumask: Introduce DYING mask
  cpumask: Make cpu_{online,possible,present,active}() inline
  rseq: Optimise rseq_get_rseq_cs() and clear_rseq_cs()
  ...

1 files changed, 27 insertions, 6 deletions

diff --git a/kernel/kthread.c b/kernel/kthread.c
index a1972eba2917..fe3f2a40d61e 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -84,6 +84,25 @@ static inline struct kthread *to_kthread(struct task_struct *k)
 	return (__force void *)k->set_child_tid;
 }
 
+/*
+ * Variant of to_kthread() that doesn't assume @p is a kthread.
+ *
+ * Per construction; when:
+ *
+ *   (p->flags & PF_KTHREAD) && p->set_child_tid
+ *
+ * the task is both a kthread and struct kthread is persistent. However
+ * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and
+ * begin_new_exec()).
+ */
+static inline struct kthread *__to_kthread(struct task_struct *p)
+{
+	void *kthread = (__force void *)p->set_child_tid;
+	if (kthread && !(p->flags & PF_KTHREAD))
+		kthread = NULL;
+	return kthread;
+}
+
 void free_kthread_struct(struct task_struct *k)
 {
 	struct kthread *kthread;
@@ -168,8 +187,9 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
  */
 void *kthread_func(struct task_struct *task)
 {
-	if (task->flags & PF_KTHREAD)
-		return to_kthread(task)->threadfn;
+	struct kthread *kthread = __to_kthread(task);
+	if (kthread)
+		return kthread->threadfn;
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(kthread_func);
@@ -199,10 +219,11 @@ EXPORT_SYMBOL_GPL(kthread_data);
  */
 void *kthread_probe_data(struct task_struct *task)
 {
-	struct kthread *kthread = to_kthread(task);
+	struct kthread *kthread = __to_kthread(task);
 	void *data = NULL;
 
-	copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
+	if (kthread)
+		copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
 	return data;
 }
 
@@ -514,9 +535,9 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu)
 	set_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
 }
 
-bool kthread_is_per_cpu(struct task_struct *k)
+bool kthread_is_per_cpu(struct task_struct *p)
 {
-	struct kthread *kthread = to_kthread(k);
+	struct kthread *kthread = __to_kthread(p);
 	if (!kthread)
 		return false;