Merge tag 'sched-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Core & fair scheduler changes:

   - Tweak wait_task_inactive() to force dequeue sched_delayed tasks
     (John Stultz)

   - Adhere to place_entity() constraints (Peter Zijlstra)

   - Allow decaying util_est when util_avg > CPU capacity (Pierre
     Gondois)

   - Fix up wake_up_sync() vs DELAYED_DEQUEUE (Xuewen Yan)

  Energy management:

   - Introduce sched_update_asym_prefer_cpu() (K Prateek Nayak)

   - cpufreq/amd-pstate: Update asym_prefer_cpu when core rankings
     change (K Prateek Nayak)

   - Align uclamp and util_est and call before freq update (Xuewen Yan)

  CPU isolation:

   - Make use of more than one housekeeping CPU (Phil Auld)

  RT scheduler:

   - Fix race in push_rt_task() (Harshit Agarwal)

   - Add kernel cmdline option for rt_group_sched (Michal Koutný)

  Scheduler topology support:

   - Improve topology_span_sane speed (Steve Wahl)

  Scheduler debugging:

   - Move and extend the sched_process_exit() tracepoint (Andrii
     Nakryiko)

   - Add RT_GROUP WARN checks for non-root task_groups (Michal Koutný)

   - Fix trace_sched_switch(.prev_state) (Peter Zijlstra)

   - Untangle cond_resched() and live-patching (Peter Zijlstra)

  Fixes and cleanups:

   - Misc fixes and cleanups (K Prateek Nayak, Michal Koutný, Peter
     Zijlstra, Xuewen Yan)"

* tag 'sched-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  sched/uclamp: Align uclamp and util_est and call before freq update
  sched/util_est: Simplify condition for util_est_{en,de}queue()
  sched/fair: Fixup wake_up_sync() vs DELAYED_DEQUEUE
  sched,livepatch: Untangle cond_resched() and live-patching
  sched/core: Tweak wait_task_inactive() to force dequeue sched_delayed tasks
  sched/fair: Adhere to place_entity() constraints
  sched/debug: Print the local group's asym_prefer_cpu
  cpufreq/amd-pstate: Update asym_prefer_cpu when core rankings change
  sched/topology: Introduce sched_update_asym_prefer_cpu()
  sched/fair: Use READ_ONCE() to read sg->asym_prefer_cpu
  sched/isolation: Make use of more than one housekeeping cpu
  sched/rt: Fix race in push_rt_task
  sched: Add annotations to RT_GROUP_SCHED fields
  sched: Add RT_GROUP WARN checks for non-root task_groups
  sched: Do not construct nor expose RT_GROUP_SCHED structures if disabled
  sched: Bypass bandwitdh checks with runtime disabled RT_GROUP_SCHED
  sched: Skip non-root task_groups with disabled RT_GROUP_SCHED
  sched: Add commadline option for RT_GROUP_SCHED toggling
  sched: Always initialize rt_rq's task_group
  sched: Remove unneeed macro wrap
  ...

1 files changed, 14 insertions, 35 deletions

diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index ba069459c101..2351a19ac2a9 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -29,22 +29,13 @@ static unsigned int klp_signals_cnt;
 
 /*
  * When a livepatch is in progress, enable klp stack checking in
- * cond_resched().  This helps CPU-bound kthreads get patched.
+ * schedule().  This helps CPU-bound kthreads get patched.
  */
-#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
-#define klp_cond_resched_enable() sched_dynamic_klp_enable()
-#define klp_cond_resched_disable() sched_dynamic_klp_disable()
-
-#else /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
 
 DEFINE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
-EXPORT_SYMBOL(klp_sched_try_switch_key);
 
-#define klp_cond_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
-#define klp_cond_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
-
-#endif /* CONFIG_PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
+#define klp_resched_enable() static_branch_enable(&klp_sched_try_switch_key)
+#define klp_resched_disable() static_branch_disable(&klp_sched_try_switch_key)
 
 /*
  * This work can be performed periodically to finish patching or unpatching any
@@ -365,26 +356,18 @@ static bool klp_try_switch_task(struct task_struct *task)
 
 void __klp_sched_try_switch(void)
 {
-	if (likely(!klp_patch_pending(current)))
-		return;
-
 	/*
-	 * This function is called from cond_resched() which is called in many
-	 * places throughout the kernel.  Using the klp_mutex here might
-	 * deadlock.
-	 *
-	 * Instead, disable preemption to prevent racing with other callers of
-	 * klp_try_switch_task().  Thanks to task_call_func() they won't be
-	 * able to switch this task while it's running.
+	 * This function is called from __schedule() while a context switch is
+	 * about to happen. Preemption is already disabled and klp_mutex
+	 * can't be acquired.
+	 * Disabled preemption is used to prevent racing with other callers of
+	 * klp_try_switch_task(). Thanks to task_call_func() they won't be
+	 * able to switch to this task while it's running.
 	 */
-	preempt_disable();
+	lockdep_assert_preemption_disabled();
 
-	/*
-	 * Make sure current didn't get patched between the above check and
-	 * preempt_disable().
-	 */
-	if (unlikely(!klp_patch_pending(current)))
-		goto out;
+	if (likely(!klp_patch_pending(current)))
+		return;
 
 	/*
 	 * Enforce the order of the TIF_PATCH_PENDING read above and the
@@ -395,11 +378,7 @@ void __klp_sched_try_switch(void)
 	smp_rmb();
 
 	klp_try_switch_task(current);
-
-out:
-	preempt_enable();
 }
-EXPORT_SYMBOL(__klp_sched_try_switch);
 
 /*
  * Sends a fake signal to all non-kthread tasks with TIF_PATCH_PENDING set.
@@ -508,7 +487,7 @@ void klp_try_complete_transition(void)
 	}
 
 	/* Done!  Now cleanup the data structures. */
-	klp_cond_resched_disable();
+	klp_resched_disable();
 	patch = klp_transition_patch;
 	klp_complete_transition();
 
@@ -560,7 +539,7 @@ void klp_start_transition(void)
 			set_tsk_thread_flag(task, TIF_PATCH_PENDING);
 	}
 
-	klp_cond_resched_enable();
+	klp_resched_enable();
 
 	klp_signals_cnt = 0;
 }