Merge tag 'sched-core-2025-07-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

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

   - Better tracking of maximum lag of tasks in presence of different
     slices duration, for better handling of lag in the fair scheduler
     (Vincent Guittot)

   - Clean up and standardize #if/#else/#endif markers throughout the
     entire scheduler code base (Ingo Molnar)

   - Make SMP unconditional: build the SMP scheduler's data structures
     and logic on UP kernel too, even though they are not used, to
     simplify the scheduler and remove around 200 #ifdef/[#else]/#endif
     blocks from the scheduler (Ingo Molnar)

   - Reorganize cgroup bandwidth control interface handling for better
     interfacing with sched_ext (Tejun Heo)

  Balancing:

   - Bump sd->max_newidle_lb_cost when newidle balance fails (Chris
     Mason)

   - Remove sched_domain_topology_level::flags to simplify the code
     (Prateek Nayak)

   - Simplify and clean up build_sched_topology() (Li Chen)

   - Optimize build_sched_topology() on large machines (Li Chen)

  Real-time scheduling:

   - Add initial version of proxy execution: a mechanism for
     mutex-owning tasks to inherit the scheduling context of higher
     priority waiters.

     Currently limited to a single runqueue and conditional on
     CONFIG_EXPERT, and other limitations (John Stultz, Peter Zijlstra,
     Valentin Schneider)

   - Deadline scheduler (Juri Lelli):
      - Fix dl_servers initialization order (Juri Lelli)
      - Fix DL scheduler's root domain reinitialization logic (Juri
        Lelli)
      - Fix accounting bugs after global limits change (Juri Lelli)
      - Fix scalability regression by implementing less agressive
        dl_server handling (Peter Zijlstra)

  PSI:

   - Improve scalability by optimizing psi_group_change() cpu_clock()
     usage (Peter Zijlstra)

  Rust changes:

   - Make Task, CondVar and PollCondVar methods inline to avoid
     unnecessary function calls (Kunwu Chan, Panagiotis Foliadis)

   - Add might_sleep() support for Rust code: Rust's "#[track_caller]"
     mechanism is used so that Rust's might_sleep() doesn't need to be
     defined as a macro (Fujita Tomonori)

   - Introduce file_from_location() (Boqun Feng)

  Debugging & instrumentation:

   - Make clangd usable with scheduler source code files again (Peter
     Zijlstra)

   - tools: Add root_domains_dump.py which dumps root domains info (Juri
     Lelli)

   - tools: Add dl_bw_dump.py for printing bandwidth accounting info
     (Juri Lelli)

  Misc cleanups & fixes:

   - Remove play_idle() (Feng Lee)

   - Fix check_preemption_disabled() (Sebastian Andrzej Siewior)

   - Do not call __put_task_struct() on RT if pi_blocked_on is set (Luis
     Claudio R. Goncalves)

   - Correct the comment in place_entity() (wang wei)"

* tag 'sched-core-2025-07-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (84 commits)
  sched/idle: Remove play_idle()
  sched: Do not call __put_task_struct() on rt if pi_blocked_on is set
  sched: Start blocked_on chain processing in find_proxy_task()
  sched: Fix proxy/current (push,pull)ability
  sched: Add an initial sketch of the find_proxy_task() function
  sched: Fix runtime accounting w/ split exec & sched contexts
  sched: Move update_curr_task logic into update_curr_se
  locking/mutex: Add p->blocked_on wrappers for correctness checks
  locking/mutex: Rework task_struct::blocked_on
  sched: Add CONFIG_SCHED_PROXY_EXEC & boot argument to enable/disable
  sched/topology: Remove sched_domain_topology_level::flags
  x86/smpboot: avoid SMT domain attach/destroy if SMT is not enabled
  x86/smpboot: moves x86_topology to static initialize and truncate
  x86/smpboot: remove redundant CONFIG_SCHED_SMT
  smpboot: introduce SDTL_INIT() helper to tidy sched topology setup
  tools/sched: Add dl_bw_dump.py for printing bandwidth accounting info
  tools/sched: Add root_domains_dump.py which dumps root domains info
  sched/deadline: Fix accounting after global limits change
  sched/deadline: Reset extra_bw to max_bw when clearing root domains
  sched/deadline: Initialize dl_servers after SMP
  ...

4 files changed, 39 insertions, 7 deletions

diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 6e6f6071cfa2..949103fd8e9b 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -53,17 +53,18 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 {
 	lockdep_assert_held(&lock->wait_lock);
 
-	/* Mark the current thread as blocked on the lock: */
-	task->blocked_on = waiter;
+	/* Current thread can't be already blocked (since it's executing!) */
+	DEBUG_LOCKS_WARN_ON(__get_task_blocked_on(task));
 }
 
 void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			 struct task_struct *task)
 {
+	struct mutex *blocked_on = __get_task_blocked_on(task);
+
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
 	DEBUG_LOCKS_WARN_ON(waiter->task != task);
-	DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
-	task->blocked_on = NULL;
+	DEBUG_LOCKS_WARN_ON(blocked_on && blocked_on != lock);
 
 	INIT_LIST_HEAD(&waiter->list);
 	waiter->task = NULL;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index a39ecccbd106..80d778fedd60 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -644,6 +644,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 			goto err_early_kill;
 	}
 
+	__set_task_blocked_on(current, lock);
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
@@ -680,6 +681,12 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		first = __mutex_waiter_is_first(lock, &waiter);
 
+		/*
+		 * As we likely have been woken up by task
+		 * that has cleared our blocked_on state, re-set
+		 * it to the lock we are trying to acquire.
+		 */
+		set_task_blocked_on(current, lock);
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -691,8 +698,15 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		if (first) {
 			trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+			/*
+			 * mutex_optimistic_spin() can call schedule(), so
+			 * clear blocked on so we don't become unselectable
+			 * to run.
+			 */
+			clear_task_blocked_on(current, lock);
 			if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
 				break;
+			set_task_blocked_on(current, lock);
 			trace_contention_begin(lock, LCB_F_MUTEX);
 		}
 
@@ -700,6 +714,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 acquired:
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 
 	if (ww_ctx) {
@@ -729,9 +744,11 @@ skip_wait:
 	return 0;
 
 err:
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
+	WARN_ON(__get_task_blocked_on(current));
 	trace_contention_end(lock, ret);
 	raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
 	debug_mutex_free_waiter(&waiter);
@@ -942,6 +959,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
+		__clear_task_blocked_on(next, lock);
 		wake_q_add(&wake_q, next);
 	}
 
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index cbff35b9b7ae..2e8080a9bee3 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -6,7 +6,7 @@
  *
  *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
-
+#ifndef CONFIG_PREEMPT_RT
 /*
  * This is the control structure for tasks blocked on mutex, which resides
  * on the blocked task's kernel stack:
@@ -70,3 +70,4 @@ extern void debug_mutex_init(struct mutex *lock, const char *name,
 # define debug_mutex_unlock(lock)			do { } while (0)
 # define debug_mutex_init(lock, name, key)		do { } while (0)
 #endif /* !CONFIG_DEBUG_MUTEXES */
+#endif /* CONFIG_PREEMPT_RT */
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 37f025a096c9..086fd5487ca7 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -284,6 +284,12 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
 #ifndef WW_RT
 		debug_mutex_wake_waiter(lock, waiter);
 #endif
+		/*
+		 * When waking up the task to die, be sure to clear the
+		 * blocked_on pointer. Otherwise we can see circular
+		 * blocked_on relationships that can't resolve.
+		 */
+		__clear_task_blocked_on(waiter->task, lock);
 		wake_q_add(wake_q, waiter->task);
 	}
 
@@ -331,9 +337,15 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
 		 * it's wounded in __ww_mutex_check_kill() or has a
 		 * wakeup pending to re-read the wounded state.
 		 */
-		if (owner != current)
+		if (owner != current) {
+			/*
+			 * When waking up the task to wound, be sure to clear the
+			 * blocked_on pointer. Otherwise we can see circular
+			 * blocked_on relationships that can't resolve.
+			 */
+			__clear_task_blocked_on(owner, lock);
 			wake_q_add(wake_q, owner);
-
+		}
 		return true;
 	}