Merge tag 'sched-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Update Daniel Bristot de Oliveira's entry in MAINTAINERS,
   and credit him in CREDITS

 - Harmonize the lock-yielding behavior on dynamically selected
   preemption models with static ones

 - Reorganize the code a bit: split out sched/syscalls.c to reduce
   the size of sched/core.c

 - Micro-optimize psi_group_change()

 - Fix set_load_weight() for SCHED_IDLE tasks

 - Misc cleanups & fixes

* tag 'sched-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Update MAINTAINERS and CREDITS
  sched/fair: set_load_weight() must also call reweight_task() for SCHED_IDLE tasks
  sched/psi: Optimise psi_group_change a bit
  sched/core: Drop spinlocks on contention iff kernel is preemptible
  sched/core: Move preempt_model_*() helpers from sched.h to preempt.h
  sched/balance: Skip unnecessary updates to idle load balancer's flags
  idle: Remove stale RCU comment
  sched/headers: Move struct pre-declarations to the beginning of the header
  sched/core: Clean up kernel/sched/sched.h a bit
  sched/core: Simplify prefetch_curr_exec_start()
  sched: Fix spelling in comments
  sched/syscalls: Split out kernel/sched/syscalls.c from kernel/sched/core.c

Author: torvalds

CREDITS

@@ -271,6 +271,9 @@ D: Driver for WaveFront soundcards (Turtle Beach Maui, Tropez, Tropez+)
 D: Various bugfixes and changes to sound drivers
 S: USA
 
+N: Daniel Bristot de Oliveira
+D: Scheduler contributions, notably: SCHED_DEADLINE
+
 N: Carlos Henrique Bauer
 E: [email protected]
 E: [email protected]

Documentation/admin-guide/kernel-parameters.txt

@@ -4728,7 +4728,9 @@
 			none - Limited to cond_resched() calls
 			voluntary - Limited to cond_resched() and might_sleep() calls
 			full - Any section that isn't explicitly preempt disabled
-			       can be preempted anytime.
+			       can be preempted anytime.  Tasks will also yield
+			       contended spinlocks (if the critical section isn't
+			       explicitly preempt disabled beyond the lock itself).
 
 	print-fatal-signals=
 			[KNL] debug: print fatal signals

MAINTAINERS

@@ -20047,7 +20047,6 @@ R:	Dietmar Eggemann <[email protected]> (SCHED_NORMAL)
 R:	Steven Rostedt <[email protected]> (SCHED_FIFO/SCHED_RR)
 R:	Ben Segall <[email protected]> (CONFIG_CFS_BANDWIDTH)
 R:	Mel Gorman <[email protected]> (CONFIG_NUMA_BALANCING)
-R:	Daniel Bristot de Oliveira <[email protected]> (SCHED_DEADLINE)
 R:	Valentin Schneider <[email protected]> (TOPOLOGY)
 L:	[email protected]
 S:	Maintained

include/linux/preempt.h

@@ -481,4 +481,45 @@ DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable())
 DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace())
 DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+extern bool preempt_model_none(void);
+extern bool preempt_model_voluntary(void);
+extern bool preempt_model_full(void);
+
+#else
+
+static inline bool preempt_model_none(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_NONE);
+}
+static inline bool preempt_model_voluntary(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
+}
+static inline bool preempt_model_full(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT);
+}
+
+#endif
+
+static inline bool preempt_model_rt(void)
+{
+	return IS_ENABLED(CONFIG_PREEMPT_RT);
+}
+
+/*
+ * Does the preemption model allow non-cooperative preemption?
+ *
+ * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with
+ * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the
+ * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the
+ * PREEMPT_NONE model.
+ */
+static inline bool preempt_model_preemptible(void)
+{
+	return preempt_model_full() || preempt_model_rt();
+}
+
 #endif /* __LINUX_PREEMPT_H */

include/linux/sched.h

@@ -2064,47 +2064,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
 	__cond_resched_rwlock_write(lock);					\
 })
 
-#ifdef CONFIG_PREEMPT_DYNAMIC
-
-extern bool preempt_model_none(void);
-extern bool preempt_model_voluntary(void);
-extern bool preempt_model_full(void);
-
-#else
-
-static inline bool preempt_model_none(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT_NONE);
-}
-static inline bool preempt_model_voluntary(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
-}
-static inline bool preempt_model_full(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT);
-}
-
-#endif
-
-static inline bool preempt_model_rt(void)
-{
-	return IS_ENABLED(CONFIG_PREEMPT_RT);
-}
-
-/*
- * Does the preemption model allow non-cooperative preemption?
- *
- * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with
- * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the
- * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the
- * PREEMPT_NONE model.
- */
-static inline bool preempt_model_preemptible(void)
-{
-	return preempt_model_full() || preempt_model_rt();
-}
-
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());

include/linux/spinlock.h

@@ -462,11 +462,10 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
  */
 static inline int spin_needbreak(spinlock_t *lock)
 {
-#ifdef CONFIG_PREEMPTION
+	if (!preempt_model_preemptible())
+		return 0;
+
 	return spin_is_contended(lock);
-#else
-	return 0;
-#endif
 }
 
 /*
@@ -479,11 +478,10 @@ static inline int spin_needbreak(spinlock_t *lock)
  */
 static inline int rwlock_needbreak(rwlock_t *lock)
 {
-#ifdef CONFIG_PREEMPTION
+	if (!preempt_model_preemptible())
+		return 0;
+
 	return rwlock_is_contended(lock);
-#else
-	return 0;
-#endif
 }
 
 /*

kernel/sched/build_policy.c

@@ -52,3 +52,4 @@
 #include "cputime.c"
 #include "deadline.c"
 
+#include "syscalls.c"

kernel/sched/clock.c

@@ -340,7 +340,7 @@ static notrace u64 sched_clock_remote(struct sched_clock_data *scd)
 	this_clock = sched_clock_local(my_scd);
 	/*
 	 * We must enforce atomic readout on 32-bit, otherwise the
-	 * update on the remote CPU can hit inbetween the readout of
+	 * update on the remote CPU can hit in between the readout of
 	 * the low 32-bit and the high 32-bit portion.
 	 */
 	remote_clock = cmpxchg64(&scd->clock, 0, 0);
@@ -444,7 +444,7 @@ notrace void sched_clock_tick_stable(void)
 }
 
 /*
- * We are going deep-idle (irqs are disabled):
+ * We are going deep-idle (IRQs are disabled):
  */
 notrace void sched_clock_idle_sleep_event(void)
 {