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
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -6320,6 +6320,11 @@
 			Memory area to be used by remote processor image,
 			managed by CMA.
 
+	rt_group_sched=	[KNL] Enable or disable SCHED_RR/FIFO group scheduling
+			when CONFIG_RT_GROUP_SCHED=y. Defaults to
+			!CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED.
+			Format: <bool>
+
 	rw		[KNL] Mount root device read-write on boot
 
 	S		[KNL] Run init in single mode

drivers/cpufreq/amd-pstate.c

@@ -831,8 +831,10 @@ static void amd_pstate_update_limits(unsigned int cpu)
 	if (highest_perf_changed) {
 		WRITE_ONCE(cpudata->prefcore_ranking, cur_high);
 
-		if (cur_high < CPPC_MAX_PERF)
+		if (cur_high < CPPC_MAX_PERF) {
 			sched_set_itmt_core_prio((int)cur_high, cpu);
+			sched_update_asym_prefer_cpu(cpu, prev_high, cur_high);
+		}
 	}
 }
 

include/linux/livepatch_sched.h

@@ -3,27 +3,23 @@
 #define _LINUX_LIVEPATCH_SCHED_H_
 
 #include <linux/jump_label.h>
-#include <linux/static_call_types.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_LIVEPATCH
 
 void __klp_sched_try_switch(void);
 
-#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
 DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
 
-static __always_inline void klp_sched_try_switch(void)
+static __always_inline void klp_sched_try_switch(struct task_struct *curr)
 {
-	if (static_branch_unlikely(&klp_sched_try_switch_key))
+	if (static_branch_unlikely(&klp_sched_try_switch_key) &&
+	    READ_ONCE(curr->__state) & TASK_FREEZABLE)
 		__klp_sched_try_switch();
 }
 
-#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
 #else /* !CONFIG_LIVEPATCH */
-static inline void klp_sched_try_switch(void) {}
-static inline void __klp_sched_try_switch(void) {}
+static inline void klp_sched_try_switch(struct task_struct *curr) {}
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _LINUX_LIVEPATCH_SCHED_H_ */

include/linux/sched.h

@@ -44,7 +44,6 @@
 #include <linux/seqlock_types.h>
 #include <linux/kcsan.h>
 #include <linux/rv.h>
-#include <linux/livepatch_sched.h>
 #include <linux/uidgid_types.h>
 #include <linux/tracepoint-defs.h>
 #include <asm/kmap_size.h>
@@ -2089,9 +2088,6 @@ extern int __cond_resched(void);
 
 #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
 
-void sched_dynamic_klp_enable(void);
-void sched_dynamic_klp_disable(void);
-
 DECLARE_STATIC_CALL(cond_resched, __cond_resched);
 
 static __always_inline int _cond_resched(void)
@@ -2112,7 +2108,6 @@ static __always_inline int _cond_resched(void)
 
 static inline int _cond_resched(void)
 {
-	klp_sched_try_switch();
 	return __cond_resched();
 }
 
@@ -2122,7 +2117,6 @@ static inline int _cond_resched(void)
 
 static inline int _cond_resched(void)
 {
-	klp_sched_try_switch();
 	return 0;
 }
 

include/linux/sched/topology.h

@@ -195,6 +195,8 @@ struct sched_domain_topology_level {
 };
 
 extern void __init set_sched_topology(struct sched_domain_topology_level *tl);
+extern void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio);
+
 
 # define SD_INIT_NAME(type)		.name = #type
 
@@ -223,6 +225,10 @@ static inline bool cpus_share_resources(int this_cpu, int that_cpu)
 	return true;
 }
 
+static inline void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
+{
+}
+
 #endif	/* !CONFIG_SMP */
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)

include/trace/events/sched.h

@@ -326,11 +326,37 @@ DEFINE_EVENT(sched_process_template, sched_process_free,
 	     TP_ARGS(p));
 
 /*
- * Tracepoint for a task exiting:
+ * Tracepoint for a task exiting.
+ * Note, it's a superset of sched_process_template and should be kept
+ * compatible as much as possible. sched_process_exits has an extra
+ * `group_dead` argument, so sched_process_template can't be used,
+ * unfortunately, just like sched_migrate_task above.
  */
-DEFINE_EVENT(sched_process_template, sched_process_exit,
-	     TP_PROTO(struct task_struct *p),
-	     TP_ARGS(p));
+TRACE_EVENT(sched_process_exit,
+
+	TP_PROTO(struct task_struct *p, bool group_dead),
+
+	TP_ARGS(p, group_dead),
+
+	TP_STRUCT__entry(
+		__array(	char,	comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	pid			)
+		__field(	int,	prio			)
+		__field(	bool,	group_dead		)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+		__entry->pid		= p->pid;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
+		__entry->group_dead	= group_dead;
+	),
+
+	TP_printk("comm=%s pid=%d prio=%d group_dead=%s",
+		  __entry->comm, __entry->pid, __entry->prio,
+		  __entry->group_dead ? "true" : "false"
+	)
+);
 
 /*
  * Tracepoint for waiting on task to unschedule:

init/Kconfig

@@ -1075,6 +1075,17 @@ config RT_GROUP_SCHED
 	  realtime bandwidth for them.
 	  See Documentation/scheduler/sched-rt-group.rst for more information.
 
+config RT_GROUP_SCHED_DEFAULT_DISABLED
+	bool "Require boot parameter to enable group scheduling for SCHED_RR/FIFO"
+	depends on RT_GROUP_SCHED
+	default n
+	help
+	  When set, the RT group scheduling is disabled by default. The option
+	  is in inverted form so that mere RT_GROUP_SCHED enables the group
+	  scheduling.
+
+	  Say N if unsure.
+
 config EXT_GROUP_SCHED
 	bool
 	depends on SCHED_CLASS_EXT && CGROUP_SCHED

kernel/exit.c

@@ -942,12 +942,12 @@ void __noreturn do_exit(long code)
 
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
+	trace_sched_process_exit(tsk, group_dead);
 
 	exit_mm();
 
 	if (group_dead)
 		acct_process();
-	trace_sched_process_exit(tsk);
 
 	exit_sem(tsk);
 	exit_shm(tsk);

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;
 }