Commit eaed94d1 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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
  ...
parents 3ba121c9 90ca9410

Documentation/admin-guide/kernel-parameters.txt

+5 −0
Original line number Diff line number Diff line
@@ -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

+3 −1
Original line number Diff line number Diff line
@@ -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

+5 −9
Original line number Diff line number Diff line
@@ -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

+0 −6
Original line number Diff line number Diff line
@@ -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

+6 −0
Original line number Diff line number Diff line
@@ -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)