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
  ...

1 files changed, 72 insertions, 57 deletions

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ad04a5c3162a2..2024c1d36402d 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -136,6 +136,10 @@
  * cost-wise, yet way more sensitive and accurate than periodic
  * sampling of the aggregate task states would be.
  */
+#include <linux/sched/clock.h>
+#include <linux/workqueue.h>
+#include <linux/psi.h>
+#include "sched.h"
 
 static int psi_bug __read_mostly;
 
@@ -172,6 +176,28 @@ struct psi_group psi_system = {
 	.pcpu = &system_group_pcpu,
 };
 
+static DEFINE_PER_CPU(seqcount_t, psi_seq);
+
+static inline void psi_write_begin(int cpu)
+{
+	write_seqcount_begin(per_cpu_ptr(&psi_seq, cpu));
+}
+
+static inline void psi_write_end(int cpu)
+{
+	write_seqcount_end(per_cpu_ptr(&psi_seq, cpu));
+}
+
+static inline u32 psi_read_begin(int cpu)
+{
+	return read_seqcount_begin(per_cpu_ptr(&psi_seq, cpu));
+}
+
+static inline bool psi_read_retry(int cpu, u32 seq)
+{
+	return read_seqcount_retry(per_cpu_ptr(&psi_seq, cpu), seq);
+}
+
 static void psi_avgs_work(struct work_struct *work);
 
 static void poll_timer_fn(struct timer_list *t);
@@ -182,7 +208,7 @@ static void group_init(struct psi_group *group)
 
 	group->enabled = true;
 	for_each_possible_cpu(cpu)
-		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
+		seqcount_init(per_cpu_ptr(&psi_seq, cpu));
 	group->avg_last_update = sched_clock();
 	group->avg_next_update = group->avg_last_update + psi_period;
 	mutex_init(&group->avgs_lock);
@@ -262,14 +288,14 @@ static void get_recent_times(struct psi_group *group, int cpu,
 
 	/* Snapshot a coherent view of the CPU state */
 	do {
-		seq = read_seqcount_begin(&groupc->seq);
+		seq = psi_read_begin(cpu);
 		now = cpu_clock(cpu);
 		memcpy(times, groupc->times, sizeof(groupc->times));
 		state_mask = groupc->state_mask;
 		state_start = groupc->state_start;
 		if (cpu == current_cpu)
 			memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
-	} while (read_seqcount_retry(&groupc->seq, seq));
+	} while (psi_read_retry(cpu, seq));
 
 	/* Calculate state time deltas against the previous snapshot */
 	for (s = 0; s < NR_PSI_STATES; s++) {
@@ -768,31 +794,21 @@ static void record_times(struct psi_group_cpu *groupc, u64 now)
 		groupc->times[PSI_NONIDLE] += delta;
 }
 
+#define for_each_group(iter, group) \
+	for (typeof(group) iter = group; iter; iter = iter->parent)
+
 static void psi_group_change(struct psi_group *group, int cpu,
 			     unsigned int clear, unsigned int set,
-			     bool wake_clock)
+			     u64 now, bool wake_clock)
 {
 	struct psi_group_cpu *groupc;
 	unsigned int t, m;
 	u32 state_mask;
-	u64 now;
 
 	lockdep_assert_rq_held(cpu_rq(cpu));
 	groupc = per_cpu_ptr(group->pcpu, cpu);
 
 	/*
-	 * First we update the task counts according to the state
-	 * change requested through the @clear and @set bits.
-	 *
-	 * Then if the cgroup PSI stats accounting enabled, we
-	 * assess the aggregate resource states this CPU's tasks
-	 * have been in since the last change, and account any
-	 * SOME and FULL time these may have resulted in.
-	 */
-	write_seqcount_begin(&groupc->seq);
-	now = cpu_clock(cpu);
-
-	/*
 	 * Start with TSK_ONCPU, which doesn't have a corresponding
 	 * task count - it's just a boolean flag directly encoded in
 	 * the state mask. Clear, set, or carry the current state if
@@ -843,7 +859,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
 
 		groupc->state_mask = state_mask;
 
-		write_seqcount_end(&groupc->seq);
 		return;
 	}
 
@@ -864,8 +879,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
 
 	groupc->state_mask = state_mask;
 
-	write_seqcount_end(&groupc->seq);
-
 	if (state_mask & group->rtpoll_states)
 		psi_schedule_rtpoll_work(group, 1, false);
 
@@ -900,24 +913,29 @@ static void psi_flags_change(struct task_struct *task, int clear, int set)
 void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
-	struct psi_group *group;
+	u64 now;
 
 	if (!task->pid)
 		return;
 
 	psi_flags_change(task, clear, set);
 
-	group = task_psi_group(task);
-	do {
-		psi_group_change(group, cpu, clear, set, true);
-	} while ((group = group->parent));
+	psi_write_begin(cpu);
+	now = cpu_clock(cpu);
+	for_each_group(group, task_psi_group(task))
+		psi_group_change(group, cpu, clear, set, now, true);
+	psi_write_end(cpu);
 }
 
 void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		     bool sleep)
 {
-	struct psi_group *group, *common = NULL;
+	struct psi_group *common = NULL;
 	int cpu = task_cpu(prev);
+	u64 now;
+
+	psi_write_begin(cpu);
+	now = cpu_clock(cpu);
 
 	if (next->pid) {
 		psi_flags_change(next, 0, TSK_ONCPU);
@@ -926,16 +944,15 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		 * ancestors with @prev, those will already have @prev's
 		 * TSK_ONCPU bit set, and we can stop the iteration there.
 		 */
-		group = task_psi_group(next);
-		do {
-			if (per_cpu_ptr(group->pcpu, cpu)->state_mask &
-			    PSI_ONCPU) {
+		for_each_group(group, task_psi_group(next)) {
+			struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
+
+			if (groupc->state_mask & PSI_ONCPU) {
 				common = group;
 				break;
 			}
-
-			psi_group_change(group, cpu, 0, TSK_ONCPU, true);
-		} while ((group = group->parent));
+			psi_group_change(group, cpu, 0, TSK_ONCPU, now, true);
+		}
 	}
 
 	if (prev->pid) {
@@ -968,12 +985,11 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 
 		psi_flags_change(prev, clear, set);
 
-		group = task_psi_group(prev);
-		do {
+		for_each_group(group, task_psi_group(prev)) {
 			if (group == common)
 				break;
-			psi_group_change(group, cpu, clear, set, wake_clock);
-		} while ((group = group->parent));
+			psi_group_change(group, cpu, clear, set, now, wake_clock);
+		}
 
 		/*
 		 * TSK_ONCPU is handled up to the common ancestor. If there are
@@ -983,20 +999,21 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		 */
 		if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) {
 			clear &= ~TSK_ONCPU;
-			for (; group; group = group->parent)
-				psi_group_change(group, cpu, clear, set, wake_clock);
+			for_each_group(group, common)
+				psi_group_change(group, cpu, clear, set, now, wake_clock);
 		}
 	}
+	psi_write_end(cpu);
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_struct *prev)
 {
 	int cpu = task_cpu(curr);
-	struct psi_group *group;
 	struct psi_group_cpu *groupc;
 	s64 delta;
 	u64 irq;
+	u64 now;
 
 	if (static_branch_likely(&psi_disabled) || !irqtime_enabled())
 		return;
@@ -1005,8 +1022,7 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st
 		return;
 
 	lockdep_assert_rq_held(rq);
-	group = task_psi_group(curr);
-	if (prev && task_psi_group(prev) == group)
+	if (prev && task_psi_group(prev) == task_psi_group(curr))
 		return;
 
 	irq = irq_time_read(cpu);
@@ -1015,27 +1031,24 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st
 		return;
 	rq->psi_irq_time = irq;
 
-	do {
-		u64 now;
+	psi_write_begin(cpu);
+	now = cpu_clock(cpu);
 
+	for_each_group(group, task_psi_group(curr)) {
 		if (!group->enabled)
 			continue;
 
 		groupc = per_cpu_ptr(group->pcpu, cpu);
 
-		write_seqcount_begin(&groupc->seq);
-		now = cpu_clock(cpu);
-
 		record_times(groupc, now);
 		groupc->times[PSI_IRQ_FULL] += delta;
 
-		write_seqcount_end(&groupc->seq);
-
 		if (group->rtpoll_states & (1 << PSI_IRQ_FULL))
 			psi_schedule_rtpoll_work(group, 1, false);
-	} while ((group = group->parent));
+	}
+	psi_write_end(cpu);
 }
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /**
  * psi_memstall_enter - mark the beginning of a memory stall section
@@ -1221,12 +1234,14 @@ void psi_cgroup_restart(struct psi_group *group)
 		return;
 
 	for_each_possible_cpu(cpu) {
-		struct rq *rq = cpu_rq(cpu);
-		struct rq_flags rf;
+		u64 now;
+
+		guard(rq_lock_irq)(cpu_rq(cpu));
 
-		rq_lock_irq(rq, &rf);
-		psi_group_change(group, cpu, 0, 0, true);
-		rq_unlock_irq(rq, &rf);
+		psi_write_begin(cpu);
+		now = cpu_clock(cpu);
+		psi_group_change(group, cpu, 0, 0, now, true);
+		psi_write_end(cpu);
 	}
 }
 #endif /* CONFIG_CGROUPS */
@@ -1651,7 +1666,7 @@ static const struct proc_ops psi_irq_proc_ops = {
 	.proc_poll	= psi_fop_poll,
 	.proc_release	= psi_fop_release,
 };
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 static int __init psi_proc_init(void)
 {