Merge tag 'sched-core-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Fair scheduler (SCHED_FAIR) enhancements:

   - Behavioral improvements:
      - Untangle NEXT_BUDDY and pick_next_task() (Peter Zijlstra)

   - Delayed-dequeue enhancements & fixes: (Vincent Guittot)
      - Rename h_nr_running into h_nr_queued
      - Add new cfs_rq.h_nr_runnable
      - Use the new cfs_rq.h_nr_runnable
      - Removed unsued cfs_rq.h_nr_delayed
      - Rename cfs_rq.idle_h_nr_running into h_nr_idle
      - Remove unused cfs_rq.idle_nr_running
      - Rename cfs_rq.nr_running into nr_queued
      - Do not try to migrate delayed dequeue task
      - Fix variable declaration position
      - Encapsulate set custom slice in a __setparam_fair() function

   - Fixes:
      - Fix race between yield_to() and try_to_wake_up() (Tianchen Ding)
      - Fix CPU bandwidth limit bypass during CPU hotplug (Vishal
        Chourasia)

   - Cleanups:
      - Clean up in migrate_degrades_locality() to improve readability
        (Peter Zijlstra)
      - Mark m*_vruntime() with __maybe_unused (Andy Shevchenko)
      - Update comments after sched_tick() rename (Sebastian Andrzej
        Siewior)
      - Remove CONFIG_CFS_BANDWIDTH=n definition of cfs_bandwidth_used()
        (Valentin Schneider)

  Deadline scheduler (SCHED_DL) enhancements:

   - Restore dl_server bandwidth on non-destructive root domain changes
     (Juri Lelli)

   - Correctly account for allocated bandwidth during hotplug (Juri
     Lelli)

   - Check bandwidth overflow earlier for hotplug (Juri Lelli)

   - Clean up goto label in pick_earliest_pushable_dl_task() (John
     Stultz)

   - Consolidate timer cancellation (Wander Lairson Costa)

  Load-balancer enhancements:

   - Improve performance by prioritizing migrating eligible tasks in
     sched_balance_rq() (Hao Jia)

   - Do not compute NUMA Balancing stats unnecessarily during
     load-balancing (K Prateek Nayak)

   - Do not compute overloaded status unnecessarily during
     load-balancing (K Prateek Nayak)

  Generic scheduling code enhancements:

   - Use READ_ONCE() in task_on_rq_queued(), to consistently use the
     WRITE_ONCE() updated ->on_rq field (Harshit Agarwal)

  Isolated CPUs support enhancements: (Waiman Long)

   - Make "isolcpus=nohz" equivalent to "nohz_full"
   - Consolidate housekeeping cpumasks that are always identical
   - Remove HK_TYPE_SCHED
   - Unify HK_TYPE_{TIMER|TICK|MISC} to HK_TYPE_KERNEL_NOISE

  RSEQ enhancements:

   - Validate read-only fields under DEBUG_RSEQ config (Mathieu
     Desnoyers)

  PSI enhancements:

   - Fix race when task wakes up before psi_sched_switch() adjusts flags
     (Chengming Zhou)

  IRQ time accounting performance enhancements: (Yafang Shao)

   - Define sched_clock_irqtime as static key
   - Don't account irq time if sched_clock_irqtime is disabled

  Virtual machine scheduling enhancements:

   - Don't try to catch up excess steal time (Suleiman Souhlal)

  Heterogenous x86 CPU scheduling enhancements: (K Prateek Nayak)

   - Convert "sysctl_sched_itmt_enabled" to boolean
   - Use guard() for itmt_update_mutex
   - Move the "sched_itmt_enabled" sysctl to debugfs
   - Remove x86_smt_flags and use cpu_smt_flags directly
   - Use x86_sched_itmt_flags for PKG domain unconditionally

  Debugging code & instrumentation enhancements:

   - Change need_resched warnings to pr_err() (David Rientjes)
   - Print domain name in /proc/schedstat (K Prateek Nayak)
   - Fix value reported by hot tasks pulled in /proc/schedstat (Peter
     Zijlstra)
   - Report the different kinds of imbalances in /proc/schedstat
     (Swapnil Sapkal)
   - Move sched domain name out of CONFIG_SCHED_DEBUG (Swapnil Sapkal)
   - Update Schedstat version to 17 (Swapnil Sapkal)"

* tag 'sched-core-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  rseq: Fix rseq unregistration regression
  psi: Fix race when task wakes up before psi_sched_switch() adjusts flags
  sched, psi: Don't account irq time if sched_clock_irqtime is disabled
  sched: Don't account irq time if sched_clock_irqtime is disabled
  sched: Define sched_clock_irqtime as static key
  sched/fair: Do not compute overloaded status unnecessarily during lb
  sched/fair: Do not compute NUMA Balancing stats unnecessarily during lb
  x86/topology: Use x86_sched_itmt_flags for PKG domain unconditionally
  x86/topology: Remove x86_smt_flags and use cpu_smt_flags directly
  x86/itmt: Move the "sched_itmt_enabled" sysctl to debugfs
  x86/itmt: Use guard() for itmt_update_mutex
  x86/itmt: Convert "sysctl_sched_itmt_enabled" to boolean
  sched/core: Prioritize migrating eligible tasks in sched_balance_rq()
  sched/debug: Change need_resched warnings to pr_err
  sched/fair: Encapsulate set custom slice in a __setparam_fair() function
  sched: Fix race between yield_to() and try_to_wake_up()
  docs: Update Schedstat version to 17
  sched/stats: Print domain name in /proc/schedstat
  sched: Move sched domain name out of CONFIG_SCHED_DEBUG
  sched: Report the different kinds of imbalances in /proc/schedstat
  ...

3 files changed, 37 insertions, 67 deletions

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 3973cb9bb2e6..ec134b719144 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -251,7 +251,7 @@ extern bool x86_topology_update;
 #include <asm/percpu.h>
 
 DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority);
-extern unsigned int __read_mostly sysctl_sched_itmt_enabled;
+extern bool __read_mostly sysctl_sched_itmt_enabled;
 
 /* Interface to set priority of a cpu */
 void sched_set_itmt_core_prio(int prio, int core_cpu);
@@ -264,7 +264,7 @@ void sched_clear_itmt_support(void);
 
 #else /* CONFIG_SCHED_MC_PRIO */
 
-#define sysctl_sched_itmt_enabled	0
+#define sysctl_sched_itmt_enabled	false
 static inline void sched_set_itmt_core_prio(int prio, int core_cpu)
 {
 }
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index 51b805c727fc..9cea1fc36c18 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/cpumask.h>
 #include <linux/cpuset.h>
+#include <linux/debugfs.h>
 #include <linux/mutex.h>
 #include <linux/sysctl.h>
 #include <linux/nodemask.h>
@@ -34,49 +35,38 @@ static bool __read_mostly sched_itmt_capable;
  * of higher turbo frequency for cpus supporting Intel Turbo Boost Max
  * Technology 3.0.
  *
- * It can be set via /proc/sys/kernel/sched_itmt_enabled
+ * It can be set via /sys/kernel/debug/x86/sched_itmt_enabled
  */
-unsigned int __read_mostly sysctl_sched_itmt_enabled;
+bool __read_mostly sysctl_sched_itmt_enabled;
 
-static int sched_itmt_update_handler(const struct ctl_table *table, int write,
-				     void *buffer, size_t *lenp, loff_t *ppos)
+static ssize_t sched_itmt_enabled_write(struct file *filp,
+					const char __user *ubuf,
+					size_t cnt, loff_t *ppos)
 {
-	unsigned int old_sysctl;
-	int ret;
+	ssize_t result;
+	bool orig;
 
-	mutex_lock(&itmt_update_mutex);
+	guard(mutex)(&itmt_update_mutex);
 
-	if (!sched_itmt_capable) {
-		mutex_unlock(&itmt_update_mutex);
-		return -EINVAL;
-	}
-
-	old_sysctl = sysctl_sched_itmt_enabled;
-	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	orig = sysctl_sched_itmt_enabled;
+	result = debugfs_write_file_bool(filp, ubuf, cnt, ppos);
 
-	if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) {
+	if (sysctl_sched_itmt_enabled != orig) {
 		x86_topology_update = true;
 		rebuild_sched_domains();
 	}
 
-	mutex_unlock(&itmt_update_mutex);
-
-	return ret;
+	return result;
 }
 
-static struct ctl_table itmt_kern_table[] = {
-	{
-		.procname	= "sched_itmt_enabled",
-		.data		= &sysctl_sched_itmt_enabled,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_itmt_update_handler,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
+static const struct file_operations dfs_sched_itmt_fops = {
+	.read =         debugfs_read_file_bool,
+	.write =        sched_itmt_enabled_write,
+	.open =         simple_open,
+	.llseek =       default_llseek,
 };
 
-static struct ctl_table_header *itmt_sysctl_header;
+static struct dentry *dfs_sched_itmt;
 
 /**
  * sched_set_itmt_support() - Indicate platform supports ITMT
@@ -97,16 +87,18 @@ static struct ctl_table_header *itmt_sysctl_header;
  */
 int sched_set_itmt_support(void)
 {
-	mutex_lock(&itmt_update_mutex);
+	guard(mutex)(&itmt_update_mutex);
 
-	if (sched_itmt_capable) {
-		mutex_unlock(&itmt_update_mutex);
+	if (sched_itmt_capable)
 		return 0;
-	}
 
-	itmt_sysctl_header = register_sysctl("kernel", itmt_kern_table);
-	if (!itmt_sysctl_header) {
-		mutex_unlock(&itmt_update_mutex);
+	dfs_sched_itmt = debugfs_create_file_unsafe("sched_itmt_enabled",
+						    0644,
+						    arch_debugfs_dir,
+						    &sysctl_sched_itmt_enabled,
+						    &dfs_sched_itmt_fops);
+	if (IS_ERR_OR_NULL(dfs_sched_itmt)) {
+		dfs_sched_itmt = NULL;
 		return -ENOMEM;
 	}
 
@@ -117,8 +109,6 @@ int sched_set_itmt_support(void)
 	x86_topology_update = true;
 	rebuild_sched_domains();
 
-	mutex_unlock(&itmt_update_mutex);
-
 	return 0;
 }
 
@@ -134,18 +124,15 @@ int sched_set_itmt_support(void)
  */
 void sched_clear_itmt_support(void)
 {
-	mutex_lock(&itmt_update_mutex);
+	guard(mutex)(&itmt_update_mutex);
 
-	if (!sched_itmt_capable) {
-		mutex_unlock(&itmt_update_mutex);
+	if (!sched_itmt_capable)
 		return;
-	}
+
 	sched_itmt_capable = false;
 
-	if (itmt_sysctl_header) {
-		unregister_sysctl_table(itmt_sysctl_header);
-		itmt_sysctl_header = NULL;
-	}
+	debugfs_remove(dfs_sched_itmt);
+	dfs_sched_itmt = NULL;
 
 	if (sysctl_sched_itmt_enabled) {
 		/* disable sched_itmt if we are no longer ITMT capable */
@@ -153,8 +140,6 @@ void sched_clear_itmt_support(void)
 		x86_topology_update = true;
 		rebuild_sched_domains();
 	}
-
-	mutex_unlock(&itmt_update_mutex);
 }
 
 int arch_asym_cpu_priority(int cpu)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0e3f9bad0395..c10850ae6f09 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -483,12 +483,6 @@ static int x86_core_flags(void)
 	return cpu_core_flags() | x86_sched_itmt_flags();
 }
 #endif
-#ifdef CONFIG_SCHED_SMT
-static int x86_smt_flags(void)
-{
-	return cpu_smt_flags();
-}
-#endif
 #ifdef CONFIG_SCHED_CLUSTER
 static int x86_cluster_flags(void)
 {
@@ -496,15 +490,6 @@ static int x86_cluster_flags(void)
 }
 #endif
 
-static int x86_die_flags(void)
-{
-	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU) ||
-	    cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES))
-		return x86_sched_itmt_flags();
-
-	return 0;
-}
-
 /*
  * Set if a package/die has multiple NUMA nodes inside.
  * AMD Magny-Cours, Intel Cluster-on-Die, and Intel
@@ -520,7 +505,7 @@ static void __init build_sched_topology(void)
 
 #ifdef CONFIG_SCHED_SMT
 	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT)
+		cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT)
 	};
 #endif
 #ifdef CONFIG_SCHED_CLUSTER
@@ -540,7 +525,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(PKG)
+			cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(PKG)
 		};
 	}