Merge tag 'timers-nohz-2026-06-13' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip

Pull NOHZ updates from Thomas Gleixner:

 - Fix a long standing TOCTOU in get_cpu_sleep_time_us()

 - Make the CPU offline NOHZ handling more robust by disabling NOHZ on
   the outgoing CPU early instead of creating unneeded state which needs
   to be undone.

 - Unify idle CPU time accounting instead of having two different
   accounting mechanisms. These two different mechanisms are not really
   independent, but the different properties can in the worst case cause
   that gloabl idle time can be observed going backwards.

 - Consolidate the idle/iowait time retrieval interfaces instead of
   converting back and forth between them.

 - Make idle interrupt time accounting more robust. The original code
   assumes that interrupt time accouting is enabled and therefore stops
   elapsing idle time while an interrupt is handled in NOHZ dyntick
   state. That assumption is not correct as interrupt time accounting
   can be disabled at compile and runtime.

 - Fix an accounting error between dyntick idle time and dyntick idle
   steal time. The stolen time is not accounted and therefore idle time
   becomes inaccurate. The stolen time is now accounted after the fact
   as there is no way to predict the steal time upfront.

* tag 'timers-nohz-2026-06-13' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip:
  sched/cputime: Handle dyntick-idle steal time correctly
  sched/cputime: Handle idle irqtime gracefully
  sched/cputime: Provide get_cpu_[idle|iowait]_time_us() off-case
  tick/sched: Consolidate idle time fetching APIs
  tick/sched: Account tickless idle cputime only when tick is stopped
  tick/sched: Remove unused fields
  tick/sched: Move dyntick-idle cputime accounting to cputime code
  tick/sched: Remove nohz disabled special case in cputime fetch
  tick/sched: Unify idle cputime accounting
  s390/time: Prepare to stop elapsing in dynticks-idle
  powerpc/time: Prepare to stop elapsing in dynticks-idle
  sched/cputime: Correctly support generic vtime idle time
  sched/cputime: Remove superfluous and error prone kcpustat_field() parameter
  sched/idle: Handle offlining first in idle loop
  tick/sched: Fix TOCTOU in nohz idle time fetch

3 files changed, 82 insertions, 20 deletions

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index b97ce2df376f..fce1392e2140 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -34,7 +34,14 @@ enum cpu_usage_stat {
 };
 
 struct kernel_cpustat {
-	u64 cpustat[NR_STATS];
+#ifdef CONFIG_NO_HZ_COMMON
+	bool		idle_dyntick;
+	bool		idle_elapse;
+	seqcount_t	idle_sleeptime_seq;
+	u64		idle_entrytime;
+	u64		idle_stealtime[2];
+#endif
+	u64		cpustat[NR_STATS];
 };
 
 struct kernel_stat {
@@ -99,23 +106,68 @@ static inline unsigned long kstat_cpu_irqs_sum(unsigned int cpu)
 	return kstat_cpu(cpu).irqs_sum;
 }
 
+#ifdef CONFIG_NO_HZ_COMMON
+extern void kcpustat_dyntick_start(u64 now);
+extern void kcpustat_dyntick_stop(u64 now);
+extern void kcpustat_irq_enter(u64 now);
+extern void kcpustat_irq_exit(u64 now);
+extern u64 kcpustat_field_idle(int cpu);
+extern u64 kcpustat_field_iowait(int cpu);
+
+static inline bool kcpustat_idle_dyntick(void)
+{
+	return __this_cpu_read(kernel_cpustat.idle_dyntick);
+}
+#else
+static inline u64 kcpustat_field_idle(int cpu)
+{
+	return kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
+}
+static inline u64 kcpustat_field_iowait(int cpu)
+{
+	return kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
+}
+
+static inline bool kcpustat_idle_dyntick(void)
+{
+	return false;
+}
+#endif /* CONFIG_NO_HZ_COMMON */
+
+extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
+extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
+
+/* Fetch cputime values when vtime is disabled on a CPU */
+static inline u64 kcpustat_field_default(enum cpu_usage_stat usage, int cpu)
+{
+	if (usage == CPUTIME_IDLE)
+		return kcpustat_field_idle(cpu);
+	if (usage == CPUTIME_IOWAIT)
+		return kcpustat_field_iowait(cpu);
+	return kcpustat_cpu(cpu).cpustat[usage];
+}
+
+static inline void kcpustat_cpu_fetch_default(struct kernel_cpustat *dst, int cpu)
+{
+	*dst = kcpustat_cpu(cpu);
+	dst->cpustat[CPUTIME_IDLE] = kcpustat_field_idle(cpu);
+	dst->cpustat[CPUTIME_IOWAIT] = kcpustat_field_iowait(cpu);
+}
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern u64 kcpustat_field(struct kernel_cpustat *kcpustat,
-			  enum cpu_usage_stat usage, int cpu);
+extern u64 kcpustat_field(enum cpu_usage_stat usage, int cpu);
 extern void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu);
 #else
-static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat,
-				 enum cpu_usage_stat usage, int cpu)
+static inline u64 kcpustat_field(enum cpu_usage_stat usage, int cpu)
 {
-	return kcpustat->cpustat[usage];
+	return kcpustat_field_default(usage, cpu);
 }
 
 static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
 {
-	*dst = kcpustat_cpu(cpu);
+	kcpustat_cpu_fetch_default(dst, cpu);
 }
-
-#endif
+#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
 extern void account_user_time(struct task_struct *, u64);
 extern void account_guest_time(struct task_struct *, u64);
@@ -124,19 +176,17 @@ extern void account_system_index_time(struct task_struct *, u64,
 				      enum cpu_usage_stat);
 extern void account_steal_time(u64);
 extern void account_idle_time(u64);
-extern u64 get_idle_time(struct kernel_cpustat *kcs, int cpu);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static inline void account_process_tick(struct task_struct *tsk, int user)
 {
-	vtime_flush(tsk);
+	if (!kcpustat_idle_dyntick())
+		vtime_flush(tsk);
 }
 #else
 extern void account_process_tick(struct task_struct *, int user);
 #endif
 
-extern void account_idle_ticks(unsigned long ticks);
-
 #ifdef CONFIG_SCHED_CORE
 extern void __account_forceidle_time(struct task_struct *tsk, u64 delta);
 #endif
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 738007d6f577..1cf4651f09ad 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -139,8 +139,6 @@ extern bool tick_nohz_idle_got_tick(void);
 extern ktime_t tick_nohz_get_next_hrtimer(void);
 extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
-extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
-extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
 #else /* !CONFIG_NO_HZ_COMMON */
 #define tick_nohz_enabled (0)
 static inline bool tick_nohz_is_active(void) { return false; }
@@ -162,8 +160,6 @@ static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 	*delta_next = TICK_NSEC;
 	return *delta_next;
 }
-static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
-static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 #endif /* !CONFIG_NO_HZ_COMMON */
 
 /*
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 29dd5b91dd7d..9dc25b04a119 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -10,7 +10,6 @@
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 extern void vtime_account_kernel(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
@@ -27,16 +26,33 @@ static inline void vtime_guest_exit(struct task_struct *tsk) { }
 static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
 #endif
 
+static inline bool vtime_generic_enabled_cpu(int cpu)
+{
+	return context_tracking_enabled_cpu(cpu);
+}
+
+static inline bool vtime_generic_enabled_this_cpu(void)
+{
+	return context_tracking_enabled_this_cpu();
+}
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+extern void vtime_account_idle(struct task_struct *tsk);
 extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset);
 extern void vtime_account_softirq(struct task_struct *tsk);
 extern void vtime_account_hardirq(struct task_struct *tsk);
 extern void vtime_flush(struct task_struct *tsk);
+extern void vtime_reset(void);
+extern void vtime_dyntick_start(void);
+extern void vtime_dyntick_stop(void);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { }
 static inline void vtime_account_softirq(struct task_struct *tsk) { }
 static inline void vtime_account_hardirq(struct task_struct *tsk) { }
 static inline void vtime_flush(struct task_struct *tsk) { }
+static inline void vtime_reset(void) { }
+static inline void vtime_dyntick_start(void) { }
+static inline void vtime_dyntick_stop(void) { }
 #endif
 
 /*
@@ -74,12 +90,12 @@ static inline bool vtime_accounting_enabled(void)
 
 static inline bool vtime_accounting_enabled_cpu(int cpu)
 {
-	return context_tracking_enabled_cpu(cpu);
+	return vtime_generic_enabled_cpu(cpu);
 }
 
 static inline bool vtime_accounting_enabled_this_cpu(void)
 {
-	return context_tracking_enabled_this_cpu();
+	return vtime_generic_enabled_this_cpu();
 }
 
 extern void vtime_task_switch_generic(struct task_struct *prev);