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

Pull timer core updates from Thomas Gleixner:
 "Updates for the time/timer core subsystem:

   - Harden the user space controllable hrtimer interfaces further to
     protect against unpriviledged DoS attempts by arming timers in the
     past.

   - Add per-capacity hierarchies to the timer migration code to prevent
     timer migration accross different capacity domains. This code has
     been disabled last minute as there is a pathological problem with
     SoCs which advertise a larger number of capacity domains. The
     problem is under investigation and the code won't be active before
     v7.3, but that turned out to be less intrusive than a full revert
     as it preserves the preparatory steps and allows people to work on
     the final resolution

   - Export time namespace functionality as a recent user can be built
     as a module.

   - Initialize the jiffies clocksource before using it. The recent
     hardening against time moving backward requires that the related
     members of struct clocksource have been initialized, otherwise it
     clamps the readout to 0, which makes time stand sill and causes
     boot delays.

   - Fix a more than twenty year old PID reference count leak in an
     error path of the POSIX CPU timer code.

   - The usual small fixes, improvements and cleanups all over the
     place"

* tag 'timers-core-2026-06-13' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip: (31 commits)
  posix-cpu-timers: Fix pid refcount leak in do_cpu_nanosleep() error path
  time/jiffies: Register jiffies clocksource before usage
  timers/migration: Temporarily disable per capacity hierarchies
  timers/migration: Turn tmigr_hierarchy level_list into a flexible array
  timers/migration: Deactivate per-capacity hierarchies under nohz_full
  timers/migration: Fix hotplug migrator selection target on asymetric capacity machines
  ntsync: Honour caller's time namespace for absolute MONOTONIC timeouts
  time/namespace: Export init_time_ns and do_timens_ktime_to_host()
  timers/migration: Update stale @online doc to @available
  timers: Fix flseep() typo in kernel-doc comment
  hrtimer: Fix the bogus return type of __hrtimer_start_range_ns()
  hrtimer: Return ktime_t from hrtimer_get_next_event()/hrtimer_next_event_without()
  clocksource: Clean up clocksource_update_freq() functions
  alarmtimer: Remove stale return description from alarm_handle_timer()
  selftests/posix_timers: Use CLOCK_THREAD_CPUTIME_ID for ITIMER_PROF measurements
  scripts/timers: Add timer_migration_tree.py
  timers/migration: Handle capacity in connect tracepoints
  timers/migration: Split per-capacity hierarchies
  timers/migration: Track CPUs in a hierarchy
  timers/migration: Abstract out hierarchy to prepare for CPU capacity awareness
  ...

6 files changed, 53 insertions, 31 deletions

diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
index 3ffa5341dce2..2014288ca2f4 100644
--- a/include/linux/alarmtimer.h
+++ b/include/linux/alarmtimer.h
@@ -42,11 +42,14 @@ struct alarm {
 	void			*data;
 };
 
+static __always_inline ktime_t alarm_get_expires(struct alarm *alarm)
+{
+	return alarm->node.expires;
+}
+
 void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
 		void (*function)(struct alarm *, ktime_t));
-void alarm_start(struct alarm *alarm, ktime_t start);
-void alarm_start_relative(struct alarm *alarm, ktime_t start);
-void alarm_restart(struct alarm *alarm);
+bool alarm_start_timer(struct alarm *alarm, ktime_t expires, bool relative);
 int alarm_try_to_cancel(struct alarm *alarm);
 int alarm_cancel(struct alarm *alarm);
 
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index c5b34c16602e..b12a6d19aa60 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -239,8 +239,6 @@ __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq);
 extern int
 __devm_clocksource_register_scale(struct device *dev, struct clocksource *cs,
 				  u32 scale, u32 freq);
-extern void
-__clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq);
 
 /*
  * Don't call this unless you are a default clocksource
@@ -273,16 +271,6 @@ static inline int devm_clocksource_register_khz(struct device *dev,
 	return __devm_clocksource_register_scale(dev, cs, 1000, khz);
 }
 
-static inline void __clocksource_update_freq_hz(struct clocksource *cs, u32 hz)
-{
-	__clocksource_update_freq_scale(cs, 1, hz);
-}
-
-static inline void __clocksource_update_freq_khz(struct clocksource *cs, u32 khz)
-{
-	__clocksource_update_freq_scale(cs, 1000, khz);
-}
-
 #ifdef CONFIG_ARCH_CLOCKSOURCE_INIT
 extern void clocksource_arch_init(struct clocksource *cs);
 #else
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 46412c00033a..68b2a69dd24d 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -110,7 +110,7 @@ static const unsigned int max_slack_shift = 2;
  * fsleep - flexible sleep which autoselects the best mechanism
  * @usecs:	requested sleep duration in microseconds
  *
- * flseep() selects the best mechanism that will provide maximum 25% slack
+ * fsleep() selects the best mechanism that will provide maximum 25% slack
  * to the requested sleep duration. Therefore it uses:
  *
  * * udelay() loop for sleep durations <= 10 microseconds to avoid hrtimer
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 9ced498fefaa..6862dea0acc5 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -206,6 +206,9 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 				   u64 range_ns, const enum hrtimer_mode mode);
 
+extern bool hrtimer_start_range_ns_user(struct hrtimer *timer, ktime_t tim,
+					u64 range_ns, const enum hrtimer_mode mode);
+
 /**
  * hrtimer_start - (re)start an hrtimer
  * @timer:	the timer to be added
@@ -223,17 +226,28 @@ static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 
-static inline void hrtimer_start_expires(struct hrtimer *timer,
-					 enum hrtimer_mode mode)
+static inline void hrtimer_start_expires(struct hrtimer *timer, enum hrtimer_mode mode)
 {
-	u64 delta;
 	ktime_t soft, hard;
+	u64 delta;
+
 	soft = hrtimer_get_softexpires(timer);
 	hard = hrtimer_get_expires(timer);
 	delta = ktime_to_ns(ktime_sub(hard, soft));
 	hrtimer_start_range_ns(timer, soft, delta, mode);
 }
 
+static inline bool hrtimer_start_expires_user(struct hrtimer *timer, enum hrtimer_mode mode)
+{
+	ktime_t soft, hard;
+	u64 delta;
+
+	soft = hrtimer_get_softexpires(timer);
+	hard = hrtimer_get_expires(timer);
+	delta = ktime_to_ns(ktime_sub(hard, soft));
+	return hrtimer_start_range_ns_user(timer, soft, delta, mode);
+}
+
 void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl,
 				   enum hrtimer_mode mode);
 
@@ -254,8 +268,8 @@ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer)
 	return __hrtimer_get_remaining(timer, false);
 }
 
-extern u64 hrtimer_get_next_event(void);
-extern u64 hrtimer_next_event_without(const struct hrtimer *exclude);
+extern ktime_t hrtimer_get_next_event(void);
+extern ktime_t hrtimer_next_event_without(const struct hrtimer *exclude);
 
 extern bool hrtimer_active(const struct hrtimer *timer);
 
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 07cbb9836b91..ca82fd62dc30 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -299,6 +299,19 @@ DECLARE_EVENT_CLASS(hrtimer_class,
 );
 
 /**
+ * hrtimer_start_expired - Invoked when a expired timer was started
+ * @hrtimer:	pointer to struct hrtimer
+ *
+ * Preceeded by a hrtimer_start tracepoint.
+ */
+DEFINE_EVENT(hrtimer_class, hrtimer_start_expired,
+
+	TP_PROTO(struct hrtimer *hrtimer),
+
+	TP_ARGS(hrtimer)
+);
+
+/**
  * hrtimer_expire_exit - called immediately after the hrtimer callback returns
  * @hrtimer:	pointer to struct hrtimer
  *
diff --git a/include/trace/events/timer_migration.h b/include/trace/events/timer_migration.h
index 61171b13c687..0b135e9301b1 100644
--- a/include/trace/events/timer_migration.h
+++ b/include/trace/events/timer_migration.h
@@ -33,15 +33,16 @@ TRACE_EVENT(tmigr_group_set,
 
 TRACE_EVENT(tmigr_connect_child_parent,
 
-	TP_PROTO(struct tmigr_group *child),
+	TP_PROTO(struct tmigr_hierarchy *hier, struct tmigr_group *child),
 
-	TP_ARGS(child),
+	TP_ARGS(hier, child),
 
 	TP_STRUCT__entry(
 		__field( void *,	child		)
 		__field( void *,	parent		)
 		__field( unsigned int,	lvl		)
 		__field( unsigned int,	numa_node	)
+		__field( unsigned int,	capacity	)
 		__field( unsigned int,	num_children	)
 		__field( u32,		groupmask	)
 	),
@@ -51,26 +52,28 @@ TRACE_EVENT(tmigr_connect_child_parent,
 		__entry->parent		= child->parent;
 		__entry->lvl		= child->parent->level;
 		__entry->numa_node	= child->parent->numa_node;
+		__entry->capacity	= hier->capacity;
 		__entry->num_children	= child->parent->num_children;
 		__entry->groupmask	= child->groupmask;
 	),
 
-	TP_printk("group=%p groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
-		  __entry->child,  __entry->groupmask, __entry->parent,
-		  __entry->lvl, __entry->numa_node, __entry->num_children)
+	TP_printk("group=%p groupmask=%0x parent=%p lvl=%d numa=%d capacity=%d num_children=%d",
+		  __entry->child,  __entry->groupmask, __entry->parent, __entry->lvl,
+		  __entry->numa_node, __entry->capacity, __entry->num_children)
 );
 
 TRACE_EVENT(tmigr_connect_cpu_parent,
 
-	TP_PROTO(struct tmigr_cpu *tmc),
+	TP_PROTO(struct tmigr_hierarchy *hier, struct tmigr_cpu *tmc),
 
-	TP_ARGS(tmc),
+	TP_ARGS(hier, tmc),
 
 	TP_STRUCT__entry(
 		__field( void *,	parent		)
 		__field( unsigned int,	cpu		)
 		__field( unsigned int,	lvl		)
 		__field( unsigned int,	numa_node	)
+		__field( unsigned int,	capacity	)
 		__field( unsigned int,	num_children	)
 		__field( u32,		groupmask	)
 	),
@@ -80,13 +83,14 @@ TRACE_EVENT(tmigr_connect_cpu_parent,
 		__entry->cpu		= tmc->cpuevt.cpu;
 		__entry->lvl		= tmc->tmgroup->level;
 		__entry->numa_node	= tmc->tmgroup->numa_node;
+		__entry->capacity	= hier->capacity;
 		__entry->num_children	= tmc->tmgroup->num_children;
 		__entry->groupmask	= tmc->groupmask;
 	),
 
-	TP_printk("cpu=%d groupmask=%0x parent=%p lvl=%d numa=%d num_children=%d",
-		  __entry->cpu,	 __entry->groupmask, __entry->parent,
-		  __entry->lvl, __entry->numa_node, __entry->num_children)
+	TP_printk("cpu=%d groupmask=%0x parent=%p lvl=%d numa=%d capacity=%d num_children=%d",
+		  __entry->cpu,	 __entry->groupmask, __entry->parent, __entry->lvl,
+		  __entry->numa_node, __entry->capacity, __entry->num_children)
 );
 
 DECLARE_EVENT_CLASS(tmigr_group_and_cpu,