Merge tag 'timers-urgent-2024-04-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fixes from Ingo Molnar:
 "Fix various timer bugs:

   - Fix a timer migration bug that may result in missed events

   - Fix timer migration group hierarchy event updates

   - Fix a PowerPC64 build warning

   - Fix a handful of DocBook annotation bugs"

* tag 'timers-urgent-2024-04-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timers/migration: Return early on deactivation
  timers/migration: Fix ignored event due to missing CPU update
  vdso: Use CONFIG_PAGE_SHIFT in vdso/datapage.h
  timers: Fix text inconsistencies and spelling
  tick/sched: Fix struct tick_sched doc warnings
  tick/sched: Fix various kernel-doc warnings
  timers: Fix kernel-doc format and add Return values
  time/timekeeping: Fix kernel-doc warnings and typos
  time/timecounter: Fix inline documentation

4 files changed, 58 insertions, 16 deletions

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 269e21590df5..1331216a9cae 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -697,6 +697,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu)
 
 /**
  * tick_nohz_update_jiffies - update jiffies when idle was interrupted
+ * @now: current ktime_t
  *
  * Called from interrupt entry when the CPU was idle
  *
@@ -794,7 +795,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
  * This time is measured via accounting rather than sampling,
  * and is as accurate as ktime_get() is.
  *
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu
  */
 u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
 {
@@ -820,7 +821,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
  * This time is measured via accounting rather than sampling,
  * and is as accurate as ktime_get() is.
  *
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu
  */
 u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 {
@@ -1287,6 +1288,8 @@ void tick_nohz_irq_exit(void)
 
 /**
  * tick_nohz_idle_got_tick - Check whether or not the tick handler has run
+ *
+ * Return: %true if the tick handler has run, otherwise %false
  */
 bool tick_nohz_idle_got_tick(void)
 {
@@ -1305,6 +1308,8 @@ bool tick_nohz_idle_got_tick(void)
  * stopped, it returns the next hrtimer.
  *
  * Called from power state control code with interrupts disabled
+ *
+ * Return: the next expiration time
  */
 ktime_t tick_nohz_get_next_hrtimer(void)
 {
@@ -1320,6 +1325,8 @@ ktime_t tick_nohz_get_next_hrtimer(void)
  * The return value of this function and/or the value returned by it through the
  * @delta_next pointer can be negative which must be taken into account by its
  * callers.
+ *
+ * Return: the expected length of the current sleep
  */
 ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 {
@@ -1357,8 +1364,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 /**
  * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
  * for a particular CPU.
+ * @cpu: target CPU number
  *
  * Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for @cpu
  */
 unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
 {
@@ -1371,6 +1381,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
  * tick_nohz_get_idle_calls - return the current idle calls counter value
  *
  * Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for the current CPU
  */
 unsigned long tick_nohz_get_idle_calls(void)
 {
@@ -1559,7 +1571,7 @@ early_param("skew_tick", skew_tick);
 
 /**
  * tick_setup_sched_timer - setup the tick emulation timer
- * @mode: tick_nohz_mode to setup for
+ * @hrtimer: whether to use the hrtimer or not
  */
 void tick_setup_sched_timer(bool hrtimer)
 {
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index e11c4dc65bcb..b4a7822f495d 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -46,8 +46,8 @@ struct tick_device {
  * @next_tick:		Next tick to be fired when in dynticks mode.
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_waketime:	Time when the idle was interrupted
+ * @idle_sleeptime_seq:	sequence counter for data consistency
  * @idle_entrytime:	Time when the idle call was entered
- * @nohz_mode:		Mode - one state of tick_nohz_mode
  * @last_jiffies:	Base jiffies snapshot when next event was last computed
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
  * @timer_expires:	Anticipated timer expiration time (in case sched tick is stopped)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index dee29f1f5b75..3baf2fbe6848 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -64,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64);
 
 /*
  * The timer wheel has LVL_DEPTH array levels. Each level provides an array of
- * LVL_SIZE buckets. Each level is driven by its own clock and therefor each
+ * LVL_SIZE buckets. Each level is driven by its own clock and therefore each
  * level has a different granularity.
  *
- * The level granularity is:		LVL_CLK_DIV ^ lvl
+ * The level granularity is:		LVL_CLK_DIV ^ level
  * The level clock frequency is:	HZ / (LVL_CLK_DIV ^ level)
  *
  * The array level of a newly armed timer depends on the relative expiry
  * time. The farther the expiry time is away the higher the array level and
- * therefor the granularity becomes.
+ * therefore the granularity becomes.
  *
  * Contrary to the original timer wheel implementation, which aims for 'exact'
  * expiry of the timers, this implementation removes the need for recascading
@@ -207,7 +207,7 @@ EXPORT_SYMBOL(jiffies_64);
  * struct timer_base - Per CPU timer base (number of base depends on config)
  * @lock:		Lock protecting the timer_base
  * @running_timer:	When expiring timers, the lock is dropped. To make
- *			sure not to race agains deleting/modifying a
+ *			sure not to race against deleting/modifying a
  *			currently running timer, the pointer is set to the
  *			timer, which expires at the moment. If no timer is
  *			running, the pointer is NULL.
@@ -737,7 +737,7 @@ static bool timer_is_static_object(void *addr)
 }
 
 /*
- * fixup_init is called when:
+ * timer_fixup_init is called when:
  * - an active object is initialized
  */
 static bool timer_fixup_init(void *addr, enum debug_obj_state state)
@@ -761,7 +761,7 @@ static void stub_timer(struct timer_list *unused)
 }
 
 /*
- * fixup_activate is called when:
+ * timer_fixup_activate is called when:
  * - an active object is activated
  * - an unknown non-static object is activated
  */
@@ -783,7 +783,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
 }
 
 /*
- * fixup_free is called when:
+ * timer_fixup_free is called when:
  * - an active object is freed
  */
 static bool timer_fixup_free(void *addr, enum debug_obj_state state)
@@ -801,7 +801,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state)
 }
 
 /*
- * fixup_assert_init is called when:
+ * timer_fixup_assert_init is called when:
  * - an untracked/uninit-ed object is found
  */
 static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
@@ -914,7 +914,7 @@ static void do_init_timer(struct timer_list *timer,
  * @key: lockdep class key of the fake lock used for tracking timer
  *       sync lock dependencies
  *
- * init_timer_key() must be done to a timer prior calling *any* of the
+ * init_timer_key() must be done to a timer prior to calling *any* of the
  * other timer functions.
  */
 void init_timer_key(struct timer_list *timer,
@@ -1417,7 +1417,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown)
 	 * If @shutdown is set then the lock has to be taken whether the
 	 * timer is pending or not to protect against a concurrent rearm
 	 * which might hit between the lockless pending check and the lock
-	 * aquisition. By taking the lock it is ensured that such a newly
+	 * acquisition. By taking the lock it is ensured that such a newly
 	 * enqueued timer is dequeued and cannot end up with
 	 * timer->function == NULL in the expiry code.
 	 *
@@ -2306,7 +2306,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem,
 
 		/*
 		 * When timer base is not set idle, undo the effect of
-		 * tmigr_cpu_deactivate() to prevent inconsitent states - active
+		 * tmigr_cpu_deactivate() to prevent inconsistent states - active
 		 * timer base but inactive timer migration hierarchy.
 		 *
 		 * When timer base was already marked idle, nothing will be
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index c63a0afdcebe..ccba875d2234 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -751,6 +751,33 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 
 		first_childevt = evt = data->evt;
 
+		/*
+		 * Walking the hierarchy is required in any case when a
+		 * remote expiry was done before. This ensures to not lose
+		 * already queued events in non active groups (see section
+		 * "Required event and timerqueue update after a remote
+		 * expiry" in the documentation at the top).
+		 *
+		 * The two call sites which are executed without a remote expiry
+		 * before, are not prevented from propagating changes through
+		 * the hierarchy by the return:
+		 *  - When entering this path by tmigr_new_timer(), @evt->ignore
+		 *    is never set.
+		 *  - tmigr_inactive_up() takes care of the propagation by
+		 *    itself and ignores the return value. But an immediate
+		 *    return is possible if there is a parent, sparing group
+		 *    locking at this level, because the upper walking call to
+		 *    the parent will take care about removing this event from
+		 *    within the group and update next_expiry accordingly.
+		 *
+		 * However if there is no parent, ie: the hierarchy has only a
+		 * single level so @group is the top level group, make sure the
+		 * first event information of the group is updated properly and
+		 * also handled properly, so skip this fast return path.
+		 */
+		if (evt->ignore && !remote && group->parent)
+			return true;
+
 		raw_spin_lock(&group->lock);
 
 		childstate.state = 0;
@@ -762,8 +789,11 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
 	 * queue when the expiry time changed only or when it could be ignored.
 	 */
 	if (timerqueue_node_queued(&evt->nextevt)) {
-		if ((evt->nextevt.expires == nextexp) && !evt->ignore)
+		if ((evt->nextevt.expires == nextexp) && !evt->ignore) {
+			/* Make sure not to miss a new CPU event with the same expiry */
+			evt->cpu = first_childevt->cpu;
 			goto check_toplvl;
+		}
 
 		if (!timerqueue_del(&group->events, &evt->nextevt))
 			WRITE_ONCE(group->next_expiry, KTIME_MAX);