From f29536bf1721802d2ebdc7893ed2991d4da0a4b6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 31 Mar 2024 10:26:50 -0700 Subject: tick/sched: Fix various kernel-doc warnings Fix a slew of kernel-doc warnings in tick-sched.c: tick-sched.c:650: warning: Function parameter or struct member 'now' not described in 'tick_nohz_update_jiffies' tick-sched.c:741: warning: No description found for return value of 'get_cpu_idle_time_us' tick-sched.c:767: warning: No description found for return value of 'get_cpu_iowait_time_us' tick-sched.c:1210: warning: No description found for return value of 'tick_nohz_idle_got_tick' tick-sched.c:1228: warning: No description found for return value of 'tick_nohz_get_next_hrtimer' tick-sched.c:1243: warning: No description found for return value of 'tick_nohz_get_sleep_length' tick-sched.c:1282: warning: Function parameter or struct member 'cpu' not described in 'tick_nohz_get_idle_calls_cpu' tick-sched.c:1282: warning: No description found for return value of 'tick_nohz_get_idle_calls_cpu' tick-sched.c:1294: warning: No description found for return value of 'tick_nohz_get_idle_calls' tick-sched.c:1577: warning: Function parameter or struct member 'hrtimer' not described in 'tick_setup_sched_timer' tick-sched.c:1577: warning: Excess function parameter 'mode' description in 'tick_setup_sched_timer' Signed-off-by: Randy Dunlap Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240331172652.14086-5-rdunlap@infradead.org --- kernel/time/tick-sched.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'kernel') 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) { -- cgit v1.2.3 From ba6ad57b803e33ed509213a5e840427dbef501d6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 31 Mar 2024 10:26:51 -0700 Subject: tick/sched: Fix struct tick_sched doc warnings Fix kernel-doc warnings in struct tick_sched: tick-sched.h:103: warning: Function parameter or struct member 'idle_sleeptime_seq' not described in 'tick_sched' tick-sched.h:104: warning: Excess struct member 'nohz_mode' description in 'tick_sched' Signed-off-by: Randy Dunlap Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240331172652.14086-6-rdunlap@infradead.org --- kernel/time/tick-sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') 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) -- cgit v1.2.3 From 9e643ab59d7ee4332994671720a9528bac62e9b7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 31 Mar 2024 10:26:52 -0700 Subject: timers: Fix text inconsistencies and spelling Fix some text for consistency: s/lvl/level/ in a comment and use correct/full function names in comments. Correct spelling errors as reported by codespell. Signed-off-by: Randy Dunlap Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240331172652.14086-7-rdunlap@infradead.org --- kernel/time/timer.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel') 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 -- cgit v1.2.3 From 61f7fdf8fd00ce33d30ca3fae8d643c0850ce945 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 1 Apr 2024 23:48:59 +0200 Subject: timers/migration: Fix ignored event due to missing CPU update When a group event is updated with its expiry unchanged but a different CPU, that target change may go unnoticed and the event may be propagated up with a stale CPU value. The following depicts a scenario that has been actually observed: [GRP2:0] migrator = GRP1:1 active = GRP1:1 nextevt = TGRP1:0 (T0) / \ [GRP1:0] [GRP1:1] migrator = NONE [...] active = NONE nextevt = TGRP0:0 (T0) / \ [GRP0:0] [...] migrator = NONE active = NONE nextevt = T0 / \ 0 (T0) 1 (T1) idle idle 0) The hierarchy has 3 levels. The left part (GRP1:0) is all idle, including CPU 0 and CPU 1 which have a timer each: T0 and T1. They have the same expiry value. [GRP2:0] migrator = GRP1:1 active = GRP1:1 nextevt = KTIME_MAX / \ [GRP1:0] [GRP1:1] migrator = NONE [...] active = NONE nextevt = TGRP0:0 (T0) / \ [GRP0:0] [...] migrator = NONE active = NONE nextevt = T0 / \ 0 (T0) 1 (T1) idle idle 1) The migrator in GRP1:1 handles remotely T0. The event is dequeued from the top and T0 executed. [GRP2:0] migrator = GRP1:1 active = GRP1:1 nextevt = KTIME_MAX / \ [GRP1:0] [GRP1:1] migrator = NONE [...] active = NONE nextevt = TGRP0:0 (T0) / \ [GRP0:0] [...] migrator = NONE active = NONE nextevt = T1 / \ 0 1 (T1) idle idle 2) The migrator in GRP1:1 fetches the next timer for CPU 0 and finds none. But it updates the events from its groups, starting with GRP0:0 which now has T1 as its next event. So far so good. [GRP2:0] migrator = GRP1:1 active = GRP1:1 nextevt = KTIME_MAX / \ [GRP1:0] [GRP1:1] migrator = NONE [...] active = NONE nextevt = TGRP0:0 (T0) / \ [GRP0:0] [...] migrator = NONE active = NONE nextevt = T1 / \ 0 1 (T1) idle idle 3) The migrator in GRP1:1 proceeds upward and updates the events in GRP1:0. The child event TGRP0:0 is found queued with the same expiry as before. And therefore it is left unchanged. However the target CPU is not the same but that fact is ignored so TGRP0:0 still points to CPU 0 when it should point to CPU 1. [GRP2:0] migrator = GRP1:1 active = GRP1:1 nextevt = TGRP1:0 (T0) / \ [GRP1:0] [GRP1:1] migrator = NONE [...] active = NONE nextevt = TGRP0:0 (T0) / \ [GRP0:0] [...] migrator = NONE active = NONE nextevt = T1 / \ 0 1 (T1) idle idle 4) The propagation has reached the top level and TGRP1:0, having TGRP0:0 as its first event, also wrongly points to CPU 0. TGRP1:0 is added to the top level group. [GRP2:0] migrator = GRP1:1 active = GRP1:1 nextevt = KTIME_MAX / \ [GRP1:0] [GRP1:1] migrator = NONE [...] active = NONE nextevt = TGRP0:0 (T0) / \ [GRP0:0] [...] migrator = NONE active = NONE nextevt = T1 / \ 0 1 (T1) idle idle 5) The migrator in GRP1:1 dequeues the next event in top level pointing to CPU 0. But since it actually doesn't see any real event in CPU 0, it early returns. 6) T1 is left unhandled until either CPU 0 or CPU 1 wake up. Some other bad scenario may involve trees with just two levels. Fix this with unconditionally updating the CPU of the child event before considering to early return while updating a queued event with an unchanged expiry value. Fixes: 7ee988770326 ("timers: Implement the hierarchical pull model") Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Reviewed-by: Anna-Maria Behnsen Link: https://lore.kernel.org/r/Zg2Ct6M2RJAYHgCB@localhost.localdomain --- kernel/time/timer_migration.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c63a0afdcebe..e3075e40cb43 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -762,8 +762,11 @@ 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); -- cgit v1.2.3 From 7a96a84bfbee96871bb16c70ee3e93d564e190f4 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Fri, 5 Apr 2024 10:53:21 +0200 Subject: timers/migration: Return early on deactivation Commit 4b6f4c5a67c0 ("timer/migration: Remove buggy early return on deactivation") removed the logic to return early in tmigr_update_events() on deactivation. With this the problem with a not properly updated first global event in a hierarchy containing only a single group was fixed. But when having a look at this code path with a hierarchy with more than a single level, now unnecessary work is done (example is partially copied from the message of the commit mentioned above): [GRP1:0] migrator = GRP0:0 active = GRP0:0 nextevt = T0:0i, T0:1 / \ [GRP0:0] [GRP0:1] migrator = 0 migrator = NONE active = 0 active = NONE nextevt = T0i, T1 nextevt = T2 / \ / \ 0 (T0i) 1 (T1) 2 (T2) 3 active idle idle idle 0) CPU 0 is active thus its event is ignored (the letter 'i') and so are upper levels' events. CPU 1 is idle and has the timer T1 enqueued. CPU 2 also has a timer. The expiry order is T0 (ignored) < T1 < T2 [GRP1:0] migrator = GRP0:0 active = GRP0:0 nextevt = T0:0i, T0:1 / \ [GRP0:0] [GRP0:1] migrator = NONE migrator = NONE active = NONE active = NONE nextevt = T1 nextevt = T2 / \ / \ 0 (T0i) 1 (T1) 2 (T2) 3 idle idle idle idle 1) CPU 0 goes idle without global event queued. Therefore KTIME_MAX is pushed as its next expiry and its own event kept as "ignore". Without this early return the following steps happen in tmigr_update_events() when child = null and group = GRP0:0 : lock(GRP0:0->lock); timerqueue_del(GRP0:0, T0i); unlock(GRP0:0->lock); [GRP1:0] migrator = NONE active = NONE nextevt = T0:0, T0:1 / \ [GRP0:0] [GRP0:1] migrator = NONE migrator = NONE active = NONE active = NONE nextevt = T1 nextevt = T2 / \ / \ 0 (T0i) 1 (T1) 2 (T2) 3 idle idle idle idle 2) The change now propagates up to the top. Then tmigr_update_events() updates the group event of GRP0:0 and executes the following steps (child = GRP0:0 and group = GRP0:0): lock(GRP0:0->lock); lock(GRP1:0->lock); evt = tmigr_next_groupevt(GRP0:0); -> this removes the ignored events in GRP0:0 ... update GRP1:0 group event and timerqueue ... unlock(GRP1:0->lock); unlock(GRP0:0->lock); So the dance in 1) with locking the GRP0:0->lock and removing the T0i from the timerqueue is redundand as this is done nevertheless in 2) when tmigr_next_groupevt(GRP0:0) is executed. Revert commit 4b6f4c5a67c0 ("timer/migration: Remove buggy early return on deactivation") and add a condition into return path to skip the return only, when hierarchy contains a single group. Adapt comments accordingly. Fixes: 4b6f4c5a67c0 ("timer/migration: Remove buggy early return on deactivation") Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/r/87cyr49on2.fsf@somnus --- kernel/time/timer_migration.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'kernel') diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index e3075e40cb43..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; -- cgit v1.2.3