From 4702f4eceb639b6af199151e352e570943619d98 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Mon, 10 Nov 2025 10:38:53 +0100 Subject: hrtimer: Store time as ktime_t in restart block MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The hrtimer core uses ktime_t to represent times, use that also for the restart block. CPU timers internally use nanoseconds instead of ktime_t but use the same restart block, so use the correct accessors for those. Signed-off-by: Thomas Weißschuh Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20251110-restart-block-expiration-v1-3-5d39cc93df4f@linutronix.de --- include/linux/restart_block.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 7e50bbc94e47..36ddfa1ec301 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -43,7 +43,7 @@ struct restart_block { struct __kernel_timespec __user *rmtp; struct old_timespec32 __user *compat_rmtp; }; - u64 expires; + ktime_t expires; } nanosleep; /* For poll */ struct { -- cgit v1.2.3 From 4518767be9089ea4f54754ad27364d6134fc46e2 Mon Sep 17 00:00:00 2001 From: Jianyun Gao Date: Sat, 27 Sep 2025 17:34:10 +0800 Subject: time: Fix a few typos in time[r] related code comments Signed-off-by: Jianyun Gao Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20250927093411.1509275-1-jianyungao89@gmail.com --- include/linux/delay.h | 8 ++++---- kernel/time/posix-timers.c | 2 +- kernel/time/timer_migration.c | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/delay.h b/include/linux/delay.h index 89866bab100d..46412c00033a 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -68,7 +68,7 @@ void usleep_range_state(unsigned long min, unsigned long max, * @min: Minimum time in microseconds to sleep * @max: Maximum time in microseconds to sleep * - * For basic information please refere to usleep_range_state(). + * For basic information please refer to usleep_range_state(). * * The task will be in the state TASK_UNINTERRUPTIBLE during the sleep. */ @@ -82,10 +82,10 @@ static inline void usleep_range(unsigned long min, unsigned long max) * @min: Minimum time in microseconds to sleep * @max: Maximum time in microseconds to sleep * - * For basic information please refere to usleep_range_state(). + * For basic information please refer to usleep_range_state(). * * The sleeping task has the state TASK_IDLE during the sleep to prevent - * contribution to the load avarage. + * contribution to the load average. */ static inline void usleep_range_idle(unsigned long min, unsigned long max) { @@ -96,7 +96,7 @@ static inline void usleep_range_idle(unsigned long min, unsigned long max) * ssleep - wrapper for seconds around msleep * @seconds: Requested sleep duration in seconds * - * Please refere to msleep() for detailed information. + * Please refer to msleep() for detailed information. */ static inline void ssleep(unsigned int seconds) { diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index aa3120104a51..36dbb8146517 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1242,7 +1242,7 @@ SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, * sys_clock_settime(). The kernel internal timekeeping is always using * nanoseconds precision independent of the clocksource device which is * used to read the time from. The resolution of that device only - * affects the presicion of the time returned by sys_clock_gettime(). + * affects the precision of the time returned by sys_clock_gettime(). * * Returns: * 0 Success. @tp contains the resolution diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 19ddfa96b9df..57e38674e56e 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -708,7 +708,7 @@ void tmigr_cpu_activate(void) /* * Returns true, if there is nothing to be propagated to the next level * - * @data->firstexp is set to expiry of first gobal event of the (top level of + * @data->firstexp is set to expiry of first global event of the (top level of * the) hierarchy, but only when hierarchy is completely idle. * * The child and group states need to be read under the lock, to prevent a race -- cgit v1.2.3 From 8312cab5ff4702389a86129051eba6ea046a71a1 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Thu, 20 Nov 2025 15:56:47 +0100 Subject: timers/migration: Rename 'online' bit to 'available' The timer migration hierarchy excludes offline CPUs via the tmigr_is_not_available function, which is essentially checking the online bit for the CPU. Rename the online bit to available and all references in function names and tracepoint to generalise the concept of available CPUs. Signed-off-by: Gabriele Monaco Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Reviewed-by: Thomas Gleixner Link: https://patch.msgid.link/20251120145653.296659-2-gmonaco@redhat.com --- include/trace/events/timer_migration.h | 4 ++-- kernel/time/timer_migration.c | 24 ++++++++++++------------ kernel/time/timer_migration.h | 2 +- 3 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/trace/events/timer_migration.h b/include/trace/events/timer_migration.h index 47db5eaf2f9a..61171b13c687 100644 --- a/include/trace/events/timer_migration.h +++ b/include/trace/events/timer_migration.h @@ -173,14 +173,14 @@ DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_active, TP_ARGS(tmc) ); -DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_online, +DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_available, TP_PROTO(struct tmigr_cpu *tmc), TP_ARGS(tmc) ); -DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_offline, +DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_unavailable, TP_PROTO(struct tmigr_cpu *tmc), diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 57e38674e56e..2cfebed35e22 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -429,7 +429,7 @@ static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc) { - return !(tmc->tmgroup && tmc->online); + return !(tmc->tmgroup && tmc->available); } /* @@ -926,7 +926,7 @@ static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now, * updated the event takes care when hierarchy is completely * idle. Otherwise the migrator does it as the event is enqueued. */ - if (!tmc->online || tmc->remote || tmc->cpuevt.ignore || + if (!tmc->available || tmc->remote || tmc->cpuevt.ignore || now < tmc->cpuevt.nextevt.expires) { raw_spin_unlock_irq(&tmc->lock); return; @@ -973,7 +973,7 @@ static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now, * (See also section "Required event and timerqueue update after a * remote expiry" in the documentation at the top) */ - if (!tmc->online || !tmc->idle) { + if (!tmc->available || !tmc->idle) { timer_unlock_remote_bases(cpu); goto unlock; } @@ -1422,19 +1422,19 @@ static long tmigr_trigger_active(void *unused) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - WARN_ON_ONCE(!tmc->online || tmc->idle); + WARN_ON_ONCE(!tmc->available || tmc->idle); return 0; } -static int tmigr_cpu_offline(unsigned int cpu) +static int tmigr_clear_cpu_available(unsigned int cpu) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); int migrator; u64 firstexp; raw_spin_lock_irq(&tmc->lock); - tmc->online = false; + tmc->available = false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); /* @@ -1442,7 +1442,7 @@ static int tmigr_cpu_offline(unsigned int cpu) * offline; Therefore nextevt value is set to KTIME_MAX */ firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX); - trace_tmigr_cpu_offline(tmc); + trace_tmigr_cpu_unavailable(tmc); raw_spin_unlock_irq(&tmc->lock); if (firstexp != KTIME_MAX) { @@ -1453,7 +1453,7 @@ static int tmigr_cpu_offline(unsigned int cpu) return 0; } -static int tmigr_cpu_online(unsigned int cpu) +static int tmigr_set_cpu_available(unsigned int cpu) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); @@ -1462,11 +1462,11 @@ static int tmigr_cpu_online(unsigned int cpu) return -EINVAL; raw_spin_lock_irq(&tmc->lock); - trace_tmigr_cpu_online(tmc); + trace_tmigr_cpu_available(tmc); tmc->idle = timer_base_is_idle(); if (!tmc->idle) __tmigr_cpu_activate(tmc); - tmc->online = true; + tmc->available = true; raw_spin_unlock_irq(&tmc->lock); return 0; } @@ -1758,7 +1758,7 @@ static int tmigr_add_cpu(unsigned int cpu) * The (likely) current CPU is expected to be online in the hierarchy, * otherwise the old root may not be active as expected. */ - WARN_ON_ONCE(!per_cpu_ptr(&tmigr_cpu, raw_smp_processor_id())->online); + WARN_ON_ONCE(!per_cpu_ptr(&tmigr_cpu, raw_smp_processor_id())->available); ret = tmigr_setup_groups(-1, old_root->numa_node, old_root, true); } @@ -1854,7 +1854,7 @@ static int __init tmigr_init(void) goto err; ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online", - tmigr_cpu_online, tmigr_cpu_offline); + tmigr_set_cpu_available, tmigr_clear_cpu_available); if (ret) goto err; diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index ae19f70f8170..70879cde6fdd 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -97,7 +97,7 @@ struct tmigr_group { */ struct tmigr_cpu { raw_spinlock_t lock; - bool online; + bool available; bool idle; bool remote; struct tmigr_group *tmgroup; -- cgit v1.2.3 From b56651007fc018effe695a68d48caa6970b23094 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 20 Nov 2025 15:56:52 +0100 Subject: cpumask: Add initialiser to use cleanup helpers Now we can simplify a code that allocates cpumasks for local needs. Automatic variables have to be initialized at declaration, or at least before any possibility for the logic to return, so that compiler wouldn't try to call an associate destructor function on a random stack number. Because cpumask_var_t, depending on the CPUMASK_OFFSTACK config, is either a pointer or an array, we have to have a macro for initialization. So define a CPUMASK_VAR_NULL macro, which allows to init struct cpumask pointer with NULL when CPUMASK_OFFSTACK is enabled, and effectively a no-op when CPUMASK_OFFSTACK is disabled (initialisation optimised out with -O2). Signed-off-by: Yury Norov Signed-off-by: Gabriele Monaco Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://patch.msgid.link/20251120145653.296659-7-gmonaco@redhat.com --- include/linux/cpumask.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ff8f41ab7ce6..68be522449ec 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -1005,6 +1005,7 @@ static __always_inline unsigned int cpumask_size(void) #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly +#define CPUMASK_VAR_NULL NULL bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); @@ -1051,6 +1052,7 @@ static __always_inline bool cpumask_available(cpumask_var_t mask) #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly +#define CPUMASK_VAR_NULL {} static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { -- cgit v1.2.3 From 7dec062cfcf27808dbb70a0b231d1a698792743d Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Thu, 20 Nov 2025 15:56:53 +0100 Subject: timers/migration: Exclude isolated cpus from hierarchy The timer migration mechanism allows active CPUs to pull timers from idle ones to improve the overall idle time. This is however undesired when CPU intensive workloads run on isolated cores, as the algorithm would move the timers from housekeeping to isolated cores, negatively affecting the isolation. Exclude isolated cores from the timer migration algorithm, extend the concept of unavailable cores, currently used for offline ones, to isolated ones: * A core is unavailable if isolated or offline; * A core is available if non isolated and online; A core is considered unavailable as isolated if it belongs to: * the isolcpus (domain) list * an isolated cpuset Except if it is: * in the nohz_full list (already idle for the hierarchy) * the nohz timekeeper core (must be available to handle global timers) CPUs are added to the hierarchy during late boot, excluding isolated ones, the hierarchy is also adapted when the cpuset isolation changes. Due to how the timer migration algorithm works, any CPU part of the hierarchy can have their global timers pulled by remote CPUs and have to pull remote timers, only skipping pulling remote timers would break the logic. For this reason, prevent isolated CPUs from pulling remote global timers, but also the other way around: any global timer started on an isolated CPU will run there. This does not break the concept of isolation (global timers don't come from outside the CPU) and, if considered inappropriate, can usually be mitigated with other isolation techniques (e.g. IRQ pinning). This effect was noticed on a 128 cores machine running oslat on the isolated cores (1-31,33-63,65-95,97-127). The tool monopolises CPUs, and the CPU with lowest count in a timer migration hierarchy (here 1 and 65) appears as always active and continuously pulls global timers, from the housekeeping CPUs. This ends up moving driver work (e.g. delayed work) to isolated CPUs and causes latency spikes: before the change: # oslat -c 1-31,33-63,65-95,97-127 -D 62s ... Maximum: 1203 10 3 4 ... 5 (us) after the change: # oslat -c 1-31,33-63,65-95,97-127 -D 62s ... Maximum: 10 4 3 4 3 ... 5 (us) The same behaviour was observed on a machine with as few as 20 cores / 40 threads with isocpus set to: 1-9,11-39 with rtla-osnoise-top. Signed-off-by: Gabriele Monaco Signed-off-by: Thomas Gleixner Tested-by: John B. Wyatt IV Reviewed-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://patch.msgid.link/20251120145653.296659-8-gmonaco@redhat.com --- include/linux/timer.h | 9 +++ kernel/cgroup/cpuset.c | 3 + kernel/time/timer_migration.c | 143 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 155 insertions(+) (limited to 'include') diff --git a/include/linux/timer.h b/include/linux/timer.h index 0414d9e6b4fc..62e1cea71125 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -188,4 +188,13 @@ int timers_dead_cpu(unsigned int cpu); #define timers_dead_cpu NULL #endif +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask); +#else +static inline int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) +{ + return 0; +} +#endif + #endif diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index cf34623fe66f..bfc3b319e1c0 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1350,6 +1350,9 @@ static void update_isolation_cpumasks(bool isolcpus_updated) ret = workqueue_unbound_exclude_cpumask(isolated_cpus); WARN_ON_ONCE(ret < 0); + + ret = tmigr_isolated_exclude_cpumask(isolated_cpus); + WARN_ON_ONCE(ret < 0); } /** diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index a01c7f8bdf52..18dda1aa782d 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "timer_migration.h" #include "tick-internal.h" @@ -427,8 +428,13 @@ static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); /* * CPUs available for timer migration. * Protected by cpuset_mutex (with cpus_read_lock held) or cpus_write_lock. + * Additionally tmigr_available_mutex serializes set/clear operations with each other. */ static cpumask_var_t tmigr_available_cpumask; +static DEFINE_MUTEX(tmigr_available_mutex); + +/* Enabled during late initcall */ +static DEFINE_STATIC_KEY_FALSE(tmigr_exclude_isolated); #define TMIGR_NONE 0xFF #define BIT_CNT 8 @@ -438,6 +444,33 @@ static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc) return !(tmc->tmgroup && tmc->available); } +/* + * Returns true if @cpu should be excluded from the hierarchy as isolated. + * Domain isolated CPUs don't participate in timer migration, nohz_full CPUs + * are still part of the hierarchy but become idle (from a tick and timer + * migration perspective) when they stop their tick. This lets the timekeeping + * CPU handle their global timers. Marking also isolated CPUs as idle would be + * too costly, hence they are completely excluded from the hierarchy. + * This check is necessary, for instance, to prevent offline isolated CPUs from + * being incorrectly marked as available once getting back online. + * + * This function returns false during early boot and the isolation logic is + * enabled only after isolated CPUs are marked as unavailable at late boot. + * The tick CPU can be isolated at boot, however we cannot mark it as + * unavailable to avoid having no global migrator for the nohz_full CPUs. This + * should be ensured by the callers of this function: implicitly from hotplug + * callbacks and explicitly in tmigr_init_isolation() and + * tmigr_isolated_exclude_cpumask(). + */ +static inline bool tmigr_is_isolated(int cpu) +{ + if (!static_branch_unlikely(&tmigr_exclude_isolated)) + return false; + return (!housekeeping_cpu(cpu, HK_TYPE_DOMAIN) || + cpuset_cpu_is_isolated(cpu)) && + housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE); +} + /* * Returns true, when @childmask corresponds to the group migrator or when the * group is not active - so no migrator is set. @@ -1439,8 +1472,12 @@ static int tmigr_clear_cpu_available(unsigned int cpu) int migrator; u64 firstexp; + guard(mutex)(&tmigr_available_mutex); + cpumask_clear_cpu(cpu, tmigr_available_cpumask); scoped_guard(raw_spinlock_irq, &tmc->lock) { + if (!tmc->available) + return 0; tmc->available = false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); @@ -1468,8 +1505,15 @@ static int tmigr_set_cpu_available(unsigned int cpu) if (WARN_ON_ONCE(!tmc->tmgroup)) return -EINVAL; + if (tmigr_is_isolated(cpu)) + return 0; + + guard(mutex)(&tmigr_available_mutex); + cpumask_set_cpu(cpu, tmigr_available_cpumask); scoped_guard(raw_spinlock_irq, &tmc->lock) { + if (tmc->available) + return 0; trace_tmigr_cpu_available(tmc); tmc->idle = timer_base_is_idle(); if (!tmc->idle) @@ -1479,6 +1523,105 @@ static int tmigr_set_cpu_available(unsigned int cpu) return 0; } +static void tmigr_cpu_isolate(struct work_struct *ignored) +{ + tmigr_clear_cpu_available(smp_processor_id()); +} + +static void tmigr_cpu_unisolate(struct work_struct *ignored) +{ + tmigr_set_cpu_available(smp_processor_id()); +} + +/** + * tmigr_isolated_exclude_cpumask - Exclude given CPUs from hierarchy + * @exclude_cpumask: the cpumask to be excluded from timer migration hierarchy + * + * This function can be called from cpuset code to provide the new set of + * isolated CPUs that should be excluded from the hierarchy. + * Online CPUs not present in exclude_cpumask but already excluded are brought + * back to the hierarchy. + * Functions to isolate/unisolate need to be called locally and can sleep. + */ +int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) +{ + struct work_struct __percpu *works __free(free_percpu) = + alloc_percpu(struct work_struct); + cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL; + int cpu; + + lockdep_assert_cpus_held(); + + if (!works) + return -ENOMEM; + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + + /* + * First set previously isolated CPUs as available (unisolate). + * This cpumask contains only CPUs that switched to available now. + */ + cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); + cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); + + for_each_cpu(cpu, cpumask) { + struct work_struct *work = per_cpu_ptr(works, cpu); + + INIT_WORK(work, tmigr_cpu_unisolate); + schedule_work_on(cpu, work); + } + for_each_cpu(cpu, cpumask) + flush_work(per_cpu_ptr(works, cpu)); + + /* + * Then clear previously available CPUs (isolate). + * This cpumask contains only CPUs that switched to not available now. + * There cannot be overlap with the newly available ones. + */ + cpumask_and(cpumask, exclude_cpumask, tmigr_available_cpumask); + cpumask_and(cpumask, cpumask, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)); + /* + * Handle this here and not in the cpuset code because exclude_cpumask + * might include also the tick CPU if included in isolcpus. + */ + for_each_cpu(cpu, cpumask) { + if (!tick_nohz_cpu_hotpluggable(cpu)) { + cpumask_clear_cpu(cpu, cpumask); + break; + } + } + + for_each_cpu(cpu, cpumask) { + struct work_struct *work = per_cpu_ptr(works, cpu); + + INIT_WORK(work, tmigr_cpu_isolate); + schedule_work_on(cpu, work); + } + for_each_cpu(cpu, cpumask) + flush_work(per_cpu_ptr(works, cpu)); + + return 0; +} + +static int __init tmigr_init_isolation(void) +{ + cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL; + + static_branch_enable(&tmigr_exclude_isolated); + + if (!housekeeping_enabled(HK_TYPE_DOMAIN)) + return 0; + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); + + /* Protect against RCU torture hotplug testing */ + guard(cpus_read_lock)(); + return tmigr_isolated_exclude_cpumask(cpumask); +} +late_initcall(tmigr_init_isolation); + static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, int node) { -- cgit v1.2.3