From 5bc78502322a5e4eef3f1b2a2813751dc6434143 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 20 Oct 2020 09:47:13 -0400 Subject: sched: fix exit_mm vs membarrier (v4) exit_mm should issue memory barriers after user-space memory accesses, before clearing current->mm, to order user-space memory accesses performed prior to exit_mm before clearing tsk->mm, which has the effect of skipping the membarrier private expedited IPIs. exit_mm should also update the runqueue's membarrier_state so membarrier global expedited IPIs are not sent when they are not needed. The membarrier system call can be issued concurrently with do_exit if we have thread groups created with CLONE_VM but not CLONE_THREAD. Here is the scenario I have in mind: Two thread groups are created, A and B. Thread group B is created by issuing clone from group A with flag CLONE_VM set, but not CLONE_THREAD. Let's assume we have a single thread within each thread group (Thread A and Thread B). The AFAIU we can have: Userspace variables: int x = 0, y = 0; CPU 0 CPU 1 Thread A Thread B (in thread group A) (in thread group B) x = 1 barrier() y = 1 exit() exit_mm() current->mm = NULL; r1 = load y membarrier() skips CPU 0 (no IPI) because its current mm is NULL r2 = load x BUG_ON(r1 == 1 && r2 == 0) Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201020134715.13909-2-mathieu.desnoyers@efficios.com --- include/linux/sched/mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux/sched') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index d5ece7a9a403..a91fb3ad9ec7 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -347,6 +347,8 @@ static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) extern void membarrier_exec_mmap(struct mm_struct *mm); +extern void membarrier_update_current_mm(struct mm_struct *next_mm); + #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, @@ -361,6 +363,9 @@ static inline void membarrier_exec_mmap(struct mm_struct *mm) static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } +static inline void membarrier_update_current_mm(struct mm_struct *next_mm) +{ +} #endif #endif /* _LINUX_SCHED_MM_H */ -- cgit v1.2.3 From 1cf12e08bc4d50a76b80c42a3109c53d8794a0c9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 16 Sep 2020 09:27:18 +0200 Subject: sched/hotplug: Consolidate task migration on CPU unplug With the new mechanism which kicks tasks off the outgoing CPU at the end of schedule() the situation on an outgoing CPU right before the stopper thread brings it down completely is: - All user tasks and all unbound kernel threads have either been migrated away or are not running and the next wakeup will move them to a online CPU. - All per CPU kernel threads, except cpu hotplug thread and the stopper thread have either been unbound or parked by the responsible CPU hotplug callback. That means that at the last step before the stopper thread is invoked the cpu hotplug thread is the last legitimate running task on the outgoing CPU. Add a final wait step right before the stopper thread is kicked which ensures that any still running tasks on the way to park or on the way to kick themself of the CPU are either sleeping or gone. This allows to remove the migrate_tasks() crutch in sched_cpu_dying(). If sched_cpu_dying() detects that there is still another running task aside of the stopper thread then it will explode with the appropriate fireworks. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Reviewed-by: Daniel Bristot de Oliveira Link: https://lkml.kernel.org/r/20201023102346.547163969@infradead.org --- include/linux/sched/hotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/sched') diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h index 9a62ffdd296f..412cdaba33eb 100644 --- a/include/linux/sched/hotplug.h +++ b/include/linux/sched/hotplug.h @@ -11,8 +11,10 @@ extern int sched_cpu_activate(unsigned int cpu); extern int sched_cpu_deactivate(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU +extern int sched_cpu_wait_empty(unsigned int cpu); extern int sched_cpu_dying(unsigned int cpu); #else +# define sched_cpu_wait_empty NULL # define sched_cpu_dying NULL #endif -- cgit v1.2.3 From 31f6a8c0a471be7d7d05c93eac50fcb729e79b9d Mon Sep 17 00:00:00 2001 From: Ionela Voinescu Date: Tue, 27 Oct 2020 18:07:11 +0000 Subject: sched/topology,schedutil: Wrap sched domains rebuild Add the rebuild_sched_domains_energy() function to wrap the functionality that rebuilds the scheduling domains if any of the Energy Aware Scheduling (EAS) initialisation conditions change. This functionality is used when schedutil is added or removed or when EAS is enabled or disabled through the sched_energy_aware sysctl. Therefore, create a single function that is used in both these cases and that can be later reused. Signed-off-by: Ionela Voinescu Signed-off-by: Peter Zijlstra (Intel) Acked-by: Quentin Perret Acked-by: Rafael J. Wysocki Link: https://lkml.kernel.org/r/20201027180713.7642-2-ionela.voinescu@arm.com --- include/linux/sched/topology.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/sched') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 9ef7bf686a9f..8f0f778b7c91 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -225,6 +225,14 @@ static inline bool cpus_share_cache(int this_cpu, int that_cpu) #endif /* !CONFIG_SMP */ +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) +extern void rebuild_sched_domains_energy(void); +#else +static inline void rebuild_sched_domains_energy(void) +{ +} +#endif + #ifndef arch_scale_cpu_capacity /** * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU. -- cgit v1.2.3