From 2ff899e3516437354204423ef0a94994717b8e6a Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Thu, 13 Mar 2025 18:10:21 +0100 Subject: sched/deadline: Rebuild root domain accounting after every update Rebuilding of root domains accounting information (total_bw) is currently broken on some cases, e.g. suspend/resume on aarch64. Problem is that the way we keep track of domain changes and try to add bandwidth back is convoluted and fragile. Fix it by simplify things by making sure bandwidth accounting is cleared and completely restored after root domains changes (after root domains are again stable). To be sure we always call dl_rebuild_rd_accounting while holding cpuset_mutex we also add cpuset_reset_sched_domains() wrapper. Fixes: 53916d5fd3c0 ("sched/deadline: Check bandwidth overflow earlier for hotplug") Reported-by: Jon Hunter Co-developed-by: Waiman Long Signed-off-by: Waiman Long Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Tested-by: Dietmar Eggemann Link: https://lore.kernel.org/r/Z9MRfeJKJUOyUSto@jlelli-thinkpadt14gen4.remote.csb --- include/linux/cpuset.h | 6 ++++++ include/linux/sched/deadline.h | 1 + include/linux/sched/topology.h | 2 ++ 3 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 835e7b793f6a..17cc90d900f9 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -128,6 +128,7 @@ extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); +extern void cpuset_reset_sched_domains(void); /* * read_mems_allowed_begin is required when making decisions involving @@ -264,6 +265,11 @@ static inline void rebuild_sched_domains(void) partition_sched_domains(1, NULL, NULL); } +static inline void cpuset_reset_sched_domains(void) +{ + partition_sched_domains(1, NULL, NULL); +} + static inline void cpuset_print_current_mems_allowed(void) { } diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 6ec578600b24..f9aabbc9d22e 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -34,6 +34,7 @@ static inline bool dl_time_before(u64 a, u64 b) struct root_domain; extern void dl_add_task_root_domain(struct task_struct *p); extern void dl_clear_root_domain(struct root_domain *rd); +extern void dl_clear_root_domain_cpu(int cpu); #endif /* CONFIG_SMP */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7f3dbafe1817..1622232bd08b 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -166,6 +166,8 @@ static inline struct cpumask *sched_domain_span(struct sched_domain *sd) return to_cpumask(sd->span); } +extern void dl_rebuild_rd_accounting(void); + extern void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new); -- cgit v1.2.3