Hotplug operations are destructive w.r.t. cpusets. In case such an operation is performed on a CPU belonging to an exlusive cpuset, the -dl bandwidth information associated with the corresponding root domain is gone even if the operation fails (in sched_cpu_inactive()).
For this reason we need to move the check we currently have in sched_cpu_inactive() to cpuset_cpu_inactive() to prevent useless cpusets reconfiguration in the CPU_DOWN_FAILED path. Signed-off-by: Juri Lelli <juri.le...@arm.com> Cc: Ingo Molnar <mi...@redhat.com> Cc: Peter Zijlstra <pet...@infradead.org> Cc: Juri Lelli <juri.le...@gmail.com> Cc: linux-kernel@vger.kernel.org --- kernel/sched/core.c | 56 ++++++++++++++++++++++++++--------------------------- 1 file changed, 28 insertions(+), 28 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 62671f5..213d26d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5320,36 +5320,13 @@ static int sched_cpu_active(struct notifier_block *nfb, static int sched_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned long flags; - long cpu = (long)hcpu; - struct dl_bw *dl_b; - switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: - set_cpu_active(cpu, false); - - /* explicitly allow suspend */ - if (!(action & CPU_TASKS_FROZEN)) { - bool overflow; - int cpus; - - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(cpu); - overflow = __dl_overflow(dl_b, cpus, 0, 0); - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (overflow) - return notifier_from_errno(-EBUSY); - } + set_cpu_active((long)hcpu, false); return NOTIFY_OK; + default: + return NOTIFY_DONE; } - - return NOTIFY_DONE; } static int __init migration_init(void) @@ -7000,7 +6977,6 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, */ case CPU_ONLINE: - case CPU_DOWN_FAILED: cpuset_update_active_cpus(true); break; default: @@ -7012,8 +6988,32 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action) { + unsigned long flags; + long cpu = (long)hcpu; + struct dl_bw *dl_b; + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: + /* explicitly allow suspend */ + if (!(action & CPU_TASKS_FROZEN)) { + bool overflow; + int cpus; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (overflow) { + trace_printk("hotplug failed for cpu %lu", cpu); + return notifier_from_errno(-EBUSY); + } + } cpuset_update_active_cpus(false); break; case CPU_DOWN_PREPARE_FROZEN: -- 2.2.2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/