On Thu, Apr 02, 2015 at 11:47:04AM -0700, tip-bot for Juri Lelli wrote:
> Commit-ID: 3c18d447b3b36a8d3c90dc37dfbd363cdb685d0a
> Gitweb: http://git.kernel.org/tip/3c18d447b3b36a8d3c90dc37dfbd363cdb685d0a
> Author: Juri Lelli <[email protected]>
> AuthorDate: Tue, 31 Mar 2015 09:53:37 +0100
> Committer: Ingo Molnar <[email protected]>
> CommitDate: Thu, 2 Apr 2015 17:42:56 +0200
>
> sched/core: Check for available DL bandwidth in cpuset_cpu_inactive()
>
> 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 <[email protected]>
> Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
> Cc: Juri Lelli <[email protected]>
> Link:
> http://lkml.kernel.org/r/[email protected]
> Signed-off-by: Ingo Molnar <[email protected]>
> ---
> 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 4c49e75..28b0d75 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -5337,36 +5337,13 @@ 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)
> @@ -7006,7 +6983,6 @@ 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:
> @@ -7018,8 +6994,32 @@ 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);
Look ma,
someone forgot debugging code:
...
[ 0.000000] RCU restricting CPUs from NR_CPUS=8 to nr_cpu_ids=2.
[ 0.000000] RCU: Adjusting geometry for rcu_fanout_leaf=16, nr_cpu_ids=2
[ 0.000000]
[ 0.000000] **********************************************************
[ 0.000000] ** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **
[ 0.000000] ** **
[ 0.000000] ** trace_printk() being used. Allocating extra memory. **
[ 0.000000] ** **
[ 0.000000] ** This means that this is a DEBUG kernel and it is **
[ 0.000000] ** unsafe for production use. **
[ 0.000000] ** **
[ 0.000000] ** If you see this message and you are not debugging **
[ 0.000000] ** the kernel, report this immediately to your vendor! **
[ 0.000000] ** **
[ 0.000000] ** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **
[ 0.000000] **********************************************************
Fix coming up.
--
Regards/Gruss,
Boris.
ECO tip #101: Trim your mails when you reply.
--
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
