struct uclamp_rq was zeroed out entirely in assumption that in the first
call to uclamp_rq_inc() they'd be initialized correctly in accordance to
default settings.
But when next patch introduces a static key to skip
uclamp_rq_{inc,dec}() until userspace opts in to use uclamp, schedutil
will fail to perform any frequency changes because the
rq->uclamp[UCLAMP_MAX].value is zeroed at init and stays as such. Which
means all rqs are capped to 0 by default.
Fix it by making sure we do proper initialization at init without
relying on uclamp_rq_inc() doing it later.
Fixes: 69842cba9ace ("sched/uclamp: Add CPU's clamp buckets refcounting")
Signed-off-by: Qais Yousef <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Vincent Guittot <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Ben Segall <[email protected]>
Cc: Mel Gorman <[email protected]>
CC: Patrick Bellasi <[email protected]>
Cc: Chris Redpath <[email protected]>
Cc: Lukasz Luba <[email protected]>
Cc: [email protected]
---
kernel/sched/core.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a43c84c27c6f..4265861e13e9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1248,6 +1248,22 @@ static void uclamp_fork(struct task_struct *p)
}
}
+static void __init init_uclamp_rq(struct rq *rq)
+{
+ enum uclamp_id clamp_id;
+ struct uclamp_rq *uc_rq = rq->uclamp;
+
+ for_each_clamp_id(clamp_id) {
+ memset(uc_rq[clamp_id].bucket,
+ 0,
+ sizeof(struct uclamp_bucket)*UCLAMP_BUCKETS);
+
+ uc_rq[clamp_id].value = uclamp_none(clamp_id);
+ }
+
+ rq->uclamp_flags = 0;
+}
+
static void __init init_uclamp(void)
{
struct uclamp_se uc_max = {};
@@ -1256,11 +1272,8 @@ static void __init init_uclamp(void)
mutex_init(&uclamp_mutex);
- for_each_possible_cpu(cpu) {
- memset(&cpu_rq(cpu)->uclamp, 0,
- sizeof(struct uclamp_rq)*UCLAMP_CNT);
- cpu_rq(cpu)->uclamp_flags = 0;
- }
+ for_each_possible_cpu(cpu)
+ init_uclamp_rq(cpu_rq(cpu));
for_each_clamp_id(clamp_id) {
uclamp_se_set(&init_task.uclamp_req[clamp_id],
--
2.17.1
Hi Qais,
On Fri, Jun 19, 2020 at 19:20:10 +0200, Qais Yousef <[email protected]> wrote...
> struct uclamp_rq was zeroed out entirely in assumption that in the first
> call to uclamp_rq_inc() they'd be initialized correctly in accordance to
> default settings.
>
> But when next patch introduces a static key to skip
> uclamp_rq_{inc,dec}() until userspace opts in to use uclamp, schedutil
> will fail to perform any frequency changes because the
> rq->uclamp[UCLAMP_MAX].value is zeroed at init and stays as such. Which
> means all rqs are capped to 0 by default.
Does not this means the problem is more likely with uclamp_rq_util_with(),
which should be guarded?
Otherwise, we will also keep doing useless min/max aggregations each
time schedutil calls that function, thus not completely removing
uclamp overheads while user-space has not opted in.
What about dropping this and add the guard in the following patch, along
with the others?
> Fix it by making sure we do proper initialization at init without
>
> Fix it by making sure we do proper initialization at init without
> relying on uclamp_rq_inc() doing it later.
>
> Fixes: 69842cba9ace ("sched/uclamp: Add CPU's clamp buckets refcounting")
> Signed-off-by: Qais Yousef <[email protected]>
> Cc: Juri Lelli <[email protected]>
> Cc: Vincent Guittot <[email protected]>
> Cc: Dietmar Eggemann <[email protected]>
> Cc: Steven Rostedt <[email protected]>
> Cc: Ben Segall <[email protected]>
> Cc: Mel Gorman <[email protected]>
> CC: Patrick Bellasi <[email protected]>
> Cc: Chris Redpath <[email protected]>
> Cc: Lukasz Luba <[email protected]>
> Cc: [email protected]
> ---
> kernel/sched/core.c | 23 ++++++++++++++++++-----
> 1 file changed, 18 insertions(+), 5 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index a43c84c27c6f..4265861e13e9 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -1248,6 +1248,22 @@ static void uclamp_fork(struct task_struct *p)
> }
> }
>
> +static void __init init_uclamp_rq(struct rq *rq)
> +{
> + enum uclamp_id clamp_id;
> + struct uclamp_rq *uc_rq = rq->uclamp;
> +
> + for_each_clamp_id(clamp_id) {
> + memset(uc_rq[clamp_id].bucket,
> + 0,
> + sizeof(struct uclamp_bucket)*UCLAMP_BUCKETS);
> +
> + uc_rq[clamp_id].value = uclamp_none(clamp_id);
> + }
> +
> + rq->uclamp_flags = 0;
> +}
> +
> static void __init init_uclamp(void)
> {
> struct uclamp_se uc_max = {};
> @@ -1256,11 +1272,8 @@ static void __init init_uclamp(void)
>
> mutex_init(&uclamp_mutex);
>
> - for_each_possible_cpu(cpu) {
> - memset(&cpu_rq(cpu)->uclamp, 0,
> - sizeof(struct uclamp_rq)*UCLAMP_CNT);
> - cpu_rq(cpu)->uclamp_flags = 0;
> - }
> + for_each_possible_cpu(cpu)
> + init_uclamp_rq(cpu_rq(cpu));
>
> for_each_clamp_id(clamp_id) {
> uclamp_se_set(&init_task.uclamp_req[clamp_id],
On 06/24/20 09:26, Patrick Bellasi wrote:
>
> Hi Qais,
>
> On Fri, Jun 19, 2020 at 19:20:10 +0200, Qais Yousef <[email protected]> wrote...
>
> > struct uclamp_rq was zeroed out entirely in assumption that in the first
> > call to uclamp_rq_inc() they'd be initialized correctly in accordance to
> > default settings.
> >
> > But when next patch introduces a static key to skip
> > uclamp_rq_{inc,dec}() until userspace opts in to use uclamp, schedutil
> > will fail to perform any frequency changes because the
> > rq->uclamp[UCLAMP_MAX].value is zeroed at init and stays as such. Which
> > means all rqs are capped to 0 by default.
>
> Does not this means the problem is more likely with uclamp_rq_util_with(),
> which should be guarded?
The initialization is wrong and needs to be fixed, no? So I won't say
uclamp_rq_util_with() has any problem.
For RT boosting to work as-is, uclamp_rq_util_with() needs to stay the same,
otherwise we need to add extra logic to deal with that. Which I don't think is
worth it or necessary. The function is called from sugov and
find_energy_efficient_cpu(), both of which aren't a worry to make this call
unconditionally IMO.
Thanks
--
Qais Yousef
>
> Otherwise, we will also keep doing useless min/max aggregations each
> time schedutil calls that function, thus not completely removing
> uclamp overheads while user-space has not opted in.
>
> What about dropping this and add the guard in the following patch, along
> with the others?
>
> > Fix it by making sure we do proper initialization at init without
>
> >
> > Fix it by making sure we do proper initialization at init without
> > relying on uclamp_rq_inc() doing it later.
> >
> > Fixes: 69842cba9ace ("sched/uclamp: Add CPU's clamp buckets refcounting")
> > Signed-off-by: Qais Yousef <[email protected]>
> > Cc: Juri Lelli <[email protected]>
> > Cc: Vincent Guittot <[email protected]>
> > Cc: Dietmar Eggemann <[email protected]>
> > Cc: Steven Rostedt <[email protected]>
> > Cc: Ben Segall <[email protected]>
> > Cc: Mel Gorman <[email protected]>
> > CC: Patrick Bellasi <[email protected]>
> > Cc: Chris Redpath <[email protected]>
> > Cc: Lukasz Luba <[email protected]>
> > Cc: [email protected]
> > ---
> > kernel/sched/core.c | 23 ++++++++++++++++++-----
> > 1 file changed, 18 insertions(+), 5 deletions(-)
> >
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index a43c84c27c6f..4265861e13e9 100644
> > --- a/kernel/sched/core.c
> > +++ b/kernel/sched/core.c
> > @@ -1248,6 +1248,22 @@ static void uclamp_fork(struct task_struct *p)
> > }
> > }
> >
> > +static void __init init_uclamp_rq(struct rq *rq)
> > +{
> > + enum uclamp_id clamp_id;
> > + struct uclamp_rq *uc_rq = rq->uclamp;
> > +
> > + for_each_clamp_id(clamp_id) {
> > + memset(uc_rq[clamp_id].bucket,
> > + 0,
> > + sizeof(struct uclamp_bucket)*UCLAMP_BUCKETS);
> > +
> > + uc_rq[clamp_id].value = uclamp_none(clamp_id);
> > + }
> > +
> > + rq->uclamp_flags = 0;
> > +}
> > +
> > static void __init init_uclamp(void)
> > {
> > struct uclamp_se uc_max = {};
> > @@ -1256,11 +1272,8 @@ static void __init init_uclamp(void)
> >
> > mutex_init(&uclamp_mutex);
> >
> > - for_each_possible_cpu(cpu) {
> > - memset(&cpu_rq(cpu)->uclamp, 0,
> > - sizeof(struct uclamp_rq)*UCLAMP_CNT);
> > - cpu_rq(cpu)->uclamp_flags = 0;
> > - }
> > + for_each_possible_cpu(cpu)
> > + init_uclamp_rq(cpu_rq(cpu));
> >
> > for_each_clamp_id(clamp_id) {
> > uclamp_se_set(&init_task.uclamp_req[clamp_id],
>