From: Zhen Lei <thunder.leizhen@huawei.com>
In kernels built with either CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y or
CONFIG_NO_HZ_FULL=y, additional CPUs must be added to rcu_nocb_mask.
Except that kernels booted without the rcu_nocbs= will not have
allocated rcu_nocb_mask. And the current rcu_init_nohz() function uses
its need_rcu_nocb_mask and offload_all local variables to track the
rcu_nocb and nohz_full state.
But there is a much simpler approach, namely creating a cpumask pointer
to track the default and then using cpumask_available() to check the
rcu_nocb_mask state. This commit takes this approach, thereby simplifying
and shortening the rcu_init_nohz() function.
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
kernel/rcu/tree_nocb.h | 32 +++++++++-----------------------
1 file changed, 9 insertions(+), 23 deletions(-)
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 0a5f0ef414845..c8167be2288fa 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1210,45 +1210,31 @@ EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload);
void __init rcu_init_nohz(void)
{
int cpu;
- bool need_rcu_nocb_mask = false;
- bool offload_all = false;
struct rcu_data *rdp;
+ const struct cpumask *cpumask = NULL;
#if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL)
- if (!rcu_state.nocb_is_setup) {
- need_rcu_nocb_mask = true;
- offload_all = true;
- }
-#endif /* #if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL) */
-
-#if defined(CONFIG_NO_HZ_FULL)
- if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) {
- need_rcu_nocb_mask = true;
- offload_all = false; /* NO_HZ_FULL has its own mask. */
- }
-#endif /* #if defined(CONFIG_NO_HZ_FULL) */
+ cpumask = cpu_possible_mask;
+#elif defined(CONFIG_NO_HZ_FULL)
+ if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask))
+ cpumask = tick_nohz_full_mask;
+#endif
- if (need_rcu_nocb_mask) {
+ if (cpumask) {
if (!cpumask_available(rcu_nocb_mask)) {
if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
return;
}
}
+
+ cpumask_or(rcu_nocb_mask, rcu_nocb_mask, cpumask);
rcu_state.nocb_is_setup = true;
}
if (!rcu_state.nocb_is_setup)
return;
-#if defined(CONFIG_NO_HZ_FULL)
- if (tick_nohz_full_running)
- cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
-#endif /* #if defined(CONFIG_NO_HZ_FULL) */
-
- if (offload_all)
- cpumask_setall(rcu_nocb_mask);
-
if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
cpumask_and(rcu_nocb_mask, cpu_possible_mask,
--
2.31.1.189.g2e36527f23On Wed, Aug 31, 2022 at 11:10:44AM -0700, Paul E. McKenney wrote:
> From: Zhen Lei <thunder.leizhen@huawei.com>
>
> In kernels built with either CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y or
> CONFIG_NO_HZ_FULL=y, additional CPUs must be added to rcu_nocb_mask.
> Except that kernels booted without the rcu_nocbs= will not have
> allocated rcu_nocb_mask. And the current rcu_init_nohz() function uses
> its need_rcu_nocb_mask and offload_all local variables to track the
> rcu_nocb and nohz_full state.
>
> But there is a much simpler approach, namely creating a cpumask pointer
> to track the default and then using cpumask_available() to check the
> rcu_nocb_mask state. This commit takes this approach, thereby simplifying
> and shortening the rcu_init_nohz() function.
>
> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
> Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> ---
> kernel/rcu/tree_nocb.h | 32 +++++++++-----------------------
> 1 file changed, 9 insertions(+), 23 deletions(-)
>
> diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
> index 0a5f0ef414845..c8167be2288fa 100644
> --- a/kernel/rcu/tree_nocb.h
> +++ b/kernel/rcu/tree_nocb.h
> @@ -1210,45 +1210,31 @@ EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload);
> void __init rcu_init_nohz(void)
> {
> int cpu;
> - bool need_rcu_nocb_mask = false;
> - bool offload_all = false;
> struct rcu_data *rdp;
> + const struct cpumask *cpumask = NULL;
>
> #if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL)
> - if (!rcu_state.nocb_is_setup) {
> - need_rcu_nocb_mask = true;
> - offload_all = true;
> - }
> -#endif /* #if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL) */
> -
> -#if defined(CONFIG_NO_HZ_FULL)
> - if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) {
> - need_rcu_nocb_mask = true;
> - offload_all = false; /* NO_HZ_FULL has its own mask. */
> - }
> -#endif /* #if defined(CONFIG_NO_HZ_FULL) */
> + cpumask = cpu_possible_mask;
You're missing the rcu_state.nocb_is_setup check, so
CONFIG_RCU_NOCB_CPU_DEFAULT_ALL will now always override the rcu_nocbs=
parameter (should be the other way around).
> +#elif defined(CONFIG_NO_HZ_FULL)
> + if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask))
> + cpumask = tick_nohz_full_mask;
> +#endif
A subtle behaviour difference here too: CONFIG_RCU_NOCB_CPU_DEFAULT_ALL will
now override nohz_full=
I don't mind, it's probably what we want in the end, but the changelog should
tell about it, or even better, this should be a separate change.
Thanks.
>
> - if (need_rcu_nocb_mask) {
> + if (cpumask) {
> if (!cpumask_available(rcu_nocb_mask)) {
> if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
> pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
> return;
> }
> }
> +
> + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, cpumask);
> rcu_state.nocb_is_setup = true;
> }
>
> if (!rcu_state.nocb_is_setup)
> return;
>
> -#if defined(CONFIG_NO_HZ_FULL)
> - if (tick_nohz_full_running)
> - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
> -#endif /* #if defined(CONFIG_NO_HZ_FULL) */
> -
> - if (offload_all)
> - cpumask_setall(rcu_nocb_mask);
> -
> if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
> pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
> cpumask_and(rcu_nocb_mask, cpu_possible_mask,
> --
> 2.31.1.189.g2e36527f23
>
On Thu, Sep 01, 2022 at 11:15:57AM +0200, Frederic Weisbecker wrote:
> On Wed, Aug 31, 2022 at 11:10:44AM -0700, Paul E. McKenney wrote:
> > From: Zhen Lei <thunder.leizhen@huawei.com>
> >
> > In kernels built with either CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y or
> > CONFIG_NO_HZ_FULL=y, additional CPUs must be added to rcu_nocb_mask.
> > Except that kernels booted without the rcu_nocbs= will not have
> > allocated rcu_nocb_mask. And the current rcu_init_nohz() function uses
> > its need_rcu_nocb_mask and offload_all local variables to track the
> > rcu_nocb and nohz_full state.
> >
> > But there is a much simpler approach, namely creating a cpumask pointer
> > to track the default and then using cpumask_available() to check the
> > rcu_nocb_mask state. This commit takes this approach, thereby simplifying
> > and shortening the rcu_init_nohz() function.
> >
> > Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
> > Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
> > Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> > ---
> > kernel/rcu/tree_nocb.h | 32 +++++++++-----------------------
> > 1 file changed, 9 insertions(+), 23 deletions(-)
> >
> > diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
> > index 0a5f0ef414845..c8167be2288fa 100644
> > --- a/kernel/rcu/tree_nocb.h
> > +++ b/kernel/rcu/tree_nocb.h
> > @@ -1210,45 +1210,31 @@ EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload);
> > void __init rcu_init_nohz(void)
> > {
> > int cpu;
> > - bool need_rcu_nocb_mask = false;
> > - bool offload_all = false;
> > struct rcu_data *rdp;
> > + const struct cpumask *cpumask = NULL;
> >
> > #if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL)
> > - if (!rcu_state.nocb_is_setup) {
> > - need_rcu_nocb_mask = true;
> > - offload_all = true;
> > - }
> > -#endif /* #if defined(CONFIG_RCU_NOCB_CPU_DEFAULT_ALL) */
> > -
> > -#if defined(CONFIG_NO_HZ_FULL)
> > - if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) {
> > - need_rcu_nocb_mask = true;
> > - offload_all = false; /* NO_HZ_FULL has its own mask. */
> > - }
> > -#endif /* #if defined(CONFIG_NO_HZ_FULL) */
> > + cpumask = cpu_possible_mask;
>
> You're missing the rcu_state.nocb_is_setup check, so
> CONFIG_RCU_NOCB_CPU_DEFAULT_ALL will now always override the rcu_nocbs=
> parameter (should be the other way around).
This is indeed a problem, so especially thank you for looking this over!
I will revert this patch.
> > +#elif defined(CONFIG_NO_HZ_FULL)
> > + if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask))
> > + cpumask = tick_nohz_full_mask;
> > +#endif
>
> A subtle behaviour difference here too: CONFIG_RCU_NOCB_CPU_DEFAULT_ALL will
> now override nohz_full=
>
> I don't mind, it's probably what we want in the end, but the changelog should
> tell about it, or even better, this should be a separate change.
Good point. Perhaps the key point is that if there is nohz_full=,
rcu_nocbs=, and CONFIG_RCU_NOCB_CPU_DEFAULT_ALL, we still need rcu_nocbs=
to include at least those bits set by nohz_full=.
Are there any other constraints?
Zhen Lei, please feel free to submit an updated patch.
Thanx, Paul
> Thanks.
>
> >
> > - if (need_rcu_nocb_mask) {
> > + if (cpumask) {
> > if (!cpumask_available(rcu_nocb_mask)) {
> > if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
> > pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
> > return;
> > }
> > }
> > +
> > + cpumask_or(rcu_nocb_mask, rcu_nocb_mask, cpumask);
> > rcu_state.nocb_is_setup = true;
> > }
> >
> > if (!rcu_state.nocb_is_setup)
> > return;
> >
> > -#if defined(CONFIG_NO_HZ_FULL)
> > - if (tick_nohz_full_running)
> > - cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
> > -#endif /* #if defined(CONFIG_NO_HZ_FULL) */
> > -
> > - if (offload_all)
> > - cpumask_setall(rcu_nocb_mask);
> > -
> > if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
> > pr_info("\tNote: kernel parameter 'rcu_nocbs=', 'nohz_full', or 'isolcpus=' contains nonexistent CPUs.\n");
> > cpumask_and(rcu_nocb_mask, cpu_possible_mask,
> > --
> > 2.31.1.189.g2e36527f23
> >
On Thu, Sep 01, 2022 at 03:25:20AM -0700, Paul E. McKenney wrote: > On Thu, Sep 01, 2022 at 11:15:57AM +0200, Frederic Weisbecker wrote: > > > +#elif defined(CONFIG_NO_HZ_FULL) > > > + if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) > > > + cpumask = tick_nohz_full_mask; > > > +#endif > > > > A subtle behaviour difference here too: CONFIG_RCU_NOCB_CPU_DEFAULT_ALL will > > now override nohz_full= > > > > I don't mind, it's probably what we want in the end, but the changelog should > > tell about it, or even better, this should be a separate change. > > Good point. Perhaps the key point is that if there is nohz_full=, > rcu_nocbs=, and CONFIG_RCU_NOCB_CPU_DEFAULT_ALL, we still need rcu_nocbs= > to include at least those bits set by nohz_full=. Not sure I get what you mean. nohz_full= should in any case always force rcu_nocbs at least on the nohz_full CPUs. For example assuming the following combination: rcu_nocbs=6, nohz_full=7 AND CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y, then the result should be: NOCB CPUs = 6,7 NOHZ_FULL CPUs = 7 (CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y is overriden by rcu_nocbs=6). Now if we have nohz_full=7 AND CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y, then the result is expected to be either: NOCB CPUs = 7 (upstream behaviour) NOHZ_FULL CPUs = 7 or NOCB CPUs = all NOHZ_FULL CPUs = 7 The second makes more sense IMHO but that should be in a separate change. Thanks.
On Thu, Sep 01, 2022 at 01:11:14PM +0200, Frederic Weisbecker wrote: > On Thu, Sep 01, 2022 at 03:25:20AM -0700, Paul E. McKenney wrote: > > On Thu, Sep 01, 2022 at 11:15:57AM +0200, Frederic Weisbecker wrote: > > > > +#elif defined(CONFIG_NO_HZ_FULL) > > > > + if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) > > > > + cpumask = tick_nohz_full_mask; > > > > +#endif > > > > > > A subtle behaviour difference here too: CONFIG_RCU_NOCB_CPU_DEFAULT_ALL will > > > now override nohz_full= > > > > > > I don't mind, it's probably what we want in the end, but the changelog should > > > tell about it, or even better, this should be a separate change. > > > > Good point. Perhaps the key point is that if there is nohz_full=, > > rcu_nocbs=, and CONFIG_RCU_NOCB_CPU_DEFAULT_ALL, we still need rcu_nocbs= > > to include at least those bits set by nohz_full=. > > Not sure I get what you mean. nohz_full= should in any case always force > rcu_nocbs at least on the nohz_full CPUs. > > For example assuming the following combination: rcu_nocbs=6, nohz_full=7 AND > CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y, then the result should be: > > NOCB CPUs = 6,7 > NOHZ_FULL CPUs = 7 > > (CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y is overriden by rcu_nocbs=6). > > Now if we have nohz_full=7 AND CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y, then the > result is expected to be either: > > NOCB CPUs = 7 (upstream behaviour) > NOHZ_FULL CPUs = 7 > > or > > NOCB CPUs = all > NOHZ_FULL CPUs = 7 > > The second makes more sense IMHO but that should be in a separate change. Your examples are consistent with what I was trying to say. ;-) Thanx, Paul
On 2022/9/1 19:11, Frederic Weisbecker wrote: > On Thu, Sep 01, 2022 at 03:25:20AM -0700, Paul E. McKenney wrote: >> On Thu, Sep 01, 2022 at 11:15:57AM +0200, Frederic Weisbecker wrote: >>>> +#elif defined(CONFIG_NO_HZ_FULL) >>>> + if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) >>>> + cpumask = tick_nohz_full_mask; >>>> +#endif >>> >>> A subtle behaviour difference here too: CONFIG_RCU_NOCB_CPU_DEFAULT_ALL will >>> now override nohz_full= >>> >>> I don't mind, it's probably what we want in the end, but the changelog should >>> tell about it, or even better, this should be a separate change. >> >> Good point. Perhaps the key point is that if there is nohz_full=, >> rcu_nocbs=, and CONFIG_RCU_NOCB_CPU_DEFAULT_ALL, we still need rcu_nocbs= >> to include at least those bits set by nohz_full=. > > Not sure I get what you mean. nohz_full= should in any case always force > rcu_nocbs at least on the nohz_full CPUs. > > For example assuming the following combination: rcu_nocbs=6, nohz_full=7 AND > CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y, then the result should be: > > NOCB CPUs = 6,7 > NOHZ_FULL CPUs = 7 > > (CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y is overriden by rcu_nocbs=6). > > Now if we have nohz_full=7 AND CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y, then the > result is expected to be either: > > NOCB CPUs = 7 (upstream behaviour) > NOHZ_FULL CPUs = 7 OK, I got it. CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y takes effect only when there are no 'rcu_nocbs=' and 'nohz_full='. > > or > > NOCB CPUs = all > NOHZ_FULL CPUs = 7 > > The second makes more sense IMHO but that should be in a separate change. OK, in this case, CONFIG_RCU_NOCB_CPU_DEFAULT_ALL=y takes effect only when there is no 'rcu_nocbs='. > > Thanks. > . > -- Regards, Zhen Lei
© 2016 - 2026 Red Hat, Inc.