"mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
to, however in the IPI sending loop, "mask_ofl_ipi" along with another
variable "mask_ofl_test" might also get modified to record which CPU's
quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
variables seems to be redundant for such a propose, so this patch clean
things a little by solely using "mask_ofl_test" for recording and
"mask_ofl_ipi" for iteration. This would improve the readibility of the
IPI sending loop in sync_rcu_exp_select_node_cpus().
Signed-off-by: Boqun Feng <[email protected]>
---
kernel/rcu/tree_exp.h | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 69c5aa64fcfd..212470018752 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
}
ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
put_cpu();
- if (!ret) {
- mask_ofl_ipi &= ~mask;
+ /* The CPU responses the IPI, and will report QS itself */
+ if (!ret)
continue;
- }
+
/* Failed, raced with CPU hotplug operation. */
raw_spin_lock_irqsave_rcu_node(rnp, flags);
if ((rnp->qsmaskinitnext & mask) &&
@@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
schedule_timeout_uninterruptible(1);
goto retry_ipi;
}
- /* CPU really is offline, so we can ignore it. */
- if (!(rnp->expmask & mask))
- mask_ofl_ipi &= ~mask;
+ /* CPU really is offline, and we need its QS to pass GP. */
+ if (rnp->expmask & mask)
+ mask_ofl_test |= mask;
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/* Report quiescent states for those that went offline. */
- mask_ofl_test |= mask_ofl_ipi;
if (mask_ofl_test)
rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
}
--
2.23.0
On Tue, Oct 08, 2019 at 01:01:40PM +0800, Boqun Feng wrote:
> "mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
> to, however in the IPI sending loop, "mask_ofl_ipi" along with another
> variable "mask_ofl_test" might also get modified to record which CPU's
> quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
> variables seems to be redundant for such a propose, so this patch clean
> things a little by solely using "mask_ofl_test" for recording and
> "mask_ofl_ipi" for iteration. This would improve the readibility of the
> IPI sending loop in sync_rcu_exp_select_node_cpus().
>
> Signed-off-by: Boqun Feng <[email protected]>
Queued for further review and testing, thank you!!!
Thanx, Paul
> ---
> kernel/rcu/tree_exp.h | 13 ++++++-------
> 1 file changed, 6 insertions(+), 7 deletions(-)
>
> diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> index 69c5aa64fcfd..212470018752 100644
> --- a/kernel/rcu/tree_exp.h
> +++ b/kernel/rcu/tree_exp.h
> @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> }
> ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> put_cpu();
> - if (!ret) {
> - mask_ofl_ipi &= ~mask;
> + /* The CPU responses the IPI, and will report QS itself */
> + if (!ret)
> continue;
> - }
> +
> /* Failed, raced with CPU hotplug operation. */
> raw_spin_lock_irqsave_rcu_node(rnp, flags);
> if ((rnp->qsmaskinitnext & mask) &&
> @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> schedule_timeout_uninterruptible(1);
> goto retry_ipi;
> }
> - /* CPU really is offline, so we can ignore it. */
> - if (!(rnp->expmask & mask))
> - mask_ofl_ipi &= ~mask;
> + /* CPU really is offline, and we need its QS to pass GP. */
> + if (rnp->expmask & mask)
> + mask_ofl_test |= mask;
> raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> }
> /* Report quiescent states for those that went offline. */
> - mask_ofl_test |= mask_ofl_ipi;
> if (mask_ofl_test)
> rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> }
> --
> 2.23.0
>
On Tue, Oct 08, 2019 at 01:01:40PM +0800, Boqun Feng wrote:
> "mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
> to, however in the IPI sending loop, "mask_ofl_ipi" along with another
> variable "mask_ofl_test" might also get modified to record which CPU's
> quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
> variables seems to be redundant for such a propose, so this patch clean
> things a little by solely using "mask_ofl_test" for recording and
> "mask_ofl_ipi" for iteration. This would improve the readibility of the
> IPI sending loop in sync_rcu_exp_select_node_cpus().
>
> Signed-off-by: Boqun Feng <[email protected]>
> ---
Reviewed-by: Joel Fernandes (Google) <[email protected]>
thanks,
- Joel
> kernel/rcu/tree_exp.h | 13 ++++++-------
> 1 file changed, 6 insertions(+), 7 deletions(-)
>
> diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> index 69c5aa64fcfd..212470018752 100644
> --- a/kernel/rcu/tree_exp.h
> +++ b/kernel/rcu/tree_exp.h
> @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> }
> ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> put_cpu();
> - if (!ret) {
> - mask_ofl_ipi &= ~mask;
> + /* The CPU responses the IPI, and will report QS itself */
> + if (!ret)
> continue;
> - }
> +
> /* Failed, raced with CPU hotplug operation. */
> raw_spin_lock_irqsave_rcu_node(rnp, flags);
> if ((rnp->qsmaskinitnext & mask) &&
> @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> schedule_timeout_uninterruptible(1);
> goto retry_ipi;
> }
> - /* CPU really is offline, so we can ignore it. */
> - if (!(rnp->expmask & mask))
> - mask_ofl_ipi &= ~mask;
> + /* CPU really is offline, and we need its QS to pass GP. */
> + if (rnp->expmask & mask)
> + mask_ofl_test |= mask;
> raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> }
> /* Report quiescent states for those that went offline. */
> - mask_ofl_test |= mask_ofl_ipi;
> if (mask_ofl_test)
> rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> }
> --
> 2.23.0
>
On Tue, 8 Oct 2019 at 18:30, Joel Fernandes <[email protected]> wrote:
>
> On Tue, Oct 08, 2019 at 01:01:40PM +0800, Boqun Feng wrote:
> > "mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
> > to, however in the IPI sending loop, "mask_ofl_ipi" along with another
> > variable "mask_ofl_test" might also get modified to record which CPU's
> > quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
> > variables seems to be redundant for such a propose, so this patch clean
> > things a little by solely using "mask_ofl_test" for recording and
> > "mask_ofl_ipi" for iteration. This would improve the readibility of the
> > IPI sending loop in sync_rcu_exp_select_node_cpus().
> >
> > Signed-off-by: Boqun Feng <[email protected]>
> > ---
>
> Reviewed-by: Joel Fernandes (Google) <[email protected]>
>
> thanks,
>
> - Joel
Acked-by: Marco Elver <[email protected]>
If this is the official patch for the fix to the KCSAN reported
data-race, it'd be great to include the tag:
Reported-by: [email protected]
so the bot knows this was fixed.
Thanks!
-- Marco
> > kernel/rcu/tree_exp.h | 13 ++++++-------
> > 1 file changed, 6 insertions(+), 7 deletions(-)
> >
> > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> > index 69c5aa64fcfd..212470018752 100644
> > --- a/kernel/rcu/tree_exp.h
> > +++ b/kernel/rcu/tree_exp.h
> > @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > }
> > ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> > put_cpu();
> > - if (!ret) {
> > - mask_ofl_ipi &= ~mask;
> > + /* The CPU responses the IPI, and will report QS itself */
> > + if (!ret)
> > continue;
> > - }
> > +
> > /* Failed, raced with CPU hotplug operation. */
> > raw_spin_lock_irqsave_rcu_node(rnp, flags);
> > if ((rnp->qsmaskinitnext & mask) &&
> > @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > schedule_timeout_uninterruptible(1);
> > goto retry_ipi;
> > }
> > - /* CPU really is offline, so we can ignore it. */
> > - if (!(rnp->expmask & mask))
> > - mask_ofl_ipi &= ~mask;
> > + /* CPU really is offline, and we need its QS to pass GP. */
> > + if (rnp->expmask & mask)
> > + mask_ofl_test |= mask;
> > raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> > }
> > /* Report quiescent states for those that went offline. */
> > - mask_ofl_test |= mask_ofl_ipi;
> > if (mask_ofl_test)
> > rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> > }
> > --
> > 2.23.0
> >
On Tue, Oct 08, 2019 at 06:35:45PM +0200, Marco Elver wrote:
> On Tue, 8 Oct 2019 at 18:30, Joel Fernandes <[email protected]> wrote:
> >
> > On Tue, Oct 08, 2019 at 01:01:40PM +0800, Boqun Feng wrote:
> > > "mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
> > > to, however in the IPI sending loop, "mask_ofl_ipi" along with another
> > > variable "mask_ofl_test" might also get modified to record which CPU's
> > > quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
> > > variables seems to be redundant for such a propose, so this patch clean
> > > things a little by solely using "mask_ofl_test" for recording and
> > > "mask_ofl_ipi" for iteration. This would improve the readibility of the
> > > IPI sending loop in sync_rcu_exp_select_node_cpus().
> > >
> > > Signed-off-by: Boqun Feng <[email protected]>
> > > ---
> >
> > Reviewed-by: Joel Fernandes (Google) <[email protected]>
> >
> > thanks,
> >
> > - Joel
>
> Acked-by: Marco Elver <[email protected]>
>
> If this is the official patch for the fix to the KCSAN reported
> data-race, it'd be great to include the tag:
> Reported-by: [email protected]
> so the bot knows this was fixed.
It is just an optimization that got triggerred due to debugging of the
reported issue but does (should) not fix the issue.
Boqun, are you going to be posting another patch which just uses mask_ofl_ipi
in the for_each(..) loop? (without using _snap) as Paul suggested?
Paul mentioned other places where rnp->expmask is locklessly accessed so I
think that may be fixed separately (such as the stall-warning code). Paul,
were you planning on fixing all such accesses together (other than this code)
or should I look into it more? I guess for the stall case, KCSAN would have
to trigger stalls to see those issues.
thanks,
- Joel
>
> Thanks!
> -- Marco
>
> > > kernel/rcu/tree_exp.h | 13 ++++++-------
> > > 1 file changed, 6 insertions(+), 7 deletions(-)
> > >
> > > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> > > index 69c5aa64fcfd..212470018752 100644
> > > --- a/kernel/rcu/tree_exp.h
> > > +++ b/kernel/rcu/tree_exp.h
> > > @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > }
> > > ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> > > put_cpu();
> > > - if (!ret) {
> > > - mask_ofl_ipi &= ~mask;
> > > + /* The CPU responses the IPI, and will report QS itself */
> > > + if (!ret)
> > > continue;
> > > - }
> > > +
> > > /* Failed, raced with CPU hotplug operation. */
> > > raw_spin_lock_irqsave_rcu_node(rnp, flags);
> > > if ((rnp->qsmaskinitnext & mask) &&
> > > @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > schedule_timeout_uninterruptible(1);
> > > goto retry_ipi;
> > > }
> > > - /* CPU really is offline, so we can ignore it. */
> > > - if (!(rnp->expmask & mask))
> > > - mask_ofl_ipi &= ~mask;
> > > + /* CPU really is offline, and we need its QS to pass GP. */
> > > + if (rnp->expmask & mask)
> > > + mask_ofl_test |= mask;
> > > raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> > > }
> > > /* Report quiescent states for those that went offline. */
> > > - mask_ofl_test |= mask_ofl_ipi;
> > > if (mask_ofl_test)
> > > rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> > > }
> > > --
> > > 2.23.0
> > >
On Tue, Oct 08, 2019 at 01:01:21PM -0400, Joel Fernandes wrote:
> On Tue, Oct 08, 2019 at 06:35:45PM +0200, Marco Elver wrote:
> > On Tue, 8 Oct 2019 at 18:30, Joel Fernandes <[email protected]> wrote:
> > >
> > > On Tue, Oct 08, 2019 at 01:01:40PM +0800, Boqun Feng wrote:
> > > > "mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
> > > > to, however in the IPI sending loop, "mask_ofl_ipi" along with another
> > > > variable "mask_ofl_test" might also get modified to record which CPU's
> > > > quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
> > > > variables seems to be redundant for such a propose, so this patch clean
> > > > things a little by solely using "mask_ofl_test" for recording and
> > > > "mask_ofl_ipi" for iteration. This would improve the readibility of the
> > > > IPI sending loop in sync_rcu_exp_select_node_cpus().
> > > >
> > > > Signed-off-by: Boqun Feng <[email protected]>
> > > > ---
> > >
> > > Reviewed-by: Joel Fernandes (Google) <[email protected]>
> > >
> > > thanks,
> > >
> > > - Joel
> >
> > Acked-by: Marco Elver <[email protected]>
> >
Thank you both!
> > If this is the official patch for the fix to the KCSAN reported
> > data-race, it'd be great to include the tag:
> > Reported-by: [email protected]
> > so the bot knows this was fixed.
>
> It is just an optimization that got triggerred due to debugging of the
> reported issue but does (should) not fix the issue.
>
Right.
> Boqun, are you going to be posting another patch which just uses mask_ofl_ipi
> in the for_each(..) loop? (without using _snap) as Paul suggested?
>
IIUC, Paul already has this fix along with other ->expmask queued in his
dev branch:
https://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git/commit/?h=dev&id=4e4fefe0630dcf7415d62e6d9171c8f209444376
, and with the proper "Reported-by" tag to give syzbot credit.
Regards,
Boqun
> Paul mentioned other places where rnp->expmask is locklessly accessed so I
> think that may be fixed separately (such as the stall-warning code). Paul,
> were you planning on fixing all such accesses together (other than this code)
> or should I look into it more? I guess for the stall case, KCSAN would have
> to trigger stalls to see those issues.
>
> thanks,
>
> - Joel
>
> >
> > Thanks!
> > -- Marco
> >
> > > > kernel/rcu/tree_exp.h | 13 ++++++-------
> > > > 1 file changed, 6 insertions(+), 7 deletions(-)
> > > >
> > > > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> > > > index 69c5aa64fcfd..212470018752 100644
> > > > --- a/kernel/rcu/tree_exp.h
> > > > +++ b/kernel/rcu/tree_exp.h
> > > > @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > > }
> > > > ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> > > > put_cpu();
> > > > - if (!ret) {
> > > > - mask_ofl_ipi &= ~mask;
> > > > + /* The CPU responses the IPI, and will report QS itself */
> > > > + if (!ret)
> > > > continue;
> > > > - }
> > > > +
> > > > /* Failed, raced with CPU hotplug operation. */
> > > > raw_spin_lock_irqsave_rcu_node(rnp, flags);
> > > > if ((rnp->qsmaskinitnext & mask) &&
> > > > @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > > schedule_timeout_uninterruptible(1);
> > > > goto retry_ipi;
> > > > }
> > > > - /* CPU really is offline, so we can ignore it. */
> > > > - if (!(rnp->expmask & mask))
> > > > - mask_ofl_ipi &= ~mask;
> > > > + /* CPU really is offline, and we need its QS to pass GP. */
> > > > + if (rnp->expmask & mask)
> > > > + mask_ofl_test |= mask;
> > > > raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> > > > }
> > > > /* Report quiescent states for those that went offline. */
> > > > - mask_ofl_test |= mask_ofl_ipi;
> > > > if (mask_ofl_test)
> > > > rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> > > > }
> > > > --
> > > > 2.23.0
> > > >
On Wed, Oct 09, 2019 at 10:20:17AM +0800, Boqun Feng wrote:
[snip]
> > Boqun, are you going to be posting another patch which just uses mask_ofl_ipi
> > in the for_each(..) loop? (without using _snap) as Paul suggested?
> >
>
> IIUC, Paul already has this fix along with other ->expmask queued in his
> dev branch:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git/commit/?h=dev&id=4e4fefe0630dcf7415d62e6d9171c8f209444376
>
> , and with the proper "Reported-by" tag to give syzbot credit.
Yes, I see it now. So Marco you should be good ;)
thanks!
- Joel
>
> Regards,
> Boqun
>
> > Paul mentioned other places where rnp->expmask is locklessly accessed so I
> > think that may be fixed separately (such as the stall-warning code). Paul,
> > were you planning on fixing all such accesses together (other than this code)
> > or should I look into it more? I guess for the stall case, KCSAN would have
> > to trigger stalls to see those issues.
> >
> > thanks,
> >
> > - Joel
> >
> > >
> > > Thanks!
> > > -- Marco
> > >
> > > > > kernel/rcu/tree_exp.h | 13 ++++++-------
> > > > > 1 file changed, 6 insertions(+), 7 deletions(-)
> > > > >
> > > > > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> > > > > index 69c5aa64fcfd..212470018752 100644
> > > > > --- a/kernel/rcu/tree_exp.h
> > > > > +++ b/kernel/rcu/tree_exp.h
> > > > > @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > > > }
> > > > > ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> > > > > put_cpu();
> > > > > - if (!ret) {
> > > > > - mask_ofl_ipi &= ~mask;
> > > > > + /* The CPU responses the IPI, and will report QS itself */
> > > > > + if (!ret)
> > > > > continue;
> > > > > - }
> > > > > +
> > > > > /* Failed, raced with CPU hotplug operation. */
> > > > > raw_spin_lock_irqsave_rcu_node(rnp, flags);
> > > > > if ((rnp->qsmaskinitnext & mask) &&
> > > > > @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > > > schedule_timeout_uninterruptible(1);
> > > > > goto retry_ipi;
> > > > > }
> > > > > - /* CPU really is offline, so we can ignore it. */
> > > > > - if (!(rnp->expmask & mask))
> > > > > - mask_ofl_ipi &= ~mask;
> > > > > + /* CPU really is offline, and we need its QS to pass GP. */
> > > > > + if (rnp->expmask & mask)
> > > > > + mask_ofl_test |= mask;
> > > > > raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> > > > > }
> > > > > /* Report quiescent states for those that went offline. */
> > > > > - mask_ofl_test |= mask_ofl_ipi;
> > > > > if (mask_ofl_test)
> > > > > rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> > > > > }
> > > > > --
> > > > > 2.23.0
> > > > >
On Tue, Oct 08, 2019 at 12:30:28PM -0400, Joel Fernandes wrote:
> On Tue, Oct 08, 2019 at 01:01:40PM +0800, Boqun Feng wrote:
> > "mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
> > to, however in the IPI sending loop, "mask_ofl_ipi" along with another
> > variable "mask_ofl_test" might also get modified to record which CPU's
> > quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
> > variables seems to be redundant for such a propose, so this patch clean
> > things a little by solely using "mask_ofl_test" for recording and
> > "mask_ofl_ipi" for iteration. This would improve the readibility of the
> > IPI sending loop in sync_rcu_exp_select_node_cpus().
> >
> > Signed-off-by: Boqun Feng <[email protected]>
> > ---
>
> Reviewed-by: Joel Fernandes (Google) <[email protected]>
Applied, thank you!
Thanx, Paul
> thanks,
>
> - Joel
>
> > kernel/rcu/tree_exp.h | 13 ++++++-------
> > 1 file changed, 6 insertions(+), 7 deletions(-)
> >
> > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> > index 69c5aa64fcfd..212470018752 100644
> > --- a/kernel/rcu/tree_exp.h
> > +++ b/kernel/rcu/tree_exp.h
> > @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > }
> > ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> > put_cpu();
> > - if (!ret) {
> > - mask_ofl_ipi &= ~mask;
> > + /* The CPU responses the IPI, and will report QS itself */
> > + if (!ret)
> > continue;
> > - }
> > +
> > /* Failed, raced with CPU hotplug operation. */
> > raw_spin_lock_irqsave_rcu_node(rnp, flags);
> > if ((rnp->qsmaskinitnext & mask) &&
> > @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > schedule_timeout_uninterruptible(1);
> > goto retry_ipi;
> > }
> > - /* CPU really is offline, so we can ignore it. */
> > - if (!(rnp->expmask & mask))
> > - mask_ofl_ipi &= ~mask;
> > + /* CPU really is offline, and we need its QS to pass GP. */
> > + if (rnp->expmask & mask)
> > + mask_ofl_test |= mask;
> > raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> > }
> > /* Report quiescent states for those that went offline. */
> > - mask_ofl_test |= mask_ofl_ipi;
> > if (mask_ofl_test)
> > rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> > }
> > --
> > 2.23.0
> >
On Tue, Oct 08, 2019 at 06:35:45PM +0200, Marco Elver wrote:
> On Tue, 8 Oct 2019 at 18:30, Joel Fernandes <[email protected]> wrote:
> >
> > On Tue, Oct 08, 2019 at 01:01:40PM +0800, Boqun Feng wrote:
> > > "mask_ofl_ipi" is used for iterate CPUs which IPIs are needed to send
> > > to, however in the IPI sending loop, "mask_ofl_ipi" along with another
> > > variable "mask_ofl_test" might also get modified to record which CPU's
> > > quiesent state can be reported by sync_rcu_exp_select_node_cpus(). Two
> > > variables seems to be redundant for such a propose, so this patch clean
> > > things a little by solely using "mask_ofl_test" for recording and
> > > "mask_ofl_ipi" for iteration. This would improve the readibility of the
> > > IPI sending loop in sync_rcu_exp_select_node_cpus().
> > >
> > > Signed-off-by: Boqun Feng <[email protected]>
> > > ---
> >
> > Reviewed-by: Joel Fernandes (Google) <[email protected]>
> >
> > thanks,
> >
> > - Joel
>
> Acked-by: Marco Elver <[email protected]>
>
> If this is the official patch for the fix to the KCSAN reported
> data-race, it'd be great to include the tag:
> Reported-by: [email protected]
> so the bot knows this was fixed.
I applied your Acked-by to both patches, but please let me know if you
intended something else. Either way, thank you both for finding this
and for your testing!
Thanx, Paul
> Thanks!
> -- Marco
>
> > > kernel/rcu/tree_exp.h | 13 ++++++-------
> > > 1 file changed, 6 insertions(+), 7 deletions(-)
> > >
> > > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> > > index 69c5aa64fcfd..212470018752 100644
> > > --- a/kernel/rcu/tree_exp.h
> > > +++ b/kernel/rcu/tree_exp.h
> > > @@ -387,10 +387,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > }
> > > ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0);
> > > put_cpu();
> > > - if (!ret) {
> > > - mask_ofl_ipi &= ~mask;
> > > + /* The CPU responses the IPI, and will report QS itself */
> > > + if (!ret)
> > > continue;
> > > - }
> > > +
> > > /* Failed, raced with CPU hotplug operation. */
> > > raw_spin_lock_irqsave_rcu_node(rnp, flags);
> > > if ((rnp->qsmaskinitnext & mask) &&
> > > @@ -401,13 +401,12 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
> > > schedule_timeout_uninterruptible(1);
> > > goto retry_ipi;
> > > }
> > > - /* CPU really is offline, so we can ignore it. */
> > > - if (!(rnp->expmask & mask))
> > > - mask_ofl_ipi &= ~mask;
> > > + /* CPU really is offline, and we need its QS to pass GP. */
> > > + if (rnp->expmask & mask)
> > > + mask_ofl_test |= mask;
> > > raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
> > > }
> > > /* Report quiescent states for those that went offline. */
> > > - mask_ofl_test |= mask_ofl_ipi;
> > > if (mask_ofl_test)
> > > rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
> > > }
> > > --
> > > 2.23.0
> > >