Because nmsk and irqmsk are stable, extra atomicity is not required.

Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 lib/group_cpus.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index ee272c4cefcc..8eb18c6bbf3b 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -24,8 +24,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
 		if (cpu >= nr_cpu_ids)
 			return;
 
-		cpumask_clear_cpu(cpu, nmsk);
-		cpumask_set_cpu(cpu, irqmsk);
+		__cpumask_clear_cpu(cpu, nmsk);
+		__cpumask_set_cpu(cpu, irqmsk);
 		cpus_per_grp--;
 
 		/* If the cpu has siblings, use them first */
@@ -34,9 +34,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
 			sibl = cpumask_next(sibl, siblmsk);
 			if (sibl >= nr_cpu_ids)
 				break;
-			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
-				continue;
-			cpumask_set_cpu(sibl, irqmsk);
+			__cpumask_clear_cpu(sibl, nmsk);
+			__cpumask_set_cpu(sibl, irqmsk);
 			cpus_per_grp--;
 		}
 	}
-- 
2.40.1

On Thu, Dec 07, 2023 at 12:38:56PM -0800, Yury Norov wrote:
> Because nmsk and irqmsk are stable, extra atomicity is not required.
> 
> Signed-off-by: Yury Norov <yury.norov@gmail.com>
> ---
>  lib/group_cpus.c | 9 ++++-----
>  1 file changed, 4 insertions(+), 5 deletions(-)
> 
> diff --git a/lib/group_cpus.c b/lib/group_cpus.c
> index ee272c4cefcc..8eb18c6bbf3b 100644
> --- a/lib/group_cpus.c
> +++ b/lib/group_cpus.c
> @@ -24,8 +24,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
>  		if (cpu >= nr_cpu_ids)
>  			return;
>  
> -		cpumask_clear_cpu(cpu, nmsk);
> -		cpumask_set_cpu(cpu, irqmsk);
> +		__cpumask_clear_cpu(cpu, nmsk);
> +		__cpumask_set_cpu(cpu, irqmsk);
>  		cpus_per_grp--;
>  
>  		/* If the cpu has siblings, use them first */
> @@ -34,9 +34,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
>  			sibl = cpumask_next(sibl, siblmsk);
>  			if (sibl >= nr_cpu_ids)
>  				break;
> -			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
> -				continue;
> -			cpumask_set_cpu(sibl, irqmsk);
> +			__cpumask_clear_cpu(sibl, nmsk);
> +			__cpumask_set_cpu(sibl, irqmsk);
>  			cpus_per_grp--;

Here the change isn't simply to remove atomicity, and the test
part of cpumask_test_and_clear_cpu() is removed, so logic is changed,
I feel the correct change should be:

	if (cpumask_test_cpu(sibl, nmsk)) {
		__cpumask_clear_cpu(sibl, nmsk);
		__cpumask_set_cpu(sibl, irqmsk);
  		cpus_per_grp--;
	}



Thanks,
Ming

On Fri, Dec 08, 2023 at 09:31:27AM +0800, Ming Lei wrote:
> On Thu, Dec 07, 2023 at 12:38:56PM -0800, Yury Norov wrote:
> > Because nmsk and irqmsk are stable, extra atomicity is not required.
> > 
> > Signed-off-by: Yury Norov <yury.norov@gmail.com>
> > ---
> >  lib/group_cpus.c | 9 ++++-----
> >  1 file changed, 4 insertions(+), 5 deletions(-)
> > 
> > diff --git a/lib/group_cpus.c b/lib/group_cpus.c
> > index ee272c4cefcc..8eb18c6bbf3b 100644
> > --- a/lib/group_cpus.c
> > +++ b/lib/group_cpus.c
> > @@ -24,8 +24,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
> >  		if (cpu >= nr_cpu_ids)
> >  			return;
> >  
> > -		cpumask_clear_cpu(cpu, nmsk);
> > -		cpumask_set_cpu(cpu, irqmsk);
> > +		__cpumask_clear_cpu(cpu, nmsk);
> > +		__cpumask_set_cpu(cpu, irqmsk);
> >  		cpus_per_grp--;
> >  
> >  		/* If the cpu has siblings, use them first */
> > @@ -34,9 +34,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
> >  			sibl = cpumask_next(sibl, siblmsk);
> >  			if (sibl >= nr_cpu_ids)
> >  				break;
> > -			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
> > -				continue;
> > -			cpumask_set_cpu(sibl, irqmsk);
> > +			__cpumask_clear_cpu(sibl, nmsk);
> > +			__cpumask_set_cpu(sibl, irqmsk);
> >  			cpus_per_grp--;
> 
> Here the change isn't simply to remove atomicity, and the test
> part of cpumask_test_and_clear_cpu() is removed, so logic is changed,
> I feel the correct change should be:
> 
> 	if (cpumask_test_cpu(sibl, nmsk)) {
> 		__cpumask_clear_cpu(sibl, nmsk);
> 		__cpumask_set_cpu(sibl, irqmsk);
>   		cpus_per_grp--;
> 	}

Ohh. My mistake is that I put this patch prior to the #3, so people
bisecting the kernel may hit this problem... 

You're right here, but check the following patch: it switches the
for() loop to for_each_cpu_and_from(sibl, siblmsk, nmsk), and it means
that inside the loop sibl indexes set bits in both siblmsk and nmsk.

Now, because both masks are stable when the grp_spread_init_one() is
called, there's no chance to get nmks.sibl cleared suddenly, and it
means we can just drop the check.

Does this makes sense to you?

I can send v3 with a proper order of patches, if needed.

Thanks,
Yury

On Thu, Dec 07, 2023 at 06:49:20PM -0800, Yury Norov wrote:
> On Fri, Dec 08, 2023 at 09:31:27AM +0800, Ming Lei wrote:
> > On Thu, Dec 07, 2023 at 12:38:56PM -0800, Yury Norov wrote:
> > > Because nmsk and irqmsk are stable, extra atomicity is not required.
> > > 
> > > Signed-off-by: Yury Norov <yury.norov@gmail.com>
> > > ---
> > >  lib/group_cpus.c | 9 ++++-----
> > >  1 file changed, 4 insertions(+), 5 deletions(-)
> > > 
> > > diff --git a/lib/group_cpus.c b/lib/group_cpus.c
> > > index ee272c4cefcc..8eb18c6bbf3b 100644
> > > --- a/lib/group_cpus.c
> > > +++ b/lib/group_cpus.c
> > > @@ -24,8 +24,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
> > >  		if (cpu >= nr_cpu_ids)
> > >  			return;
> > >  
> > > -		cpumask_clear_cpu(cpu, nmsk);
> > > -		cpumask_set_cpu(cpu, irqmsk);
> > > +		__cpumask_clear_cpu(cpu, nmsk);
> > > +		__cpumask_set_cpu(cpu, irqmsk);
> > >  		cpus_per_grp--;
> > >  
> > >  		/* If the cpu has siblings, use them first */
> > > @@ -34,9 +34,8 @@ static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
> > >  			sibl = cpumask_next(sibl, siblmsk);
> > >  			if (sibl >= nr_cpu_ids)
> > >  				break;
> > > -			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
> > > -				continue;
> > > -			cpumask_set_cpu(sibl, irqmsk);
> > > +			__cpumask_clear_cpu(sibl, nmsk);
> > > +			__cpumask_set_cpu(sibl, irqmsk);
> > >  			cpus_per_grp--;
> > 
> > Here the change isn't simply to remove atomicity, and the test
> > part of cpumask_test_and_clear_cpu() is removed, so logic is changed,
> > I feel the correct change should be:
> > 
> > 	if (cpumask_test_cpu(sibl, nmsk)) {
> > 		__cpumask_clear_cpu(sibl, nmsk);
> > 		__cpumask_set_cpu(sibl, irqmsk);
> >   		cpus_per_grp--;
> > 	}
> 
> Ohh. My mistake is that I put this patch prior to the #3, so people
> bisecting the kernel may hit this problem... 
> 
> You're right here, but check the following patch: it switches the
> for() loop to for_each_cpu_and_from(sibl, siblmsk, nmsk), and it means
> that inside the loop sibl indexes set bits in both siblmsk and nmsk.
> 
> Now, because both masks are stable when the grp_spread_init_one() is
> called, there's no chance to get nmks.sibl cleared suddenly, and it
> means we can just drop the check.
> 
> Does this makes sense to you?
> 
> I can send v3 with a proper order of patches, if needed.

v3 is correct, and I'd suggest to either fix v2 or re-order v3,
otherwise both patch 2 and 3 are not easy to follow.


Thanks,
Ming