Re: [PATCH 04/11] powerpc/smp: Enable small core scheduling sooner

[Srikar Dronamraju <srikar@linux.vnet.ibm.com>]

* Gautham R Shenoy <ego@linux.vnet.ibm.com> [2020-07-17 11:18:21]:

> On Tue, Jul 14, 2020 at 10:06:17AM +0530, Srikar Dronamraju wrote:
> > Enable small core scheduling as soon as we detect that we are in a
> > system that supports thread group. Doing so would avoid a redundant
> > check.
> > 
> > Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
> > Cc: Michael Ellerman <michaele@au1.ibm.com>
> > Cc: Nick Piggin <npiggin@au1.ibm.com>
> > Cc: Oliver OHalloran <oliveroh@au1.ibm.com>
> > Cc: Nathan Lynch <nathanl@linux.ibm.com>
> > Cc: Michael Neuling <mikey@linux.ibm.com>
> > Cc: Anton Blanchard <anton@au1.ibm.com>
> > Cc: Gautham R Shenoy <ego@linux.vnet.ibm.com>
> > Cc: Vaidyanathan Srinivasan <svaidy@linux.ibm.com>
> > Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
> 
> I don't see a problem with this.
> 
> However, since we are now going to be maintaining a single topology
> structure, wouldn't it be better to collate all the changes being made
> to the mask_functions/flags/names of this structure within a single
> function so that it becomes easier to keep track of what all changes
> are going into the topology and why are we doing it?
> 

My intent was to move the topology updates early as soon as they are
detected. Currently the shared_cache want cannot be detected early. 
But I think its possible to detect shared_cache early with some cleanups.
And if we do, then we should be able to call this up pretty early.

> 
> > ---
> >  arch/powerpc/kernel/smp.c | 12 ++++++------
> >  1 file changed, 6 insertions(+), 6 deletions(-)
> > 
> > diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> > index 24529f6134aa..7d430fc536cc 100644
> > --- a/arch/powerpc/kernel/smp.c
> > +++ b/arch/powerpc/kernel/smp.c
> > @@ -892,6 +892,12 @@ static int init_big_cores(void)
> >  	}
> > 
> >  	has_big_cores = true;
> > +
> > +#ifdef CONFIG_SCHED_SMT
> > +	pr_info("Big cores detected. Using small core scheduling\n");
> > +	powerpc_topology[0].mask = smallcore_smt_mask;
> > +#endif
> > +
> >  	return 0;
> >  }
> > 
> > @@ -1383,12 +1389,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
> > 
> >  	dump_numa_cpu_topology();
> > 
> > -#ifdef CONFIG_SCHED_SMT
> > -	if (has_big_cores) {
> > -		pr_info("Big cores detected but using small core scheduling\n");
> > -		powerpc_topology[0].mask = smallcore_smt_mask;
> > -	}
> > -#endif
> >  	set_sched_topology(powerpc_topology);
> >  }
> > 
> > -- 
> > 2.17.1
> > 

-- 
Thanks and Regards
Srikar Dronamraju