[PATCH v3] topology: make core_mask include at least cluster_siblings

[Sudeep Holla]

On Tue, Mar 08, 2022 at 10:30:12AM +0000, Will Deacon wrote:
> On Fri, Mar 04, 2022 at 09:01:36AM -0800, Darren Hart wrote:
> > Ampere Altra defines CPU clusters in the ACPI PPTT. They share a Snoop
> > Control Unit, but have no shared CPU-side last level cache.
> > 
> > cpu_coregroup_mask() will return a cpumask with weight 1, while
> > cpu_clustergroup_mask() will return a cpumask with weight 2.
> > 
> > As a result, build_sched_domain() will BUG() once per CPU with:
> > 
> > BUG: arch topology borken
> > the CLS domain not a subset of the MC domain
> > 
> > The MC level cpumask is then extended to that of the CLS child, and is
> > later removed entirely as redundant. This sched domain topology is an
> > improvement over previous topologies, or those built without
> > SCHED_CLUSTER, particularly for certain latency sensitive workloads.
> > With the current scheduler model and heuristics, this is a desirable
> > default topology for Ampere Altra and Altra Max system.
> > 
> > Rather than create a custom sched domains topology structure and
> > introduce new logic in arch/arm64 to detect these systems, update the
> > core_mask so coregroup is never a subset of clustergroup, extending it
> > to cluster_siblings if necessary.
> > 
> > This has the added benefit over a custom topology of working for both
> > symmetric and asymmetric topologies. It does not address systems where
> > the cluster topology is above a populated mc topology, but these are not
> > considered today and can be addressed separately if and when they
> > appear.
> > 
> > The final sched domain topology for a 2 socket Ampere Altra system is
> > unchanged with or without CONFIG_SCHED_CLUSTER, and the BUG is avoided:
> > 
> > For CPU0:
> > 
> > CONFIG_SCHED_CLUSTER=y
> > CLS  [0-1]
> > DIE  [0-79]
> > NUMA [0-159]
> > 
> > CONFIG_SCHED_CLUSTER is not set
> > DIE  [0-79]
> > NUMA [0-159]
> > 
> > Cc: Sudeep Holla <sudeep.holla at arm.com>
> > Cc: Greg Kroah-Hartman <gregkh at linuxfoundation.org>
> > Cc: "Rafael J. Wysocki" <rafael at kernel.org>
> > Cc: Catalin Marinas <catalin.marinas at arm.com>
> > Cc: Will Deacon <will at kernel.org>
> > Cc: Peter Zijlstra <peterz at infradead.org>
> > Cc: Vincent Guittot <vincent.guittot at linaro.org>
> > Cc: Barry Song <song.bao.hua at hisilicon.com>
> > Cc: Valentin Schneider <valentin.schneider at arm.com>
> > Cc: D. Scott Phillips <scott at os.amperecomputing.com>
> > Cc: Ilkka Koskinen <ilkka at os.amperecomputing.com>
> > Cc: <stable at vger.kernel.org> # 5.16.x
> > Suggested-by: Barry Song <song.bao.hua at hisilicon.com>
> > Signed-off-by: Darren Hart <darren at os.amperecomputing.com>
> > ---
> > v1: Drop MC level if coregroup weight == 1
> > v2: New sd topo in arch/arm64/kernel/smp.c
> > v3: No new topo, extend core_mask to cluster_siblings
> > 
> >  drivers/base/arch_topology.c | 8 ++++++++
> >  1 file changed, 8 insertions(+)
> > 
> > diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
> > index 976154140f0b..a96f45db928b 100644
> > --- a/drivers/base/arch_topology.c
> > +++ b/drivers/base/arch_topology.c
> > @@ -628,6 +628,14 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
> >  			core_mask = &cpu_topology[cpu].llc_sibling;
> >  	}
> >  
> > +	/*
> > +	 * For systems with no shared cpu-side LLC but with clusters defined,
> > +	 * extend core_mask to cluster_siblings. The sched domain builder will
> > +	 * then remove MC as redundant with CLS if SCHED_CLUSTER is enabled.
> > +	 */
> > +	if (cpumask_subset(core_mask, &cpu_topology[cpu].cluster_sibling))
> > +		core_mask = &cpu_topology[cpu].cluster_sibling;
> > +
> 
> Sudeep, Vincent, are you happy with this now?
> 

It looks good to me. Since I don't have much knowledge on scheduler, I asked
Dietmar to have a look as well just in case if I am missing any other impact.
For now,

Acked-by: Sudeep Holla <sudeep.holla at arm.com>

--
Regards,
Sudeep