Re: [PATCH 06/11] powerpc/smp: Generalize 2nd sched domain

[Gautham R Shenoy <ego@linux.vnet.ibm.com>]

On Tue, Jul 14, 2020 at 10:06:19AM +0530, Srikar Dronamraju wrote:
> Currently "CACHE" domain happens to be the 2nd sched domain as per
> powerpc_topology. This domain will collapse if cpumask of l2-cache is
> same as SMT domain. However we could generalize this domain such that it
> could mean either be a "CACHE" domain or a "BIGCORE" domain.
> 
> While setting up the "CACHE" domain, check if shared_cache is already
> set.
> 
> 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>
> ---
>  arch/powerpc/kernel/smp.c | 48 +++++++++++++++++++++++++++------------
>  1 file changed, 34 insertions(+), 14 deletions(-)
> 
> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> index 875f57e41355..f8faf75135af 100644
> --- a/arch/powerpc/kernel/smp.c
> +++ b/arch/powerpc/kernel/smp.c
> @@ -85,6 +85,14 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
>  EXPORT_PER_CPU_SYMBOL(cpu_core_map);
>  EXPORT_SYMBOL_GPL(has_big_cores);
> 
> +enum {
> +#ifdef CONFIG_SCHED_SMT
> +	smt_idx,
> +#endif
> +	bigcore_idx,
> +	die_idx,
> +};
> +
>  #define MAX_THREAD_LIST_SIZE	8
>  #define THREAD_GROUP_SHARE_L1   1
>  struct thread_groups {
> @@ -851,13 +859,7 @@ static int powerpc_shared_cache_flags(void)
>   */
>  static const struct cpumask *shared_cache_mask(int cpu)
>  {
> -	if (shared_caches)
> -		return cpu_l2_cache_mask(cpu);
> -
> -	if (has_big_cores)
> -		return cpu_smallcore_mask(cpu);
> -
> -	return cpu_smt_mask(cpu);
> +	return per_cpu(cpu_l2_cache_map, cpu);
>  }
> 
>  #ifdef CONFIG_SCHED_SMT
> @@ -867,11 +869,16 @@ static const struct cpumask *smallcore_smt_mask(int cpu)
>  }
>  #endif
> 
> +static const struct cpumask *cpu_bigcore_mask(int cpu)
> +{
> +	return cpu_core_mask(cpu);

It should be cpu_smt_mask() if we want the redundant big-core to be
degenerated in favour of the SMT level on P8, no? Because
cpu_core_mask refers to all the CPUs that are in the same chip.


> +}
> +
>  static struct sched_domain_topology_level powerpc_topology[] = {
>  #ifdef CONFIG_SCHED_SMT
>  	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
>  #endif
> -	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
> +	{ cpu_bigcore_mask, SD_INIT_NAME(BIGCORE) },
>  	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
>  	{ NULL, },
>  };
> @@ -895,7 +902,7 @@ static int init_big_cores(void)
> 
>  #ifdef CONFIG_SCHED_SMT
>  	pr_info("Big cores detected. Using small core scheduling\n");
> -	powerpc_topology[0].mask = smallcore_smt_mask;
> +	powerpc_topology[smt_idx].mask = smallcore_smt_mask;
>  #endif
> 
>  	return 0;
> @@ -1319,7 +1326,6 @@ static void add_cpu_to_masks(int cpu)
>  void start_secondary(void *unused)
>  {
>  	unsigned int cpu = smp_processor_id();
> -	struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
> 
>  	mmgrab(&init_mm);
>  	current->active_mm = &init_mm;
> @@ -1345,14 +1351,20 @@ void start_secondary(void *unused)
>  	/* Update topology CPU masks */
>  	add_cpu_to_masks(cpu);
> 
> -	if (has_big_cores)
> -		sibling_mask = cpu_smallcore_mask;
>  	/*
>  	 * Check for any shared caches. Note that this must be done on a
>  	 * per-core basis because one core in the pair might be disabled.
>  	 */
> -	if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu)))
> -		shared_caches = true;
> +	if (!shared_caches) {
> +		struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
> +		struct cpumask *mask = cpu_l2_cache_mask(cpu);
> +
> +		if (has_big_cores)
> +			sibling_mask = cpu_smallcore_mask;
> +
> +		if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu)))
> +			shared_caches = true;

Shouldn't we use cpumask_subset() here ?

  			
> +	}
> 
>  	set_numa_node(numa_cpu_lookup_table[cpu]);
>  	set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
> @@ -1390,6 +1402,14 @@ void __init smp_cpus_done(unsigned int max_cpus)
>  		smp_ops->bringup_done();
> 
>  	dump_numa_cpu_topology();
> +	if (shared_caches) {
> +		pr_info("Using shared cache scheduler topology\n");
> +		powerpc_topology[bigcore_idx].mask = shared_cache_mask;
> +#ifdef CONFIG_SCHED_DEBUG
> +		powerpc_topology[bigcore_idx].name = "CACHE";
> +#endif
> +		powerpc_topology[bigcore_idx].sd_flags = powerpc_shared_cache_flags;
> +	}


I would much rather that we have all the topology-fixups done in one
function.

fixup_topology(void) {
     if (has_big_core)
        powerpc_topology[smt_idx].mask = smallcore_smt_mask;

    if (shared_caches) {
       const char *name = "CACHE";
       powerpc_topology[bigcore_idx].mask = shared_cache_mask;
       strlcpy(powerpc_topology[bigcore_idx].name, name,
       				strlen(name));
       powerpc_topology[bigcore_idx].sd_flags = powerpc_shared_cache_flags;
    }

    /* Any other changes to the topology structure here */

And also as an optimization, get rid of degenerate structures here
itself so that we don't pay additional penalty while building the
sched-domains each time.

}

> 
>  	set_sched_topology(powerpc_topology);
>  }
> -- 
> 2.17.1
>