[PATCH 07/11] Powerpc/numa: Detect support for coregroup

[Gautham R Shenoy]

On Tue, Jul 14, 2020 at 10:06:20AM +0530, Srikar Dronamraju wrote:
> Add support for grouping cores based on the device-tree classification.
> - The last domain in the associativity domains always refers to the
> core.
> - If primary reference domain happens to be the penultimate domain in
> the associativity domains device-tree property, then there are no
> coregroups. However if its not a penultimate domain, then there are
> coregroups. There can be more than one coregroup. For now we would be
> interested in the last or the smallest coregroups.
> 
> Cc: linuxppc-dev <linuxppc-dev at lists.ozlabs.org>
> Cc: Michael Ellerman <michaele at au1.ibm.com>
> Cc: Nick Piggin <npiggin at au1.ibm.com>
> Cc: Oliver OHalloran <oliveroh at au1.ibm.com>
> Cc: Nathan Lynch <nathanl at linux.ibm.com>
> Cc: Michael Neuling <mikey at linux.ibm.com>
> Cc: Anton Blanchard <anton at au1.ibm.com>
> Cc: Gautham R Shenoy <ego at linux.vnet.ibm.com>
> Cc: Vaidyanathan Srinivasan <svaidy at linux.ibm.com>
> Signed-off-by: Srikar Dronamraju <srikar at linux.vnet.ibm.com>

This looks good to me from the discovery of the core-group point of
view.

Reviewed-by: Gautham R. Shenoy <ego at linux.vnet.ibm.com>

> ---
>  arch/powerpc/include/asm/smp.h |  1 +
>  arch/powerpc/kernel/smp.c      |  1 +
>  arch/powerpc/mm/numa.c         | 34 +++++++++++++++++++++-------------
>  3 files changed, 23 insertions(+), 13 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
> index 49a25e2400f2..5bdc17a7049f 100644
> --- a/arch/powerpc/include/asm/smp.h
> +++ b/arch/powerpc/include/asm/smp.h
> @@ -28,6 +28,7 @@
>  extern int boot_cpuid;
>  extern int spinning_secondaries;
>  extern u32 *cpu_to_phys_id;
> +extern bool coregroup_enabled;
> 
>  extern void cpu_die(void);
>  extern int cpu_to_chip_id(int cpu);
> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> index f8faf75135af..96e47450d9b3 100644
> --- a/arch/powerpc/kernel/smp.c
> +++ b/arch/powerpc/kernel/smp.c
> @@ -74,6 +74,7 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 };
> 
>  struct task_struct *secondary_current;
>  bool has_big_cores;
> +bool coregroup_enabled;
> 
>  DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
>  DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index fc7b0505bdd8..a43eab455be4 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -887,7 +887,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
>  static void __init find_possible_nodes(void)
>  {
>  	struct device_node *rtas;
> -	u32 numnodes, i;
> +	const __be32 *domains;
> +	int prop_length, max_nodes;
> +	u32 i;
> 
>  	if (!numa_enabled)
>  		return;
> @@ -896,25 +898,31 @@ static void __init find_possible_nodes(void)
>  	if (!rtas)
>  		return;
> 
> -	if (of_property_read_u32_index(rtas, "ibm,current-associativity-domains",
> -				min_common_depth, &numnodes)) {
> -		/*
> -		 * ibm,current-associativity-domains is a fairly recent
> -		 * property. If it doesn't exist, then fallback on
> -		 * ibm,max-associativity-domains. Current denotes what the
> -		 * platform can support compared to max which denotes what the
> -		 * Hypervisor can support.
> -		 */
> -		if (of_property_read_u32_index(rtas, "ibm,max-associativity-domains",
> -				min_common_depth, &numnodes))
> +	/*
> +	 * ibm,current-associativity-domains is a fairly recent property. If
> +	 * it doesn't exist, then fallback on ibm,max-associativity-domains.
> +	 * Current denotes what the platform can support compared to max
> +	 * which denotes what the Hypervisor can support.
> +	 */
> +	domains = of_get_property(rtas, "ibm,current-associativity-domains",
> +					&prop_length);
> +	if (!domains) {
> +		domains = of_get_property(rtas, "ibm,max-associativity-domains",
> +					&prop_length);
> +		if (!domains)
>  			goto out;
>  	}
> 
> -	for (i = 0; i < numnodes; i++) {
> +	max_nodes = of_read_number(&domains[min_common_depth], 1);
> +	for (i = 0; i < max_nodes; i++) {
>  		if (!node_possible(i))
>  			node_set(i, node_possible_map);
>  	}
> 
> +	prop_length /= sizeof(int);
> +	if (prop_length > min_common_depth + 2)
> +		coregroup_enabled = 1;
> +
>  out:
>  	of_node_put(rtas);
>  }
> -- 
> 2.17.1
>