Re: [PATCH v5 3/4] arm64: topology: Support SMT control on ACPI based system

[Dietmar Eggemann <dietmar.eggemann@arm.com>]

On 06/08/2024 10:53, Yicong Yang wrote:
> From: Yicong Yang <yangyicong@hisilicon.com>
> 
> For ACPI we'll build the topology from PPTT and we cannot directly
> get the SMT number of each core. Instead using a temporary xarray
> to record the SMT number of each core when building the topology
> and we can know the largest SMT number in the system. Then we can
> enable the support of SMT control.
> 
> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
> ---
>  arch/arm64/kernel/topology.c | 24 ++++++++++++++++++++++++
>  1 file changed, 24 insertions(+)
> 
> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> index 1a2c72f3e7f8..f72e1e55b05e 100644
> --- a/arch/arm64/kernel/topology.c
> +++ b/arch/arm64/kernel/topology.c
> @@ -15,8 +15,10 @@
>  #include <linux/arch_topology.h>
>  #include <linux/cacheinfo.h>
>  #include <linux/cpufreq.h>
> +#include <linux/cpu_smt.h>
>  #include <linux/init.h>
>  #include <linux/percpu.h>
> +#include <linux/xarray.h>
>  
>  #include <asm/cpu.h>
>  #include <asm/cputype.h>
> @@ -43,11 +45,16 @@ static bool __init acpi_cpu_is_threaded(int cpu)
>   */
>  int __init parse_acpi_topology(void)
>  {
> +	int thread_num, max_smt_thread_num = 1;
> +	struct xarray core_threads;
>  	int cpu, topology_id;
> +	void *entry;
>  
>  	if (acpi_disabled)
>  		return 0;
>  
> +	xa_init(&core_threads);
> +
>  	for_each_possible_cpu(cpu) {
>  		topology_id = find_acpi_cpu_topology(cpu, 0);
>  		if (topology_id < 0)
> @@ -57,6 +64,20 @@ int __init parse_acpi_topology(void)
>  			cpu_topology[cpu].thread_id = topology_id;
>  			topology_id = find_acpi_cpu_topology(cpu, 1);
>  			cpu_topology[cpu].core_id   = topology_id;
> +
> +			entry = xa_load(&core_threads, topology_id);
> +			if (!entry) {
> +				xa_store(&core_threads, topology_id,
> +					 xa_mk_value(1), GFP_KERNEL);
> +			} else {
> +				thread_num = xa_to_value(entry);
> +				thread_num++;
> +				xa_store(&core_threads, topology_id,
> +					 xa_mk_value(thread_num), GFP_KERNEL);
> +
> +				if (thread_num > max_smt_thread_num)
> +					max_smt_thread_num = thread_num;
> +			}

So the xarray contains one element for each core_id with the information
how often the core_id occurs? I assume you have to iterate over all
possible CPUs since you don't know which logical CPUs belong to the same
core_id.

>  		} else {
>  			cpu_topology[cpu].thread_id  = -1;
>  			cpu_topology[cpu].core_id    = topology_id;
> @@ -67,6 +88,9 @@ int __init parse_acpi_topology(void)
>  		cpu_topology[cpu].package_id = topology_id;
>  	}
>  
> +	cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
> +
> +	xa_destroy(&core_threads);
>  	return 0;
>  }
>  #endif

Tested on ThunderX2:

$ cat /proc/schedstat | head -6 | tail -4 | awk '{ print $1, $2 }'
cpu0 0
domain0 00000000,00000000,00000000,00000000,00000001,00000001,00000001,00000001
                                                   ^        ^        ^        ^
domain1 00000000,00000000,00000000,00000000,ffffffff,ffffffff,ffffffff,ffffffff
domain2 ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff,ffffffff

detecting 'max_smt_thread_num = 4' correctly.