[PATCH v11 3/4] arm64: topology: Support SMT control on ACPI based system

Hanjun Guo guohanjun at huawei.com
Mon Feb 24 22:08:45 PST 2025


On 2025/2/18 22:10, Yicong Yang wrote:
> From: Yicong Yang <yangyicong at 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 heterogeneous information (from ACPI_PPTT_ACPI_IDENTICAL)
> and SMT information of the first core in its heterogeneous CPU cluster
> when building the topology. Then we can know the largest SMT number
> in the system. If a homogeneous system's using ACPI 6.2 or later,
> all the CPUs should be under the root node of PPTT. There'll be
> only one entry in the xarray and all the CPUs in the system will
> be assumed identical.
> 
> The core's SMT control provides two interface to the users [1]:
> 1) enable/disable SMT by writing on/off
> 2) enable/disable SMT by writing thread number 1/max_thread_number
> 
> If a system have more than one SMT thread number the 2) may
> not handle it well, since there're multiple thread numbers in the
> system and 2) only accept 1/max_thread_number. So issue a warning
> to notify the users if such system detected.
> 
> [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/ABI/testing/sysfs-devices-system-cpu#n542
> 
> Reviewed-by: Jonathan Cameron <Jonathan.Cameron at huawei.com>
> Signed-off-by: Yicong Yang <yangyicong at hisilicon.com>
> ---
>   arch/arm64/kernel/topology.c | 66 ++++++++++++++++++++++++++++++++++++
>   1 file changed, 66 insertions(+)
> 
> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> index 1a2c72f3e7f8..6eba1ac091ee 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>
> @@ -37,17 +39,28 @@ static bool __init acpi_cpu_is_threaded(int cpu)
>   	return !!is_threaded;
>   }
>   
> +struct cpu_smt_info {
> +	unsigned int thread_num;
> +	int core_id;
> +};
> +
>   /*
>    * Propagate the topology information of the processor_topology_node tree to the
>    * cpu_topology array.
>    */
>   int __init parse_acpi_topology(void)
>   {
> +	unsigned int max_smt_thread_num = 0;
> +	struct cpu_smt_info *entry;
> +	struct xarray hetero_cpu;
> +	unsigned long hetero_id;
>   	int cpu, topology_id;
>   
>   	if (acpi_disabled)
>   		return 0;
>   
> +	xa_init(&hetero_cpu);
> +
>   	for_each_possible_cpu(cpu) {
>   		topology_id = find_acpi_cpu_topology(cpu, 0);
>   		if (topology_id < 0)
> @@ -57,6 +70,34 @@ 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;
> +
> +			/*
> +			 * In the PPTT, CPUs below a node with the 'identical
> +			 * implementation' flag have the same number of threads.
> +			 * Count the number of threads for only one CPU (i.e.
> +			 * one core_id) among those with the same hetero_id.
> +			 * See the comment of find_acpi_cpu_topology_hetero_id()
> +			 * for more details.
> +			 *
> +			 * One entry is created for each node having:
> +			 * - the 'identical implementation' flag
> +			 * - its parent not having the flag
> +			 */
> +			hetero_id = find_acpi_cpu_topology_hetero_id(cpu);
> +			entry = xa_load(&hetero_cpu, hetero_id);
> +			if (!entry) {
> +				entry = kzalloc(sizeof(*entry), GFP_KERNEL);
> +				WARN_ON_ONCE(!entry);
> +
> +				if (entry) {
> +					entry->core_id = topology_id;
> +					entry->thread_num = 1;
> +					xa_store(&hetero_cpu, hetero_id,
> +						 entry, GFP_KERNEL);
> +				}
> +			} else if (entry->core_id == topology_id) {
> +				entry->thread_num++;
> +			}
>   		} else {
>   			cpu_topology[cpu].thread_id  = -1;
>   			cpu_topology[cpu].core_id    = topology_id;
> @@ -67,6 +108,31 @@ int __init parse_acpi_topology(void)
>   		cpu_topology[cpu].package_id = topology_id;
>   	}
>   
> +	/*
> +	 * This should be a short loop depending on the number of heterogeneous
> +	 * CPU clusters. Typically on a homogeneous system there's only one
> +	 * entry in the XArray.
> +	 */
> +	xa_for_each(&hetero_cpu, hetero_id, entry) {
> +		if (entry->thread_num != max_smt_thread_num && max_smt_thread_num)
> +			pr_warn_once("Heterogeneous SMT topology is partly supported by SMT control\n");
> +
> +		max_smt_thread_num = max(max_smt_thread_num, entry->thread_num);
> +		xa_erase(&hetero_cpu, hetero_id);
> +		kfree(entry);
> +	}
> +
> +	/*
> +	 * Notify the CPU framework of the SMT support. Initialize the
> +	 * max_smt_thread_num to 1 if no SMT support detected. A thread
> +	 * number of 1 can be handled by the framework so we don't need
> +	 * to check max_smt_thread_num to see we support SMT or not.
> +	 */
> +	if (!max_smt_thread_num)
> +		max_smt_thread_num = 1;
> +
> +	cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
> +	xa_destroy(&hetero_cpu);
>   	return 0;
>   }
>   #endif

Looks good to me,

Reviewed-by: Hanjun Guo <guohanjun at huawei.com>

Thanks
Hanjun



More information about the linux-arm-kernel mailing list