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 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
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
---
arch/arm64/kernel/topology.c | 57 ++++++++++++++++++++++++++++++++++++
1 file changed, 57 insertions(+)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 1a2c72f3e7f8..47f838d6e823 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 {
+ 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)
{
+ 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 +70,32 @@ 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 = (struct cpu_smt_info *)xa_load(&hetero_cpu, hetero_id);
+ if (!entry) {
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ WARN_ON(!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 +106,24 @@ 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");
+
+ if (entry->thread_num > max_smt_thread_num)
+ max_smt_thread_num = entry->thread_num;
+
+ xa_erase(&hetero_cpu, hetero_id);
+ kfree(entry);
+ }
+
+ cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
+ xa_destroy(&hetero_cpu);
return 0;
}
#endif
--
2.24.0
On 10/30/24 13:54, 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 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
> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
> ---
> arch/arm64/kernel/topology.c | 57 ++++++++++++++++++++++++++++++++++++
> 1 file changed, 57 insertions(+)
>
> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> index 1a2c72f3e7f8..47f838d6e823 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 {
> + 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)
> {
> + 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 +70,32 @@ 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 = (struct cpu_smt_info *)xa_load(&hetero_cpu, hetero_id);
> + if (!entry) {
> + entry = kzalloc(sizeof(*entry), GFP_KERNEL);
> + WARN_ON(!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 +106,24 @@ 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");
> +
> + if (entry->thread_num > max_smt_thread_num)
> + max_smt_thread_num = entry->thread_num;
> +
> + xa_erase(&hetero_cpu, hetero_id);
> + kfree(entry);
> + }
I think you need to check that max_smt_thread_num !=0,
like in the DT path. Otherwise on a platform with no SMT,
max_smt_thread_num = 0 and I hit:
kernel/cpu::cpu_smt_set_num_threads()
WARN_ON(!num_threads || (num_threads > max_threads));
->
if (max_smt_thread_num)
cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
> +
> + cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
> + xa_destroy(&hetero_cpu);
> return 0;
> }
> #endif
On 2024/11/8 1:20, Pierre Gondois wrote:
>
>
> On 10/30/24 13:54, 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 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
>> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
>> ---
>> arch/arm64/kernel/topology.c | 57 ++++++++++++++++++++++++++++++++++++
>> 1 file changed, 57 insertions(+)
>>
[...]
>> @@ -67,6 +106,24 @@ 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");
>> +
>> + if (entry->thread_num > max_smt_thread_num)
>> + max_smt_thread_num = entry->thread_num;
>> +
>> + xa_erase(&hetero_cpu, hetero_id);
>> + kfree(entry);
>> + }
>
> I think you need to check that max_smt_thread_num !=0,
> like in the DT path. Otherwise on a platform with no SMT,
> max_smt_thread_num = 0 and I hit:
>
> kernel/cpu::cpu_smt_set_num_threads()
> WARN_ON(!num_threads || (num_threads > max_threads));
>
>
> ->
> if (max_smt_thread_num)
> cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
>
sorry for this silly mistake. yes we should do the same like in the DT path.
I'll get this fixed. thanks for testing.
>> +
>> + cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
>> + xa_destroy(&hetero_cpu);
>> return 0;
>> }
>> #endif
>
> .
© 2016 - 2024 Red Hat, Inc.