On 2024/12/20 15:53, Yicong Yang wrote:
> From: Yicong Yang <yangyic...@hisilicon.com>
>
> Currently if architectures want to support HOTPLUG_SMT they need to
> provide a topology_is_primary_thread() telling the framework which
> thread in the SMT cannot offline. However arm64 doesn't have a
> restriction on which thread in the SMT cannot offline, a simplest
> choice is that just make 1st thread as the "primary" thread. So
> just make this as the default implementation in the framework and
> let architectures like x86 that have special primary thread to
> override this function (which they've already done).
>
> There's no need to provide a stub function if !CONFIG_SMP or
> !CONFIG_HOTPLUG_SMP. In such case the testing CPU is already
> the 1st CPU in the SMT so it's always the primary thread.
>
> Signed-off-by: Yicong Yang <yangyic...@hisilicon.com>
> ---
> As questioned in v9 [1] whether this works on architectures not using
> CONFIG_GENERIC_ARCH_TOPOLOGY, hacked on LoongArch VM and this also works.
> Architectures should use this on their own situation.
> [1]
> https://lore.kernel.org/linux-arm-kernel/427bd639-33c3-47e4-9e83-68c428eb1...@arm.com/
>
> [root@localhost smt]# uname -m
> loongarch64
> [root@localhost smt]# pwd
> /sys/devices/system/cpu/smt
> [root@localhost smt]# cat ../possible
> 0-3
> [root@localhost smt]# cat ../online
> 0-3
> [root@localhost smt]# cat control
> on
> [root@localhost smt]# echo off > control
> [root@localhost smt]# cat control
> off
> [root@localhost smt]# cat ../online
> 0,2
> [root@localhost smt]# echo on > control
> [root@localhost smt]# cat control
> on
> [root@localhost smt]# cat ../online
> 0-3
Tested with below code using the topology_is_primary_thread() introduced
in this patch. Tested on an ACPI-based QEMU VM emulating SMT2.
Subject: [PATCH] LoongArch: Support HOTPLUG_SMT on ACPI-based system
Support HOTPLUG_SMT on ACPI-based system using generic
topology_is_primary_thread().
Signed-off-by: Yicong Yang <yangyic...@hisilicon.com>
---
arch/loongarch/Kconfig | 1 +
arch/loongarch/kernel/acpi.c | 26 ++++++++++++++++++++++++--
2 files changed, 25 insertions(+), 2 deletions(-)
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index dae3a9104ca6..bed1b0640b97 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -172,6 +172,7 @@ config LOONGARCH
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_TIF_NOHZ
select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP
+ select HOTPLUG_SMT if HOTPLUG_CPU
select IRQ_FORCED_THREADING
select IRQ_LOONGARCH_CPU
select LOCK_MM_AND_FIND_VMA
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 382a09a7152c..e642b0de57e7 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -15,9 +15,11 @@
#include <linux/memblock.h>
#include <linux/of_fdt.h>
#include <linux/serial_core.h>
+#include <linux/xarray.h>
#include <asm/io.h>
#include <asm/numa.h>
#include <asm/loongson.h>
+#include <linux/cpu_smt.h>
int acpi_disabled;
EXPORT_SYMBOL(acpi_disabled);
@@ -175,8 +177,12 @@ int pptt_enabled;
int __init parse_acpi_topology(void)
{
+ int thread_num, max_smt_thread_num = 1;
+ struct xarray core_threads;
int cpu, topology_id;
+ void *entry;
+ xa_init(&core_threads);
for_each_possible_cpu(cpu) {
topology_id = find_acpi_cpu_topology(cpu, 0);
if (topology_id < 0) {
@@ -184,19 +190,35 @@ int __init parse_acpi_topology(void)
return -ENOENT;
}
- if (acpi_pptt_cpu_is_thread(cpu) <= 0)
+ if (acpi_pptt_cpu_is_thread(cpu) <= 0) {
cpu_data[cpu].core = topology_id;
- else {
+ } else {
topology_id = find_acpi_cpu_topology(cpu, 1);
if (topology_id < 0)
return -ENOENT;
cpu_data[cpu].core = 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;
+ }
}
}
pptt_enabled = 1;
+ cpu_smt_set_num_threads(max_smt_thread_num, max_smt_thread_num);
+ xa_destroy(&core_threads);
return 0;
}
--
2.24.0
>
> arch/powerpc/include/asm/topology.h | 1 +
> arch/x86/include/asm/topology.h | 2 +-
> include/linux/topology.h | 22 ++++++++++++++++++++++
> 3 files changed, 24 insertions(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/include/asm/topology.h
> b/arch/powerpc/include/asm/topology.h
> index 16bacfe8c7a2..da15b5efe807 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -152,6 +152,7 @@ static inline bool topology_is_primary_thread(unsigned
> int cpu)
> {
> return cpu == cpu_first_thread_sibling(cpu);
> }
> +#define topology_is_primary_thread topology_is_primary_thread
>
> static inline bool topology_smt_thread_allowed(unsigned int cpu)
> {
> diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
> index fd41103ad342..faa0d6334ea4 100644
> --- a/arch/x86/include/asm/topology.h
> +++ b/arch/x86/include/asm/topology.h
> @@ -228,11 +228,11 @@ static inline bool topology_is_primary_thread(unsigned
> int cpu)
> {
> return cpumask_test_cpu(cpu, cpu_primary_thread_mask);
> }
> +#define topology_is_primary_thread topology_is_primary_thread
>
> #else /* CONFIG_SMP */
> static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0;
> }
> static inline int topology_max_smt_threads(void) { return 1; }
> -static inline bool topology_is_primary_thread(unsigned int cpu) { return
> true; }
> static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; }
> #endif /* !CONFIG_SMP */
>
> diff --git a/include/linux/topology.h b/include/linux/topology.h
> index 52f5850730b3..b3aba443c4eb 100644
> --- a/include/linux/topology.h
> +++ b/include/linux/topology.h
> @@ -240,6 +240,28 @@ static inline const struct cpumask *cpu_smt_mask(int cpu)
> }
> #endif
>
> +#ifndef topology_is_primary_thread
> +
> +#define topology_is_primary_thread topology_is_primary_thread
> +
> +static inline bool topology_is_primary_thread(unsigned int cpu)
> +{
> + /*
> + * On SMT hotplug the primary thread of the SMT won't be disabled.
> + * Architectures do have a special primary thread (e.g. x86) need
> + * to override this function. Otherwise just make the first thread
> + * in the SMT as the primary thread.
> + *
> + * The sibling cpumask of an offline CPU contains always the CPU
> + * itself for architectures using CONFIG_GENERIC_ARCH_TOPOLOGY.
> + * Other architectures should use this depend on their own
> + * situation.
> + */
> + return cpu == cpumask_first(topology_sibling_cpumask(cpu));
> +}
> +
> +#endif
> +
> static inline const struct cpumask *cpu_cpu_mask(int cpu)
> {
> return cpumask_of_node(cpu_to_node(cpu));
>
