Looked closely at this one, was wondering about using TOPO_ROOT_DOMAIN
when the original looked at the leaf of TYPE_CORE. But I think you
probably have it right, and I checked both a newer and an older
system, and the UV info line that prints "apic_pns" gets the same
value as before.
Reviewed-by: Steve Wahl <steve.wahl@xxxxxxx>
On Fri, Jul 28, 2023 at 02:13:30PM +0200, Thomas Gleixner wrote:
> The package shift has been already evaluated by the early CPU init.
>
> Put the mindless copy right next to the original leaf 0xb parser.
>
> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: Steve Wahl <steve.wahl@xxxxxxx>
> Cc: Mike Travis <mike.travis@xxxxxxx>
> Cc: Dimitri Sivanich <dimitri.sivanich@xxxxxxx>
> Cc: Russ Anderson <russ.anderson@xxxxxxx>
> ---
> arch/x86/include/asm/topology.h | 5 +++
> arch/x86/kernel/apic/x2apic_uv_x.c | 52 ++++++-------------------------------
> 2 files changed, 14 insertions(+), 43 deletions(-)
>
> --- a/arch/x86/include/asm/topology.h
> +++ b/arch/x86/include/asm/topology.h
> @@ -126,6 +126,11 @@ static inline unsigned int topology_get_
> return x86_topo_system.dom_size[dom];
> }
>
> +static inline unsigned int topology_get_domain_shift(enum x86_topology_domains dom)
> +{
> + return dom == TOPO_SMT_DOMAIN ? 0 : x86_topo_system.dom_shifts[dom - 1];
> +}
> +
> extern const struct cpumask *cpu_coregroup_mask(int cpu);
> extern const struct cpumask *cpu_clustergroup_mask(int cpu);
>
> --- a/arch/x86/kernel/apic/x2apic_uv_x.c
> +++ b/arch/x86/kernel/apic/x2apic_uv_x.c
> @@ -241,54 +241,20 @@ static void __init uv_tsc_check_sync(voi
> is_uv(UV3) ? sname.s3.field : \
> undef)
>
> -/* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
> -
> -#define SMT_LEVEL 0 /* Leaf 0xb SMT level */
> -#define INVALID_TYPE 0 /* Leaf 0xb sub-leaf types */
> -#define SMT_TYPE 1
> -#define CORE_TYPE 2
> -#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff)
> -#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f)
> -
> -static void set_x2apic_bits(void)
> -{
> - unsigned int eax, ebx, ecx, edx, sub_index;
> - unsigned int sid_shift;
> -
> - cpuid(0, &eax, &ebx, &ecx, &edx);
> - if (eax < 0xb) {
> - pr_info("UV: CPU does not have CPUID.11\n");
> - return;
> - }
> -
> - cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
> - if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) {
> - pr_info("UV: CPUID.11 not implemented\n");
> - return;
> - }
> -
> - sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
> - sub_index = 1;
> - do {
> - cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
> - if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
> - sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
> - break;
> - }
> - sub_index++;
> - } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
> -
> - uv_cpuid.apicid_shift = 0;
> - uv_cpuid.apicid_mask = (~(-1 << sid_shift));
> - uv_cpuid.socketid_shift = sid_shift;
> -}
> -
> static void __init early_get_apic_socketid_shift(void)
> {
> + unsigned int sid_shift = topology_get_domain_shift(TOPO_ROOT_DOMAIN);
> +
> if (is_uv2_hub() || is_uv3_hub())
> uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
>
> - set_x2apic_bits();
> + if (sid_shift) {
> + uv_cpuid.apicid_shift = 0;
> + uv_cpuid.apicid_mask = (~(-1 << sid_shift));
> + uv_cpuid.socketid_shift = sid_shift;
> + } else {
> + pr_info("UV: CPU does not have valid CPUID.11\n");
> + }
>
> pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
> pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
>
--
Steve Wahl, Hewlett Packard Enterprise
