Hi Xiaoyao,
On Sun, Jan 14, 2024 at 10:31:50PM +0800, Xiaoyao Li wrote:
> Date: Sun, 14 Jan 2024 22:31:50 +0800
> From: Xiaoyao Li <[email protected]>
> Subject: Re: [PATCH v7 14/16] i386: Use CPUCacheInfo.share_level to encode
> CPUID[4]
>
> On 1/8/2024 4:27 PM, Zhao Liu wrote:
> > From: Zhao Liu <[email protected]>
> >
> > CPUID[4].EAX[bits 25:14] is used to represent the cache topology for
> > Intel CPUs.
> >
> > After cache models have topology information, we can use
> > CPUCacheInfo.share_level to decide which topology level to be encoded
> > into CPUID[4].EAX[bits 25:14].
> >
> > And since maximum_processor_id (original "num_apic_ids") is parsed
> > based on cpu topology levels, which are verified when parsing smp, it's
> > no need to check this value by "assert(num_apic_ids > 0)" again, so
> > remove this assert.
> >
> > Additionally, wrap the encoding of CPUID[4].EAX[bits 31:26] into a
> > helper to make the code cleaner.
> >
> > Signed-off-by: Zhao Liu <[email protected]>
> > Tested-by: Babu Moger <[email protected]>
> > Tested-by: Yongwei Ma <[email protected]>
> > Acked-by: Michael S. Tsirkin <[email protected]>
> > ---
> > Changes since v1:
> > * Use "enum CPUTopoLevel share_level" as the parameter in
> > max_processor_ids_for_cache().
> > * Make cache_into_passthrough case also use
> > max_processor_ids_for_cache() and max_core_ids_in_package() to
> > encode CPUID[4]. (Yanan)
> > * Rename the title of this patch (the original is "i386: Use
> > CPUCacheInfo.share_level to encode CPUID[4].EAX[bits 25:14]").
> > ---
> > target/i386/cpu.c | 70 +++++++++++++++++++++++++++++------------------
> > 1 file changed, 43 insertions(+), 27 deletions(-)
> >
> > diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> > index 81e07474acef..b23e8190dc68 100644
> > --- a/target/i386/cpu.c
> > +++ b/target/i386/cpu.c
> > @@ -235,22 +235,53 @@ static uint8_t cpuid2_cache_descriptor(CPUCacheInfo
> > *cache)
> > ((t) == UNIFIED_CACHE) ? CACHE_TYPE_UNIFIED : \
> > 0 /* Invalid value */)
> > +static uint32_t max_processor_ids_for_cache(X86CPUTopoInfo *topo_info,
> > + enum CPUTopoLevel share_level)
>
> I prefer the name to max_lp_ids_share_the_cache()
Yes, lp is more accurate.
>
> > +{
> > + uint32_t num_ids = 0;
> > +
> > + switch (share_level) {
> > + case CPU_TOPO_LEVEL_CORE:
> > + num_ids = 1 << apicid_core_offset(topo_info);
> > + break;
> > + case CPU_TOPO_LEVEL_DIE:
> > + num_ids = 1 << apicid_die_offset(topo_info);
> > + break;
> > + case CPU_TOPO_LEVEL_PACKAGE:
> > + num_ids = 1 << apicid_pkg_offset(topo_info);
> > + break;
> > + default:
> > + /*
> > + * Currently there is no use case for SMT and MODULE, so use
> > + * assert directly to facilitate debugging.
> > + */
> > + g_assert_not_reached();
> > + }
> > +
> > + return num_ids - 1;
>
> suggest to just return num_ids, and let the caller to do the -1 work.
Emm, SDM calls the whole "num_ids - 1" (CPUID.0x4.EAX[bits 14-25]) as
"maximum number of addressable IDs for logical processors sharing this
cache"...
So if this helper just names "num_ids" as max_lp_ids_share_the_cache,
I'm not sure there would be ambiguity here?
>
> > +}
> > +
> > +static uint32_t max_core_ids_in_package(X86CPUTopoInfo *topo_info)
> > +{
> > + uint32_t num_cores = 1 << (apicid_pkg_offset(topo_info) -
> > + apicid_core_offset(topo_info));
> > + return num_cores - 1;
>
> ditto.
>
> > +}
> > /* Encode cache info for CPUID[4] */
> > static void encode_cache_cpuid4(CPUCacheInfo *cache,
> > - int num_apic_ids, int num_cores,
> > + X86CPUTopoInfo *topo_info,
> > uint32_t *eax, uint32_t *ebx,
> > uint32_t *ecx, uint32_t *edx)
> > {
> > assert(cache->size == cache->line_size * cache->associativity *
> > cache->partitions * cache->sets);
> > - assert(num_apic_ids > 0);
> > *eax = CACHE_TYPE(cache->type) |
> > CACHE_LEVEL(cache->level) |
> > (cache->self_init ? CACHE_SELF_INIT_LEVEL : 0) |
> > - ((num_cores - 1) << 26) |
> > - ((num_apic_ids - 1) << 14);
> > + (max_core_ids_in_package(topo_info) << 26) |
> > + (max_processor_ids_for_cache(topo_info, cache->share_level) <<
> > 14);
>
> by the way, we can change the order of the two line. :)
Yes!
Thanks,
Zhao
>
> > assert(cache->line_size > 0);
> > assert(cache->partitions > 0);
> > @@ -6263,56 +6294,41 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t
> > index, uint32_t count,
> > int host_vcpus_per_cache = 1 + ((*eax & 0x3FFC000) >> 14);
> > if (cores_per_pkg > 1) {
> > - int addressable_cores_offset =
> > -
> > apicid_pkg_offset(&topo_info) -
> > -
> > apicid_core_offset(&topo_info);
> > -
> > *eax &= ~0xFC000000;
> > - *eax |= (1 << (addressable_cores_offset - 1)) << 26;
> > + *eax |= max_core_ids_in_package(&topo_info) << 26;
> > }
> > if (host_vcpus_per_cache > cpus_per_pkg) {
> > - int pkg_offset = apicid_pkg_offset(&topo_info);
> > -
> > *eax &= ~0x3FFC000;
> > - *eax |= (1 << (pkg_offset - 1)) << 14;
> > + *eax |=
> > + max_processor_ids_for_cache(&topo_info,
> > + CPU_TOPO_LEVEL_PACKAGE) <<
> > 14;
> > }
> > }
> > } else if (cpu->vendor_cpuid_only && IS_AMD_CPU(env)) {
> > *eax = *ebx = *ecx = *edx = 0;
> > } else {
> > *eax = 0;
> > - int addressable_cores_offset = apicid_pkg_offset(&topo_info) -
> > - apicid_core_offset(&topo_info);
> > - int core_offset, die_offset;
> > switch (count) {
> > case 0: /* L1 dcache info */
> > - core_offset = apicid_core_offset(&topo_info);
> > encode_cache_cpuid4(env->cache_info_cpuid4.l1d_cache,
> > - (1 << core_offset),
> > - (1 << addressable_cores_offset),
> > + &topo_info,
> > eax, ebx, ecx, edx);
> > break;
> > case 1: /* L1 icache info */
> > - core_offset = apicid_core_offset(&topo_info);
> > encode_cache_cpuid4(env->cache_info_cpuid4.l1i_cache,
> > - (1 << core_offset),
> > - (1 << addressable_cores_offset),
> > + &topo_info,
> > eax, ebx, ecx, edx);
> > break;
> > case 2: /* L2 cache info */
> > - core_offset = apicid_core_offset(&topo_info);
> > encode_cache_cpuid4(env->cache_info_cpuid4.l2_cache,
> > - (1 << core_offset),
> > - (1 << addressable_cores_offset),
> > + &topo_info,
> > eax, ebx, ecx, edx);
> > break;
> > case 3: /* L3 cache info */
> > - die_offset = apicid_die_offset(&topo_info);
> > if (cpu->enable_l3_cache) {
> > encode_cache_cpuid4(env->cache_info_cpuid4.l3_cache,
> > - (1 << die_offset),
> > - (1 << addressable_cores_offset),
> > + &topo_info,
> > eax, ebx, ecx, edx);
> > break;
> > }
>
