Re: [PATCH v10 2/5] i386: Populate AMD Processor Cache Information for cpuid 0x8000001D

From: "Duran, Leo" <leo.duran@amd.com>
To: "Moger, Babu" <Babu.Moger@amd.com>,
	"mst@redhat.com" <mst@redhat.com>,
	"marcel.apfelbaum@gmail.com" <marcel.apfelbaum@gmail.com>,
	"pbonzini@redhat.com" <pbonzini@redhat.com>,
	"rth@twiddle.net" <rth@twiddle.net>,
	"ehabkost@redhat.com" <ehabkost@redhat.com>,
	"mtosatti@redhat.com" <mtosatti@redhat.com>
Cc: "geoff@hostfission.com" <geoff@hostfission.com>,
	"kash@tripleback.net" <kash@tripleback.net>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>
Subject: Re: [PATCH v10 2/5] i386: Populate AMD Processor Cache Information for cpuid 0x8000001D
Date: Tue, 22 May 2018 01:32:20 +0000	[thread overview]
Message-ID: <CY4PR12MB181551D174221BF3CC5F209AF9940@CY4PR12MB1815.namprd12.prod.outlook.com> (raw)
In-Reply-To: <1526949675-106737-3-git-send-email-babu.moger@amd.com>

Babu,

If num_sharing_l3_cache() uses MAX_NODES_EPYC, then that function It’s EPYC specific.

An alternative would be to use a data member (e.g., max_nodes_per_socket)) that get initialized (via another helper function) to MAX_NODES_EPYC.

Basically, ideally the functions that return CPUID information do *not* use EPYC-specific macros, like MAX_NODES_EPYC.

Leo.

> -----Original Message-----
> From: Moger, Babu
> Sent: Monday, May 21, 2018 7:41 PM
> To: mst@redhat.com; marcel.apfelbaum@gmail.com; pbonzini@redhat.com;
> rth@twiddle.net; ehabkost@redhat.com; mtosatti@redhat.com
> Cc: qemu-devel@nongnu.org; kvm@vger.kernel.org; Moger, Babu
> <Babu.Moger@amd.com>; kash@tripleback.net; geoff@hostfission.com
> Subject: [PATCH v10 2/5] i386: Populate AMD Processor Cache Information
> for cpuid 0x8000001D
> 
> Add information for cpuid 0x8000001D leaf. Populate cache topology
> information for different cache types(Data Cache, Instruction Cache, L2 and
> L3) supported by 0x8000001D leaf. Please refer Processor Programming
> Reference (PPR) for AMD Family 17h Model for more details.
> 
> Signed-off-by: Babu Moger <babu.moger@amd.com>
> ---
>  target/i386/cpu.c | 103
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  target/i386/kvm.c |  29 +++++++++++++--
>  2 files changed, 129 insertions(+), 3 deletions(-)
> 
> diff --git a/target/i386/cpu.c b/target/i386/cpu.c index d9773b6..1dd060a
> 100644
> --- a/target/i386/cpu.c
> +++ b/target/i386/cpu.c
> @@ -336,6 +336,85 @@ static void
> encode_cache_cpuid80000006(CPUCacheInfo *l2,
>      }
>  }
> 
> +/* Definitions used for building CPUID Leaf 0x8000001D and 0x8000001E
> +*/
> +/* Please refer AMD64 Architecture Programmer’s Manual Volume 3 */
> +#define MAX_CCX 2 #define MAX_CORES_IN_CCX 4 #define
> MAX_NODES_EPYC 4
> +#define MAX_CORES_IN_NODE 8
> +
> +/* Number of logical processors sharing L3 cache */
> +#define NUM_SHARING_CACHE(threads, num_sharing)   ((threads > 1) ? \
> +                         (((num_sharing - 1) * threads) + 1)  : \
> +                         (num_sharing - 1))
> +/*
> + * L3 Cache is shared between all the cores in a core complex.
> + * Maximum cores that can share L3 is 4.
> + */
> +static int num_sharing_l3_cache(int nr_cores) {
> +    int i, nodes = 1;
> +
> +    /* Check if we can fit all the cores in one CCX */
> +    if (nr_cores <= MAX_CORES_IN_CCX) {
> +        return nr_cores;
> +    }
> +    /*
> +     * Figure out the number of nodes(or dies) required to build
> +     * this config. Max cores in a node is 8
> +     */
> +    for (i = nodes; i <= MAX_NODES_EPYC; i++) {
> +        if (nr_cores <= (i * MAX_CORES_IN_NODE)) {
> +            nodes = i;
> +            break;
> +        }
> +        /* We support nodes 1, 2, 4 */
> +        if (i == 3) {
> +            continue;
> +        }
> +    }
> +    /* Spread the cores accros all the CCXs and return max cores in a ccx */
> +    return (nr_cores / (nodes * MAX_CCX)) +
> +            ((nr_cores % (nodes * MAX_CCX)) ? 1 : 0); }
> +
> +/* Encode cache info for CPUID[8000001D] */ static void
> +encode_cache_cpuid8000001d(CPUCacheInfo *cache, CPUState *cs,
> +                                uint32_t *eax, uint32_t *ebx,
> +                                uint32_t *ecx, uint32_t *edx) {
> +    uint32_t num_share_l3;
> +    assert(cache->size == cache->line_size * cache->associativity *
> +                          cache->partitions * cache->sets);
> +
> +    *eax = CACHE_TYPE(cache->type) | CACHE_LEVEL(cache->level) |
> +               (cache->self_init ? CACHE_SELF_INIT_LEVEL : 0);
> +
> +    /* L3 is shared among multiple cores */
> +    if (cache->level == 3) {
> +        num_share_l3 = num_sharing_l3_cache(cs->nr_cores);
> +        *eax |= (NUM_SHARING_CACHE(cs->nr_threads, num_share_l3) <<
> 14);
> +    } else {
> +        *eax |= ((cs->nr_threads - 1) << 14);
> +    }
> +
> +    assert(cache->line_size > 0);
> +    assert(cache->partitions > 0);
> +    assert(cache->associativity > 0);
> +    /* We don't implement fully-associative caches */
> +    assert(cache->associativity < cache->sets);
> +    *ebx = (cache->line_size - 1) |
> +           ((cache->partitions - 1) << 12) |
> +           ((cache->associativity - 1) << 22);
> +
> +    assert(cache->sets > 0);
> +    *ecx = cache->sets - 1;
> +
> +    *edx = (cache->no_invd_sharing ? CACHE_NO_INVD_SHARING : 0) |
> +           (cache->inclusive ? CACHE_INCLUSIVE : 0) |
> +           (cache->complex_indexing ? CACHE_COMPLEX_IDX : 0); }
> +
>  /*
>   * Definitions of the hardcoded cache entries we expose:
>   * These are legacy cache values. If there is a need to change any @@ -
> 4005,6 +4084,30 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index,
> uint32_t count,
>              *edx = 0;
>          }
>          break;
> +    case 0x8000001D:
> +        *eax = 0;
> +        switch (count) {
> +        case 0: /* L1 dcache info */
> +            encode_cache_cpuid8000001d(env->cache_info_amd.l1d_cache, cs,
> +                                       eax, ebx, ecx, edx);
> +            break;
> +        case 1: /* L1 icache info */
> +            encode_cache_cpuid8000001d(env->cache_info_amd.l1i_cache, cs,
> +                                       eax, ebx, ecx, edx);
> +            break;
> +        case 2: /* L2 cache info */
> +            encode_cache_cpuid8000001d(env->cache_info_amd.l2_cache, cs,
> +                                       eax, ebx, ecx, edx);
> +            break;
> +        case 3: /* L3 cache info */
> +            encode_cache_cpuid8000001d(env->cache_info_amd.l3_cache, cs,
> +                                       eax, ebx, ecx, edx);
> +            break;
> +        default: /* end of info */
> +            *eax = *ebx = *ecx = *edx = 0;
> +            break;
> +        }
> +        break;
>      case 0xC0000000:
>          *eax = env->cpuid_xlevel2;
>          *ebx = 0;
> diff --git a/target/i386/kvm.c b/target/i386/kvm.c index d6666a4..a8bf7eb
> 100644
> --- a/target/i386/kvm.c
> +++ b/target/i386/kvm.c
> @@ -979,9 +979,32 @@ int kvm_arch_init_vcpu(CPUState *cs)
>          }
>          c = &cpuid_data.entries[cpuid_i++];
> 
> -        c->function = i;
> -        c->flags = 0;
> -        cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
> +        switch (i) {
> +        case 0x8000001d:
> +            /* Query for all AMD cache information leaves */
> +            for (j = 0; ; j++) {
> +                c->function = i;
> +                c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
> +                c->index = j;
> +                cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx,
> + &c->edx);
> +
> +                if (c->eax == 0) {
> +                    break;
> +                }
> +                if (cpuid_i == KVM_MAX_CPUID_ENTRIES) {
> +                    fprintf(stderr, "cpuid_data is full, no space for "
> +                            "cpuid(eax:0x%x,ecx:0x%x)\n", i, j);
> +                    abort();
> +                }
> +                c = &cpuid_data.entries[cpuid_i++];
> +            }
> +            break;
> +        default:
> +            c->function = i;
> +            c->flags = 0;
> +            cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx);
> +            break;
> +        }
>      }
> 
>      /* Call Centaur's CPUID instructions they are supported. */
> --
> 1.8.3.1