[Qemu-devel] [PATCH] AMD Processor Topology Information

[Stanislav Lanci <pixo@polepetko.eu>]

V2:
Adds information about cache size and topology on leaf 0x8000001D for family 17h
Without the added cache topology guest with SMT suffers latency problems

Add CPUID 0x8000001E for describing AMD Processor Topology Information
Disables warning about smt for 17h family of AMD CPUs

Signed-off-by: Stanislav Lanci <pixo@polepetko.eu>
---
 target/i386/cpu.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 target/i386/kvm.c | 28 +++++++++++++++--
 2 files changed, 117 insertions(+), 4 deletions(-)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index ddc45abd70..1545e3fe31 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -113,7 +113,9 @@
 /* L1 instruction cache: */
 #define L1I_LINE_SIZE         64
 #define L1I_ASSOCIATIVITY      8
+#define L1I_ASSOC_AMD_ZEN      4
 #define L1I_SETS              64
+#define L1I_SETS_AMD_ZEN     256
 #define L1I_PARTITIONS         1
 /* Size = LINE_SIZE*ASSOCIATIVITY*SETS*PARTITIONS = 32KiB */
 #define L1I_DESCRIPTOR CPUID_2_L1I_32KB_8WAY_64B
@@ -125,7 +127,9 @@
 /* Level 2 unified cache: */
 #define L2_LINE_SIZE          64
 #define L2_ASSOCIATIVITY      16
+#define L2_ASSOC_AMD_ZEN       8
 #define L2_SETS             4096
+#define L2_SETS_AMD_ZEN     1024
 #define L2_PARTITIONS          1
 /* Size = LINE_SIZE*ASSOCIATIVITY*SETS*PARTITIONS = 4MiB */
 /*FIXME: CPUID leaf 2 descriptor is inconsistent with CPUID leaf 4 */
@@ -142,6 +146,7 @@
 #define L3_N_LINE_SIZE         64
 #define L3_N_ASSOCIATIVITY     16
 #define L3_N_SETS           16384
+#define L3_N_SETS_AMD_ZEN    4096
 #define L3_N_PARTITIONS         1
 #define L3_N_DESCRIPTOR CPUID_2_L3_16MB_16WAY_64B
 #define L3_N_LINES_PER_TAG      1
@@ -3072,6 +3077,91 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             *edx = 0;
         }
         break;
+    case 0x8000001D: /* AMD TOPOEXT cache info for ZEN */
+        if (cpu->cache_info_passthrough) {
+            host_cpuid(index, count, eax, ebx, ecx, edx);
+            break;
+        } else if ((env->cpuid_version & 0xFF00F00) == 0x800F00) {
+            *eax = 0;
+            switch (count) {
+            case 0: /* L1 dcache info */
+                *eax |= CPUID_4_TYPE_DCACHE | \
+                        CPUID_4_LEVEL(1) | \
+                        CPUID_4_SELF_INIT_LEVEL | \
+                        ((cs->nr_threads - 1) << 14);
+                *ebx = (L1D_LINE_SIZE - 1) | \
+                       ((L1D_PARTITIONS - 1) << 12) | \
+                       ((L1D_ASSOCIATIVITY - 1) << 22);
+                *ecx = L1D_SETS - 1;
+                *edx = 0;
+                break;
+            case 1: /* L1 icache info */
+                *eax |= CPUID_4_TYPE_ICACHE | \
+                        CPUID_4_LEVEL(1) | \
+                        CPUID_4_SELF_INIT_LEVEL | \
+                        ((cs->nr_threads - 1) << 14);
+                *ebx = (L1I_LINE_SIZE - 1) | \
+                       ((L1I_PARTITIONS - 1) << 12) | \
+                       ((L1I_ASSOC_AMD_ZEN - 1) << 22);
+                *ecx = L1I_SETS_AMD_ZEN - 1;
+                *edx = 0;
+                break;
+            case 2: /* L2 cache info */
+                *eax |= CPUID_4_TYPE_UNIFIED | \
+                        CPUID_4_LEVEL(2) | \
+                        CPUID_4_SELF_INIT_LEVEL | \
+                        ((cs->nr_threads - 1) << 14);
+                *ebx = (L2_LINE_SIZE - 1) | \
+                       ((L2_PARTITIONS - 1) << 12) | \
+                       ((L2_ASSOC_AMD_ZEN - 1) << 22);
+                *ecx = L2_SETS_AMD_ZEN - 1;
+                *edx = CPUID_4_INCLUSIVE;
+                break;
+            case 3: /* L3 cache info */
+                if (!cpu->enable_l3_cache) {
+                    *eax = 0;
+                    *ebx = 0;
+                    *ecx = 0;
+                    *edx = 0;
+                    break;
+                }
+                *eax |= CPUID_4_TYPE_UNIFIED | \
+                        CPUID_4_LEVEL(3) | \
+                        CPUID_4_SELF_INIT_LEVEL | \
+                        ((cs->nr_cores * cs->nr_threads - 1) << 14);
+                *ebx = (L3_N_LINE_SIZE - 1) | \
+                       ((L3_N_PARTITIONS - 1) << 12) | \
+                       ((L3_N_ASSOCIATIVITY - 1) << 22);
+                *ecx = L3_N_SETS_AMD_ZEN - 1;
+                *edx = CPUID_4_NO_INVD_SHARING;
+                break;
+            default: /* end of info */
+                *eax = 0;
+                *ebx = 0;
+                *ecx = 0;
+                *edx = 0;
+                break;
+            }
+        } else {
+            *eax = 0;
+            *ebx = 0;
+            *ecx = 0;
+            *edx = 0;
+        }
+        break;
+    case 0x8000001E: /* AMD TOPOEXT cpu topology info for ZEN */
+        if ((env->cpuid_version & 0xFF00F00) == 0x800F00) {
+            *eax = cpu->apic_id;
+            *ebx = (cs->nr_threads - 1) << 8 | cpu->core_id;
+            *ecx = cpu->socket_id;
+            *edx = 0;
+        } else {
+            *eax = 0;
+            *ebx = 0;
+            *ecx = 0;
+            *edx = 0;
+        }
+        break;
     case 0xC0000000:
         *eax = env->cpuid_xlevel2;
         *ebx = 0;
@@ -3742,7 +3832,8 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp)
      * NOTE: the following code has to follow qemu_init_vcpu(). Otherwise
      * cs->nr_threads hasn't be populated yet and the checking is incorrect.
      */
-    if (!IS_INTEL_CPU(env) && cs->nr_threads > 1 && !ht_warned) {
+    if (!IS_INTEL_CPU(env) && cs->nr_threads > 1 && !ht_warned && \
+       (env->cpuid_version & 0xFF00F00) != 0x800F00) {
         error_report("AMD CPU doesn't support hyperthreading. Please configure"
                      " -smp options properly.");
         ht_warned = true;
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index 6db7783edc..d6b4e1ae74 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -869,9 +869,31 @@ 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:
+            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. */
-- 
2.15.0