[Qemu-devel] [PATCH v4 1/3] target/i386: Add CPUID.1F generation support for multi-dies PCMachine

[Like Xu <like.xu@linux.intel.com>]

The CPUID.1F as Intel V2 Extended Topology Enumeration Leaf would be
exposed if guests want to emulate multiple software-visible die within
each package. Per Intel's SDM, the 0x1f is a superset of 0xb, thus they
can be generated by almost same code as 0xb except die_offset setting.

If the number of dies per package is greater than 1, the cpuid_min_level
would be adjusted to 0x1f regardless of whether the host supports CPUID.1F.
Likewise, the CPUID.1F wouldn't be exposed if env->nr_dies < 2.

Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
---
 target/i386/cpu.c | 41 +++++++++++++++++++++++++++++++++++++++++
 target/i386/cpu.h |  1 +
 target/i386/kvm.c | 12 ++++++++++++
 3 files changed, 54 insertions(+)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 88908a6373..efcbe6a2b2 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -4439,6 +4439,42 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             *ecx |= CPUID_TOPOLOGY_LEVEL_INVALID;
         }
 
+        assert(!(*eax & ~0x1f));
+        *ebx &= 0xffff; /* The count doesn't need to be reliable. */
+        break;
+    case 0x1F:
+        /* V2 Extended Topology Enumeration Leaf */
+        if (env->nr_dies < 2) {
+            *eax = *ebx = *ecx = *edx = 0;
+            break;
+        }
+
+        *ecx = count & 0xff;
+        *edx = cpu->apic_id;
+        switch (count) {
+        case 0:
+            *eax = apicid_core_offset(env->nr_dies, cs->nr_cores,
+                                                    cs->nr_threads);
+            *ebx = cs->nr_threads;
+            *ecx |= CPUID_TOPOLOGY_LEVEL_SMT;
+            break;
+        case 1:
+            *eax = apicid_die_offset(env->nr_dies, cs->nr_cores,
+                                                   cs->nr_threads);
+            *ebx = cs->nr_cores * cs->nr_threads;
+            *ecx |= CPUID_TOPOLOGY_LEVEL_CORE;
+            break;
+        case 2:
+            *eax = apicid_pkg_offset(env->nr_dies, cs->nr_cores,
+                                                   cs->nr_threads);
+            *ebx = env->nr_dies * cs->nr_cores * cs->nr_threads;
+            *ecx |= CPUID_TOPOLOGY_LEVEL_DIE;
+            break;
+        default:
+            *eax = 0;
+            *ebx = 0;
+            *ecx |= CPUID_TOPOLOGY_LEVEL_INVALID;
+        }
         assert(!(*eax & ~0x1f));
         *ebx &= 0xffff; /* The count doesn't need to be reliable. */
         break;
@@ -5116,6 +5152,11 @@ static void x86_cpu_expand_features(X86CPU *cpu, Error **errp)
             x86_cpu_adjust_level(cpu, &cpu->env.cpuid_min_level, 0x14);
         }
 
+        /* CPU topology with multi-dies support requires CPUID[0x1F] */
+        if (env->nr_dies > 1) {
+            x86_cpu_adjust_level(cpu, &env->cpuid_min_level, 0x1F);
+        }
+
         /* SVM requires CPUID[0x8000000A] */
         if (env->features[FEAT_8000_0001_ECX] & CPUID_EXT3_SVM) {
             x86_cpu_adjust_level(cpu, &env->cpuid_min_xlevel, 0x8000000A);
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 46dd81f6b7..eec6e4b7b7 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -726,6 +726,7 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS];
 #define CPUID_TOPOLOGY_LEVEL_INVALID  (0U << 8)
 #define CPUID_TOPOLOGY_LEVEL_SMT      (1U << 8)
 #define CPUID_TOPOLOGY_LEVEL_CORE     (2U << 8)
+#define CPUID_TOPOLOGY_LEVEL_DIE      (5U << 8)
 
 /* MSR Feature Bits */
 #define MSR_ARCH_CAP_RDCL_NO    (1U << 0)
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index 6899061b4e..5deb4248ac 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -1080,6 +1080,10 @@ int kvm_arch_init_vcpu(CPUState *cs)
             }
             break;
         }
+        case 0x1f:
+            if (env->nr_dies < 2) {
+                break;
+            }
         case 4:
         case 0xb:
         case 0xd:
@@ -1087,6 +1091,11 @@ int kvm_arch_init_vcpu(CPUState *cs)
                 if (i == 0xd && j == 64) {
                     break;
                 }
+
+                if (i == 0x1f && j == 64) {
+                    break;
+                }
+
                 c->function = i;
                 c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
                 c->index = j;
@@ -1098,6 +1107,9 @@ int kvm_arch_init_vcpu(CPUState *cs)
                 if (i == 0xb && !(c->ecx & 0xff00)) {
                     break;
                 }
+                if (i == 0x1f && !(c->ecx & 0xff00)) {
+                    break;
+                }
                 if (i == 0xd && c->eax == 0) {
                     continue;
                 }
-- 
2.21.0