From: Zhao Liu <zhao1.liu@intel.com>

At present, the subleaf 0x02 of CPUID[0x1F] is bound to the "die" level.

In fact, the specific topology level exposed in 0x1F depends on the
platform's support for extension levels (module, tile and die).

To help expose "module" level in 0x1F, decouple CPUID[0x1F] subleaf
with specific topology level.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Message-ID: <20240424154929.1487382-12-zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/cpu.c | 135 +++++++++++++++++++++++++++++++++++++---------
 1 file changed, 110 insertions(+), 25 deletions(-)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index d350eb8a736..f95d539eeff 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -269,6 +269,115 @@ static void encode_cache_cpuid4(CPUCacheInfo *cache,
            (cache->complex_indexing ? CACHE_COMPLEX_IDX : 0);
 }
 
+static uint32_t num_threads_by_topo_level(X86CPUTopoInfo *topo_info,
+                                          enum CPUTopoLevel topo_level)
+{
+    switch (topo_level) {
+    case CPU_TOPO_LEVEL_SMT:
+        return 1;
+    case CPU_TOPO_LEVEL_CORE:
+        return topo_info->threads_per_core;
+    case CPU_TOPO_LEVEL_DIE:
+        return topo_info->threads_per_core * topo_info->cores_per_die;
+    case CPU_TOPO_LEVEL_PACKAGE:
+        return topo_info->threads_per_core * topo_info->cores_per_die *
+               topo_info->dies_per_pkg;
+    default:
+        g_assert_not_reached();
+    }
+    return 0;
+}
+
+static uint32_t apicid_offset_by_topo_level(X86CPUTopoInfo *topo_info,
+                                            enum CPUTopoLevel topo_level)
+{
+    switch (topo_level) {
+    case CPU_TOPO_LEVEL_SMT:
+        return 0;
+    case CPU_TOPO_LEVEL_CORE:
+        return apicid_core_offset(topo_info);
+    case CPU_TOPO_LEVEL_DIE:
+        return apicid_die_offset(topo_info);
+    case CPU_TOPO_LEVEL_PACKAGE:
+        return apicid_pkg_offset(topo_info);
+    default:
+        g_assert_not_reached();
+    }
+    return 0;
+}
+
+static uint32_t cpuid1f_topo_type(enum CPUTopoLevel topo_level)
+{
+    switch (topo_level) {
+    case CPU_TOPO_LEVEL_INVALID:
+        return CPUID_1F_ECX_TOPO_LEVEL_INVALID;
+    case CPU_TOPO_LEVEL_SMT:
+        return CPUID_1F_ECX_TOPO_LEVEL_SMT;
+    case CPU_TOPO_LEVEL_CORE:
+        return CPUID_1F_ECX_TOPO_LEVEL_CORE;
+    case CPU_TOPO_LEVEL_DIE:
+        return CPUID_1F_ECX_TOPO_LEVEL_DIE;
+    default:
+        /* Other types are not supported in QEMU. */
+        g_assert_not_reached();
+    }
+    return 0;
+}
+
+static void encode_topo_cpuid1f(CPUX86State *env, uint32_t count,
+                                X86CPUTopoInfo *topo_info,
+                                uint32_t *eax, uint32_t *ebx,
+                                uint32_t *ecx, uint32_t *edx)
+{
+    X86CPU *cpu = env_archcpu(env);
+    unsigned long level, next_level;
+    uint32_t num_threads_next_level, offset_next_level;
+
+    assert(count + 1 < CPU_TOPO_LEVEL_MAX);
+
+    /*
+     * Find the No.(count + 1) topology level in avail_cpu_topo bitmap.
+     * The search starts from bit 1 (CPU_TOPO_LEVEL_INVALID + 1).
+     */
+    level = CPU_TOPO_LEVEL_INVALID;
+    for (int i = 0; i <= count; i++) {
+        level = find_next_bit(env->avail_cpu_topo,
+                              CPU_TOPO_LEVEL_PACKAGE,
+                              level + 1);
+
+        /*
+         * CPUID[0x1f] doesn't explicitly encode the package level,
+         * and it just encodes the invalid level (all fields are 0)
+         * into the last subleaf of 0x1f.
+         */
+        if (level == CPU_TOPO_LEVEL_PACKAGE) {
+            level = CPU_TOPO_LEVEL_INVALID;
+            break;
+        }
+    }
+
+    if (level == CPU_TOPO_LEVEL_INVALID) {
+        num_threads_next_level = 0;
+        offset_next_level = 0;
+    } else {
+        next_level = find_next_bit(env->avail_cpu_topo,
+                                   CPU_TOPO_LEVEL_PACKAGE,
+                                   level + 1);
+        num_threads_next_level = num_threads_by_topo_level(topo_info,
+                                                           next_level);
+        offset_next_level = apicid_offset_by_topo_level(topo_info,
+                                                        next_level);
+    }
+
+    *eax = offset_next_level;
+    /* The count (bits 15-00) doesn't need to be reliable. */
+    *ebx = num_threads_next_level & 0xffff;
+    *ecx = (count & 0xff) | (cpuid1f_topo_type(level) << 8);
+    *edx = cpu->apic_id;
+
+    assert(!(*eax & ~0x1f));
+}
+
 /* Encode cache info for CPUID[0x80000005].ECX or CPUID[0x80000005].EDX */
 static uint32_t encode_cache_cpuid80000005(CPUCacheInfo *cache)
 {
@@ -6447,31 +6556,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             break;
         }
 
-        *ecx = count & 0xff;
-        *edx = cpu->apic_id;
-        switch (count) {
-        case 0:
-            *eax = apicid_core_offset(&topo_info);
-            *ebx = topo_info.threads_per_core;
-            *ecx |= CPUID_1F_ECX_TOPO_LEVEL_SMT << 8;
-            break;
-        case 1:
-            *eax = apicid_die_offset(&topo_info);
-            *ebx = topo_info.cores_per_die * topo_info.threads_per_core;
-            *ecx |= CPUID_1F_ECX_TOPO_LEVEL_CORE << 8;
-            break;
-        case 2:
-            *eax = apicid_pkg_offset(&topo_info);
-            *ebx = threads_per_pkg;
-            *ecx |= CPUID_1F_ECX_TOPO_LEVEL_DIE << 8;
-            break;
-        default:
-            *eax = 0;
-            *ebx = 0;
-            *ecx |= CPUID_1F_ECX_TOPO_LEVEL_INVALID << 8;
-        }
-        assert(!(*eax & ~0x1f));
-        *ebx &= 0xffff; /* The count doesn't need to be reliable. */
+        encode_topo_cpuid1f(env, count, &topo_info, eax, ebx, ecx, edx);
         break;
     case 0xD: {
         /* Processor Extended State */
-- 
2.45.1