[PATCH v7 05/16] i386: Decouple CPUID[0x1F] subleaf with specific topology level

[Zhao Liu <zhao1.liu@linux.intel.com>]

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.

Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
Tested-by: Babu Moger <babu.moger@amd.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
---
Changes since v3:
 * New patch to prepare to expose module level in 0x1F.
 * Move the CPUTopoLevel enumeration definition from "i386: Add cache
   topology info in CPUCacheInfo" to this patch. Note, to align with
   topology types in SDM, revert the name of CPU_TOPO_LEVEL_UNKNOW to
   CPU_TOPO_LEVEL_INVALID.
---
 target/i386/cpu.c | 136 +++++++++++++++++++++++++++++++++++++---------
 target/i386/cpu.h |  15 +++++
 2 files changed, 126 insertions(+), 25 deletions(-)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index bc440477d13d..5c295c9a9e2d 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -269,6 +269,116 @@ static void encode_cache_cpuid4(CPUCacheInfo *cache,
            (cache->complex_indexing ? CACHE_COMPLEX_IDX : 0);
 }
 
+static uint32_t num_cpus_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)
+{
+    static DECLARE_BITMAP(topo_bitmap, CPU_TOPO_LEVEL_MAX);
+    X86CPU *cpu = env_archcpu(env);
+    unsigned long level, next_level;
+    uint32_t num_cpus_next_level, offset_next_level;
+
+    /*
+     * Initialize the bitmap to decide which levels should be
+     * encoded in 0x1f.
+     */
+    if (!count) {
+        /* SMT and core levels are exposed in 0x1f leaf by default. */
+        set_bit(CPU_TOPO_LEVEL_SMT, topo_bitmap);
+        set_bit(CPU_TOPO_LEVEL_CORE, topo_bitmap);
+
+        if (env->nr_dies > 1) {
+            set_bit(CPU_TOPO_LEVEL_DIE, topo_bitmap);
+        }
+    }
+
+    *ecx = count & 0xff;
+    *edx = cpu->apic_id;
+
+    level = find_first_bit(topo_bitmap, CPU_TOPO_LEVEL_MAX);
+    if (level == CPU_TOPO_LEVEL_MAX) {
+        num_cpus_next_level = 0;
+        offset_next_level = 0;
+
+        /* Encode CPU_TOPO_LEVEL_INVALID into the last subleaf of 0x1f. */
+        level = CPU_TOPO_LEVEL_INVALID;
+    } else {
+        next_level = find_next_bit(topo_bitmap, CPU_TOPO_LEVEL_MAX, level + 1);
+        if (next_level == CPU_TOPO_LEVEL_MAX) {
+            next_level = CPU_TOPO_LEVEL_PACKAGE;
+        }
+
+        num_cpus_next_level = num_cpus_by_topo_level(topo_info, next_level);
+        offset_next_level = apicid_offset_by_topo_level(topo_info, next_level);
+    }
+
+    *eax = offset_next_level;
+    *ebx = num_cpus_next_level;
+    *ecx |= cpuid1f_topo_type(level) << 8;
+
+    assert(!(*eax & ~0x1f));
+    *ebx &= 0xffff; /* The count doesn't need to be reliable. */
+    if (level != CPU_TOPO_LEVEL_MAX) {
+        clear_bit(level, topo_bitmap);
+    }
+}
+
 /* Encode cache info for CPUID[0x80000005].ECX or CPUID[0x80000005].EDX */
 static uint32_t encode_cache_cpuid80000005(CPUCacheInfo *cache)
 {
@@ -6284,31 +6394,7 @@ 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 = cpus_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 */
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index f47bad46db5e..9c78cfc3f322 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1008,6 +1008,21 @@ uint64_t x86_cpu_get_supported_feature_word(FeatureWord w,
 #define CPUID_MWAIT_IBE     (1U << 1) /* Interrupts can exit capability */
 #define CPUID_MWAIT_EMX     (1U << 0) /* enumeration supported */
 
+/*
+ * CPUTopoLevel is the general i386 topology hierarchical representation,
+ * ordered by increasing hierarchical relationship.
+ * Its enumeration value is not bound to the type value of Intel (CPUID[0x1F])
+ * or AMD (CPUID[0x80000026]).
+ */
+enum CPUTopoLevel {
+    CPU_TOPO_LEVEL_INVALID,
+    CPU_TOPO_LEVEL_SMT,
+    CPU_TOPO_LEVEL_CORE,
+    CPU_TOPO_LEVEL_DIE,
+    CPU_TOPO_LEVEL_PACKAGE,
+    CPU_TOPO_LEVEL_MAX,
+};
+
 /* CPUID[0xB].ECX level types */
 #define CPUID_B_ECX_TOPO_LEVEL_INVALID  0
 #define CPUID_B_ECX_TOPO_LEVEL_SMT      1
-- 
2.34.1