qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Zhao Liu <zhao1.liu@linux.intel.com>
To: "Eduardo Habkost" <eduardo@habkost.net>,
	"Marcel Apfelbaum" <marcel.apfelbaum@gmail.com>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>,
	"Yanan Wang" <wangyanan55@huawei.com>,
	"Michael S . Tsirkin" <mst@redhat.com>,
	"Richard Henderson" <richard.henderson@linaro.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>
Cc: qemu-devel@nongnu.org, Zhenyu Wang <zhenyu.z.wang@intel.com>,
	Zhao Liu <zhao1.liu@intel.com>,
	Zhuocheng Ding <zhuocheng.ding@intel.com>
Subject: [PATCH 07/18] i386: Support modules_per_die in X86CPUTopoInfo
Date: Thu,  2 Feb 2023 17:49:18 +0800	[thread overview]
Message-ID: <20230202094929.343799-8-zhao1.liu@linux.intel.com> (raw)
In-Reply-To: <20230202094929.343799-1-zhao1.liu@linux.intel.com>

From: Zhuocheng Ding <zhuocheng.ding@intel.com>

Support module level in i386 cpu topology structure "X86CPUTopoInfo".

Before updating APIC ID parsing rule with module level, the
apicid_core_width() temporarily combines the core and module levels
together.

At present, we don't expose module level in CPUID.1FH because currently
linux (v6.2-rc6) doesn't support module level. And exposing module and
die levels at the same time in CPUID.1FH will cause linux to calculate
the wrong die_id. The module level should be exposed until the real
machine has the module level in CPUID.1FH.

In addition, update topology structure in test-x86-apicid.c.

Signed-off-by: Zhuocheng Ding <zhuocheng.ding@intel.com>
Co-developed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
 hw/i386/x86.c                |  3 ++-
 include/hw/i386/topology.h   | 13 ++++++++---
 target/i386/cpu.c            | 17 ++++++++------
 tests/unit/test-x86-apicid.c | 45 +++++++++++++++++++-----------------
 4 files changed, 46 insertions(+), 32 deletions(-)

diff --git a/hw/i386/x86.c b/hw/i386/x86.c
index 66902d1c0923..3f6e0dd7b827 100644
--- a/hw/i386/x86.c
+++ b/hw/i386/x86.c
@@ -70,7 +70,8 @@ inline void init_topo_info(X86CPUTopoInfo *topo_info,
     MachineState *ms = MACHINE(x86ms);
 
     topo_info->dies_per_pkg = ms->smp.dies;
-    topo_info->cores_per_die = ms->smp.cores;
+    topo_info->modules_per_die = ms->smp.clusters;
+    topo_info->cores_per_module = ms->smp.cores;
     topo_info->threads_per_core = ms->smp.threads;
 }
 
diff --git a/include/hw/i386/topology.h b/include/hw/i386/topology.h
index 81573f6cfde0..bbb00dc4aad8 100644
--- a/include/hw/i386/topology.h
+++ b/include/hw/i386/topology.h
@@ -54,7 +54,8 @@ typedef struct X86CPUTopoIDs {
 
 typedef struct X86CPUTopoInfo {
     unsigned dies_per_pkg;
-    unsigned cores_per_die;
+    unsigned modules_per_die;
+    unsigned cores_per_module;
     unsigned threads_per_core;
 } X86CPUTopoInfo;
 
@@ -78,7 +79,12 @@ static inline unsigned apicid_smt_width(X86CPUTopoInfo *topo_info)
  */
 static inline unsigned apicid_core_width(X86CPUTopoInfo *topo_info)
 {
-    return apicid_bitwidth_for_count(topo_info->cores_per_die);
+    /*
+     * TODO: Will separate module info from core_width when update
+     * APIC ID with module level.
+     */
+    return apicid_bitwidth_for_count(topo_info->cores_per_module *
+                                     topo_info->modules_per_die);
 }
 
 /* Bit width of the Die_ID field */
@@ -128,7 +134,8 @@ static inline void x86_topo_ids_from_idx(X86CPUTopoInfo *topo_info,
                                          X86CPUTopoIDs *topo_ids)
 {
     unsigned nr_dies = topo_info->dies_per_pkg;
-    unsigned nr_cores = topo_info->cores_per_die;
+    unsigned nr_cores = topo_info->cores_per_module *
+                        topo_info->modules_per_die;
     unsigned nr_threads = topo_info->threads_per_core;
 
     topo_ids->pkg_id = cpu_index / (nr_dies * nr_cores * nr_threads);
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 61ec9a7499b8..6f3d114c7d12 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -336,7 +336,9 @@ static void encode_cache_cpuid8000001d(CPUCacheInfo *cache,
 
     /* L3 is shared among multiple cores */
     if (cache->level == 3) {
-        l3_threads = topo_info->cores_per_die * topo_info->threads_per_core;
+        l3_threads = topo_info->modules_per_die *
+                     topo_info->cores_per_module *
+                     topo_info->threads_per_core;
         *eax |= (l3_threads - 1) << 14;
     } else {
         *eax |= ((topo_info->threads_per_core - 1) << 14);
@@ -5218,11 +5220,12 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
     uint32_t cpus_per_pkg;
 
     topo_info.dies_per_pkg = env->nr_dies;
-    topo_info.cores_per_die = cs->nr_cores / env->nr_dies;
+    topo_info.modules_per_die = env->nr_modules;
+    topo_info.cores_per_module = cs->nr_cores / env->nr_dies / env->nr_modules;
     topo_info.threads_per_core = cs->nr_threads;
 
-    cpus_per_pkg = topo_info.dies_per_pkg * topo_info.cores_per_die *
-                   topo_info.threads_per_core;
+    cpus_per_pkg = topo_info.dies_per_pkg * topo_info.modules_per_die *
+                   topo_info.cores_per_module * topo_info.threads_per_core;
 
     /* Calculate & apply limits for different index ranges */
     if (index >= 0xC0000000) {
@@ -5298,8 +5301,8 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             if (*eax & 31) {
                 int host_vcpus_per_cache = 1 + ((*eax & 0x3FFC000) >> 14);
                 int vcpus_per_socket = cpus_per_pkg;
-                int cores_per_socket = topo_info.cores_per_die *
-                                       topo_info.dies_per_pkg;
+                int cores_per_socket = cpus_per_pkg /
+                                       topo_info.threads_per_core;
                 if (cores_per_socket > 1) {
                     *eax &= ~0xFC000000;
                     *eax |= (pow2ceil(cores_per_socket) - 1) << 26;
@@ -5483,7 +5486,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             break;
         case 1:
             *eax = apicid_die_offset(&topo_info);
-            *ebx = topo_info.cores_per_die * topo_info.threads_per_core;
+            *ebx = cpus_per_pkg / topo_info.dies_per_pkg;
             *ecx |= CPUID_TOPOLOGY_LEVEL_CORE;
             break;
         case 2:
diff --git a/tests/unit/test-x86-apicid.c b/tests/unit/test-x86-apicid.c
index 2b104f86d7c2..f21b8a5d95c2 100644
--- a/tests/unit/test-x86-apicid.c
+++ b/tests/unit/test-x86-apicid.c
@@ -30,13 +30,16 @@ static void test_topo_bits(void)
 {
     X86CPUTopoInfo topo_info = {0};
 
-    /* simple tests for 1 thread per core, 1 core per die, 1 die per package */
-    topo_info = (X86CPUTopoInfo) {1, 1, 1};
+    /*
+     * simple tests for 1 thread per core, 1 core per module,
+     *                  1 module per die, 1 die per package
+     */
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 1};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 0);
     g_assert_cmpuint(apicid_core_width(&topo_info), ==, 0);
     g_assert_cmpuint(apicid_die_width(&topo_info), ==, 0);
 
-    topo_info = (X86CPUTopoInfo) {1, 1, 1};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 1};
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 0), ==, 0);
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 1), ==, 1);
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 2), ==, 2);
@@ -45,39 +48,39 @@ static void test_topo_bits(void)
 
     /* Test field width calculation for multiple values
      */
-    topo_info = (X86CPUTopoInfo) {1, 1, 2};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 2};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 1);
-    topo_info = (X86CPUTopoInfo) {1, 1, 3};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 3};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 2);
-    topo_info = (X86CPUTopoInfo) {1, 1, 4};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 4};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 2);
 
-    topo_info = (X86CPUTopoInfo) {1, 1, 14};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 14};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 4);
-    topo_info = (X86CPUTopoInfo) {1, 1, 15};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 15};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 4);
-    topo_info = (X86CPUTopoInfo) {1, 1, 16};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 16};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 4);
-    topo_info = (X86CPUTopoInfo) {1, 1, 17};
+    topo_info = (X86CPUTopoInfo) {1, 1, 1, 17};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 5);
 
 
-    topo_info = (X86CPUTopoInfo) {1, 30, 2};
+    topo_info = (X86CPUTopoInfo) {1, 1, 30, 2};
     g_assert_cmpuint(apicid_core_width(&topo_info), ==, 5);
-    topo_info = (X86CPUTopoInfo) {1, 31, 2};
+    topo_info = (X86CPUTopoInfo) {1, 1, 31, 2};
     g_assert_cmpuint(apicid_core_width(&topo_info), ==, 5);
-    topo_info = (X86CPUTopoInfo) {1, 32, 2};
+    topo_info = (X86CPUTopoInfo) {1, 1, 32, 2};
     g_assert_cmpuint(apicid_core_width(&topo_info), ==, 5);
-    topo_info = (X86CPUTopoInfo) {1, 33, 2};
+    topo_info = (X86CPUTopoInfo) {1, 1, 33, 2};
     g_assert_cmpuint(apicid_core_width(&topo_info), ==, 6);
 
-    topo_info = (X86CPUTopoInfo) {1, 30, 2};
+    topo_info = (X86CPUTopoInfo) {1, 1, 30, 2};
     g_assert_cmpuint(apicid_die_width(&topo_info), ==, 0);
-    topo_info = (X86CPUTopoInfo) {2, 30, 2};
+    topo_info = (X86CPUTopoInfo) {2, 1, 30, 2};
     g_assert_cmpuint(apicid_die_width(&topo_info), ==, 1);
-    topo_info = (X86CPUTopoInfo) {3, 30, 2};
+    topo_info = (X86CPUTopoInfo) {3, 1, 30, 2};
     g_assert_cmpuint(apicid_die_width(&topo_info), ==, 2);
-    topo_info = (X86CPUTopoInfo) {4, 30, 2};
+    topo_info = (X86CPUTopoInfo) {4, 1, 30, 2};
     g_assert_cmpuint(apicid_die_width(&topo_info), ==, 2);
 
     /* build a weird topology and see if IDs are calculated correctly
@@ -85,18 +88,18 @@ static void test_topo_bits(void)
 
     /* This will use 2 bits for thread ID and 3 bits for core ID
      */
-    topo_info = (X86CPUTopoInfo) {1, 6, 3};
+    topo_info = (X86CPUTopoInfo) {1, 1, 6, 3};
     g_assert_cmpuint(apicid_smt_width(&topo_info), ==, 2);
     g_assert_cmpuint(apicid_core_offset(&topo_info), ==, 2);
     g_assert_cmpuint(apicid_die_offset(&topo_info), ==, 5);
     g_assert_cmpuint(apicid_pkg_offset(&topo_info), ==, 5);
 
-    topo_info = (X86CPUTopoInfo) {1, 6, 3};
+    topo_info = (X86CPUTopoInfo) {1, 1, 6, 3};
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 0), ==, 0);
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 1), ==, 1);
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 2), ==, 2);
 
-    topo_info = (X86CPUTopoInfo) {1, 6, 3};
+    topo_info = (X86CPUTopoInfo) {1, 1, 6, 3};
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 1 * 3 + 0), ==,
                      (1 << 2) | 0);
     g_assert_cmpuint(x86_apicid_from_cpu_idx(&topo_info, 1 * 3 + 1), ==,
-- 
2.34.1



  parent reply	other threads:[~2023-02-02  9:44 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-02  9:49 [PATCH 00/18] Support smp.clusters for x86 Zhao Liu
2023-02-02  9:49 ` [PATCH 01/18] machine: Fix comment of machine_parse_smp_config() Zhao Liu
2023-02-02  9:49 ` [PATCH 02/18] tests: Rename test-x86-cpuid.c to test-x86-apicid.c Zhao Liu
2023-02-02  9:49 ` [PATCH 03/18] softmmu: Fix CPUSTATE.nr_cores' calculation Zhao Liu
2023-02-02  9:49 ` [PATCH 04/18] i386/cpu: Fix number of addressable IDs in CPUID.04H Zhao Liu
2023-02-02  9:49 ` [PATCH 05/18] i386/cpu: Consolidate the use of topo_info in cpu_x86_cpuid() Zhao Liu
2023-02-02  9:49 ` [PATCH 06/18] i386: Introduce module-level cpu topology to CPUX86State Zhao Liu
2023-02-02  9:49 ` Zhao Liu [this message]
2023-02-02  9:49 ` [PATCH 08/18] i386: Support module_id in X86CPUTopoIDs Zhao Liu
2023-02-02  9:49 ` [PATCH 09/18] i386: Fix comment style in topology.h Zhao Liu
2023-02-02  9:49 ` [PATCH 10/18] i386: Update APIC ID parsing rule to support module level Zhao Liu
2023-02-02  9:49 ` [PATCH 11/18] i386/cpu: Introduce cluster-id to X86CPU Zhao Liu
2023-02-02  9:49 ` [PATCH 12/18] tests: Add test case of APIC ID for module level parsing Zhao Liu
2023-02-02  9:49 ` [PATCH 13/18] hw/i386/pc: Support smp.clusters for x86 PC machine Zhao Liu
2023-02-02  9:49 ` [PATCH 14/18] i386: Add cache topology info in CPUCacheInfo Zhao Liu
2023-02-02  9:49 ` [PATCH 15/18] i386: Use CPUCacheInfo.share_level to encode CPUID[4].EAX[bits 25:14] Zhao Liu
2023-02-02  9:49 ` [PATCH 16/18] i386: Fix NumSharingCache for CPUID[0x8000001D].EAX[bits 25:14] Zhao Liu
2023-02-02  9:49 ` [PATCH 17/18] i386: Use CPUCacheInfo.share_level to encode " Zhao Liu
2023-02-02  9:49 ` [PATCH 18/18] i386: Add new property to control L2 cache topo in CPUID.04H Zhao Liu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230202094929.343799-8-zhao1.liu@linux.intel.com \
    --to=zhao1.liu@linux.intel.com \
    --cc=eduardo@habkost.net \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=wangyanan55@huawei.com \
    --cc=zhao1.liu@intel.com \
    --cc=zhenyu.z.wang@intel.com \
    --cc=zhuocheng.ding@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).