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>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Richard Henderson" <richard.henderson@linaro.org>,
	"Eric Blake" <eblake@redhat.com>,
	"Markus Armbruster" <armbru@redhat.com>,
	"Marcelo Tosatti" <mtosatti@redhat.com>
Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org,
	Babu Moger <babu.moger@amd.com>,
	Xiaoyao Li <xiaoyao.li@intel.com>,
	Zhenyu Wang <zhenyu.z.wang@intel.com>,
	Zhuocheng Ding <zhuocheng.ding@intel.com>,
	Yongwei Ma <yongwei.ma@intel.com>, Zhao Liu <zhao1.liu@intel.com>
Subject: [PATCH v8 20/21] i386/cpu: Use CPUCacheInfo.share_level to encode CPUID[4]
Date: Wed, 31 Jan 2024 18:13:49 +0800	[thread overview]
Message-ID: <20240131101350.109512-21-zhao1.liu@linux.intel.com> (raw)
In-Reply-To: <20240131101350.109512-1-zhao1.liu@linux.intel.com>

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

CPUID[4].EAX[bits 25:14] is used to represent the cache topology for
Intel CPUs.

After cache models have topology information, we can use
CPUCacheInfo.share_level to decide which topology level to be encoded
into CPUID[4].EAX[bits 25:14].

And since with the helper max_processor_ids_for_cache(), the filed
CPUID[4].EAX[bits 25:14] (original virable "num_apic_ids") is parsed
based on cpu topology levels, which are verified when parsing -smp, it's
no need to check this value by "assert(num_apic_ids > 0)" again, so
remove this assert().

Additionally, wrap the encoding of CPUID[4].EAX[bits 31:26] into a
helper to make the code cleaner.

Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
Changes since v7:
 * Renamed max_processor_ids_for_cache() to max_thread_ids_for_cache().
   (Xiaoyao)
 * Dropped Michael/Babu's ACKed/Tested tags since the code change.
 * Re-added Yongwei's Tested tag For his re-testing.

Changes since v1:
 * Used "enum CPUTopoLevel share_level" as the parameter in
   max_processor_ids_for_cache().
 * Made cache_into_passthrough case also use
   max_processor_ids_for_cache() and max_core_ids_in_package() to
   encode CPUID[4]. (Yanan)
 * Renamed the title of this patch (the original is "i386: Use
   CPUCacheInfo.share_level to encode CPUID[4].EAX[bits 25:14]").
---
 target/i386/cpu.c | 76 ++++++++++++++++++++++++++++-------------------
 1 file changed, 45 insertions(+), 31 deletions(-)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index f167df4f6df1..fbfebdc2caf3 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -235,22 +235,53 @@ static uint8_t cpuid2_cache_descriptor(CPUCacheInfo *cache)
                        ((t) == UNIFIED_CACHE) ? CACHE_TYPE_UNIFIED : \
                        0 /* Invalid value */)
 
+static uint32_t max_thread_ids_for_cache(X86CPUTopoInfo *topo_info,
+                                         enum CPUTopoLevel share_level)
+{
+    uint32_t num_ids = 0;
+
+    switch (share_level) {
+    case CPU_TOPO_LEVEL_CORE:
+        num_ids = 1 << apicid_core_offset(topo_info);
+        break;
+    case CPU_TOPO_LEVEL_DIE:
+        num_ids = 1 << apicid_die_offset(topo_info);
+        break;
+    case CPU_TOPO_LEVEL_PACKAGE:
+        num_ids = 1 << apicid_pkg_offset(topo_info);
+        break;
+    default:
+        /*
+         * Currently there is no use case for SMT and MODULE, so use
+         * assert directly to facilitate debugging.
+         */
+        g_assert_not_reached();
+    }
+
+    return num_ids - 1;
+}
+
+static uint32_t max_core_ids_in_package(X86CPUTopoInfo *topo_info)
+{
+    uint32_t num_cores = 1 << (apicid_pkg_offset(topo_info) -
+                               apicid_core_offset(topo_info));
+    return num_cores - 1;
+}
 
 /* Encode cache info for CPUID[4] */
 static void encode_cache_cpuid4(CPUCacheInfo *cache,
-                                int num_apic_ids, int num_cores,
+                                X86CPUTopoInfo *topo_info,
                                 uint32_t *eax, uint32_t *ebx,
                                 uint32_t *ecx, uint32_t *edx)
 {
     assert(cache->size == cache->line_size * cache->associativity *
                           cache->partitions * cache->sets);
 
-    assert(num_apic_ids > 0);
     *eax = CACHE_TYPE(cache->type) |
            CACHE_LEVEL(cache->level) |
            (cache->self_init ? CACHE_SELF_INIT_LEVEL : 0) |
-           ((num_cores - 1) << 26) |
-           ((num_apic_ids - 1) << 14);
+           (max_core_ids_in_package(topo_info) << 26) |
+           (max_thread_ids_for_cache(topo_info, cache->share_level) << 14);
 
     assert(cache->line_size > 0);
     assert(cache->partitions > 0);
@@ -6246,10 +6277,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
                (cpuid2_cache_descriptor(env->cache_info_cpuid2.l1i_cache) <<  8) |
                (cpuid2_cache_descriptor(env->cache_info_cpuid2.l2_cache));
         break;
-    case 4: {
-        int addressable_cores_width;
-        int addressable_threads_width;
-
+    case 4:
         /* cache info: needed for Core compatibility */
         if (cpu->cache_info_passthrough) {
             x86_cpu_get_cache_cpuid(index, count, eax, ebx, ecx, edx);
@@ -6261,55 +6289,42 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
                 int host_vcpus_per_cache = 1 + ((*eax & 0x3FFC000) >> 14);
 
                 if (cores_per_pkg > 1) {
-                    addressable_cores_width = apicid_pkg_offset(&topo_info) -
-                                              apicid_core_offset(&topo_info);
-
                     *eax &= ~0xFC000000;
-                    *eax |= ((1 << addressable_cores_width) - 1) << 26;
+                    *eax |= max_core_ids_in_package(&topo_info) << 26;
                 }
                 if (host_vcpus_per_cache > threads_per_pkg) {
-                    /* Share the cache at package level. */
-                    addressable_threads_width = apicid_pkg_offset(&topo_info);
-
                     *eax &= ~0x3FFC000;
-                    *eax |= ((1 << addressable_threads_width) - 1) << 14;
+
+                    /* Share the cache at package level. */
+                    *eax |= max_thread_ids_for_cache(&topo_info,
+                                CPU_TOPO_LEVEL_PACKAGE) << 14;
                 }
             }
         } else if (cpu->vendor_cpuid_only && IS_AMD_CPU(env)) {
             *eax = *ebx = *ecx = *edx = 0;
         } else {
             *eax = 0;
-            addressable_cores_width = apicid_pkg_offset(&topo_info) -
-                                      apicid_core_offset(&topo_info);
 
             switch (count) {
             case 0: /* L1 dcache info */
-                addressable_threads_width = apicid_core_offset(&topo_info);
                 encode_cache_cpuid4(env->cache_info_cpuid4.l1d_cache,
-                                    (1 << addressable_threads_width),
-                                    (1 << addressable_cores_width),
+                                    &topo_info,
                                     eax, ebx, ecx, edx);
                 break;
             case 1: /* L1 icache info */
-                addressable_threads_width = apicid_core_offset(&topo_info);
                 encode_cache_cpuid4(env->cache_info_cpuid4.l1i_cache,
-                                    (1 << addressable_threads_width),
-                                    (1 << addressable_cores_width),
+                                    &topo_info,
                                     eax, ebx, ecx, edx);
                 break;
             case 2: /* L2 cache info */
-                addressable_threads_width = apicid_core_offset(&topo_info);
                 encode_cache_cpuid4(env->cache_info_cpuid4.l2_cache,
-                                    (1 << addressable_threads_width),
-                                    (1 << addressable_cores_width),
+                                    &topo_info,
                                     eax, ebx, ecx, edx);
                 break;
             case 3: /* L3 cache info */
                 if (cpu->enable_l3_cache) {
-                    addressable_threads_width = apicid_die_offset(&topo_info);
                     encode_cache_cpuid4(env->cache_info_cpuid4.l3_cache,
-                                        (1 << addressable_threads_width),
-                                        (1 << addressable_cores_width),
+                                        &topo_info,
                                         eax, ebx, ecx, edx);
                     break;
                 }
@@ -6320,7 +6335,6 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             }
         }
         break;
-    }
     case 5:
         /* MONITOR/MWAIT Leaf */
         *eax = cpu->mwait.eax; /* Smallest monitor-line size in bytes */
-- 
2.34.1



  parent reply	other threads:[~2024-01-31 10:06 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-31 10:13 [PATCH v8 00/21] Introduce smp.modules for x86 in QEMU Zhao Liu
2024-01-31 10:13 ` [PATCH v8 01/21] hw/core/machine: Introduce the module as a CPU topology level Zhao Liu
2024-01-31 10:13 ` [PATCH v8 02/21] hw/core/machine: Support modules in -smp Zhao Liu
2024-01-31 10:13 ` [PATCH v8 03/21] hw/core: Introduce module-id as the topology subindex Zhao Liu
2024-01-31 10:13 ` [PATCH v8 04/21] hw/core: Support module-id in numa configuration Zhao Liu
2024-01-31 10:13 ` [PATCH v8 05/21] i386/cpu: Fix i/d-cache topology to core level for Intel CPU Zhao Liu
2024-01-31 10:13 ` [PATCH v8 06/21] i386/cpu: Use APIC ID info to encode cache topo in CPUID[4] Zhao Liu
2024-01-31 10:13 ` [PATCH v8 07/21] i386/cpu: Use APIC ID info get NumSharingCache for CPUID[0x8000001D].EAX[bits 25:14] Zhao Liu
2024-01-31 10:13 ` [PATCH v8 08/21] i386/cpu: Consolidate the use of topo_info in cpu_x86_cpuid() Zhao Liu
2024-02-07  5:59   ` Philippe Mathieu-Daudé
2024-01-31 10:13 ` [PATCH v8 09/21] i386/cpu: Introduce bitmap to cache available CPU topology levels Zhao Liu
2024-01-31 10:13 ` [PATCH v8 10/21] i386: Split topology types of CPUID[0x1F] from the definitions of CPUID[0xB] Zhao Liu
2024-02-07  6:00   ` Philippe Mathieu-Daudé
2024-01-31 10:13 ` [PATCH v8 11/21] i386/cpu: Decouple CPUID[0x1F] subleaf with specific topology level Zhao Liu
2024-01-31 10:13 ` [PATCH v8 12/21] i386: Introduce module level cpu topology to CPUX86State Zhao Liu
2024-01-31 10:13 ` [PATCH v8 13/21] i386: Support modules_per_die in X86CPUTopoInfo Zhao Liu
2024-01-31 10:13 ` [PATCH v8 14/21] i386: Expose module level in CPUID[0x1F] Zhao Liu
2024-01-31 10:13 ` [PATCH v8 15/21] i386: Support module_id in X86CPUTopoIDs Zhao Liu
2024-01-31 10:13 ` [PATCH v8 16/21] i386/cpu: Introduce module-id to X86CPU Zhao Liu
2024-01-31 10:13 ` [PATCH v8 17/21] tests: Add test case of APIC ID for module level parsing Zhao Liu
2024-01-31 10:13 ` [PATCH v8 18/21] hw/i386/pc: Support smp.modules for x86 PC machine Zhao Liu
2024-01-31 10:13 ` [PATCH v8 19/21] i386: Add cache topology info in CPUCacheInfo Zhao Liu
2024-01-31 10:13 ` Zhao Liu [this message]
2024-01-31 10:13 ` [PATCH v8 21/21] i386/cpu: Use CPUCacheInfo.share_level to encode CPUID[0x8000001D].EAX[bits 25:14] Zhao Liu
2024-01-31 10:28 ` [PATCH v8 00/21] Introduce smp.modules for x86 in QEMU Daniel P. Berrangé
2024-02-01  2:57   ` Zhao Liu
2024-02-01  9:21     ` Daniel P. Berrangé
2024-02-01 16:10       ` Zhao Liu
2024-02-08 16:52         ` Daniel P. Berrangé
2024-02-15 16:56           ` Zhao Liu
2024-02-21 12:41 ` Markus Armbruster
2024-02-21 15:15   ` 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=20240131101350.109512-21-zhao1.liu@linux.intel.com \
    --to=zhao1.liu@linux.intel.com \
    --cc=armbru@redhat.com \
    --cc=babu.moger@amd.com \
    --cc=eblake@redhat.com \
    --cc=eduardo@habkost.net \
    --cc=kvm@vger.kernel.org \
    --cc=marcel.apfelbaum@gmail.com \
    --cc=mst@redhat.com \
    --cc=mtosatti@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=xiaoyao.li@intel.com \
    --cc=yongwei.ma@intel.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).