From: Zhao Liu <zhao1.liu@intel.com>
To: "Paolo Bonzini" <pbonzini@redhat.com>,
"Marcelo Tosatti" <mtosatti@redhat.com>,
"Michael S . Tsirkin" <mst@redhat.com>,
"Daniel P . Berrangé" <berrange@redhat.com>,
"Igor Mammedov" <imammedo@redhat.com>,
"Marcel Apfelbaum" <marcel.apfelbaum@gmail.com>,
"Richard Henderson" <richard.henderson@linaro.org>,
"Eduardo Habkost" <eduardo@habkost.net>
Cc: "Philippe Mathieu-Daudé" <philmd@linaro.org>,
"Babu Moger" <babu.moger@amd.com>,
"Ewan Hai" <ewanhai-oc@zhaoxin.com>, "Pu Wen" <puwen@hygon.cn>,
"Tao Su" <tao1.su@intel.com>, "Yi Lai" <yi1.lai@intel.com>,
"Dapeng Mi" <dapeng1.mi@intel.com>,
qemu-devel@nongnu.org, kvm@vger.kernel.org,
"Zhao Liu" <zhao1.liu@intel.com>
Subject: [PATCH 13/16] i386/cpu: Select legacy cache model based on vendor in CPUID 0x80000005
Date: Fri, 20 Jun 2025 17:27:31 +0800 [thread overview]
Message-ID: <20250620092734.1576677-14-zhao1.liu@intel.com> (raw)
In-Reply-To: <20250620092734.1576677-1-zhao1.liu@intel.com>
As preparation for merging cache_info_cpuid4 and cache_info_amd in
X86CPUState, set legacy cache model based on vendor in the CPUID
0x80000005 leaf. For AMD CPU, select legacy AMD cache model (in
cache_info_amd) as the default cache model like before, otherwise,
select legacy Intel cache model (in cache_info_cpuid4).
To ensure compatibility is not broken, add an enable_legacy_vendor_cache
flag based on x-vendor-only-v2 to indicate cases where the legacy cache
model should be used regardless of the vendor. For CPUID 0x80000005
leaf, enable_legacy_vendor_cache flag indicates to pick legacy AMD cache
model, which is for compatibility with the behavior of PC machine v10.0
and older.
The following explains how current vendor-based default legacy cache
model ensures correctness without breaking compatibility.
* For the PC machine v6.0 and older, vendor_cpuid_only=false, and
vendor_cpuid_only_v2=false.
- If the named CPU model has its own cache model, and doesn't use
legacy cache model (legacy_cache=false), then cache_info_cpuid4 and
cache_info_amd are same, so 0x80000005 leaf uses its own cache model
regardless of the vendor.
- For max/host/named CPU (without its own cache model), then the flag
enable_legacy_vendor_cache is true, they will use legacy AMD cache
model just like their previous behavior.
* For the PC machine v10.0 and older (to v6.1), vendor_cpuid_only=true,
and vendor_cpuid_only_v2=false.
- No change, since this leaf doesn't aware vendor_cpuid_only.
* For the PC machine v10.1 and newer, vendor_cpuid_only=true, and
vendor_cpuid_only_v2=true.
- If the named CPU model has its own cache model (legacy_cache=false),
then cache_info_cpuid4 & cache_info_amd both equal to its own cache
model, so it uses its own cache model in 0x80000005 leaf regardless
of the vendor. Only Intel CPUs have all-0 leaf due to
vendor_cpuid_only_2=true, and this is exactly the expected behavior.
- For max/host/named CPU (without its own cache model), then the flag
enable_legacy_vendor_cache is false, the legacy cache model is
selected based on vendor.
For AMD CPU, it will use legacy AMD cache as expected.
For Intel CPU, it will use legacy Intel cache but still get all-0
leaf due to vendor_cpuid_only_2=true as expected.
(Note) And for Zhaoxin CPU, it will use legacy Intel cache model
instead of AMD's. This is the difference brought by this change! But
it's correct since then Zhaoxin could have the consistent cache info
in CPUID 0x2, 0x4 and 0x80000005 leaves.
Here, except Zhaoxin, selecting the legacy cache model based on the
vendor does not change the previous (before the change) behavior.
And the change for Zhaoxin is also a good improvement.
Therefore, the above analysis proves that, with the help of the flag
enable_legacy_vendor_cache, it is acceptable to select the default
legacy cache model based on the vendor.
For the CPUID 0x80000005 leaf, in X86CPUState, a unified cache_info is
enough. It only needs to be initialized and configured with the
corresponding legacy cache model based on the vendor.
Cc: EwanHai <ewanhai-oc@zhaoxin.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
Note, side effect of this patch: fix the inconsistency cache info for
Zhaoxin. For more details, see the commit message above.
---
target/i386/cpu.c | 36 ++++++++++++++++++++++++++++++++----
1 file changed, 32 insertions(+), 4 deletions(-)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index afbf11569ab4..16b4ecb76113 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -7945,8 +7945,35 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
*ecx = env->cpuid_model[(index - 0x80000002) * 4 + 2];
*edx = env->cpuid_model[(index - 0x80000002) * 4 + 3];
break;
- case 0x80000005:
- /* cache info (L1 cache/TLB Associativity Field) */
+ case 0x80000005: { /* cache info (L1 cache/TLB Associativity Field) */
+ const CPUCaches *caches;
+
+ if (env->enable_legacy_vendor_cache) {
+ caches = &legacy_amd_cache_info;
+ } else {
+ /*
+ * FIXME: Temporarily select cache info model here based on
+ * vendor, and merge these 2 cache info models later.
+ *
+ * This condition covers the following cases (with
+ * enable_legacy_vendor_cache=false):
+ * - When CPU model has its own cache model and doesn't uses legacy
+ * cache model (legacy_model=off). Then cache_info_amd and
+ * cache_info_cpuid4 are the same.
+ *
+ * - For v10.1 and newer machines, when CPU model uses legacy cache
+ * model. AMD CPUs use cache_info_amd like before and non-AMD
+ * CPU will use cache_info_cpuid4. But this doesn't matter,
+ * because for Intel CPU, it will get all-0 leaf, and Zhaoxin CPU
+ * will get correct cache info. Both are expected.
+ */
+ if (IS_AMD_CPU(env)) {
+ caches = &env->cache_info_amd;
+ } else {
+ caches = &env->cache_info_cpuid4;
+ }
+ }
+
if (cpu->cache_info_passthrough) {
x86_cpu_get_cache_cpuid(index, 0, eax, ebx, ecx, edx);
break;
@@ -7961,9 +7988,10 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
(L1_ITLB_2M_ASSOC << 8) | (L1_ITLB_2M_ENTRIES);
*ebx = (L1_DTLB_4K_ASSOC << 24) | (L1_DTLB_4K_ENTRIES << 16) |
(L1_ITLB_4K_ASSOC << 8) | (L1_ITLB_4K_ENTRIES);
- *ecx = encode_cache_cpuid80000005(env->cache_info_amd.l1d_cache);
- *edx = encode_cache_cpuid80000005(env->cache_info_amd.l1i_cache);
+ *ecx = encode_cache_cpuid80000005(caches->l1d_cache);
+ *edx = encode_cache_cpuid80000005(caches->l1i_cache);
break;
+ }
case 0x80000006:
/* cache info (L2 cache/TLB/L3 cache) */
if (cpu->cache_info_passthrough) {
--
2.34.1
next prev parent reply other threads:[~2025-06-20 9:10 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-20 9:27 [PATCH 00/16] i386/cpu: Unify the cache model in X86CPUState Zhao Liu
2025-06-20 9:27 ` [PATCH 01/16] i386/cpu: Refine comment of CPUID2CacheDescriptorInfo Zhao Liu
2025-07-02 8:48 ` Mi, Dapeng
2025-07-03 7:38 ` Zhao Liu
2025-06-20 9:27 ` [PATCH 02/16] i386/cpu: Add descriptor 0x49 for CPUID 0x2 encoding Zhao Liu
2025-07-02 9:04 ` Mi, Dapeng
2025-07-03 7:39 ` Zhao Liu
2025-06-20 9:27 ` [PATCH 03/16] i386/cpu: Add default cache model for Intel CPUs with level < 4 Zhao Liu
2025-07-02 9:53 ` Mi, Dapeng
2025-07-03 7:47 ` Zhao Liu
2025-06-20 9:27 ` [PATCH 04/16] i386/cpu: Present same cache model in CPUID 0x2 & 0x4 Zhao Liu
2025-07-03 4:14 ` Mi, Dapeng
2025-07-03 6:35 ` Mi, Dapeng
2025-06-20 9:27 ` [PATCH 05/16] i386/cpu: Consolidate CPUID 0x4 leaf Zhao Liu
2025-06-26 12:10 ` Ewan Hai
2025-06-27 2:44 ` Zhao Liu
2025-07-03 6:41 ` Mi, Dapeng
2025-06-20 9:27 ` [PATCH 06/16] i386/cpu: Drop CPUID 0x2 specific cache info in X86CPUState Zhao Liu
2025-07-03 7:03 ` Mi, Dapeng
2025-06-20 9:27 ` [PATCH 07/16] i386/cpu: Mark CPUID[0x80000005] as reserved for Intel Zhao Liu
2025-07-03 7:07 ` Mi, Dapeng
2025-06-20 9:27 ` [PATCH 08/16] i386/cpu: Fix CPUID[0x80000006] for Intel CPU Zhao Liu
2025-07-03 7:09 ` Mi, Dapeng
2025-07-03 7:52 ` Zhao Liu
2025-06-20 9:27 ` [PATCH 09/16] i386/cpu: Add legacy_intel_cache_info cache model Zhao Liu
2025-07-03 7:15 ` Mi, Dapeng
2025-06-20 9:27 ` [PATCH 10/16] i386/cpu: Add legacy_amd_cache_info " Zhao Liu
2025-07-03 7:18 ` Mi, Dapeng
2025-06-20 9:27 ` [PATCH 11/16] i386/cpu: Select legacy cache model based on vendor in CPUID 0x2 Zhao Liu
2025-07-03 8:47 ` Mi, Dapeng
2025-06-20 9:27 ` [PATCH 12/16] i386/cpu: Select legacy cache model based on vendor in CPUID 0x4 Zhao Liu
2025-07-03 8:49 ` Mi, Dapeng
2025-06-20 9:27 ` Zhao Liu [this message]
2025-07-03 8:52 ` [PATCH 13/16] i386/cpu: Select legacy cache model based on vendor in CPUID 0x80000005 Mi, Dapeng
2025-06-20 9:27 ` [PATCH 14/16] i386/cpu: Select legacy cache model based on vendor in CPUID 0x80000006 Zhao Liu
2025-06-20 9:27 ` [PATCH 15/16] i386/cpu: Select legacy cache model based on vendor in CPUID 0x8000001D Zhao Liu
2025-06-20 9:27 ` [PATCH 16/16] i386/cpu: Use a unified cache_info in X86CPUState Zhao Liu
2025-07-03 8:53 ` Mi, Dapeng
2025-07-03 9:50 ` 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=20250620092734.1576677-14-zhao1.liu@intel.com \
--to=zhao1.liu@intel.com \
--cc=babu.moger@amd.com \
--cc=berrange@redhat.com \
--cc=dapeng1.mi@intel.com \
--cc=eduardo@habkost.net \
--cc=ewanhai-oc@zhaoxin.com \
--cc=imammedo@redhat.com \
--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=puwen@hygon.cn \
--cc=qemu-devel@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=tao1.su@intel.com \
--cc=yi1.lai@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).