From: "Mi, Dapeng" <dapeng1.mi@linux.intel.com>
To: "Zhao Liu" <zhao1.liu@intel.com>,
"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
Subject: Re: [PATCH 05/16] i386/cpu: Consolidate CPUID 0x4 leaf
Date: Thu, 3 Jul 2025 14:41:40 +0800 [thread overview]
Message-ID: <1318c33d-9733-4541-b9f8-691a5dc2586e@linux.intel.com> (raw)
In-Reply-To: <20250620092734.1576677-6-zhao1.liu@intel.com>
On 6/20/2025 5:27 PM, Zhao Liu wrote:
> Modern Intel CPUs use CPUID 0x4 leaf to describe cache information
> and leave space in 0x2 for prefetch and TLBs (even TLB has its own leaf
> CPUID 0x18).
>
> And 0x2 leaf provides a descriptor 0xFF to instruct software to check
> cache information in 0x4 leaf instead.
>
> Therefore, follow this behavior to encode 0xFF when Intel CPU has 0x4
> leaf with "x-consistent-cache=true" for compatibility.
>
> In addition, for older CPUs without 0x4 leaf, still enumerate the cache
> descriptor in 0x2 leaf, except the case that there's no descriptor
> matching the cache model, then directly encode 0xFF in 0x2 leaf. This
> makes sense, as in the 0x2 leaf era, all supported caches should have
> the corresponding descriptor.
>
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
> ---
> target/i386/cpu.c | 48 ++++++++++++++++++++++++++++++++++++-----------
> 1 file changed, 37 insertions(+), 11 deletions(-)
>
> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> index 2f895bf13523..a06aa1d629dc 100644
> --- a/target/i386/cpu.c
> +++ b/target/i386/cpu.c
> @@ -223,7 +223,7 @@ struct CPUID2CacheDescriptorInfo cpuid2_cache_descriptors[] = {
> * Return a CPUID 2 cache descriptor for a given cache.
> * If no known descriptor is found, return CACHE_DESCRIPTOR_UNAVAILABLE
> */
> -static uint8_t cpuid2_cache_descriptor(CPUCacheInfo *cache)
> +static uint8_t cpuid2_cache_descriptor(CPUCacheInfo *cache, bool *unmacthed)
> {
> int i;
>
> @@ -240,9 +240,44 @@ static uint8_t cpuid2_cache_descriptor(CPUCacheInfo *cache)
> }
> }
>
> + *unmacthed |= true;
> return CACHE_DESCRIPTOR_UNAVAILABLE;
> }
>
> +/* Encode cache info for CPUID[4] */
> +static void encode_cache_cpuid2(X86CPU *cpu,
> + uint32_t *eax, uint32_t *ebx,
> + uint32_t *ecx, uint32_t *edx)
> +{
> + CPUX86State *env = &cpu->env;
> + CPUCaches *caches = &env->cache_info_cpuid2;
> + int l1d, l1i, l2, l3;
> + bool unmatched = false;
> +
> + *eax = 1; /* Number of CPUID[EAX=2] calls required */
> + *ebx = *ecx = *edx = 0;
> +
> + l1d = cpuid2_cache_descriptor(caches->l1d_cache, &unmatched);
> + l1i = cpuid2_cache_descriptor(caches->l1i_cache, &unmatched);
> + l2 = cpuid2_cache_descriptor(caches->l2_cache, &unmatched);
> + l3 = cpuid2_cache_descriptor(caches->l3_cache, &unmatched);
> +
> + if (!cpu->consistent_cache ||
> + (env->cpuid_min_level < 0x4 && !unmatched)) {
> + /*
> + * Though SDM defines code 0x40 for cases with no L2 or L3. It's
> + * also valid to just ignore l3's code if there's no l2.
> + */
> + if (cpu->enable_l3_cache) {
> + *ecx = l3;
> + }
> + *edx = (l1d << 16) | (l1i << 8) | l2;
> + } else {
> + *ecx = 0;
> + *edx = CACHE_DESCRIPTOR_UNAVAILABLE;
> + }
> +}
> +
> /* CPUID Leaf 4 constants: */
>
> /* EAX: */
> @@ -7451,16 +7486,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
> *eax = *ebx = *ecx = *edx = 0;
> break;
> }
> - *eax = 1; /* Number of CPUID[EAX=2] calls required */
> - *ebx = 0;
> - if (!cpu->enable_l3_cache) {
> - *ecx = 0;
> - } else {
> - *ecx = cpuid2_cache_descriptor(env->cache_info_cpuid2.l3_cache);
> - }
> - *edx = (cpuid2_cache_descriptor(env->cache_info_cpuid2.l1d_cache) << 16) |
> - (cpuid2_cache_descriptor(env->cache_info_cpuid2.l1i_cache) << 8) |
> - (cpuid2_cache_descriptor(env->cache_info_cpuid2.l2_cache));
> + encode_cache_cpuid2(cpu, eax, ebx, ecx, edx);
> break;
> case 4:
> /* cache info: needed for Core compatibility */
LGTM.
Reviewed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
next prev parent reply other threads:[~2025-07-03 6:42 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 [this message]
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 ` [PATCH 13/16] i386/cpu: Select legacy cache model based on vendor in CPUID 0x80000005 Zhao Liu
2025-07-03 8:52 ` 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=1318c33d-9733-4541-b9f8-691a5dc2586e@linux.intel.com \
--to=dapeng1.mi@linux.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 \
--cc=zhao1.liu@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).