diff mbox series

[v7,03/16] i386/cpu: Consolidate the use of topo_info in cpu_x86_cpuid()

Message ID 20240108082727.420817-4-zhao1.liu@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series Support smp.clusters for x86 in QEMU | expand

Commit Message

Zhao Liu Jan. 8, 2024, 8:27 a.m. UTC
From: Zhao Liu <zhao1.liu@intel.com>

In cpu_x86_cpuid(), there are many variables in representing the cpu
topology, e.g., topo_info, cs->nr_cores/cs->nr_threads.

Since the names of cs->nr_cores/cs->nr_threads does not accurately
represent its meaning, the use of cs->nr_cores/cs->nr_threads is prone
to confusion and mistakes.

And the structure X86CPUTopoInfo names its members clearly, thus the
variable "topo_info" should be preferred.

In addition, in cpu_x86_cpuid(), to uniformly use the topology variable,
replace env->dies with topo_info.dies_per_pkg as well.

Suggested-by: Robert Hoo <robert.hu@linux.intel.com>
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:
 * Fix typo. (Babu)

Changes since v1:
 * Extract cores_per_socket from the code block and use it as a local
   variable for cpu_x86_cpuid(). (Yanan)
 * Remove vcpus_per_socket variable and use cpus_per_pkg directly.
   (Yanan)
 * Replace env->dies with topo_info.dies_per_pkg in cpu_x86_cpuid().
---
 target/i386/cpu.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

Comments

Xiaoyao Li Jan. 10, 2024, 11:52 a.m. UTC | #1
On 1/8/2024 4:27 PM, Zhao Liu wrote:
> From: Zhao Liu <zhao1.liu@intel.com>
> 
> In cpu_x86_cpuid(), there are many variables in representing the cpu
> topology, e.g., topo_info, cs->nr_cores/cs->nr_threads.

Please use comma instead of slash. cs->nr_cores/cs->nr_threads looks 
like one variable.

> Since the names of cs->nr_cores/cs->nr_threads does not accurately
> represent its meaning, the use of cs->nr_cores/cs->nr_threads is prone
> to confusion and mistakes.
> 
> And the structure X86CPUTopoInfo names its members clearly, thus the
> variable "topo_info" should be preferred.
> 
> In addition, in cpu_x86_cpuid(), to uniformly use the topology variable,
> replace env->dies with topo_info.dies_per_pkg as well.
> 
> Suggested-by: Robert Hoo <robert.hu@linux.intel.com>
> 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:
>   * Fix typo. (Babu)
> 
> Changes since v1:
>   * Extract cores_per_socket from the code block and use it as a local
>     variable for cpu_x86_cpuid(). (Yanan)
>   * Remove vcpus_per_socket variable and use cpus_per_pkg directly.
>     (Yanan)
>   * Replace env->dies with topo_info.dies_per_pkg in cpu_x86_cpuid().
> ---
>   target/i386/cpu.c | 31 ++++++++++++++++++-------------
>   1 file changed, 18 insertions(+), 13 deletions(-)
> 
> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> index c8d2a585723a..6f8fa772ecf8 100644
> --- a/target/i386/cpu.c
> +++ b/target/i386/cpu.c
> @@ -6017,11 +6017,16 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>       uint32_t limit;
>       uint32_t signature[3];
>       X86CPUTopoInfo topo_info;
> +    uint32_t cores_per_pkg;
> +    uint32_t cpus_per_pkg;

I prefer to lps_per_pkg or threads_per_pkg.

Other than it,

Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>

>   
>       topo_info.dies_per_pkg = env->nr_dies;
>       topo_info.cores_per_die = cs->nr_cores / env->nr_dies;
>       topo_info.threads_per_core = cs->nr_threads;
>   
> +    cores_per_pkg = topo_info.cores_per_die * topo_info.dies_per_pkg;
> +    cpus_per_pkg = cores_per_pkg * topo_info.threads_per_core;
> +
>       /* Calculate & apply limits for different index ranges */
>       if (index >= 0xC0000000) {
>           limit = env->cpuid_xlevel2;
> @@ -6057,8 +6062,8 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>               *ecx |= CPUID_EXT_OSXSAVE;
>           }
>           *edx = env->features[FEAT_1_EDX];
> -        if (cs->nr_cores * cs->nr_threads > 1) {
> -            *ebx |= (cs->nr_cores * cs->nr_threads) << 16;
> +        if (cpus_per_pkg > 1) {
> +            *ebx |= cpus_per_pkg << 16;
>               *edx |= CPUID_HT;
>           }
>           if (!cpu->enable_pmu) {
> @@ -6095,8 +6100,8 @@ 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 = cs->nr_cores * cs->nr_threads;
> -                if (cs->nr_cores > 1) {
> +
> +                if (cores_per_pkg > 1) {
>                       int addressable_cores_offset =
>                                                   apicid_pkg_offset(&topo_info) -
>                                                   apicid_core_offset(&topo_info);
> @@ -6104,7 +6109,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>                       *eax &= ~0xFC000000;
>                       *eax |= (1 << (addressable_cores_offset - 1)) << 26;
>                   }
> -                if (host_vcpus_per_cache > vcpus_per_socket) {
> +                if (host_vcpus_per_cache > cpus_per_pkg) {
>                       int pkg_offset = apicid_pkg_offset(&topo_info);
>   
>                       *eax &= ~0x3FFC000;
> @@ -6249,12 +6254,12 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>           switch (count) {
>           case 0:
>               *eax = apicid_core_offset(&topo_info);
> -            *ebx = cs->nr_threads;
> +            *ebx = topo_info.threads_per_core;
>               *ecx |= CPUID_TOPOLOGY_LEVEL_SMT;
>               break;
>           case 1:
>               *eax = apicid_pkg_offset(&topo_info);
> -            *ebx = cs->nr_cores * cs->nr_threads;
> +            *ebx = cpus_per_pkg;
>               *ecx |= CPUID_TOPOLOGY_LEVEL_CORE;
>               break;
>           default:
> @@ -6274,7 +6279,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>           break;
>       case 0x1F:
>           /* V2 Extended Topology Enumeration Leaf */
> -        if (env->nr_dies < 2) {
> +        if (topo_info.dies_per_pkg < 2) {
>               *eax = *ebx = *ecx = *edx = 0;
>               break;
>           }
> @@ -6284,7 +6289,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>           switch (count) {
>           case 0:
>               *eax = apicid_core_offset(&topo_info);
> -            *ebx = cs->nr_threads;
> +            *ebx = topo_info.threads_per_core;
>               *ecx |= CPUID_TOPOLOGY_LEVEL_SMT;
>               break;
>           case 1:
> @@ -6294,7 +6299,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>               break;
>           case 2:
>               *eax = apicid_pkg_offset(&topo_info);
> -            *ebx = cs->nr_cores * cs->nr_threads;
> +            *ebx = cpus_per_pkg;
>               *ecx |= CPUID_TOPOLOGY_LEVEL_DIE;
>               break;
>           default:
> @@ -6518,7 +6523,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>            * discards multiple thread information if it is set.
>            * So don't set it here for Intel to make Linux guests happy.
>            */
> -        if (cs->nr_cores * cs->nr_threads > 1) {
> +        if (cpus_per_pkg > 1) {
>               if (env->cpuid_vendor1 != CPUID_VENDOR_INTEL_1 ||
>                   env->cpuid_vendor2 != CPUID_VENDOR_INTEL_2 ||
>                   env->cpuid_vendor3 != CPUID_VENDOR_INTEL_3) {
> @@ -6584,7 +6589,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>                *eax |= (cpu_x86_virtual_addr_width(env) << 8);
>           }
>           *ebx = env->features[FEAT_8000_0008_EBX];
> -        if (cs->nr_cores * cs->nr_threads > 1) {
> +        if (cpus_per_pkg > 1) {
>               /*
>                * Bits 15:12 is "The number of bits in the initial
>                * Core::X86::Apic::ApicId[ApicId] value that indicate
> @@ -6592,7 +6597,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>                * Bits 7:0 is "The number of threads in the package is NC+1"
>                */
>               *ecx = (apicid_pkg_offset(&topo_info) << 12) |
> -                   ((cs->nr_cores * cs->nr_threads) - 1);
> +                   (cpus_per_pkg - 1);
>           } else {
>               *ecx = 0;
>           }
Zhao Liu Jan. 11, 2024, 8:46 a.m. UTC | #2
Hi Xiaoyao,

On Wed, Jan 10, 2024 at 07:52:38PM +0800, Xiaoyao Li wrote:
> Date: Wed, 10 Jan 2024 19:52:38 +0800
> From: Xiaoyao Li <xiaoyao.li@intel.com>
> Subject: Re: [PATCH v7 03/16] i386/cpu: Consolidate the use of topo_info in
>  cpu_x86_cpuid()
> 
> On 1/8/2024 4:27 PM, Zhao Liu wrote:
> > From: Zhao Liu <zhao1.liu@intel.com>
> > 
> > In cpu_x86_cpuid(), there are many variables in representing the cpu
> > topology, e.g., topo_info, cs->nr_cores/cs->nr_threads.
> 
> Please use comma instead of slash. cs->nr_cores/cs->nr_threads looks like
> one variable.

Okay.

> 
> > Since the names of cs->nr_cores/cs->nr_threads does not accurately
> > represent its meaning, the use of cs->nr_cores/cs->nr_threads is prone
> > to confusion and mistakes.
> > 
> > And the structure X86CPUTopoInfo names its members clearly, thus the
> > variable "topo_info" should be preferred.
> > 
> > In addition, in cpu_x86_cpuid(), to uniformly use the topology variable,
> > replace env->dies with topo_info.dies_per_pkg as well.
> > 
> > Suggested-by: Robert Hoo <robert.hu@linux.intel.com>
> > 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:
> >   * Fix typo. (Babu)
> > 
> > Changes since v1:
> >   * Extract cores_per_socket from the code block and use it as a local
> >     variable for cpu_x86_cpuid(). (Yanan)
> >   * Remove vcpus_per_socket variable and use cpus_per_pkg directly.
> >     (Yanan)
> >   * Replace env->dies with topo_info.dies_per_pkg in cpu_x86_cpuid().
> > ---
> >   target/i386/cpu.c | 31 ++++++++++++++++++-------------
> >   1 file changed, 18 insertions(+), 13 deletions(-)
> > 
> > diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> > index c8d2a585723a..6f8fa772ecf8 100644
> > --- a/target/i386/cpu.c
> > +++ b/target/i386/cpu.c
> > @@ -6017,11 +6017,16 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
> >       uint32_t limit;
> >       uint32_t signature[3];
> >       X86CPUTopoInfo topo_info;
> > +    uint32_t cores_per_pkg;
> > +    uint32_t cpus_per_pkg;
> 
> I prefer to lps_per_pkg or threads_per_pkg.

Okay, lp is not common in QEMU code, so I would change this to
threads_per_pkg.

> 
> Other than it,
> 
> Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>

Thanks!

-Zhao
diff mbox series

Patch

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index c8d2a585723a..6f8fa772ecf8 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -6017,11 +6017,16 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
     uint32_t limit;
     uint32_t signature[3];
     X86CPUTopoInfo topo_info;
+    uint32_t cores_per_pkg;
+    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.threads_per_core = cs->nr_threads;
 
+    cores_per_pkg = topo_info.cores_per_die * topo_info.dies_per_pkg;
+    cpus_per_pkg = cores_per_pkg * topo_info.threads_per_core;
+
     /* Calculate & apply limits for different index ranges */
     if (index >= 0xC0000000) {
         limit = env->cpuid_xlevel2;
@@ -6057,8 +6062,8 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             *ecx |= CPUID_EXT_OSXSAVE;
         }
         *edx = env->features[FEAT_1_EDX];
-        if (cs->nr_cores * cs->nr_threads > 1) {
-            *ebx |= (cs->nr_cores * cs->nr_threads) << 16;
+        if (cpus_per_pkg > 1) {
+            *ebx |= cpus_per_pkg << 16;
             *edx |= CPUID_HT;
         }
         if (!cpu->enable_pmu) {
@@ -6095,8 +6100,8 @@  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 = cs->nr_cores * cs->nr_threads;
-                if (cs->nr_cores > 1) {
+
+                if (cores_per_pkg > 1) {
                     int addressable_cores_offset =
                                                 apicid_pkg_offset(&topo_info) -
                                                 apicid_core_offset(&topo_info);
@@ -6104,7 +6109,7 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
                     *eax &= ~0xFC000000;
                     *eax |= (1 << (addressable_cores_offset - 1)) << 26;
                 }
-                if (host_vcpus_per_cache > vcpus_per_socket) {
+                if (host_vcpus_per_cache > cpus_per_pkg) {
                     int pkg_offset = apicid_pkg_offset(&topo_info);
 
                     *eax &= ~0x3FFC000;
@@ -6249,12 +6254,12 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         switch (count) {
         case 0:
             *eax = apicid_core_offset(&topo_info);
-            *ebx = cs->nr_threads;
+            *ebx = topo_info.threads_per_core;
             *ecx |= CPUID_TOPOLOGY_LEVEL_SMT;
             break;
         case 1:
             *eax = apicid_pkg_offset(&topo_info);
-            *ebx = cs->nr_cores * cs->nr_threads;
+            *ebx = cpus_per_pkg;
             *ecx |= CPUID_TOPOLOGY_LEVEL_CORE;
             break;
         default:
@@ -6274,7 +6279,7 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         break;
     case 0x1F:
         /* V2 Extended Topology Enumeration Leaf */
-        if (env->nr_dies < 2) {
+        if (topo_info.dies_per_pkg < 2) {
             *eax = *ebx = *ecx = *edx = 0;
             break;
         }
@@ -6284,7 +6289,7 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         switch (count) {
         case 0:
             *eax = apicid_core_offset(&topo_info);
-            *ebx = cs->nr_threads;
+            *ebx = topo_info.threads_per_core;
             *ecx |= CPUID_TOPOLOGY_LEVEL_SMT;
             break;
         case 1:
@@ -6294,7 +6299,7 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
             break;
         case 2:
             *eax = apicid_pkg_offset(&topo_info);
-            *ebx = cs->nr_cores * cs->nr_threads;
+            *ebx = cpus_per_pkg;
             *ecx |= CPUID_TOPOLOGY_LEVEL_DIE;
             break;
         default:
@@ -6518,7 +6523,7 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
          * discards multiple thread information if it is set.
          * So don't set it here for Intel to make Linux guests happy.
          */
-        if (cs->nr_cores * cs->nr_threads > 1) {
+        if (cpus_per_pkg > 1) {
             if (env->cpuid_vendor1 != CPUID_VENDOR_INTEL_1 ||
                 env->cpuid_vendor2 != CPUID_VENDOR_INTEL_2 ||
                 env->cpuid_vendor3 != CPUID_VENDOR_INTEL_3) {
@@ -6584,7 +6589,7 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
              *eax |= (cpu_x86_virtual_addr_width(env) << 8);
         }
         *ebx = env->features[FEAT_8000_0008_EBX];
-        if (cs->nr_cores * cs->nr_threads > 1) {
+        if (cpus_per_pkg > 1) {
             /*
              * Bits 15:12 is "The number of bits in the initial
              * Core::X86::Apic::ApicId[ApicId] value that indicate
@@ -6592,7 +6597,7 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
              * Bits 7:0 is "The number of threads in the package is NC+1"
              */
             *ecx = (apicid_pkg_offset(&topo_info) << 12) |
-                   ((cs->nr_cores * cs->nr_threads) - 1);
+                   (cpus_per_pkg - 1);
         } else {
             *ecx = 0;
         }