diff mbox series

[v9,07/21] i386/cpu: Use APIC ID info get NumSharingCache for CPUID[0x8000001D].EAX[bits 25:14]

Message ID 20240227103231.1556302-8-zhao1.liu@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series Introduce smp.modules for x86 in QEMU | expand

Commit Message

Zhao Liu Feb. 27, 2024, 10:32 a.m. UTC
From: Zhao Liu <zhao1.liu@intel.com>

The commit 8f4202fb1080 ("i386: Populate AMD Processor Cache Information
for cpuid 0x8000001D") adds the cache topology for AMD CPU by encoding
the number of sharing threads directly.

From AMD's APM, NumSharingCache (CPUID[0x8000001D].EAX[bits 25:14])
means [1]:

The number of logical processors sharing this cache is the value of
this field incremented by 1. To determine which logical processors are
sharing a cache, determine a Share Id for each processor as follows:

ShareId = LocalApicId >> log2(NumSharingCache+1)

Logical processors with the same ShareId then share a cache. If
NumSharingCache+1 is not a power of two, round it up to the next power
of two.

From the description above, the calculation of this field should be same
as CPUID[4].EAX[bits 25:14] for Intel CPUs. So also use the offsets of
APIC ID to calculate this field.

[1]: APM, vol.3, appendix.E.4.15 Function 8000_001Dh--Cache Topology
     Information

Cc: Babu Moger <babu.moger@amd.com>
Tested-by: Yongwei Ma <yongwei.ma@intel.com>
Signed-off-by: Zhao Liu <zhao1.liu@intel.com>
---
Changes since v7:
 * Moved this patch after CPUID[4]'s similar change ("i386/cpu: Use APIC
   ID offset to encode cache topo in CPUID[4]"). (Xiaoyao)
 * Dropped Michael/Babu's Acked/Reviewed/Tested tags since the code
   change due to the rebase.
 * Re-added Yongwei's Tested tag For his re-testing (compilation on
   Intel platforms).

Changes since v3:
 * Rewrote the subject. (Babu)
 * Deleted the original "comment/help" expression, as this behavior is
   confirmed for AMD CPUs. (Babu)
 * Renamed "num_apic_ids" (v3) to "num_sharing_cache" to match spec
   definition. (Babu)

Changes since v1:
 * Renamed "l3_threads" to "num_apic_ids" in
   encode_cache_cpuid8000001d(). (Yanan)
 * Added the description of the original commit and add Cc.
---
 target/i386/cpu.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

Comments

Babu Moger Feb. 29, 2024, 3:13 p.m. UTC | #1
On 2/27/24 04:32, Zhao Liu wrote:
> From: Zhao Liu <zhao1.liu@intel.com>
> 
> The commit 8f4202fb1080 ("i386: Populate AMD Processor Cache Information
> for cpuid 0x8000001D") adds the cache topology for AMD CPU by encoding
> the number of sharing threads directly.
> 
> From AMD's APM, NumSharingCache (CPUID[0x8000001D].EAX[bits 25:14])
> means [1]:
> 
> The number of logical processors sharing this cache is the value of
> this field incremented by 1. To determine which logical processors are
> sharing a cache, determine a Share Id for each processor as follows:
> 
> ShareId = LocalApicId >> log2(NumSharingCache+1)
> 
> Logical processors with the same ShareId then share a cache. If
> NumSharingCache+1 is not a power of two, round it up to the next power
> of two.
> 
> From the description above, the calculation of this field should be same
> as CPUID[4].EAX[bits 25:14] for Intel CPUs. So also use the offsets of
> APIC ID to calculate this field.
> 
> [1]: APM, vol.3, appendix.E.4.15 Function 8000_001Dh--Cache Topology
>      Information
> 
> Cc: Babu Moger <babu.moger@amd.com>
> Tested-by: Yongwei Ma <yongwei.ma@intel.com>
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>


Reviewed-by: Babu Moger <babu.moger@amd.com>

> ---
> Changes since v7:
>  * Moved this patch after CPUID[4]'s similar change ("i386/cpu: Use APIC
>    ID offset to encode cache topo in CPUID[4]"). (Xiaoyao)
>  * Dropped Michael/Babu's Acked/Reviewed/Tested tags since the code
>    change due to the rebase.
>  * Re-added Yongwei's Tested tag For his re-testing (compilation on
>    Intel platforms).
> 
> Changes since v3:
>  * Rewrote the subject. (Babu)
>  * Deleted the original "comment/help" expression, as this behavior is
>    confirmed for AMD CPUs. (Babu)
>  * Renamed "num_apic_ids" (v3) to "num_sharing_cache" to match spec
>    definition. (Babu)
> 
> Changes since v1:
>  * Renamed "l3_threads" to "num_apic_ids" in
>    encode_cache_cpuid8000001d(). (Yanan)
>  * Added the description of the original commit and add Cc.
> ---
>  target/i386/cpu.c | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> index c77bcbc44d59..df56c7a449c8 100644
> --- a/target/i386/cpu.c
> +++ b/target/i386/cpu.c
> @@ -331,7 +331,7 @@ static void encode_cache_cpuid8000001d(CPUCacheInfo *cache,
>                                         uint32_t *eax, uint32_t *ebx,
>                                         uint32_t *ecx, uint32_t *edx)
>  {
> -    uint32_t l3_threads;
> +    uint32_t num_sharing_cache;
>      assert(cache->size == cache->line_size * cache->associativity *
>                            cache->partitions * cache->sets);
>  
> @@ -340,11 +340,11 @@ 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;
> -        *eax |= (l3_threads - 1) << 14;
> +        num_sharing_cache = 1 << apicid_die_offset(topo_info);
>      } else {
> -        *eax |= ((topo_info->threads_per_core - 1) << 14);
> +        num_sharing_cache = 1 << apicid_core_offset(topo_info);
>      }
> +    *eax |= (num_sharing_cache - 1) << 14;
>  
>      assert(cache->line_size > 0);
>      assert(cache->partitions > 0);
Xiaoyao Li March 9, 2024, 1:41 p.m. UTC | #2
On 2/27/2024 6:32 PM, Zhao Liu wrote:
> From: Zhao Liu <zhao1.liu@intel.com>
> 
> The commit 8f4202fb1080 ("i386: Populate AMD Processor Cache Information
> for cpuid 0x8000001D") adds the cache topology for AMD CPU by encoding
> the number of sharing threads directly.
> 
>  From AMD's APM, NumSharingCache (CPUID[0x8000001D].EAX[bits 25:14])
> means [1]:
> 
> The number of logical processors sharing this cache is the value of
> this field incremented by 1. To determine which logical processors are
> sharing a cache, determine a Share Id for each processor as follows:
> 
> ShareId = LocalApicId >> log2(NumSharingCache+1)
> 
> Logical processors with the same ShareId then share a cache. If
> NumSharingCache+1 is not a power of two, round it up to the next power
> of two.
> 
>  From the description above, the calculation of this field should be same
> as CPUID[4].EAX[bits 25:14] for Intel CPUs. So also use the offsets of
> APIC ID to calculate this field.
> 
> [1]: APM, vol.3, appendix.E.4.15 Function 8000_001Dh--Cache Topology
>       Information
> 
> Cc: Babu Moger <babu.moger@amd.com>
> Tested-by: Yongwei Ma <yongwei.ma@intel.com>
> Signed-off-by: Zhao Liu <zhao1.liu@intel.com>

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

> ---
> Changes since v7:
>   * Moved this patch after CPUID[4]'s similar change ("i386/cpu: Use APIC
>     ID offset to encode cache topo in CPUID[4]"). (Xiaoyao)
>   * Dropped Michael/Babu's Acked/Reviewed/Tested tags since the code
>     change due to the rebase.
>   * Re-added Yongwei's Tested tag For his re-testing (compilation on
>     Intel platforms).
> 
> Changes since v3:
>   * Rewrote the subject. (Babu)
>   * Deleted the original "comment/help" expression, as this behavior is
>     confirmed for AMD CPUs. (Babu)
>   * Renamed "num_apic_ids" (v3) to "num_sharing_cache" to match spec
>     definition. (Babu)
> 
> Changes since v1:
>   * Renamed "l3_threads" to "num_apic_ids" in
>     encode_cache_cpuid8000001d(). (Yanan)
>   * Added the description of the original commit and add Cc.
> ---
>   target/i386/cpu.c | 8 ++++----
>   1 file changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/target/i386/cpu.c b/target/i386/cpu.c
> index c77bcbc44d59..df56c7a449c8 100644
> --- a/target/i386/cpu.c
> +++ b/target/i386/cpu.c
> @@ -331,7 +331,7 @@ static void encode_cache_cpuid8000001d(CPUCacheInfo *cache,
>                                          uint32_t *eax, uint32_t *ebx,
>                                          uint32_t *ecx, uint32_t *edx)
>   {
> -    uint32_t l3_threads;
> +    uint32_t num_sharing_cache;
>       assert(cache->size == cache->line_size * cache->associativity *
>                             cache->partitions * cache->sets);
>   
> @@ -340,11 +340,11 @@ 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;
> -        *eax |= (l3_threads - 1) << 14;
> +        num_sharing_cache = 1 << apicid_die_offset(topo_info);
>       } else {
> -        *eax |= ((topo_info->threads_per_core - 1) << 14);
> +        num_sharing_cache = 1 << apicid_core_offset(topo_info);
>       }
> +    *eax |= (num_sharing_cache - 1) << 14;
>   
>       assert(cache->line_size > 0);
>       assert(cache->partitions > 0);
diff mbox series

Patch

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index c77bcbc44d59..df56c7a449c8 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -331,7 +331,7 @@  static void encode_cache_cpuid8000001d(CPUCacheInfo *cache,
                                        uint32_t *eax, uint32_t *ebx,
                                        uint32_t *ecx, uint32_t *edx)
 {
-    uint32_t l3_threads;
+    uint32_t num_sharing_cache;
     assert(cache->size == cache->line_size * cache->associativity *
                           cache->partitions * cache->sets);
 
@@ -340,11 +340,11 @@  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;
-        *eax |= (l3_threads - 1) << 14;
+        num_sharing_cache = 1 << apicid_die_offset(topo_info);
     } else {
-        *eax |= ((topo_info->threads_per_core - 1) << 14);
+        num_sharing_cache = 1 << apicid_core_offset(topo_info);
     }
+    *eax |= (num_sharing_cache - 1) << 14;
 
     assert(cache->line_size > 0);
     assert(cache->partitions > 0);