[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v11 19/21] i386: Add cache topology info in CPUCacheInfo
|
From: |
Zhao Liu |
|
Subject: |
[PATCH v11 19/21] i386: Add cache topology info in CPUCacheInfo |
|
Date: |
Wed, 24 Apr 2024 23:49:27 +0800 |
Currently, by default, the cache topology is encoded as:
1. i/d cache is shared in one core.
2. L2 cache is shared in one core.
3. L3 cache is shared in one die.
This default general setting has caused a misunderstanding, that is, the
cache topology is completely equated with a specific cpu topology, such
as the connection between L2 cache and core level, and the connection
between L3 cache and die level.
In fact, the settings of these topologies depend on the specific
platform and are not static. For example, on Alder Lake-P, every
four Atom cores share the same L2 cache.
Thus, we should explicitly define the corresponding cache topology for
different cache models to increase scalability.
Except legacy_l2_cache_cpuid2 (its default topo level is
CPU_TOPO_LEVEL_UNKNOW), explicitly set the corresponding topology level
for all other cache models. In order to be compatible with the existing
cache topology, set the CPU_TOPO_LEVEL_CORE level for the i/d cache, set
the CPU_TOPO_LEVEL_CORE level for L2 cache, and set the
CPU_TOPO_LEVEL_DIE level for L3 cache.
The field for CPUID[4].EAX[bits 25:14] or CPUID[0x8000001D].EAX[bits
25:14] will be set based on CPUCacheInfo.share_level.
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:
* Fixed cache topology uninitialization bugs for some AMD CPUs. (Babu)
* Moved the CPUTopoLevel enumeration definition to the previous 0x1f
rework patch.
Changes since v1:
* Added the prefix "CPU_TOPO_LEVEL_*" for CPU topology level names.
(Yanan)
* (Revert, pls refer "i386: Decouple CPUID[0x1F] subleaf with specific
topology level") Renamed the "INVALID" level to CPU_TOPO_LEVEL_UNKNOW.
(Yanan)
---
target/i386/cpu.c | 36 ++++++++++++++++++++++++++++++++++++
target/i386/cpu.h | 7 +++++++
2 files changed, 43 insertions(+)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 76085ec007fa..5ba44c57666d 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -551,6 +551,7 @@ static CPUCacheInfo legacy_l1d_cache = {
.sets = 64,
.partitions = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
};
/*FIXME: CPUID leaf 0x80000005 is inconsistent with leaves 2 & 4 */
@@ -565,6 +566,7 @@ static CPUCacheInfo legacy_l1d_cache_amd = {
.partitions = 1,
.lines_per_tag = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
};
/* L1 instruction cache: */
@@ -578,6 +580,7 @@ static CPUCacheInfo legacy_l1i_cache = {
.sets = 64,
.partitions = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
};
/*FIXME: CPUID leaf 0x80000005 is inconsistent with leaves 2 & 4 */
@@ -592,6 +595,7 @@ static CPUCacheInfo legacy_l1i_cache_amd = {
.partitions = 1,
.lines_per_tag = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
};
/* Level 2 unified cache: */
@@ -605,6 +609,7 @@ static CPUCacheInfo legacy_l2_cache = {
.sets = 4096,
.partitions = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
};
/*FIXME: CPUID leaf 2 descriptor is inconsistent with CPUID leaf 4 */
@@ -614,6 +619,7 @@ static CPUCacheInfo legacy_l2_cache_cpuid2 = {
.size = 2 * MiB,
.line_size = 64,
.associativity = 8,
+ .share_level = CPU_TOPO_LEVEL_INVALID,
};
@@ -627,6 +633,7 @@ static CPUCacheInfo legacy_l2_cache_amd = {
.associativity = 16,
.sets = 512,
.partitions = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
};
/* Level 3 unified cache: */
@@ -642,6 +649,7 @@ static CPUCacheInfo legacy_l3_cache = {
.self_init = true,
.inclusive = true,
.complex_indexing = true,
+ .share_level = CPU_TOPO_LEVEL_DIE,
};
/* TLB definitions: */
@@ -1940,6 +1948,7 @@ static const CPUCaches epyc_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l1i_cache = &(CPUCacheInfo) {
.type = INSTRUCTION_CACHE,
@@ -1952,6 +1961,7 @@ static const CPUCaches epyc_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l2_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -1962,6 +1972,7 @@ static const CPUCaches epyc_cache_info = {
.partitions = 1,
.sets = 1024,
.lines_per_tag = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l3_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -1975,6 +1986,7 @@ static const CPUCaches epyc_cache_info = {
.self_init = true,
.inclusive = true,
.complex_indexing = true,
+ .share_level = CPU_TOPO_LEVEL_DIE,
},
};
@@ -1990,6 +2002,7 @@ static CPUCaches epyc_v4_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l1i_cache = &(CPUCacheInfo) {
.type = INSTRUCTION_CACHE,
@@ -2002,6 +2015,7 @@ static CPUCaches epyc_v4_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l2_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2012,6 +2026,7 @@ static CPUCaches epyc_v4_cache_info = {
.partitions = 1,
.sets = 1024,
.lines_per_tag = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l3_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2025,6 +2040,7 @@ static CPUCaches epyc_v4_cache_info = {
.self_init = true,
.inclusive = true,
.complex_indexing = false,
+ .share_level = CPU_TOPO_LEVEL_DIE,
},
};
@@ -2040,6 +2056,7 @@ static const CPUCaches epyc_rome_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l1i_cache = &(CPUCacheInfo) {
.type = INSTRUCTION_CACHE,
@@ -2052,6 +2069,7 @@ static const CPUCaches epyc_rome_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l2_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2062,6 +2080,7 @@ static const CPUCaches epyc_rome_cache_info = {
.partitions = 1,
.sets = 1024,
.lines_per_tag = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l3_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2075,6 +2094,7 @@ static const CPUCaches epyc_rome_cache_info = {
.self_init = true,
.inclusive = true,
.complex_indexing = true,
+ .share_level = CPU_TOPO_LEVEL_DIE,
},
};
@@ -2090,6 +2110,7 @@ static const CPUCaches epyc_rome_v3_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l1i_cache = &(CPUCacheInfo) {
.type = INSTRUCTION_CACHE,
@@ -2102,6 +2123,7 @@ static const CPUCaches epyc_rome_v3_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l2_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2112,6 +2134,7 @@ static const CPUCaches epyc_rome_v3_cache_info = {
.partitions = 1,
.sets = 1024,
.lines_per_tag = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l3_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2125,6 +2148,7 @@ static const CPUCaches epyc_rome_v3_cache_info = {
.self_init = true,
.inclusive = true,
.complex_indexing = false,
+ .share_level = CPU_TOPO_LEVEL_DIE,
},
};
@@ -2140,6 +2164,7 @@ static const CPUCaches epyc_milan_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l1i_cache = &(CPUCacheInfo) {
.type = INSTRUCTION_CACHE,
@@ -2152,6 +2177,7 @@ static const CPUCaches epyc_milan_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l2_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2162,6 +2188,7 @@ static const CPUCaches epyc_milan_cache_info = {
.partitions = 1,
.sets = 1024,
.lines_per_tag = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l3_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2175,6 +2202,7 @@ static const CPUCaches epyc_milan_cache_info = {
.self_init = true,
.inclusive = true,
.complex_indexing = true,
+ .share_level = CPU_TOPO_LEVEL_DIE,
},
};
@@ -2190,6 +2218,7 @@ static const CPUCaches epyc_milan_v2_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l1i_cache = &(CPUCacheInfo) {
.type = INSTRUCTION_CACHE,
@@ -2202,6 +2231,7 @@ static const CPUCaches epyc_milan_v2_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l2_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2212,6 +2242,7 @@ static const CPUCaches epyc_milan_v2_cache_info = {
.partitions = 1,
.sets = 1024,
.lines_per_tag = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l3_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2225,6 +2256,7 @@ static const CPUCaches epyc_milan_v2_cache_info = {
.self_init = true,
.inclusive = true,
.complex_indexing = false,
+ .share_level = CPU_TOPO_LEVEL_DIE,
},
};
@@ -2240,6 +2272,7 @@ static const CPUCaches epyc_genoa_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l1i_cache = &(CPUCacheInfo) {
.type = INSTRUCTION_CACHE,
@@ -2252,6 +2285,7 @@ static const CPUCaches epyc_genoa_cache_info = {
.lines_per_tag = 1,
.self_init = 1,
.no_invd_sharing = true,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l2_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2262,6 +2296,7 @@ static const CPUCaches epyc_genoa_cache_info = {
.partitions = 1,
.sets = 2048,
.lines_per_tag = 1,
+ .share_level = CPU_TOPO_LEVEL_CORE,
},
.l3_cache = &(CPUCacheInfo) {
.type = UNIFIED_CACHE,
@@ -2275,6 +2310,7 @@ static const CPUCaches epyc_genoa_cache_info = {
.self_init = true,
.inclusive = true,
.complex_indexing = false,
+ .share_level = CPU_TOPO_LEVEL_DIE,
},
};
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 042eec417d0f..a28ba33365b4 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1590,6 +1590,13 @@ typedef struct CPUCacheInfo {
* address bits. CPUID[4].EDX[bit 2].
*/
bool complex_indexing;
+
+ /*
+ * Cache Topology. The level that cache is shared in.
+ * Used to encode CPUID[4].EAX[bits 25:14] or
+ * CPUID[0x8000001D].EAX[bits 25:14].
+ */
+ enum CPUTopoLevel share_level;
} CPUCacheInfo;
--
2.34.1
- [PATCH v11 08/21] i386/cpu: Consolidate the use of topo_info in cpu_x86_cpuid(), (continued)
- [PATCH v11 08/21] i386/cpu: Consolidate the use of topo_info in cpu_x86_cpuid(), Zhao Liu, 2024/04/24
- [PATCH v11 11/21] i386/cpu: Decouple CPUID[0x1F] subleaf with specific topology level, Zhao Liu, 2024/04/24
- [PATCH v11 10/21] i386: Split topology types of CPUID[0x1F] from the definitions of CPUID[0xB], Zhao Liu, 2024/04/24
- [PATCH v11 12/21] i386: Introduce module level cpu topology to CPUX86State, Zhao Liu, 2024/04/24
- [PATCH v11 13/21] i386: Support modules_per_die in X86CPUTopoInfo, Zhao Liu, 2024/04/24
- [PATCH v11 14/21] i386: Expose module level in CPUID[0x1F], Zhao Liu, 2024/04/24
- [PATCH v11 15/21] i386: Support module_id in X86CPUTopoIDs, Zhao Liu, 2024/04/24
- [PATCH v11 16/21] i386/cpu: Introduce module-id to X86CPU, Zhao Liu, 2024/04/24
- [PATCH v11 17/21] tests: Add test case of APIC ID for module level parsing, Zhao Liu, 2024/04/24
- [PATCH v11 18/21] hw/i386/pc: Support smp.modules for x86 PC machine, Zhao Liu, 2024/04/24
- [PATCH v11 19/21] i386: Add cache topology info in CPUCacheInfo,
Zhao Liu <=
- [PATCH v11 20/21] i386/cpu: Use CPUCacheInfo.share_level to encode CPUID[4], Zhao Liu, 2024/04/24
- [PATCH v11 21/21] i386/cpu: Use CPUCacheInfo.share_level to encode CPUID[0x8000001D].EAX[bits 25:14], Zhao Liu, 2024/04/24
- Re: [PATCH v11 00/21] i386: Introduce smp.modules and clean up cache topology, Philippe Mathieu-Daudé, 2024/04/25