diff mbox series

[v4,17/21] i386: Add cache topology info in CPUCacheInfo

Message ID 20230914072159.1177582-18-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 Sept. 14, 2023, 7:21 a.m. UTC 
From: Zhao Liu <zhao1.liu@intel.com>

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>
---
Changes since v3:
 * Fix cache topology uninitialization bugs for some AMD CPUs. (Babu)
 * Move the CPUTopoLevel enumeration definition to the previous 0x1f
   rework patch.

Changes since v1:
 * Add the prefix "CPU_TOPO_LEVEL_*" for CPU topology level names.
   (Yanan)
 * (Revert, pls refer "i386: Decouple CPUID[0x1F] subleaf with specific
   topology level") Rename 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 mbox series

Patch

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index d8c5e774cf95..fcb4f4da3431 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -557,6 +557,7 @@  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 */
@@ -571,6 +572,7 @@  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: */
@@ -584,6 +586,7 @@  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 */
@@ -598,6 +601,7 @@  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: */
@@ -611,6 +615,7 @@  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 */
@@ -620,6 +625,7 @@  static CPUCacheInfo legacy_l2_cache_cpuid2 = {
     .size = 2 * MiB,
     .line_size = 64,
     .associativity = 8,
+    .share_level = CPU_TOPO_LEVEL_INVALID,
 };
 
 
@@ -633,6 +639,7 @@  static CPUCacheInfo legacy_l2_cache_amd = {
     .associativity = 16,
     .sets = 512,
     .partitions = 1,
+    .share_level = CPU_TOPO_LEVEL_CORE,
 };
 
 /* Level 3 unified cache: */
@@ -648,6 +655,7 @@  static CPUCacheInfo legacy_l3_cache = {
     .self_init = true,
     .inclusive = true,
     .complex_indexing = true,
+    .share_level = CPU_TOPO_LEVEL_DIE,
 };
 
 /* TLB definitions: */
@@ -1944,6 +1952,7 @@  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,
@@ -1956,6 +1965,7 @@  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,
@@ -1966,6 +1976,7 @@  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,
@@ -1979,6 +1990,7 @@  static const CPUCaches epyc_cache_info = {
         .self_init = true,
         .inclusive = true,
         .complex_indexing = true,
+        .share_level = CPU_TOPO_LEVEL_DIE,
     },
 };
 
@@ -1994,6 +2006,7 @@  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,
@@ -2006,6 +2019,7 @@  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,
@@ -2016,6 +2030,7 @@  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,
@@ -2029,6 +2044,7 @@  static CPUCaches epyc_v4_cache_info = {
         .self_init = true,
         .inclusive = true,
         .complex_indexing = false,
+        .share_level = CPU_TOPO_LEVEL_DIE,
     },
 };
 
@@ -2044,6 +2060,7 @@  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,
@@ -2056,6 +2073,7 @@  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,
@@ -2066,6 +2084,7 @@  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,
@@ -2079,6 +2098,7 @@  static const CPUCaches epyc_rome_cache_info = {
         .self_init = true,
         .inclusive = true,
         .complex_indexing = true,
+        .share_level = CPU_TOPO_LEVEL_DIE,
     },
 };
 
@@ -2094,6 +2114,7 @@  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,
@@ -2106,6 +2127,7 @@  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,
@@ -2116,6 +2138,7 @@  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,
@@ -2129,6 +2152,7 @@  static const CPUCaches epyc_rome_v3_cache_info = {
         .self_init = true,
         .inclusive = true,
         .complex_indexing = false,
+        .share_level = CPU_TOPO_LEVEL_DIE,
     },
 };
 
@@ -2144,6 +2168,7 @@  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,
@@ -2156,6 +2181,7 @@  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,
@@ -2166,6 +2192,7 @@  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,
@@ -2179,6 +2206,7 @@  static const CPUCaches epyc_milan_cache_info = {
         .self_init = true,
         .inclusive = true,
         .complex_indexing = true,
+        .share_level = CPU_TOPO_LEVEL_DIE,
     },
 };
 
@@ -2194,6 +2222,7 @@  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,
@@ -2206,6 +2235,7 @@  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,
@@ -2216,6 +2246,7 @@  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,
@@ -2229,6 +2260,7 @@  static const CPUCaches epyc_milan_v2_cache_info = {
         .self_init = true,
         .inclusive = true,
         .complex_indexing = false,
+        .share_level = CPU_TOPO_LEVEL_DIE,
     },
 };
 
@@ -2244,6 +2276,7 @@  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,
@@ -2256,6 +2289,7 @@  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,
@@ -2266,6 +2300,7 @@  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,
@@ -2279,6 +2314,7 @@  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 fa1452380882..a13132007415 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1596,6 +1596,13 @@  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;