packages/qemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

i386: cache passthrough: Update Intel CPUID4.EAX[25:14] based on vCPU topo

Browse Source 
On Intel target, when host cache passthrough is disabled we will
emulate the guest caches with default values and initialize the
shared cpu list of the caches based on vCPU topology. However when
host cache passthrough is enabled, the shared cpu list is consistent
with host regardless what the vCPU topology is.

For example, when cache passthrough is enabled, running a guest
with vThreads=1 on a host with pThreads=2, we will get that there
are every *two* logical vCPUs sharing a L1/L2 cache, which is not
consistent with the vCPU topology (vThreads=1).

So let's reinitialize BITs[25:14] of Intel CPUID 4 based on the
actual vCPU topology instead of host pCPU topology.

Signed-off-by: Jian Wang <wangjian161@huawei.com>
Signed-off-by: Yanan Wang <wangyanan55@huawei.com>
This commit is contained in:
Chen Qun 2022-02-10 19:43:55 +08:00 committed by yezengruan
parent 9d233e7b1d
commit 0532b39a49
1 changed files with 88 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

88
i386-cache-passthrough-Update-Intel-CPUID4.EAX-25-14.patch Normal file
View File

@ -0,0 +1,88 @@
From 3eaa433ca1cbee753698893b7732819ba2e31302 Mon Sep 17 00:00:00 2001
From: Jian Wang <wangjian161@huawei.com>
Date: Thu, 10 Feb 2022 19:43:55 +0800
Subject: [PATCH] i386: cache passthrough: Update Intel CPUID4.EAX[25:14] based
on vCPU topo
On Intel target, when host cache passthrough is disabled we will
emulate the guest caches with default values and initialize the
shared cpu list of the caches based on vCPU topology. However when
host cache passthrough is enabled, the shared cpu list is consistent
with host regardless what the vCPU topology is.
For example, when cache passthrough is enabled, running a guest
with vThreads=1 on a host with pThreads=2, we will get that there
are every *two* logical vCPUs sharing a L1/L2 cache, which is not
consistent with the vCPU topology (vThreads=1).
So let's reinitialize BITs[25:14] of Intel CPUID 4 based on the
actual vCPU topology instead of host pCPU topology.
Signed-off-by: Jian Wang <wangjian161@huawei.com>
Signed-off-by: Yanan Wang <wangyanan55@huawei.com>
---
target/i386/cpu.c | 27 +++++++++++++++++++++++----
1 file changed, 23 insertions(+), 4 deletions(-)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 868cf3e7e8..c1fe2895fd 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -5196,7 +5196,7 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
{
X86CPU *cpu = env_archcpu(env);
CPUState *cs = env_cpu(env);
- uint32_t die_offset;
+ uint32_t die_offset, smt_width;
uint32_t limit;
uint32_t signature[3];
X86CPUTopoInfo topo_info;
@@ -5205,6 +5205,9 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
topo_info.cores_per_die = cs->nr_cores;
topo_info.threads_per_core = cs->nr_threads;
+ die_offset = apicid_die_offset(&topo_info);
+ smt_width = apicid_smt_width(&topo_info);
+
/* Calculate & apply limits for different index ranges */
if (index >= 0xC0000000) {
limit = env->cpuid_xlevel2;
@@ -5272,8 +5275,25 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
/* cache info: needed for Core compatibility */
if (cpu->cache_info_passthrough) {
host_cpuid(index, count, eax, ebx, ecx, edx);
- /* QEMU gives out its own APIC IDs, never pass down bits 31..26. */
- *eax &= ~0xFC000000;
+ /*
+ * QEMU gives out its own APIC IDs, never pass down bits 31..26.
+ * Update the cache topo bits 25..14, according to the guest
+ * vCPU topology instead of the host pCPU topology.
+ */
+ *eax &= ~0xFFFFC000;
+ switch (count) {
+ case 0: /* L1 dcache info */
+ case 1: /* L1 icache info */
+ case 2: /* L2 cache info */
+ *eax |= ((1 << smt_width) - 1) << 14;
+ break;
+ case 3: /* L3 cache info */
+ *eax |= ((1 << die_offset) - 1) << 14;
+ break;
+ default: /* end of info */
+ *eax = *ebx = *ecx = *edx = 0;
+ break;
+ }
if ((*eax & 31) && cs->nr_cores > 1) {
*eax |= (cs->nr_cores - 1) << 26;
}
@@ -5298,7 +5318,6 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
eax, ebx, ecx, edx);
break;
case 3: /* L3 cache info */
- die_offset = apicid_die_offset(&topo_info);
if (cpu->enable_l3_cache) {
encode_cache_cpuid4(env->cache_info_cpuid4.l3_cache,
(1 << die_offset), cs->nr_cores,
--
2.27.0