* [PATCH pve-docs] vcpu-types: Update CPU models
@ 2026-09-03 10:21 Jonas Theisen
0 siblings, 0 replies; only message in thread
From: Jonas Theisen @ 2026-09-03 10:21 UTC (permalink / raw)
To: pve-devel
Updated list of virtual CPU models of QEMU to the current state
based on pve-qemu-kvm 11.0.3-3
Signed-off-by: Jonas Theisen <j.theisen@proxmox.com>
---
qm-vcpu-list.adoc | 83 +++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 81 insertions(+), 2 deletions(-)
diff --git a/qm-vcpu-list.adoc b/qm-vcpu-list.adoc
index 2aa1bfd..9ea968a 100644
--- a/qm-vcpu-list.adoc
+++ b/qm-vcpu-list.adoc
@@ -75,8 +75,64 @@ https://en.wikipedia.org/wiki/List_of_Intel_Xeon_processors[Intel processors]
+
* 'Icelake-v6' : add "5-level EPT" ('+vmx-page-walk-5')
+
+* 'Icelake-v7' : re-enable TSX ('+hle', '+rtm')
++
* 'SapphireRapids' : https://en.wikipedia.org/wiki/Sapphire_Rapids[4th generation Xeon Scalable server processors]
-
++
+* 'SapphireRapids-v2' : add "Fill Buffer Stale Data Propagator (FBSDP)" mitigation ('+fbsdp-no'),
+"Primary Stale Data Propagator (PSDP)" mitigation ('+psdp-no'),
+"Shared Buffers Data Read (SBDR)", "Stale Data Propagator (SSDP)" mitigation ('+sbdr-ssdp-no")
++
+* 'SapphireRapids-v3' : add "Stack segment" ('+ss'), "Cache Line Demote" ('+cldemote'),
+"TSC adjust" ('+tsc-adjust','+tsc_adjust'), "Move Doubleword as Direct Store" ('+movdiri', '+movdir64b')
++
+* 'SapphireRapids-v4' : expose "Intel 0x1F CPUID leaf" ('+x-force-cpuid-0x1f'),
+remove "legacy-cache" ('-legacy-cache')
++
+* 'SapphireRapids-v5' : add CET IBT and SS ('+cet-ibt','+cet-ss')
++
+* 'SapphireRapids-v6' : add "ITS" mitigation ('+its-no')
++
+* 'SierraForest' : https://en.wikipedia.org/wiki/Sierra_Forest[6th generation Xeon Scalable server processors with E-cores]
++
+* 'SierraForest-v2' : add "Register File Data Sampling (RFDS)" mitigation ('+rfds-no'),
+"Fast Store Forwarding Predictor (FSFP)" ('+intel-psfd'),
+"Gather Data Sampling (GDS)" mitigation ('+gds-no'),
+"Stack segment" ('+ss'), "Cache Line Demote" ('+cldemote'),
+"Linear Address Masking (LAM)" ('+lam'),
+"TSC adjust" ('+tsc-adjust','+tsc_adjust'),
+"Indirect Predictor Control" ('+ipred-ctrl'),
+"Move Doubleword as Direct Store" ('+movdiri', '+movdir64b'),
+"Branch History Injection Control" ('+bhi-ctrl'),
+"Restricted Return Stack Buffer Alternate (RRSBA)" ('+rrsba-ctrl'),
+change 'stepping' from '0' to '3'
++
+* 'SierraForest-v3' : expose "Intel 0x1F CPUID leaf" ('+x-force-cpuid-0x1f'), remove "legacy-cache" ('-legacy-cache')
++
+* 'SierraForest-v4' : add CET IBT and SS ('+cet-ibt','+cet-ss')
++
+* 'SierraForest-v5' : add "ITS" mitigation ('+its-no')
++
+* 'GraniteRapids' : https://en.wikipedia.org/wiki/Granite_Rapids[6th generation Xeon Scalable server processors with P-cores]
++
+* 'GraniteRapids-v2' : add AVX10 flags ('avx10', '+avx10-version', '+avx10-128', '+avx10-256', '+avx10-512'),
+"Stack segment" ('+ss'), "Cache Line Demote" ('+cldemote'),
+"TSC adjust" ('+tsc-adjust','+tsc_adjust'),
+"Move Doubleword as Direct Store" ('+movdiri', '+movdir64b'),
+change 'stepping' from '0' to '1', 'level' and 'min-level' from '32' to '36'
++
+* 'GraniteRapids-v3' : expose "Intel 0x1F CPUID leaf" ('+x-force-cpuid-0x1f'), remove "legacy-cache" ('-legacy-cache')
++
+* 'GraniteRapids-v4' : add CET IBT and SS ('+cet-ibt','+cet-ss')
++
+* 'GraniteRapids-v5' : add "ITS" mitigation ('+its-no')
++
+* 'ClearwaterForest': https://en.wikipedia.org/wiki/Clearwater_Forest[6+ generation Xeon Scalable server processors with E-cores]
++
+* 'ClearwarterForest-v2' : add CET IBT and SS ('+cet-ibt','+cet-ss')
++
+* 'ClearwarterForest-v3' : add "ITS" mitigation ('+its-no'),
+expose "Intel 0x1F CPUID leaf" ('+x-force-cpuid-0x1f'), remove "legacy-cache" ('-legacy-cache')
AMD CPU Types
-------------
@@ -96,13 +152,36 @@ https://en.wikipedia.org/wiki/List_of_AMD_processors[AMD processors]
* 'EPYC-v3' : add missing flags ('+perfctr-core', '+clzero', '+xsaveerptr',
'+xsaves')
+
+* 'EPYC-v4' : no changes
++
+* 'EPYC-v5' : add "Software Uncorrectable Error Containment and Recovery capability" ('+succor'),
+"Machine Check Architecture (MCA) overflow recovery" ('+overflow-recov')
++
* 'EPYC-Rome' : https://en.wikipedia.org/wiki/Zen_2[2nd generation of Zen processors]
+
* 'EPYC-Rome-v2' : add Spectre v2, v4 protection ('+ibrs', '+amd-ssbd')
+
+* 'EPYC-Rome-v3' : no changes
++
+* 'EPYC-Rome-v4' : remove "XSAVES" ('-xsaves')
++
+* 'EPYC-Rome-v5' : add "Software Uncorrectable Error Containment and Recovery capability" ('+succor'),
+"Machine Check Architecture (MCA) overflow recovery" ('+overflow-recov')
++
* 'EPYC-Milan' : https://en.wikipedia.org/wiki/Zen_3[3rd generation of Zen processors]
+
* 'EPYC-Milan-v2' : add missing flags ('+vaes', '+vpclmulqdq',
'+stibp-always-on', '+amd-psfd', '+no-nested-data-bp',
'+lfence-always-serializing', '+null-sel-clr-base')
-
++
+* 'EPYC-Milan-v3' : add "Software Uncorrectable Error Containment and Recovery capability" ('+succor'),
+"Machine Check Architecture (MCA) overflow recovery" ('+overflow-recov')
++
+* 'EPYC-Genoa' : https://en.wikipedia.org/wiki/Zen_4[4th generation Zen processors]
++
+* 'EPYC-Genoa-v2' : add "Software Uncorrectable Error Containment and Recovery capability" ('+succor'),
+"Machine Check Architecture (MCA) overflow recovery" ('+overflow-recov'),
+"AMD Performance Monitoring Version 2" ('+perfmon-v2'),
+"Support for FS and GS access from user space" ('+fs-gs-base-ns')
++
+* 'EPYC-Turin' : https://en.wikipedia.org/wiki/Zen_5[5th generation Zen processors]
--
2.47.3
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2026-09-03 10:25 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-09-03 10:21 [PATCH pve-docs] vcpu-types: Update CPU models Jonas Theisen
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.