From: Mohamed Mediouni <mohamed@unpredictable.fr>
To: qemu-devel@nongnu.org
Cc: Pedro Barbuda <pbarbuda@microsoft.com>,
qemu-arm@nongnu.org,
Pierrick Bouvier <pierrick.bouvier@linaro.org>,
Mohamed Mediouni <mohamed@unpredictable.fr>,
Roman Bolshakov <rbolshakov@ddn.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
Wei Liu <wei.liu@kernel.org>,
Phil Dennis-Jordan <phil@philjordan.eu>,
Peter Maydell <peter.maydell@linaro.org>,
Zhao Liu <zhao1.liu@intel.com>,
Paolo Bonzini <pbonzini@redhat.com>
Subject: [PATCH v3 00/37] WHPX x86 updates for QEMU 11.1
Date: Wed, 22 Apr 2026 23:41:48 +0200 [thread overview]
Message-ID: <20260422214225.2242-1-mohamed@unpredictable.fr> (raw)
This rolls over my previous series posted earlier in this mailing list.
..and adds some more.
Git tree: https://github.com/mediouni-m/qemu whpx-i386-202604-4
Some highlights:
1
- user-mode x2APIC emulation (kernel-irqchip=off) for better
performance when it has to be used.
- CPU model emulation on both Windows 10 and 11
- configurable behavior for unknown MSRs and adding a way
to trap on GPFs raised by Hyper-V on MSR acccess
- when -M hyperv=off, report the hypervisor as VMware for
guests to use either the VMware CPUID leaf or the vmport
interface to get the TSC and APIC frequencies.
If the vmware CPUID frequency leaf is disabled, then KVM
is reported.
- xsave save/restore support
- Pause the VM to be able to inspect state on a fatal fault
instead of just exiting
- adding emulation of an oddball idle MSR used by Windows
when kernel-irqchip=off.
- disable kernel-irqchip and Hyper-V enlightenments for
isapc
- for Windows 10, change the default to an emulated x2APIC
(kernel-irqchip=off). The recommended way to use the Hyper-V
LAPIC is not to use -M kernel-irqchip=on, but -M pic=off.
And as the last commit, a documentation update.
Bug reports and patches are welcome.
However, due to reasons, I'll probably step aside
from this all for a bit so don't expect immediate replies.
v1->v2:
- Build fixup for macOS and OpenBSD
- a bit of cleanup
v2->v3:
Unfortunately this rev has quite a bit of changes...
- Some fixes here and there.
- Merging in Windows 10 support into something less separate.
- Move new x86-specific (at least for now) properties into a new
whpx_arch_accel_class_init method.
- Add nested virt settings and separate security domain accelerator
properties.
Magnus Kulke (1):
target/i386: add de/compaction to xsave_helper
Mohamed Mediouni (36):
target/i386: emulate: include name of unhandled instruction
whpx: i386: x2apic emulation
whpx: i386: wire up feature probing
whpx: i386: disable TbFlushHypercalls for emulated LAPIC
whpx: i386: enable x2apic by default for user-mode LAPIC
whpx: i386: reintroduce enlightenments for Windows 10
whpx: i386: introduce proper cpuid support
whpx: i386: kernel-irqchip=off fixes
whpx: i386: use WHvX64RegisterCr8 only when kernel-irqchip=off
whpx: i386: disable kernel-irqchip on Windows 10 when PIC enabled
whpx: i386: IO port fast path cleanup
whpx: i386: disable enlightenments and LAPIC for isapc
whpx: i386: interrupt priority support
hw/intc: apic: disallow APIC reads when disabled
whpx: i386: fix CPUID[1:EDX].APIC reporting
whpx: i386: set apicbase value only on success
whpx: i386: unknown MSR configurability
whpx: i386: enable GuestIdleReg enlightenment
whpx: i386: tighten APIC base validity check
whpx: i386: ignore vpassist when kernel-irqchip=off
target: i386: HLT type that ignores EFLAGS.IF
whpx: i386: add HV_X64_MSR_GUEST_IDLE when !kernel-irqchip
whpx: i386: some x2APIC awareness
whpx: i386: set WHvX64RegisterInitialApicId
whpx: i386: Pause VM on fatal exception to be able to inspect state
target/i386: emulate: use exception_payload for fault address
target/i386: make xsave_buf present unconditionally
whpx: xsave support
whpx: i386: set APIC ID only when APIC present
whpx: i386: update migration blocker message
whpx: i386: don't increment eip on MSR access raising GPF
target/i386: emulate, hvf: rdmsr/wrmsr GPF handling
whpx: i386: add feature to intercept #GP MSR accesses
whpx: i386: nested virt settings
whpx: i386: add SeparateSecurityDomain flag and make default
whpx: i386: documentation update
accel/whpx/whpx-common.c | 8 +
docs/system/whpx.rst | 40 +-
hw/intc/apic.c | 9 +
include/system/whpx-all.h | 1 +
include/system/whpx-common.h | 2 +-
include/system/whpx-internal.h | 31 +
target/arm/whpx/whpx-all.c | 5 +
target/i386/cpu.c | 27 +-
target/i386/cpu.h | 6 +-
target/i386/emulate/x86_emu.c | 14 +-
target/i386/emulate/x86_emu.h | 4 +-
target/i386/emulate/x86_mmu.c | 3 +-
target/i386/hvf/hvf-i386.h | 4 +-
target/i386/hvf/hvf.c | 9 +-
target/i386/whpx/meson.build | 1 +
target/i386/whpx/whpx-all.c | 1489 +++++++++++++++++++++++-----
target/i386/whpx/whpx-apic.c | 83 +-
target/i386/whpx/whpx-cpu-legacy.c | 158 +++
target/i386/whpx/whpx-i386.h | 12 +
target/i386/xsave_helper.c | 256 +++++
20 files changed, 1875 insertions(+), 287 deletions(-)
create mode 100644 target/i386/whpx/whpx-cpu-legacy.c
create mode 100644 target/i386/whpx/whpx-i386.h
--
2.50.1 (Apple Git-155)
next reply other threads:[~2026-04-22 21:43 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-22 21:41 Mohamed Mediouni [this message]
2026-04-22 21:41 ` [PATCH v3 01/37] target/i386: emulate: include name of unhandled instruction Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 02/37] whpx: i386: x2apic emulation Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 03/37] whpx: i386: wire up feature probing Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 04/37] whpx: i386: disable TbFlushHypercalls for emulated LAPIC Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 05/37] whpx: i386: enable x2apic by default for user-mode LAPIC Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 06/37] whpx: i386: reintroduce enlightenments for Windows 10 Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 07/37] whpx: i386: introduce proper cpuid support Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 08/37] whpx: i386: kernel-irqchip=off fixes Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 09/37] whpx: i386: use WHvX64RegisterCr8 only when kernel-irqchip=off Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 10/37] whpx: i386: disable kernel-irqchip on Windows 10 when PIC enabled Mohamed Mediouni
2026-04-22 21:41 ` [PATCH v3 11/37] whpx: i386: IO port fast path cleanup Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 12/37] whpx: i386: disable enlightenments and LAPIC for isapc Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 13/37] whpx: i386: interrupt priority support Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 14/37] hw/intc: apic: disallow APIC reads when disabled Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 15/37] whpx: i386: fix CPUID[1:EDX].APIC reporting Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 16/37] whpx: i386: set apicbase value only on success Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 17/37] whpx: i386: unknown MSR configurability Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 18/37] whpx: i386: enable GuestIdleReg enlightenment Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 19/37] whpx: i386: tighten APIC base validity check Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 20/37] whpx: i386: ignore vpassist when kernel-irqchip=off Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 21/37] target: i386: HLT type that ignores EFLAGS.IF Mohamed Mediouni
2026-04-30 13:43 ` Paolo Bonzini
2026-04-22 21:42 ` [PATCH v3 22/37] whpx: i386: add HV_X64_MSR_GUEST_IDLE when !kernel-irqchip Mohamed Mediouni
2026-04-30 13:21 ` Paolo Bonzini
2026-04-22 21:42 ` [PATCH v3 23/37] whpx: i386: some x2APIC awareness Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 24/37] whpx: i386: set WHvX64RegisterInitialApicId Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 25/37] whpx: i386: Pause VM on fatal exception to be able to inspect state Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 26/37] target/i386: emulate: use exception_payload for fault address Mohamed Mediouni
2026-04-30 13:24 ` Paolo Bonzini
2026-04-22 21:42 ` [PATCH v3 27/37] target/i386: make xsave_buf present unconditionally Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 28/37] target/i386: add de/compaction to xsave_helper Mohamed Mediouni
2026-04-30 13:31 ` Paolo Bonzini
2026-04-22 21:42 ` [PATCH v3 29/37] whpx: xsave support Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 30/37] whpx: i386: set APIC ID only when APIC present Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 31/37] whpx: i386: update migration blocker message Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 32/37] whpx: i386: don't increment eip on MSR access raising GPF Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 33/37] target/i386: emulate, hvf: rdmsr/wrmsr GPF handling Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 34/37] whpx: i386: add feature to intercept #GP MSR accesses Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 35/37] whpx: i386: nested virt settings Mohamed Mediouni
2026-04-30 13:44 ` Paolo Bonzini
2026-04-30 17:52 ` Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 36/37] whpx: i386: add SeparateSecurityDomain flag and make default Mohamed Mediouni
2026-04-22 21:42 ` [PATCH v3 37/37] whpx: i386: documentation update Mohamed Mediouni
2026-04-23 11:10 ` [PATCH v3 00/37] WHPX x86 updates for QEMU 11.1 Paolo Bonzini
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260422214225.2242-1-mohamed@unpredictable.fr \
--to=mohamed@unpredictable.fr \
--cc=mst@redhat.com \
--cc=pbarbuda@microsoft.com \
--cc=pbonzini@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=phil@philjordan.eu \
--cc=pierrick.bouvier@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=rbolshakov@ddn.com \
--cc=wei.liu@kernel.org \
--cc=zhao1.liu@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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.