Some AMD processors expose the PKRU extended save state even if they do not have
the related PKU feature in CPUID. Worse, when they do they report a size of
64, whereas the expected size of the PKRU extended save state is 8, therefore
the esa->size == eax assertion does not hold.
The state is already ignored by KVM_GET_SUPPORTED_CPUID because it
was not enabled in the host XCR0. However, QEMU kvm_cpu_xsave_init()
runs before QEMU invokes arch_prctl() to enable dynamically-enabled
save states such as XTILEDATA, and KVM_GET_SUPPORTED_CPUID hides save
states that have yet to be enabled. Therefore, kvm_cpu_xsave_init()
needs to consult the host CPUID instead of KVM_GET_SUPPORTED_CPUID,
and dies with an assertion failure.
When setting up the ExtSaveArea array to match the host, ignore features that
KVM does not report as supported. This will cause QEMU to skip the incorrect
CPUID leaf instead of tripping the assertion.
Closes: https://gitlab.com/qemu-project/qemu/-/issues/916
Reported-by: Daniel P. Berrangé <berrange@redhat.com>
Analyzed-by: Yang Zhong <yang.zhong@intel.com>
Reported-by: Peter Krempa <pkrempa@redhat.com>
Tested-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Even when the feature is not supported in guest CPUID,
still set the msr to the default value which will
be the only value KVM will accept in this case
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20220223115824.319821-1-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Windows 11 with WSL2 enabled (Hyper-V) fails to boot with Icelake-Server
{-v5} CPU model but boots well with '-cpu host'. Apparently, it expects
5-level paging and 5-level EPT support to come in pair but QEMU's
Icelake-Server CPU model lacks the later. Introduce 'Icelake-Server-v6'
CPU model with 'vmx-page-walk-5' enabled by default.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20220221145316.576138-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add AMX primary feature bits XFD and AMX_TILE to
enumerate the CPU's AMX capability. Meanwhile, add
AMX TILE and TMUL CPUID leaf and subleaves which
exist when AMX TILE is present to provide the maximum
capability of TILE and TMUL.
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220217060434.52460-6-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Intel introduces XFD faulting mechanism for extended
XSAVE features to dynamically enable the features in
runtime. If CPUID (EAX=0Dh, ECX=n, n>1).ECX[2] is set
as 1, it indicates support for XFD faulting of this
state component.
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220217060434.52460-5-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Kernel allocates 4K xstate buffer by default. For XSAVE features
which require large state component (e.g. AMX), Linux kernel
dynamically expands the xstate buffer only after the process has
acquired the necessary permissions. Those are called dynamically-
enabled XSAVE features (or dynamic xfeatures).
There are separate permissions for native tasks and guests.
Qemu should request the guest permissions for dynamic xfeatures
which will be exposed to the guest. This only needs to be done
once before the first vcpu is created.
KVM implemented one new ARCH_GET_XCOMP_SUPP system attribute API to
get host side supported_xcr0 and Qemu can decide if it can request
dynamically enabled XSAVE features permission.
https://lore.kernel.org/all/20220126152210.3044876-1-pbonzini@redhat.com/
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Message-Id: <20220217060434.52460-4-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The AMX TILECFG register and the TMMx tile data registers are
saved/restored via XSAVE, respectively in state component 17
(64 bytes) and state component 18 (8192 bytes).
Add AMX feature bits to x86_ext_save_areas array to set
up AMX components. Add structs that define the layout of
AMX XSAVE areas and use QEMU_BUILD_BUG_ON to validate the
structs sizes.
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220217060434.52460-3-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The extended state subleaves (EAX=0Dh, ECX=n, n>1).ECX[1]
indicate whether the extended state component locates
on the next 64-byte boundary following the preceding state
component when the compacted format of an XSAVE area is
used.
Right now, they are all zero because no supported component
needed the bit to be set, but the upcoming AMX feature will
use it. Fix the subleaves value according to KVM's supported
cpuid.
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220217060434.52460-2-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The "hardware version" machinery (qemu_set_hw_version(),
qemu_hw_version(), and the QEMU_HW_VERSION define) is used by fewer
than 10 files. Move it out from osdep.h into a new
qemu/hw-version.h.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220208200856.3558249-6-peter.maydell@linaro.org
* DMA support in the multiboot option ROM
* Rename default-bus-bypass-iommu
* Deprecate -watchdog and cleanup -watchdog-action
* HVF fix for <PAGE_SIZE regions
* Support TSC scaling for AMD nested virtualization
* Fix for ESP fuzzing bug
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmGBUeEUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroOh+Qf+OMRhRiv6dYjbK/5zXrx81AgxYAY3
dBUSr8v16LyrMl1U3DZWzhD+MzQsC83m/Xsh4lGxlHDWtkK9QQA5xDG95JZdY26i
MGCbbjnFHISbyBQV9Y724gPfPjOOODuoFbzafSx6VLITOcyv1ye0cm7TOjOPB+tt
E4c3JqTZ7g8a5yMe8ItkVhz5pPY+oVw8dxMNRp6Sup5Dbfx0DjacIwLasLsHfPL7
qBADfqB20ovHUzLjXu7oWgEd4KxJ6kiSCaJJu/KD36hg0wB8+WVP1o43j4PkczHT
QjU7eZaeaTrN5Cf34ttPge6QReMi5SFNCaA9O9/HLqrQgdEtt/diZWuqjQ==
=a2mC
-----END PGP SIGNATURE-----
Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging
* Build system fixes and cleanups
* DMA support in the multiboot option ROM
* Rename default-bus-bypass-iommu
* Deprecate -watchdog and cleanup -watchdog-action
* HVF fix for <PAGE_SIZE regions
* Support TSC scaling for AMD nested virtualization
* Fix for ESP fuzzing bug
# gpg: Signature made Tue 02 Nov 2021 10:57:37 AM EDT
# gpg: using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg: issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg: aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
* remotes/bonzini/tags/for-upstream: (27 commits)
configure: fix --audio-drv-list help message
configure: Remove the check for the __thread keyword
Move the l2tpv3 test from configure to meson.build
meson: remove unnecessary coreaudio test program
meson: remove pointless warnings
meson.build: Allow to disable OSS again
meson: bump submodule to 0.59.3
qtest/am53c974-test: add test for cancelling in-flight requests
esp: ensure in-flight SCSI requests are always cancelled
KVM: SVM: add migration support for nested TSC scaling
hw/i386: fix vmmouse registration
watchdog: remove select_watchdog_action
vl: deprecate -watchdog
watchdog: add information from -watchdog help to -device help
hw/i386: Rename default_bus_bypass_iommu
hvf: Avoid mapping regions < PAGE_SIZE as ram
configure: do not duplicate CPU_CFLAGS into QEMU_LDFLAGS
configure: remove useless NPTL probe
target/i386: use DMA-enabled multiboot ROM for new-enough QEMU machine types
optionrom: add a DMA-enabled multiboot ROM
...
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
I noticed -cpu help printing enough trailing spaces to make the output
at least 84 characters wide. Looks ugly unless the terminal is wider.
Ugly or not, trailing spaces are stupid.
The culprit is this line in x86_cpu_list_entry():
qemu_printf("x86 %-20s %-58s\n", name, desc);
This prints a string with minimum field left-justified right before a
newline. Change it to
qemu_printf("x86 %-20s %s\n", name, desc);
which avoids the trailing spaces and is simpler to boot.
A search for the pattern with "git-grep -E '%-[0-9]+s\\n'" found a few
more instances. Change them similarly.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Acked-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Message-Id: <20211009152401.2982862-1-armbru@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
Because core-capability releated features are model-specific and KVM
won't support it, remove the core-capability in CPU model to avoid the
warning message.
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20210827064818.4698-3-chenyi.qiang@intel.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Only declare sev_enabled() and sev_es_enabled() when CONFIG_SEV is
set, to allow the compiler to elide unused code. Remove unnecessary
stubs.
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20211007161716.453984-17-philmd@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
SEV is a x86 specific feature, and the "sev_i386.h" header
is already in target/i386/. Rename it as "sev.h" to simplify.
Patch created mechanically using:
$ git mv target/i386/sev_i386.h target/i386/sev.h
$ sed -i s/sev_i386.h/sev.h/ $(git grep -l sev_i386.h)
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20211007161716.453984-15-philmd@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Commit 00b8105324 ("target-i386: Remove assert_no_error usage")
forgot to add the "qapi/error.h" for &error_abort, add it now.
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Connor Kuehl <ckuehl@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20211007161716.453984-8-philmd@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM implements some Hyper-V 2016 functions so providing WS2008R2 version
is somewhat incorrect. While generally guests shouldn't care about it
and always check feature bits, it is known that some tools in Windows
actually check version info.
For compatibility reasons make the change for 6.2 machine types only.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210902093530.345756-9-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently, we hardcode Hyper-V version id (CPUID 0x40000002) to
WS2008R2 and it is known that certain tools in Windows check this. It
seems useful to provide some flexibility by making it possible to change
this info at will. CPUID information is defined in TLFS as:
EAX: Build Number
EBX Bits 31-16: Major Version
Bits 15-0: Minor Version
ECX Service Pack
EDX Bits 31-24: Service Branch
Bits 23-0: Service Number
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210902093530.345756-8-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The enlightenment allows to use Hyper-V SynIC with hardware APICv/AVIC
enabled. Normally, Hyper-V SynIC disables these hardware features and
suggests the guest to use paravirtualized AutoEOI feature. Linux-4.15
gains support for conditional APICv/AVIC disablement, the feature
stays on until the guest tries to use AutoEOI feature with SynIC. With
'HV_DEPRECATING_AEOI_RECOMMENDED' bit exposed, modern enough Windows/
Hyper-V versions should follow the recommendation and not use the
(unwanted) feature.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210902093530.345756-7-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
By default, KVM allows the guest to use all currently supported Hyper-V
enlightenments when Hyper-V CPUID interface was exposed, regardless of if
some features were not announced in guest visible CPUIDs. hv-enforce-cpuid
feature alters this behavior and only allows the guest to use exposed
Hyper-V enlightenments. The feature is supported by Linux >= 5.14 and is
not enabled by default in QEMU.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210902093530.345756-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
By default, KVM allows the guest to use all currently supported PV features
even when they were not announced in guest visible CPUIDs. Introduce a new
"kvm-pv-enforce-cpuid" flag to limit the supported feature set to the
exposed features. The feature is supported by Linux >= 5.10 and is not
enabled by default in QEMU.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210902093530.345756-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
SGX capabilities are enumerated through CPUID_0x12.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-16-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If the guest want to fully use SGX, the guest needs to be able to
access provisioning key. Add a new KVM_CAP_SGX_ATTRIBUTE to KVM to
support provisioning key to KVM guests.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-14-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Expose SGX to the guest if and only if KVM is enabled and supports
virtualization of SGX. While the majority of ENCLS can be emulated to
some degree, because SGX uses a hardware-based root of trust, the
attestation aspects of SGX cannot be emulated in software, i.e.
ultimately emulation will fail as software cannot generate a valid
quote/report. The complexity of partially emulating SGX in Qemu far
outweighs the value added, e.g. an SGX specific simulator for userspace
applications can emulate SGX for development and testing purposes.
Note, access to the PROVISIONKEY is not yet advertised to the guest as
KVM blocks access to the PROVISIONKEY by default and requires userspace
to provide additional credentials (via ioctl()) to expose PROVISIONKEY.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-13-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
On real hardware, on systems that supports SGX Launch Control, those
MSRs are initialized to digest of Intel's signing key; on systems that
don't support SGX Launch Control, those MSRs are not available but
hardware always uses digest of Intel's signing key in EINIT.
KVM advertises SGX LC via CPUID if and only if the MSRs are writable.
Unconditionally initialize those MSRs to digest of Intel's signing key
when CPU is realized and reset to reflect the fact. This avoids
potential bug in case kvm_arch_put_registers() is called before
kvm_arch_get_registers() is called, in which case guest's virtual
SGX_LEPUBKEYHASH MSRs will be set to 0, although KVM initializes those
to digest of Intel's signing key by default, since KVM allows those MSRs
to be updated by Qemu to support live migration.
Save/restore the SGX Launch Enclave Public Key Hash MSRs if SGX Launch
Control (LC) is exposed to the guest. Likewise, migrate the MSRs if they
are writable by the guest.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-11-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
CPUID leaf 12_1_EAX is an Intel-defined feature bits leaf enumerating
the platform's SGX capabilities that may be utilized by an enclave, e.g.
whether or not an enclave can gain access to the provision key.
Currently there are six capabilities:
- INIT: set when the enclave has has been initialized by EINIT. Cannot
be set by software, i.e. forced to zero in CPUID.
- DEBUG: permits a debugger to read/write into the enclave.
- MODE64BIT: the enclave runs in 64-bit mode
- PROVISIONKEY: grants has access to the provision key
- EINITTOKENKEY: grants access to the EINIT token key, i.e. the
enclave can generate EINIT tokens
- KSS: Key Separation and Sharing enabled for the enclave.
Note that the entirety of CPUID.0x12.0x1, i.e. all registers, enumerates
the allowed ATTRIBUTES (128 bits), but only bits 31:0 are directly
exposed to the user (via FEAT_12_1_EAX). Bits 63:32 are currently all
reserved and bits 127:64 correspond to the allowed XSAVE Feature Request
Mask, which is calculated based on other CPU features, e.g. XSAVE, MPX,
AVX, etc... and is not exposed to the user.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-10-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
CPUID leaf 12_0_EBX is an Intel-defined feature bits leaf enumerating
the platform's SGX extended capabilities. Currently there is a single
capabilitiy:
- EXINFO: record information about #PFs and #GPs in the enclave's SSA
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-9-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
CPUID leaf 12_0_EAX is an Intel-defined feature bits leaf enumerating
the CPU's SGX capabilities, e.g. supported SGX instruction sets.
Currently there are four enumerated capabilities:
- SGX1 instruction set, i.e. "base" SGX
- SGX2 instruction set for dynamic EPC management
- ENCLV instruction set for VMM oversubscription of EPC
- ENCLS-C instruction set for thread safe variants of ENCLS
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-8-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add CPUID defines for SGX and SGX Launch Control (LC), as well as
defines for their associated FEATURE_CONTROL MSR bits. Define the
Launch Enclave Public Key Hash MSRs (LE Hash MSRs), which exist
when SGX LC is present (in CPUID), and are writable when SGX LC is
enabled (in FEATURE_CONTROL).
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-7-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
VGIF provides masking capability for when virtual interrupts
are taken. (APM2)
Signed-off-by: Lara Lazier <laramglazier@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Moved int_ctl into the CPUX86State structure. It removes some
unnecessary stores and loads, and prepares for tracking the vIRQ
state even when it is masked due to vGIF.
Signed-off-by: Lara Lazier <laramglazier@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
VGIF allows STGI and CLGI to execute in guest mode and control virtual
interrupts in guest mode.
When the VGIF feature is enabled then:
* executing STGI in the guest sets bit 9 of the VMCB offset 60h.
* executing CLGI in the guest clears bit 9 of the VMCB offset 60h.
Signed-off-by: Lara Lazier <laramglazier@gmail.com>
Message-Id: <20210730070742.9674-1-laramglazier@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
APM2 requires that VMRUN and VMLOAD canonicalize (sign extend to 63
from 48/57) all base addresses in the segment registers that have been
respectively loaded.
Signed-off-by: Lara Lazier <laramglazier@gmail.com>
Message-Id: <20210804113058.45186-1-laramglazier@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The AVX_VNNI feature is not in Cooperlake platform, remove it
from cpu model.
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210820054611.84303-1-yang.zhong@intel.com>
Fixes: c1826ea6a0 ("i386/cpu: Expose AVX_VNNI instruction to guest")
Cc: qemu-stable@nongnu.org
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
At present, there's no mechanism intelligent enough to virtualize split
lock detection correctly. Remove it in Snowridge CPU model to avoid the
feature exposure.
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20210630012053.10098-1-chenyi.qiang@intel.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Missed in commit f3478392 "docs: Move deprecation, build
and license info out of system/"
Signed-off-by: Mao Zhongyi <maozhongyi@cmss.chinamobile.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20210723065828.1336760-1-maozhongyi@cmss.chinamobile.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Some cpu properties have to be set only for cpu models in builtin_x86_defs,
registered with x86_register_cpu_model_type, and not for
cpu models "base", "max", and the subclass "host".
These properties are the ones set by function x86_cpu_apply_props,
(also including kvm_default_props, tcg_default_props),
and the "vendor" property for the KVM and HVF accelerators.
After recent refactoring of cpu, which also affected these properties,
they were instead set unconditionally for all x86 cpus.
This has been detected as a bug with Nested on AMD with cpu "host",
as svm was not turned on by default, due to the wrongful setting of
kvm_default_props via x86_cpu_apply_props, which set svm to "off".
Rectify the bug introduced in commit "i386: split cpu accelerators"
and document the functions that are builtin_x86_defs-only.
Signed-off-by: Claudio Fontana <cfontana@suse.de>
Tested-by: Alexander Bulekov <alxndr@bu.edu>
Fixes: f5cc5a5c ("i386: split cpu accelerators from cpu.c,"...)
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/477
Message-Id: <20210723112921.12637-1-cfontana@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
A AMD server typically has cpuid level 0x10(test on Rome/Milan), it
should not be changed to 0x1f in multi-dies case.
* to maintain compatibility with older machine types, only implement
this change when the CPU's "x-vendor-cpuid-only" property is false
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: zhenwei pi <pizhenwei@bytedance.com>
Fixes: a94e142899 (target/i386: Add CPUID.1F generation support for multi-dies PCMachine)
Signed-off-by: zhenwei pi <pizhenwei@bytedance.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-Id: <20210708170641.49410-1-michael.roth@amd.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Currently all built-in CPUs report cache information via CPUID leaves 2
and 4, but these have never been defined for AMD. In the case of
SEV-SNP this can cause issues with CPUID enforcement. Address this by
allowing CPU types to suppress these via a new "x-vendor-cpuid-only"
CPU property, which is true by default, but switched off for older
machine types to maintain compatibility.
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: zhenwei pi <pizhenwei@bytedance.com>
Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-Id: <20210708003623.18665-1-michael.roth@amd.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
To make Hyper-V features appear in e.g. QMP query-cpu-model-expansion we
need to expand and set the corresponding CPUID leaves early. Modify
x86_cpu_get_supported_feature_word() to call newly intoduced Hyper-V
specific kvm_hv_get_supported_cpuid() instead of
kvm_arch_get_supported_cpuid(). We can't use kvm_arch_get_supported_cpuid()
as Hyper-V specific CPUID leaves intersect with KVM's.
Note, early expansion will only happen when KVM supports system wide
KVM_GET_SUPPORTED_HV_CPUID ioctl (KVM_CAP_SYS_HYPERV_CPUID).
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210608120817.1325125-6-vkuznets@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Rather than relying on the X86XSaveArea structure definition,
determine the offset of XSAVE state areas using CPUID leaf 0xd where
possible (KVM and HVF).
Signed-off-by: David Edmondson <david.edmondson@oracle.com>
Message-Id: <20210705104632.2902400-8-david.edmondson@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Provide visibility of the x86_ext_save_areas array and associated type
outside of cpu.c.
Signed-off-by: David Edmondson <david.edmondson@oracle.com>
Message-Id: <20210705104632.2902400-6-david.edmondson@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Linux 5.14 will add support for nested TSC scaling. Add the
corresponding feature in QEMU; to keep support for existing kernels,
do not add it to any processor yet.
The handling of the VMCS enumeration MSR is ugly; once we have more than
one case, we may want to add a table to check VMX features against.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This fixes host and max cpu initialization, by running the accel cpu
initialization only after all instance init functions are called for all
X86 cpu subclasses.
The bug this is fixing is related to the "max" and "host" i386 cpu
subclasses, which set cpu->max_features, which is then used at cpu
realization time.
In order to properly split the accel-specific max features code that
needs to be executed at cpu instance initialization time,
we cannot call the accel cpu initialization at the end of the x86 base
class initialization, or we will have no way to specialize
"max features" cpu behavior, overriding the "max" cpu class defaults,
and checking for the "max features" flag itself.
This patch moves the accel-specific cpu instance initialization to after
all x86 cpu instance code has been executed, including subclasses,
so that proper initialization of cpu "host" and "max" can be restored.
Fixes: f5cc5a5c ("i386: split cpu accelerators from cpu.c,"...)
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Claudio Fontana <cfontana@suse.de>
Message-Id: <20210603123001.17843-3-cfontana@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
i386 realizefn code is sensitive to ordering, and recent commits
aimed at refactoring it, splitting accelerator-specific code,
broke assumptions which need to be fixed.
We need to:
* process hyper-v enlightements first, as they assume features
not to be expanded
* only then, expand features
* after expanding features, attempt to check them and modify them in the
accel-specific realizefn code called by cpu_exec_realizefn().
* after the framework has been called via cpu_exec_realizefn,
the code can check for what has or hasn't been set by accel-specific
code, or extend its results, ie:
- check and evenually set code_urev default
- modify cpu->mwait after potentially being set from host CPUID.
- finally check for phys_bits assuming all user and accel-specific
adjustments have already been taken into account.
Fixes: f5cc5a5c ("i386: split cpu accelerators from cpu.c"...)
Fixes: 30565f10 ("cpu: call AccelCPUClass::cpu_realizefn in"...)
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Claudio Fontana <cfontana@suse.de>
Message-Id: <20210603123001.17843-2-cfontana@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Hyper-V feature leaves are weird. We have some of them in
feature_word_info[] array but we don't use feature_word_info
magic to enable them. Neither do we use feature_dependencies[]
mechanism to validate the configuration as it doesn't allign
well with Hyper-V's many-to-many dependency chains. Some of
the feature leaves hold not only feature bits, but also values.
E.g. FEAT_HV_NESTED_EAX contains both features and the supported
Enlightened VMCS range.
Hyper-V features are already represented in 'struct X86CPU' with
uint64_t hyperv_features so duplicating them in env->features adds
little (or zero) benefits. THe other half of Hyper-V emulation features
is also stored with values in hyperv_vendor_id[], hyperv_limits[],...
so env->features[] is already incomplete.
Remove Hyper-V feature leaves from env->features[] completely.
kvm_hyperv_properties[] is converted to using raw CPUID func/reg
pairs for features, this allows us to get rid of hv_cpuid_get_fw()
conversion.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20210422161130.652779-8-vkuznets@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
When cpu->hyperv_vendor is not set manually we default to "Microsoft Hv"
and in 'hv_passthrough' mode we get the information from the host. This
information is stored in cpu->hyperv_vendor_id[] array but we don't update
cpu->hyperv_vendor string so e.g. QMP's query-cpu-model-expansion output
is incorrect.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20210422161130.652779-2-vkuznets@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The 'max' CPU under TCG currently reports a family/model/stepping that
approximately corresponds to an AMD K7 vintage architecture.
The K7 series predates the introduction of 64-bit support by AMD
in the K8 series. This has been reported to lead to LLVM complaints
about generating 64-bit code for a 32-bit CPU target
LLVM ERROR: 64-bit code requested on a subtarget that doesn't support it!
It appears LLVM looks at the family/model/stepping, despite qemu64
reporting it is 64-bit capable.
This patch changes 'max' to report a CPUID with the family, model
and stepping taken from a
AMD Athlon(tm) 64 X2 Dual Core Processor 4000+
which is one of the first 64-bit AMD CPUs.
Closes https://gitlab.com/qemu-project/qemu/-/issues/191
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20210507133650.645526-3-berrange@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Paolo Bonzini
Maxim Levitsky
Vitaly Kuznetsov
Jing Liu
Yang Zhong
Peter Maydell
Gareth Webb
Richard Henderson
Markus Armbruster
Chenyi Qiang
Philippe Mathieu-Daudé
Sean Christopherson
Lara Lazier
Mao Zhongyi
Claudio Fontana
zhenwei pi
Michael Roth
David Edmondson
Daniel P. Berrangé