Use the generic kvm_running_vcpu plus a new 'handling_intr_from_guest'
variable in kvm_arch_vcpu instead of the semi-redundant current_vcpu.
kvm_before/after_interrupt() must be called while the vCPU is loaded,
(which protects against preemption), thus kvm_running_vcpu is guaranteed
to be non-NULL when handling_intr_from_guest is non-zero.
Switching to kvm_get_running_vcpu() will allows moving KVM's perf
callbacks to generic code, and the new flag will be used in a future
patch to more precisely identify the "NMI from guest" case.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20211111020738.2512932-11-seanjc@google.com
To prepare for using static_calls to optimize perf's guest callbacks,
replace ->is_in_guest and ->is_user_mode with a new multiplexed hook
->state, tweak ->handle_intel_pt_intr to play nice with being called when
there is no active guest, and drop "guest" from ->get_guest_ip.
Return '0' from ->state and ->handle_intel_pt_intr to indicate "not in
guest" so that DEFINE_STATIC_CALL_RET0 can be used to define the static
calls, i.e. no callback == !guest.
[sean: extracted from static_call patch, fixed get_ip() bug, wrote changelog]
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Originally-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20211111020738.2512932-7-seanjc@google.com
Override the Processor Trace (PT) interrupt handler for guest mode if and
only if PT is configured for host+guest mode, i.e. is being used
independently by both host and guest. If PT is configured for system
mode, the host fully controls PT and must handle all events.
Fixes: 8479e04e7d ("KVM: x86: Inject PMI for KVM guest")
Reported-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reported-by: Artem Kashkanov <artem.kashkanov@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20211111020738.2512932-4-seanjc@google.com
* Fix misuse of gfn-to-pfn cache when recording guest steal time / preempted status
* Fix selftests on APICv machines
* Fix sparse warnings
* Fix detection of KVM features in CPUID
* Cleanups for bogus writes to MSR_KVM_PV_EOI_EN
* Fixes and cleanups for MSR bitmap handling
* Cleanups for INVPCID
* Make x86 KVM_SOFT_MAX_VCPUS consistent with other architectures
Add support for AMD SEV and SEV-ES intra-host migration support. Intra
host migration provides a low-cost mechanism for userspace VMM upgrades.
In the common case for intra host migration, we can rely on the normal
ioctls for passing data from one VMM to the next. SEV, SEV-ES, and other
confidential compute environments make most of this information opaque, and
render KVM ioctls such as "KVM_GET_REGS" irrelevant. As a result, we need
the ability to pass this opaque metadata from one VMM to the next. The
easiest way to do this is to leave this data in the kernel, and transfer
ownership of the metadata from one KVM VM (or vCPU) to the next. In-kernel
hand off makes it possible to move any data that would be
unsafe/impossible for the kernel to hand directly to userspace, and
cannot be reproduced using data that can be handed to userspace.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_CAP_NR_VCPUS is used to get the "recommended" maximum number of
VCPUs and arm64/mips/riscv report num_online_cpus(). Powerpc reports
either num_online_cpus() or num_present_cpus(), s390 has multiple
constants depending on hardware features. On x86, KVM reports an
arbitrary value of '710' which is supposed to be the maximum tested
value but it's possible to test all KVM_MAX_VCPUS even when there are
less physical CPUs available.
Drop the arbitrary '710' value and return num_online_cpus() on x86 as
well. The recommendation will match other architectures and will mean
'no CPU overcommit'.
For reference, QEMU only queries KVM_CAP_NR_VCPUS to print a warning
when the requested vCPU number exceeds it. The static limit of '710'
is quite weird as smaller systems with just a few physical CPUs should
certainly "recommend" less.
Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211111134733.86601-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently when kvm_update_cpuid_runtime() runs, it assumes that the
KVM_CPUID_FEATURES leaf is located at 0x40000001. This is not true,
however, if Hyper-V support is enabled. In this case the KVM leaves will
be offset.
This patch introdues as new 'kvm_cpuid_base' field into struct
kvm_vcpu_arch to track the location of the KVM leaves and function
kvm_update_kvm_cpuid_base() (called from kvm_set_cpuid()) to locate the
leaves using the 'KVMKVMKVM\0\0\0' signature (which is now given a
definition in kvm_para.h). Adjustment of KVM_CPUID_FEATURES will hence now
target the correct leaf.
NOTE: A new for_each_possible_hypervisor_cpuid_base() macro is intoduced
into processor.h to avoid having duplicate code for the iteration
over possible hypervisor base leaves.
Signed-off-by: Paul Durrant <pdurrant@amazon.com>
Message-Id: <20211105095101.5384-3-pdurrant@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_GUESTDBG_BLOCKIRQ relies on interrupts being injected using
standard kvm's inject_pending_event, and not via APICv/AVIC.
Since this is a debug feature, just inhibit APICv/AVIC while
KVM_GUESTDBG_BLOCKIRQ is in use on at least one vCPU.
Fixes: 61e5f69ef0 ("KVM: x86: implement KVM_GUESTDBG_BLOCKIRQ")
Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Tested-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211108090245.166408-1-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In commit b043138246 ("x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is
not missed") we switched to using a gfn_to_pfn_cache for accessing the
guest steal time structure in order to allow for an atomic xchg of the
preempted field. This has a couple of problems.
Firstly, kvm_map_gfn() doesn't work at all for IOMEM pages when the
atomic flag is set, which it is in kvm_steal_time_set_preempted(). So a
guest vCPU using an IOMEM page for its steal time would never have its
preempted field set.
Secondly, the gfn_to_pfn_cache is not invalidated in all cases where it
should have been. There are two stages to the GFN->PFN conversion;
first the GFN is converted to a userspace HVA, and then that HVA is
looked up in the process page tables to find the underlying host PFN.
Correct invalidation of the latter would require being hooked up to the
MMU notifiers, but that doesn't happen---so it just keeps mapping and
unmapping the *wrong* PFN after the userspace page tables change.
In the !IOMEM case at least the stale page *is* pinned all the time it's
cached, so it won't be freed and reused by anyone else while still
receiving the steal time updates. The map/unmap dance only takes care
of the KVM administrivia such as marking the page dirty.
Until the gfn_to_pfn cache handles the remapping automatically by
integrating with the MMU notifiers, we might as well not get a
kernel mapping of it, and use the perfectly serviceable userspace HVA
that we already have. We just need to implement the atomic xchg on
the userspace address with appropriate exception handling, which is
fairly trivial.
Cc: stable@vger.kernel.org
Fixes: b043138246 ("x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <3645b9b889dac6438394194bb5586a46b68d581f.camel@infradead.org>
[I didn't entirely agree with David's assessment of the
usefulness of the gfn_to_pfn cache, and integrated the outcome
of the discussion in the above commit message. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
For SEV to work with intra host migration, contents of the SEV info struct
such as the ASID (used to index the encryption key in the AMD SP) and
the list of memory regions need to be transferred to the target VM.
This change adds a commands for a target VMM to get a source SEV VM's sev
info.
Signed-off-by: Peter Gonda <pgonda@google.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Marc Orr <marcorr@google.com>
Cc: Marc Orr <marcorr@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Wanpeng Li <wanpengli@tencent.com>
Cc: Jim Mattson <jmattson@google.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Message-Id: <20211021174303.385706-3-pgonda@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
* More progress on the protected VM front, now with the full
fixed feature set as well as the limitation of some hypercalls
after initialisation.
* Cleanup of the RAZ/WI sysreg handling, which was pointlessly
complicated
* Fixes for the vgic placement in the IPA space, together with a
bunch of selftests
* More memcg accounting of the memory allocated on behalf of a guest
* Timer and vgic selftests
* Workarounds for the Apple M1 broken vgic implementation
* KConfig cleanups
* New kvmarm.mode=none option, for those who really dislike us
RISC-V:
* New KVM port.
x86:
* New API to control TSC offset from userspace
* TSC scaling for nested hypervisors on SVM
* Switch masterclock protection from raw_spin_lock to seqcount
* Clean up function prototypes in the page fault code and avoid
repeated memslot lookups
* Convey the exit reason to userspace on emulation failure
* Configure time between NX page recovery iterations
* Expose Predictive Store Forwarding Disable CPUID leaf
* Allocate page tracking data structures lazily (if the i915
KVM-GT functionality is not compiled in)
* Cleanups, fixes and optimizations for the shadow MMU code
s390:
* SIGP Fixes
* initial preparations for lazy destroy of secure VMs
* storage key improvements/fixes
* Log the guest CPNC
Starting from this release, KVM-PPC patches will come from
Michael Ellerman's PPC tree.
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmGBOiEUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroNowwf/axlx3g9sgCwQHr12/6UF/7hL/RwP
9z+pGiUzjl2YQE+RjSvLqyd6zXh+h4dOdOKbZDLSkSTbcral/8U70ojKnQsXM0XM
1LoymxBTJqkgQBLm9LjYreEbzrPV4irk4ygEmuk3CPOHZu8xX1ei6c5LdandtM/n
XVUkXsQY+STkmnGv4P3GcPoDththCr0tBTWrFWtxa0w9hYOxx0ay1AZFlgM4FFX0
QFuRc8VBLoDJpIUjbkhsIRIbrlHc/YDGjuYnAU7lV/CIME8vf2BW6uBwIZJdYcDj
0ejozLjodEnuKXQGnc8sXFioLX2gbMyQJEvwCgRvUu/EU7ncFm1lfs7THQ==
=UxKM
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
"ARM:
- More progress on the protected VM front, now with the full fixed
feature set as well as the limitation of some hypercalls after
initialisation.
- Cleanup of the RAZ/WI sysreg handling, which was pointlessly
complicated
- Fixes for the vgic placement in the IPA space, together with a
bunch of selftests
- More memcg accounting of the memory allocated on behalf of a guest
- Timer and vgic selftests
- Workarounds for the Apple M1 broken vgic implementation
- KConfig cleanups
- New kvmarm.mode=none option, for those who really dislike us
RISC-V:
- New KVM port.
x86:
- New API to control TSC offset from userspace
- TSC scaling for nested hypervisors on SVM
- Switch masterclock protection from raw_spin_lock to seqcount
- Clean up function prototypes in the page fault code and avoid
repeated memslot lookups
- Convey the exit reason to userspace on emulation failure
- Configure time between NX page recovery iterations
- Expose Predictive Store Forwarding Disable CPUID leaf
- Allocate page tracking data structures lazily (if the i915 KVM-GT
functionality is not compiled in)
- Cleanups, fixes and optimizations for the shadow MMU code
s390:
- SIGP Fixes
- initial preparations for lazy destroy of secure VMs
- storage key improvements/fixes
- Log the guest CPNC
Starting from this release, KVM-PPC patches will come from Michael
Ellerman's PPC tree"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
RISC-V: KVM: fix boolreturn.cocci warnings
RISC-V: KVM: remove unneeded semicolon
RISC-V: KVM: Fix GPA passed to __kvm_riscv_hfence_gvma_xyz() functions
RISC-V: KVM: Factor-out FP virtualization into separate sources
KVM: s390: add debug statement for diag 318 CPNC data
KVM: s390: pv: properly handle page flags for protected guests
KVM: s390: Fix handle_sske page fault handling
KVM: x86: SGX must obey the KVM_INTERNAL_ERROR_EMULATION protocol
KVM: x86: On emulation failure, convey the exit reason, etc. to userspace
KVM: x86: Get exit_reason as part of kvm_x86_ops.get_exit_info
KVM: x86: Clarify the kvm_run.emulation_failure structure layout
KVM: s390: Add a routine for setting userspace CPU state
KVM: s390: Simplify SIGP Set Arch handling
KVM: s390: pv: avoid stalls when making pages secure
KVM: s390: pv: avoid stalls for kvm_s390_pv_init_vm
KVM: s390: pv: avoid double free of sida page
KVM: s390: pv: add macros for UVC CC values
s390/mm: optimize reset_guest_reference_bit()
s390/mm: optimize set_guest_storage_key()
s390/mm: no need for pte_alloc_map_lock() if we know the pmd is present
...
- Cleanup of extable fixup handling to be more robust, which in turn
allows to make the FPU exception fixups more robust as well.
- Change the return code for signal frame related failures from explicit
error codes to a boolean fail/success as that's all what the calling
code evaluates.
- A large refactoring of the FPU code to prepare for adding AMX support:
- Distangle the public header maze and remove especially the misnomed
kitchen sink internal.h which is despite it's name included all over
the place.
- Add a proper abstraction for the register buffer storage (struct
fpstate) which allows to dynamically size the buffer at runtime by
flipping the pointer to the buffer container from the default
container which is embedded in task_struct::tread::fpu to a
dynamically allocated container with a larger register buffer.
- Convert the code over to the new fpstate mechanism.
- Consolidate the KVM FPU handling by moving the FPU related code into
the FPU core which removes the number of exports and avoids adding
even more export when AMX has to be supported in KVM. This also
removes duplicated code which was of course unnecessary different and
incomplete in the KVM copy.
- Simplify the KVM FPU buffer handling by utilizing the new fpstate
container and just switching the buffer pointer from the user space
buffer to the KVM guest buffer when entering vcpu_run() and flipping
it back when leaving the function. This cuts the memory requirements
of a vCPU for FPU buffers in half and avoids pointless memory copy
operations.
This also solves the so far unresolved problem of adding AMX support
because the current FPU buffer handling of KVM inflicted a circular
dependency between adding AMX support to the core and to KVM. With
the new scheme of switching fpstate AMX support can be added to the
core code without affecting KVM.
- Replace various variables with proper data structures so the extra
information required for adding dynamically enabled FPU features (AMX)
can be added in one place
- Add AMX (Advanved Matrix eXtensions) support (finally):
AMX is a large XSTATE component which is going to be available with
Saphire Rapids XEON CPUs. The feature comes with an extra MSR (MSR_XFD)
which allows to trap the (first) use of an AMX related instruction,
which has two benefits:
1) It allows the kernel to control access to the feature
2) It allows the kernel to dynamically allocate the large register
state buffer instead of burdening every task with the the extra 8K
or larger state storage.
It would have been great to gain this kind of control already with
AVX512.
The support comes with the following infrastructure components:
1) arch_prctl() to
- read the supported features (equivalent to XGETBV(0))
- read the permitted features for a task
- request permission for a dynamically enabled feature
Permission is granted per process, inherited on fork() and cleared
on exec(). The permission policy of the kernel is restricted to
sigaltstack size validation, but the syscall obviously allows
further restrictions via seccomp etc.
2) A stronger sigaltstack size validation for sys_sigaltstack(2) which
takes granted permissions and the potentially resulting larger
signal frame into account. This mechanism can also be used to
enforce factual sigaltstack validation independent of dynamic
features to help with finding potential victims of the 2K
sigaltstack size constant which is broken since AVX512 support was
added.
3) Exception handling for #NM traps to catch first use of a extended
feature via a new cause MSR. If the exception was caused by the use
of such a feature, the handler checks permission for that
feature. If permission has not been granted, the handler sends a
SIGILL like the #UD handler would do if the feature would have been
disabled in XCR0. If permission has been granted, then a new fpstate
which fits the larger buffer requirement is allocated.
In the unlikely case that this allocation fails, the handler sends
SIGSEGV to the task. That's not elegant, but unavoidable as the
other discussed options of preallocation or full per task
permissions come with their own set of horrors for kernel and/or
userspace. So this is the lesser of the evils and SIGSEGV caused by
unexpected memory allocation failures is not a fundamentally new
concept either.
When allocation succeeds, the fpstate properties are filled in to
reflect the extended feature set and the resulting sizes, the
fpu::fpstate pointer is updated accordingly and the trap is disarmed
for this task permanently.
4) Enumeration and size calculations
5) Trap switching via MSR_XFD
The XFD (eXtended Feature Disable) MSR is context switched with the
same life time rules as the FPU register state itself. The mechanism
is keyed off with a static key which is default disabled so !AMX
equipped CPUs have zero overhead. On AMX enabled CPUs the overhead
is limited by comparing the tasks XFD value with a per CPU shadow
variable to avoid redundant MSR writes. In case of switching from a
AMX using task to a non AMX using task or vice versa, the extra MSR
write is obviously inevitable.
All other places which need to be aware of the variable feature sets
and resulting variable sizes are not affected at all because they
retrieve the information (feature set, sizes) unconditonally from
the fpstate properties.
6) Enable the new AMX states
Note, this is relatively new code despite the fact that AMX support is in
the works for more than a year now.
The big refactoring of the FPU code, which allowed to do a proper
integration has been started exactly 3 weeks ago. Refactoring of the
existing FPU code and of the original AMX patches took a week and has
been subject to extensive review and testing. The only fallout which has
not been caught in review and testing right away was restricted to AMX
enabled systems, which is completely irrelevant for anyone outside Intel
and their early access program. There might be dragons lurking as usual,
but so far the fine grained refactoring has held up and eventual yet
undetected fallout is bisectable and should be easily addressable before
the 5.16 release. Famous last words...
Many thanks to Chang Bae and Dave Hansen for working hard on this and
also to the various test teams at Intel who reserved extra capacity to
follow the rapid development of this closely which provides the
confidence level required to offer this rather large update for inclusion
into 5.16-rc1.
-----BEGIN PGP SIGNATURE-----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=x3WL
-----END PGP SIGNATURE-----
Merge tag 'x86-fpu-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 fpu updates from Thomas Gleixner:
- Cleanup of extable fixup handling to be more robust, which in turn
allows to make the FPU exception fixups more robust as well.
- Change the return code for signal frame related failures from
explicit error codes to a boolean fail/success as that's all what the
calling code evaluates.
- A large refactoring of the FPU code to prepare for adding AMX
support:
- Distangle the public header maze and remove especially the
misnomed kitchen sink internal.h which is despite it's name
included all over the place.
- Add a proper abstraction for the register buffer storage (struct
fpstate) which allows to dynamically size the buffer at runtime
by flipping the pointer to the buffer container from the default
container which is embedded in task_struct::tread::fpu to a
dynamically allocated container with a larger register buffer.
- Convert the code over to the new fpstate mechanism.
- Consolidate the KVM FPU handling by moving the FPU related code
into the FPU core which removes the number of exports and avoids
adding even more export when AMX has to be supported in KVM.
This also removes duplicated code which was of course
unnecessary different and incomplete in the KVM copy.
- Simplify the KVM FPU buffer handling by utilizing the new
fpstate container and just switching the buffer pointer from the
user space buffer to the KVM guest buffer when entering
vcpu_run() and flipping it back when leaving the function. This
cuts the memory requirements of a vCPU for FPU buffers in half
and avoids pointless memory copy operations.
This also solves the so far unresolved problem of adding AMX
support because the current FPU buffer handling of KVM inflicted
a circular dependency between adding AMX support to the core and
to KVM. With the new scheme of switching fpstate AMX support can
be added to the core code without affecting KVM.
- Replace various variables with proper data structures so the
extra information required for adding dynamically enabled FPU
features (AMX) can be added in one place
- Add AMX (Advanced Matrix eXtensions) support (finally):
AMX is a large XSTATE component which is going to be available with
Saphire Rapids XEON CPUs. The feature comes with an extra MSR
(MSR_XFD) which allows to trap the (first) use of an AMX related
instruction, which has two benefits:
1) It allows the kernel to control access to the feature
2) It allows the kernel to dynamically allocate the large register
state buffer instead of burdening every task with the the extra
8K or larger state storage.
It would have been great to gain this kind of control already with
AVX512.
The support comes with the following infrastructure components:
1) arch_prctl() to
- read the supported features (equivalent to XGETBV(0))
- read the permitted features for a task
- request permission for a dynamically enabled feature
Permission is granted per process, inherited on fork() and
cleared on exec(). The permission policy of the kernel is
restricted to sigaltstack size validation, but the syscall
obviously allows further restrictions via seccomp etc.
2) A stronger sigaltstack size validation for sys_sigaltstack(2)
which takes granted permissions and the potentially resulting
larger signal frame into account. This mechanism can also be used
to enforce factual sigaltstack validation independent of dynamic
features to help with finding potential victims of the 2K
sigaltstack size constant which is broken since AVX512 support
was added.
3) Exception handling for #NM traps to catch first use of a extended
feature via a new cause MSR. If the exception was caused by the
use of such a feature, the handler checks permission for that
feature. If permission has not been granted, the handler sends a
SIGILL like the #UD handler would do if the feature would have
been disabled in XCR0. If permission has been granted, then a new
fpstate which fits the larger buffer requirement is allocated.
In the unlikely case that this allocation fails, the handler
sends SIGSEGV to the task. That's not elegant, but unavoidable as
the other discussed options of preallocation or full per task
permissions come with their own set of horrors for kernel and/or
userspace. So this is the lesser of the evils and SIGSEGV caused
by unexpected memory allocation failures is not a fundamentally
new concept either.
When allocation succeeds, the fpstate properties are filled in to
reflect the extended feature set and the resulting sizes, the
fpu::fpstate pointer is updated accordingly and the trap is
disarmed for this task permanently.
4) Enumeration and size calculations
5) Trap switching via MSR_XFD
The XFD (eXtended Feature Disable) MSR is context switched with
the same life time rules as the FPU register state itself. The
mechanism is keyed off with a static key which is default
disabled so !AMX equipped CPUs have zero overhead. On AMX enabled
CPUs the overhead is limited by comparing the tasks XFD value
with a per CPU shadow variable to avoid redundant MSR writes. In
case of switching from a AMX using task to a non AMX using task
or vice versa, the extra MSR write is obviously inevitable.
All other places which need to be aware of the variable feature
sets and resulting variable sizes are not affected at all because
they retrieve the information (feature set, sizes) unconditonally
from the fpstate properties.
6) Enable the new AMX states
Note, this is relatively new code despite the fact that AMX support
is in the works for more than a year now.
The big refactoring of the FPU code, which allowed to do a proper
integration has been started exactly 3 weeks ago. Refactoring of the
existing FPU code and of the original AMX patches took a week and has
been subject to extensive review and testing. The only fallout which
has not been caught in review and testing right away was restricted
to AMX enabled systems, which is completely irrelevant for anyone
outside Intel and their early access program. There might be dragons
lurking as usual, but so far the fine grained refactoring has held up
and eventual yet undetected fallout is bisectable and should be
easily addressable before the 5.16 release. Famous last words...
Many thanks to Chang Bae and Dave Hansen for working hard on this and
also to the various test teams at Intel who reserved extra capacity
to follow the rapid development of this closely which provides the
confidence level required to offer this rather large update for
inclusion into 5.16-rc1
* tag 'x86-fpu-2021-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (110 commits)
Documentation/x86: Add documentation for using dynamic XSTATE features
x86/fpu: Include vmalloc.h for vzalloc()
selftests/x86/amx: Add context switch test
selftests/x86/amx: Add test cases for AMX state management
x86/fpu/amx: Enable the AMX feature in 64-bit mode
x86/fpu: Add XFD handling for dynamic states
x86/fpu: Calculate the default sizes independently
x86/fpu/amx: Define AMX state components and have it used for boot-time checks
x86/fpu/xstate: Prepare XSAVE feature table for gaps in state component numbers
x86/fpu/xstate: Add fpstate_realloc()/free()
x86/fpu/xstate: Add XFD #NM handler
x86/fpu: Update XFD state where required
x86/fpu: Add sanity checks for XFD
x86/fpu: Add XFD state to fpstate
x86/msr-index: Add MSRs for XFD
x86/cpufeatures: Add eXtended Feature Disabling (XFD) feature bit
x86/fpu: Reset permission and fpstate on exec()
x86/fpu: Prepare fpu_clone() for dynamically enabled features
x86/fpu/signal: Prepare for variable sigframe length
x86/signal: Use fpu::__state_user_size for sigalt stack validation
...
* Fixes for Xen emulator bugs showing up as debug kernel WARNs
* Fix another issue with SEV/ES string I/O VMGEXITs
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmF6uGIUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroNRagf/Srvk9lNcRh4cEzsczErKMyr3xOqA
jgsTSqgl1ExJI9sBLMpVYBOFGILMaMSrhLPIltKPy0Bj/E+hw8WOQwPa44QjWlSD
MAUxO1Nryt9Luc2L8uSd1c//g4fr4V1BhOaumk1lM14Q8EDfQBcDIMI2ZKueMU1+
2Q+n8/AsG63jQIINwKNidof0dzRtbfcE30Wq/8QHttIPo5wt6l0YClOlOikqNY8N
5+WSQFmuutHIXftq5Jb/Ldn/+HVukWZyZOEVwLnBpM9uBvIubNgcEakqvxsaVtAn
FHdvnA+Bk99/Xuhl+wRLQo8ofzQIQ13RQv3HPArJAJv34oAJZx2rNObVlA==
=6ofB
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm fixes from Paolo Bonzini:
- Fixes for s390 interrupt delivery
- Fixes for Xen emulator bugs showing up as debug kernel WARNs
- Fix another issue with SEV/ES string I/O VMGEXITs
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: x86: Take srcu lock in post_kvm_run_save()
KVM: SEV-ES: fix another issue with string I/O VMGEXITs
KVM: x86/xen: Fix kvm_xen_has_interrupt() sleeping in kvm_vcpu_block()
KVM: x86: switch pvclock_gtod_sync_lock to a raw spinlock
KVM: s390: preserve deliverable_mask in __airqs_kick_single_vcpu
KVM: s390: clear kicked_mask before sleeping again
Should instruction emulation fail, include the VM exit reason, etc. in
the emulation_failure data passed to userspace, in order that the VMM
can report it as a debugging aid when describing the failure.
Suggested-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: David Edmondson <david.edmondson@oracle.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210920103737.2696756-4-david.edmondson@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Extend the get_exit_info static call to provide the reason for the VM
exit. Modify relevant trace points to use this rather than extracting
the reason in the caller.
Signed-off-by: David Edmondson <david.edmondson@oracle.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210920103737.2696756-3-david.edmondson@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
For the upcoming AMX support it's necessary to do a proper integration with
KVM. Currently KVM allocates two FPU structs which are used for saving the user
state of the vCPU thread and restoring the guest state when entering
vcpu_run() and doing the reverse operation before leaving vcpu_run().
With the new fpstate mechanism this can be reduced to one extra buffer by
swapping the fpstate pointer in current:🧵:fpu. This makes the
upcoming support for AMX and XFD simpler because then fpstate information
(features, sizes, xfd) are always consistent and it does not require any
nasty workarounds.
Convert the KVM FPU code over to this new scheme.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20211022185313.019454292@linutronix.de
Use a rw_semaphore instead of a mutex to coordinate APICv updates so that
vCPUs responding to requests can take the lock for read and run in
parallel. Using a mutex forces serialization of vCPUs even though
kvm_vcpu_update_apicv() only touches data local to that vCPU or is
protected by a different lock, e.g. SVM's ir_list_lock.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211022004927.1448382-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The PIO scratch buffer is larger than a single page, and therefore
it is not possible to copy it in a single step to vcpu->arch/pio_data.
Bound each call to emulator_pio_in/out to a single page; keep
track of how many I/O operations are left in vcpu->arch.sev_pio_count,
so that the operation can be restarted in the complete_userspace_io
callback.
For OUT, this means that the previous kvm_sev_es_outs implementation
becomes an iterator of the loop, and we can consume the sev_pio_data
buffer before leaving to userspace.
For IN, instead, consuming the buffer and decreasing sev_pio_count
is always done in the complete_userspace_io callback, because that
is when the memcpy is done into sev_pio_data.
Cc: stable@vger.kernel.org
Fixes: 7ed9abfe8e ("KVM: SVM: Support string IO operations for an SEV-ES guest")
Reported-by: Felix Wilhelm <fwilhelm@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We will be using this field for OUTS emulation as well, in case the
data that is pushed via OUTS spans more than one page. In that case,
there will be a need to save the data pointer across exits to userspace.
So, change the name to something that refers to any kind of PIO.
Also spell out what it is used for, namely SEV-ES.
No functional change intended.
Cc: stable@vger.kernel.org
Fixes: 7ed9abfe8e ("KVM: SVM: Support string IO operations for an SEV-ES guest")
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paul pointed out the error messages when KVM fails to load are unhelpful
in understanding exactly what went wrong if userspace probes the "wrong"
module.
Add a mandatory kvm_x86_ops field to track vendor module names, kvm_intel
and kvm_amd, and use the name for relevant error message when KVM fails
to load so that the user knows which module failed to load.
Opportunistically tweak the "disabled by bios" error message to clarify
that _support_ was disabled, not that the module itself was magically
disabled by BIOS.
Suggested-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211018183929.897461-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
SDM section 18.2.3 mentioned that:
"IA32_PERF_GLOBAL_OVF_CTL MSR allows software to clear overflow indicator(s) of
any general-purpose or fixed-function counters via a single WRMSR."
It is R/W mentioned by SDM, we read this msr on bare-metal during perf testing,
the value is always 0 for ICX/SKX boxes on hands. Let's fill get_msr
MSR_CORE_PERF_GLOBAL_OVF_CTRL w/ 0 as hardware behavior and drop
global_ovf_ctrl variable.
Tested-by: Like Xu <likexu@tencent.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1634631160-67276-2-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Unify the flags for rmaps and page tracking data, using a
single flag in struct kvm_arch and a single loop to go
over all the address spaces and memslots. This avoids
code duplication between alloc_all_memslots_rmaps and
kvm_page_track_enable_mmu_write_tracking.
Signed-off-by: David Stevens <stevensd@chromium.org>
[This patch is the delta between David's v2 and v3, with conflicts
fixed and my own commit message. - Paolo]
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
To date, VMM-directed TSC synchronization and migration has been a bit
messy. KVM has some baked-in heuristics around TSC writes to infer if
the VMM is attempting to synchronize. This is problematic, as it depends
on host userspace writing to the guest's TSC within 1 second of the last
write.
A much cleaner approach to configuring the guest's views of the TSC is to
simply migrate the TSC offset for every vCPU. Offsets are idempotent,
and thus not subject to change depending on when the VMM actually
reads/writes values from/to KVM. The VMM can then read the TSC once with
KVM_GET_CLOCK to capture a (realtime, host_tsc) pair at the instant when
the guest is paused.
Cc: David Matlack <dmatlack@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210916181538.968978-8-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Protect the reference point for kvmclock with a seqcount, so that
kvmclock updates for all vCPUs can proceed in parallel. Xen runstate
updates will also run in parallel and not bounce the kvmclock cacheline.
Of the variables that were protected by pvclock_gtod_sync_lock,
nr_vcpus_matched_tsc is different because it is updated outside
pvclock_update_vm_gtod_copy and read inside it. Therefore, we
need to keep it protected by a spinlock. In fact it must now
be a raw spinlock, because pvclock_update_vm_gtod_copy, being the
write-side of a seqcount, is non-preemptible. Since we already
have tsc_write_lock which is a raw spinlock, we can just use
tsc_write_lock as the lock that protects the write-side of the
seqcount.
Co-developed-by: Oliver Upton <oupton@google.com>
Message-Id: <20210916181538.968978-6-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Handling the migration of TSCs correctly is difficult, in part because
Linux does not provide userspace with the ability to retrieve a (TSC,
realtime) clock pair for a single instant in time. In lieu of a more
convenient facility, KVM can report similar information in the kvm_clock
structure.
Provide userspace with a host TSC & realtime pair iff the realtime clock
is based on the TSC. If userspace provides KVM_SET_CLOCK with a valid
realtime value, advance the KVM clock by the amount of elapsed time. Do
not step the KVM clock backwards, though, as it is a monotonic
oscillator.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210916181538.968978-5-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Avoid allocating the gfn_track arrays if nothing needs them. If there
are no external to KVM users of the API (i.e. no GVT-g), then page
tracking is only needed for shadow page tables. This means that when tdp
is enabled and there are no external users, then the gfn_track arrays
can be lazily allocated when the shadow MMU is actually used. This avoid
allocations equal to .05% of guest memory when nested virtualization is
not used, if the kernel is compiled without GVT-g.
Signed-off-by: David Stevens <stevensd@chromium.org>
Message-Id: <20210922045859.2011227-3-stevensd@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
By switching from kfree() to kvfree() in kvm_arch_free_vm() Arm64 can
use the common variant. This can be accomplished by adding another
macro __KVM_HAVE_ARCH_VM_FREE, which will be used only by x86 for now.
Further simplification can be achieved by adding __kvm_arch_free_vm()
doing the common part.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-Id: <20210903130808.30142-5-jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pass struct kvm_page_fault to mmu->page_fault() instead of
extracting the arguments from the struct. FNAME(page_fault) can use
the precomputed bools from the error code.
Suggested-by: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Updates to the kvmclock parameters needs to do a complicated dance of
KVM_REQ_MCLOCK_INPROGRESS and KVM_REQ_CLOCK_UPDATE in addition to taking
pvclock_gtod_sync_lock. Place that in two functions that can be called
on all of master clock update, KVM_SET_CLOCK, and Hyper-V reenlightenment.
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Open code the call to mmu->translate_gpa() when loading nested PDPTRs and
kill off the existing helper, kvm_read_guest_page_mmu(), to discourage
incorrect use. Reading guest memory straight from an L2 GPA is extremely
rare (as evidenced by the lack of users), as very few constructs in x86
specify physical addresses, even fewer are virtualized by KVM, and even
fewer yet require emulation of L2 by L0 KVM.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210831164224.1119728-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_MAX_VCPU_ID is not specifying the highest allowed vcpu-id, but the
number of allowed vcpu-ids. This has already led to confusion, so
rename KVM_MAX_VCPU_ID to KVM_MAX_VCPU_IDS to make its semantics more
clear
Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210913135745.13944-3-jgross@suse.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_make_vcpus_request_mask() already disables preemption so just like
kvm_make_all_cpus_request_except() it can be switched to using
pre-allocated per-cpu cpumasks. This allows for improvements for both
users of the function: in Hyper-V emulation code 'tlb_flush' can now be
dropped from 'struct kvm_vcpu_hv' and kvm_make_scan_ioapic_request_mask()
gets rid of dynamic allocation.
cpumask_available() checks in kvm_make_vcpu_request() and
kvm_kick_many_cpus() can now be dropped as they checks for an impossible
condition: kvm_init() makes sure per-cpu masks are allocated.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210903075141.403071-9-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Support for 710 VCPUs was tested by Red Hat since RHEL-8.4,
so increase KVM_SOFT_MAX_VCPUS to 710.
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20210903211600.2002377-4-ehabkost@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Increase KVM_MAX_VCPUS to 1024, so we can test larger VMs.
I'm not changing KVM_SOFT_MAX_VCPUS yet because I'm afraid it
might involve complicated questions around the meaning of
"supported" and "recommended" in the upstream tree.
KVM_SOFT_MAX_VCPUS will be changed in a separate patch.
For reference, visible effects of this change are:
- KVM_CAP_MAX_VCPUS will now return 1024 (of course)
- Default value for CPUID[HYPERV_CPUID_IMPLEMENT_LIMITS (00x40000005)].EAX
will now be 1024
- KVM_MAX_VCPU_ID will change from 1151 to 4096
- Size of struct kvm will increase from 19328 to 22272 bytes
(in x86_64)
- Size of struct kvm_ioapic will increase from 1780 to 5084 bytes
(in x86_64)
- Bitmap stack variables that will grow:
- At kvm_hv_flush_tlb() kvm_hv_send_ipi(),
vp_bitmap[] and vcpu_bitmap[] will now be 128 bytes long
- vcpu_bitmap at bioapic_write_indirect() will be 128 bytes long
once patch "KVM: x86: Fix stack-out-of-bounds memory access
from ioapic_write_indirect()" is applied
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20210903211600.2002377-3-ehabkost@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Instead of requiring KVM_MAX_VCPU_ID to be manually increased
every time we increase KVM_MAX_VCPUS, set it to 4*KVM_MAX_VCPUS.
This should be enough for CPU topologies where Cores-per-Package
and Packages-per-Socket are not powers of 2.
In practice, this increases KVM_MAX_VCPU_ID from 1023 to 1152.
The only side effect of this change is making some fields in
struct kvm_ioapic larger, increasing the struct size from 1628 to
1780 bytes (in x86_64).
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20210903211600.2002377-2-ehabkost@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When the 5-level page table CPU flag is set in the host, but the guest
has CR4.LA57=0 (including the case of a 32-bit guest), the top level of
the shadow NPT page tables will be fixed, consisting of one pointer to
a lower-level table and 511 non-present entries. Extend the existing
code that creates the fixed PML4 or PDP table, to provide a fixed PML5
table if needed.
This is not needed on EPT because the number of layers in the tables
is specified in the EPTP instead of depending on the host CR4.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Message-Id: <20210818165549.3771014-3-wei.huang2@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
AMD future CPUs will require a 5-level NPT if host CR4.LA57 is set.
To prevent kvm_mmu_get_tdp_level() from incorrectly changing NPT level
on behalf of CPUs, add a new parameter in kvm_configure_mmu() to force
a fixed TDP level.
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Message-Id: <20210818165549.3771014-2-wei.huang2@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_GUESTDBG_BLOCKIRQ will allow KVM to block all interrupts
while running.
This change is mostly intended for more robust single stepping
of the guest and it has the following benefits when enabled:
* Resuming from a breakpoint is much more reliable.
When resuming execution from a breakpoint, with interrupts enabled,
more often than not, KVM would inject an interrupt and make the CPU
jump immediately to the interrupt handler and eventually return to
the breakpoint, to trigger it again.
From the user point of view it looks like the CPU never executed a
single instruction and in some cases that can even prevent forward
progress, for example, when the breakpoint is placed by an automated
script (e.g lx-symbols), which does something in response to the
breakpoint and then continues the guest automatically.
If the script execution takes enough time for another interrupt to
arrive, the guest will be stuck on the same breakpoint RIP forever.
* Normal single stepping is much more predictable, since it won't
land the debugger into an interrupt handler.
* RFLAGS.TF has less chance to be leaked to the guest:
We set that flag behind the guest's back to do single stepping
but if single step lands us into an interrupt/exception handler
it will be leaked to the guest in the form of being pushed
to the stack.
This doesn't completely eliminate this problem as exceptions
can still happen, but at least this reduces the chances
of this happening.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210811122927.900604-6-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Existing KVM code tracks the number of large pages regardless of their
sizes. Therefore, when large page of 1GB (or larger) is adopted, the
information becomes less useful because lpages counts a mix of 1G and 2M
pages.
So remove the lpages since it is easy for user space to aggregate the info.
Instead, provide a comprehensive page stats of all sizes from 4K to 512G.
Suggested-by: Ben Gardon <bgardon@google.com>
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Mingwei Zhang <mizhang@google.com>
Cc: Jing Zhang <jingzhangos@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Message-Id: <20210803044607.599629-4-mizhang@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
APICV_INHIBIT_REASON_HYPERV is currently unconditionally forced upon
SynIC activation as SynIC's AutoEOI is incompatible with APICv/AVIC. It is,
however, possible to track whether the feature was actually used by the
guest and only inhibit APICv/AVIC when needed.
TLFS suggests a dedicated 'HV_DEPRECATING_AEOI_RECOMMENDED' flag to let
Windows know that AutoEOI feature should be avoided. While it's up to
KVM userspace to set the flag, KVM can help a bit by exposing global
APICv/AVIC enablement.
Maxim:
- always set HV_DEPRECATING_AEOI_RECOMMENDED in kvm_get_hv_cpuid,
since this feature can be used regardless of AVIC
Paolo:
- use arch.apicv_update_lock to protect the hv->synic_auto_eoi_used
instead of atomic ops
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210810205251.424103-12-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently on SVM, the kvm_request_apicv_update toggles the APICv
memslot without doing any synchronization.
If there is a mismatch between that memslot state and the AVIC state,
on one of the vCPUs, an APIC mmio access can be lost:
For example:
VCPU0: enable the APIC_ACCESS_PAGE_PRIVATE_MEMSLOT
VCPU1: access an APIC mmio register.
Since AVIC is still disabled on VCPU1, the access will not be intercepted
by it, and neither will it cause MMIO fault, but rather it will just be
read/written from/to the dummy page mapped into the
APIC_ACCESS_PAGE_PRIVATE_MEMSLOT.
Fix that by adding a lock guarding the AVIC state changes, and carefully
order the operations of kvm_request_apicv_update to avoid this race:
1. Take the lock
2. Send KVM_REQ_APICV_UPDATE
3. Update the apic inhibit reason
4. Release the lock
This ensures that at (2) all vCPUs are kicked out of the guest mode,
but don't yet see the new avic state.
Then only after (4) all other vCPUs can update their AVIC state and resume.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210810205251.424103-10-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Thanks to the former patches, it is now possible to keep the APICv
memslot always enabled, and it will be invisible to the guest
when it is inhibited
This code is based on a suggestion from Sean Christopherson:
https://lkml.org/lkml/2021/7/19/2970
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210810205251.424103-9-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Introduce kvm_mmu_slot_lpages() to calculcate lpage_info and rmap array size.
The other __kvm_mmu_slot_lpages() can take an extra parameter of npages rather
than fetching from the memslot pointer. Start to use the latter one in
kvm_alloc_memslot_metadata().
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210730220455.26054-4-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the declaration of kvm_spurious_fault() to KVM's "private" x86.h,
it should never be called by anything other than low level KVM code.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
[sean: rebased to a series without __ex()/__kvm_handle_fault_on_reboot()]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210809173955.1710866-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Remove the __kvm_handle_fault_on_reboot() and __ex() macros now that all
VMX and SVM instructions use asm goto to handle the fault (or in the
case of VMREAD, completely custom logic). Drop kvm_spurious_fault()'s
asmlinkage annotation as __kvm_handle_fault_on_reboot() was the only
flow that invoked it from assembly code.
Cc: Uros Bizjak <ubizjak@gmail.com>
Cc: Like Xu <like.xu.linux@gmail.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210809173955.1710866-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Commit ae561edeb4 ("KVM: x86: DR0-DR3 are not clear on reset") added code to
ensure eff_db are updated when they're modified through non-standard paths.
But there is no reason to also update hardware DRs unless hardware breakpoints
are active or DR exiting is disabled, and in those cases updating hardware is
handled by KVM_DEBUGREG_WONT_EXIT and KVM_DEBUGREG_BP_ENABLED.
KVM_DEBUGREG_RELOAD just causes unnecesarry load of hardware DRs and is better
to be removed.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Message-Id: <20210809174307.145263-1-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add yet another spinlock for the TDP MMU and take it when marking indirect
shadow pages unsync. When using the TDP MMU and L1 is running L2(s) with
nested TDP, KVM may encounter shadow pages for the TDP entries managed by
L1 (controlling L2) when handling a TDP MMU page fault. The unsync logic
is not thread safe, e.g. the kvm_mmu_page fields are not atomic, and
misbehaves when a shadow page is marked unsync via a TDP MMU page fault,
which runs with mmu_lock held for read, not write.
Lack of a critical section manifests most visibly as an underflow of
unsync_children in clear_unsync_child_bit() due to unsync_children being
corrupted when multiple CPUs write it without a critical section and
without atomic operations. But underflow is the best case scenario. The
worst case scenario is that unsync_children prematurely hits '0' and
leads to guest memory corruption due to KVM neglecting to properly sync
shadow pages.
Use an entirely new spinlock even though piggybacking tdp_mmu_pages_lock
would functionally be ok. Usurping the lock could degrade performance when
building upper level page tables on different vCPUs, especially since the
unsync flow could hold the lock for a comparatively long time depending on
the number of indirect shadow pages and the depth of the paging tree.
For simplicity, take the lock for all MMUs, even though KVM could fairly
easily know that mmu_lock is held for write. If mmu_lock is held for
write, there cannot be contention for the inner spinlock, and marking
shadow pages unsync across multiple vCPUs will be slow enough that
bouncing the kvm_arch cacheline should be in the noise.
Note, even though L2 could theoretically be given access to its own EPT
entries, a nested MMU must hold mmu_lock for write and thus cannot race
against a TDP MMU page fault. I.e. the additional spinlock only _needs_ to
be taken by the TDP MMU, as opposed to being taken by any MMU for a VM
that is running with the TDP MMU enabled. Holding mmu_lock for read also
prevents the indirect shadow page from being freed. But as above, keep
it simple and always take the lock.
Alternative #1, the TDP MMU could simply pass "false" for can_unsync and
effectively disable unsync behavior for nested TDP. Write protecting leaf
shadow pages is unlikely to noticeably impact traditional L1 VMMs, as such
VMMs typically don't modify TDP entries, but the same may not hold true for
non-standard use cases and/or VMMs that are migrating physical pages (from
L1's perspective).
Alternative #2, the unsync logic could be made thread safe. In theory,
simply converting all relevant kvm_mmu_page fields to atomics and using
atomic bitops for the bitmap would suffice. However, (a) an in-depth audit
would be required, (b) the code churn would be substantial, and (c) legacy
shadow paging would incur additional atomic operations in performance
sensitive paths for no benefit (to legacy shadow paging).
Fixes: a2855afc7e ("KVM: x86/mmu: Allow parallel page faults for the TDP MMU")
Cc: stable@vger.kernel.org
Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210812181815.3378104-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
gfn_to_hva_cache is not thread-safe, so it is usually used only within
a vCPU (whose code is protected by vcpu->mutex). The Xen interface
implementation has such a cache in kvm->arch, but it is not really
used except to store the location of the shared info page. Replace
shinfo_set and shinfo_cache with just the value that is passed via
KVM_XEN_ATTR_TYPE_SHARED_INFO; the only complication is that the
initialization value is not zero anymore and therefore kvm_xen_init_vm
needs to be introduced.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Based on our observations, after any vm-exit associated with vPMU, there
are at least two or more perf interfaces to be called for guest counter
emulation, such as perf_event_{pause, read_value, period}(), and each one
will {lock, unlock} the same perf_event_ctx. The frequency of calls becomes
more severe when guest use counters in a multiplexed manner.
Holding a lock once and completing the KVM request operations in the perf
context would introduce a set of impractical new interfaces. So we can
further optimize the vPMU implementation by avoiding repeated calls to
these interfaces in the KVM context for at least one pattern:
After we call perf_event_pause() once, the event will be disabled and its
internal count will be reset to 0. So there is no need to pause it again
or read its value. Once the event is paused, event period will not be
updated until the next time it's resumed or reprogrammed. And there is
also no need to call perf_event_period twice for a non-running counter,
considering the perf_event for a running counter is never paused.
Based on this implementation, for the following common usage of
sampling 4 events using perf on a 4u8g guest:
echo 0 > /proc/sys/kernel/watchdog
echo 25 > /proc/sys/kernel/perf_cpu_time_max_percent
echo 10000 > /proc/sys/kernel/perf_event_max_sample_rate
echo 0 > /proc/sys/kernel/perf_cpu_time_max_percent
for i in `seq 1 1 10`
do
taskset -c 0 perf record \
-e cpu-cycles -e instructions -e branch-instructions -e cache-misses \
/root/br_instr a
done
the average latency of the guest NMI handler is reduced from
37646.7 ns to 32929.3 ns (~1.14x speed up) on the Intel ICX server.
Also, in addition to collecting more samples, no loss of sampling
accuracy was observed compared to before the optimization.
Signed-off-by: Like Xu <likexu@tencent.com>
Message-Id: <20210728120705.6855-1-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
As alluded to in commit f36f3f2846 ("KVM: add "new" argument to
kvm_arch_commit_memory_region"), a bunch of other places where struct
kvm_memory_slot is used, needs to be refactored to preserve the
"const"ness of struct kvm_memory_slot across-the-board.
Signed-off-by: Hamza Mahfooz <someguy@effective-light.com>
Message-Id: <20210713023338.57108-1-someguy@effective-light.com>
[Do not touch body of slot_rmap_walk_init. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the EDX initialization at vCPU RESET, which is now identical between
VMX and SVM, into common code.
No functional change intended.
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210713163324.627647-20-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a new statistic max_mmu_rmap_size, which stores the maximum size of rmap
for the vm.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210625153214.43106-2-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This better reflects the purpose of this variable on AMD, since
on AMD the AVIC's memory slot can be enabled and disabled dynamically.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210623113002.111448-4-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a fallback mechanism to the in-kernel instruction emulator that
allows userspace the opportunity to process an instruction the emulator
was unable to. When the in-kernel instruction emulator fails to process
an instruction it will either inject a #UD into the guest or exit to
userspace with exit reason KVM_INTERNAL_ERROR. This is because it does
not know how to proceed in an appropriate manner. This feature lets
userspace get involved to see if it can figure out a better path
forward.
Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Reviewed-by: David Edmondson <david.edmondson@oracle.com>
Message-Id: <20210510144834.658457-2-aaronlewis@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop the pre-computed last_nonleaf_level, which is arguably wrong and at
best confusing. Per the comment:
Can have large pages at levels 2..last_nonleaf_level-1.
the intent of the variable would appear to be to track what levels can
_legally_ have large pages, but that intent doesn't align with reality.
The computed value will be wrong for 5-level paging, or if 1gb pages are
not supported.
The flawed code is not a problem in practice, because except for 32-bit
PSE paging, bit 7 is reserved if large pages aren't supported at the
level. Take advantage of this invariant and simply omit the level magic
math for 64-bit page tables (including PAE).
For 32-bit paging (non-PAE), the adjustments are needed purely because
bit 7 is ignored if PSE=0. Retain that logic as is, but make
is_last_gpte() unique per PTTYPE so that the PSE check is avoided for
PAE and EPT paging. In the spirit of avoiding branches, bump the "last
nonleaf level" for 32-bit PSE paging by adding the PSE bit itself.
Note, bit 7 is ignored or has other meaning in CR3/EPTP, but despite
FNAME(walk_addr_generic) briefly grabbing CR3/EPTP in "pte", they are
not PTEs and will blow up all the other gpte helpers.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-51-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Expand the comments for the MMU roles. The interactions with gfn_track
PGD reuse in particular are hairy.
Regarding PGD reuse, add comments in the nested virtualization flows to
call out why kvm_init_mmu() is unconditionally called even when nested
TDP is used.
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-50-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop kvm_mmu.nx as there no consumers left.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-39-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rename "nxe" to "efer_nx" so that future macro magic can use the pattern
<reg>_<bit> for all CR0, CR4, and EFER bits that included in the role.
Using "efer_nx" also makes it clear that the role bit reflects EFER.NX,
not the NX bit in the corresponding PTE.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-25-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop MAXPHYADDR from mmu_role now that all MMUs have their role
invalidated after a CPUID update. Invalidating the role forces all MMUs
to re-evaluate the guest's MAXPHYADDR, and the guest's MAXPHYADDR can
only be changed only through a CPUID update.
This reverts commit de3ccd26fa.
Cc: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Warn userspace that KVM_SET_CPUID{,2} after KVM_RUN "may" cause guest
instability. Initialize last_vmentry_cpu to -1 and use it to detect if
the vCPU has been run at least once when its CPUID model is changed.
KVM does not correctly handle changes to paging related settings in the
guest's vCPU model after KVM_RUN, e.g. MAXPHYADDR, GBPAGES, etc... KVM
could theoretically zap all shadow pages, but actually making that happen
is a mess due to lock inversion (vcpu->mutex is held). And even then,
updating paging settings on the fly would only work if all vCPUs are
stopped, updated in concert with identical settings, then restarted.
To support running vCPUs with different vCPU models (that affect paging),
KVM would need to track all relevant information in kvm_mmu_page_role.
Note, that's the _page_ role, not the full mmu_role. Updating mmu_role
isn't sufficient as a vCPU can reuse a shadow page translation that was
created by a vCPU with different settings and thus completely skip the
reserved bit checks (that are tied to CPUID).
Tracking CPUID state in kvm_mmu_page_role is _extremely_ undesirable as
it would require doubling gfn_track from a u16 to a u32, i.e. would
increase KVM's memory footprint by 2 bytes for every 4kb of guest memory.
E.g. MAXPHYADDR (6 bits), GBPAGES, AMD vs. INTEL = 1 bit, and SEV C-BIT
would all need to be tracked.
In practice, there is no remotely sane use case for changing any paging
related CPUID entries on the fly, so just sweep it under the rug (after
yelling at userspace).
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Invalidate all MMUs' roles after a CPUID update to force reinitizliation
of the MMU context/helpers. Despite the efforts of commit de3ccd26fa
("KVM: MMU: record maximum physical address width in kvm_mmu_extended_role"),
there are still a handful of CPUID-based properties that affect MMU
behavior but are not incorporated into mmu_role. E.g. 1gb hugepage
support, AMD vs. Intel handling of bit 8, and SEV's C-Bit location all
factor into the guest's reserved PTE bits.
The obvious alternative would be to add all such properties to mmu_role,
but doing so provides no benefit over simply forcing a reinitialization
on every CPUID update, as setting guest CPUID is a rare operation.
Note, reinitializing all MMUs after a CPUID update does not fix all of
KVM's woes. Specifically, kvm_mmu_page_role doesn't track the CPUID
properties, which means that a vCPU can reuse shadow pages that should
not exist for the new vCPU model, e.g. that map GPAs that are now illegal
(due to MAXPHYADDR changes) or that set bits that are now reserved
(PAGE_SIZE for 1gb pages), etc...
Tracking the relevant CPUID properties in kvm_mmu_page_role would address
the majority of problems, but fully tracking that much state in the
shadow page role comes with an unpalatable cost as it would require a
non-trivial increase in KVM's memory footprint. The GBPAGES case is even
worse, as neither Intel nor AMD provides a way to disable 1gb hugepage
support in the hardware page walker, i.e. it's a virtualization hole that
can't be closed when using TDP.
In other words, resetting the MMU after a CPUID update is largely a
superficial fix. But, it will allow reverting the tracking of MAXPHYADDR
in the mmu_role, and that case in particular needs to mostly work because
KVM's shadow_root_level depends on guest MAXPHYADDR when 5-level paging
is supported. For cases where KVM botches guest behavior, the damage is
limited to that guest. But for the shadow_root_level, a misconfigured
MMU can cause KVM to incorrectly access memory, e.g. due to walking off
the end of its shadow page tables.
Fixes: 7dcd575520 ("x86/kvm/mmu: check if tdp/shadow MMU reconfiguration is needed")
Cc: Yu Zhang <yu.c.zhang@linux.intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Restore CR4.LA57 to the mmu_role to fix an amusing edge case with nested
virtualization. When KVM (L0) is using TDP, CR4.LA57 is not reflected in
mmu_role.base.level because that tracks the shadow root level, i.e. TDP
level. Normally, this is not an issue because LA57 can't be toggled
while long mode is active, i.e. the guest has to first disable paging,
then toggle LA57, then re-enable paging, thus ensuring an MMU
reinitialization.
But if L1 is crafty, it can load a new CR4 on VM-Exit and toggle LA57
without having to bounce through an unpaged section. L1 can also load a
new CR3 on exit, i.e. it doesn't even need to play crazy paging games, a
single entry PML5 is sufficient. Such shenanigans are only problematic
if L0 and L1 use TDP, otherwise L1 and L2 share an MMU that gets
reinitialized on nested VM-Enter/VM-Exit due to mmu_role.base.guest_mode.
Note, in the L2 case with nested TDP, even though L1 can switch between
L2s with different LA57 settings, thus bypassing the paging requirement,
in that case KVM's nested_mmu will track LA57 in base.level.
This reverts commit 8053f924ca.
Fixes: 8053f924ca ("KVM: x86/mmu: Drop kvm_mmu_extended_role.cr4_la57 hack")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210622175739.3610207-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Generic KVM stats are those collected in architecture independent code
or those supported by all architectures; put all generic statistics in
a separate structure. This ensures that they are defined the same way
in the statistics API which is being added, removing duplication among
different architectures in the declaration of the descriptors.
No functional change intended.
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210618222709.1858088-2-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This hypercall is used by the SEV guest to notify a change in the page
encryption status to the hypervisor. The hypercall should be invoked
only when the encryption attribute is changed from encrypted -> decrypted
and vice versa. By default all guest pages are considered encrypted.
The hypercall exits to userspace to manage the guest shared regions and
integrate with the userspace VMM's migration code.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: x86@kernel.org
Cc: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Steve Rutherford <srutherford@google.com>
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <90778988e1ee01926ff9cac447aacb745f954c8c.1623174621.git.ashish.kalra@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When emulating INVVPID for L1, free only L2+ roots, using the guest_mode
tag in the MMU role to identify L2+ roots. From L1's perspective, its
own TLB entries use VPID=0, and INVVPID is not requied to invalidate such
entries. Per Intel's SDM, INVVPID _may_ invalidate entries with VPID=0,
but it is not required to do so.
Cc: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210609234235.1244004-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop skip_mmu_sync and skip_tlb_flush from __kvm_mmu_new_pgd() now that
all call sites unconditionally skip both the sync and flush.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210609234235.1244004-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Trigger a full TLB flush on behalf of the guest on nested VM-Enter and
VM-Exit when VPID is disabled for L2. kvm_mmu_new_pgd() syncs only the
current PGD, which can theoretically leave stale, unsync'd entries in a
previous guest PGD, which could be consumed if L2 is allowed to load CR3
with PCID_NOFLUSH=1.
Rename KVM_REQ_HV_TLB_FLUSH to KVM_REQ_TLB_FLUSH_GUEST so that it can
be utilized for its obvious purpose of emulating a guest TLB flush.
Note, there is no change the actual TLB flush executed by KVM, even
though the fast PGD switch uses KVM_REQ_TLB_FLUSH_CURRENT. When VPID is
disabled for L2, vpid02 is guaranteed to be '0', and thus
nested_get_vpid02() will return the VPID that is shared by L1 and L2.
Generate the request outside of kvm_mmu_new_pgd(), as getting the common
helper to correctly identify which requested is needed is quite painful.
E.g. using KVM_REQ_TLB_FLUSH_GUEST when nested EPT is in play is wrong as
a TLB flush from the L1 kernel's perspective does not invalidate EPT
mappings. And, by using KVM_REQ_TLB_FLUSH_GUEST, nVMX can do future
simplification by moving the logic into nested_vmx_transition_tlb_flush().
Fixes: 41fab65e7c ("KVM: nVMX: Skip MMU sync on nested VMX transition when possible")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210609234235.1244004-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
if new KVM_*_SREGS2 ioctls are used, the PDPTRs are
a part of the migration state and are correctly
restored by those ioctls.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210607090203.133058-9-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Kill off pdptrs_changed() and instead go through the full kvm_set_cr3()
for PAE guest, even if the new CR3 is the same as the current CR3. For
VMX, and SVM with NPT enabled, the PDPTRs are unconditionally marked as
unavailable after VM-Exit, i.e. the optimization is dead code except for
SVM without NPT.
In the unlikely scenario that anyone cares about SVM without NPT _and_ a
PAE guest, they've got bigger problems if their guest is loading the same
CR3 so frequently that the performance of kvm_set_cr3() is notable,
especially since KVM's fast PGD switching means reloading the same CR3
does not require a full rebuild. Given that PAE and PCID are mutually
exclusive, i.e. a sync and flush are guaranteed in any case, the actual
benefits of the pdptrs_changed() optimization are marginal at best.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210607090203.133058-4-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Limiting exposed Hyper-V features requires a fast way to check if the
particular feature is exposed in guest visible CPUIDs or not. To aboid
looping through all CPUID entries on every hypercall/MSR access cache
the required leaves on CPUID update.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210521095204.2161214-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Modeled after KVM_CAP_ENFORCE_PV_FEATURE_CPUID, the new capability allows
for limiting Hyper-V features to those exposed to the guest in Hyper-V
CPUIDs (0x40000003, 0x40000004, ...).
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210521095204.2161214-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently the remote TLB flush logic is specific to VMX.
Move it to a common place so that SVM can use it as well.
Signed-off-by: Vineeth Pillai <viremana@linux.microsoft.com>
Message-Id: <4f4e4ca19778437dae502f44363a38e99e3ef5d1.1622730232.git.viremana@linux.microsoft.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add the following per-VCPU statistic to KVM debugfs to show if a given
VCPU is in guest mode:
guest_mode
Also add this as a per-VM statistic to KVM debugfs to show the total number
of VCPUs that are in guest mode in a given VM.
Signed-off-by: Krish Sadhukhan <Krish.Sadhukhan@oracle.com>
Message-Id: <20210609180340.104248-3-krish.sadhukhan@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Now that .post_leave_smm() is gone, drop "pre_" from the remaining
helpers. The helpers aren't invoked purely before SMI/RSM processing,
e.g. both helpers are invoked after state is snapshotted (from regs or
SMRAM), and the RSM helper is invoked after some amount of register state
has been stuffed.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210609185619.992058-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Now that APICv/AVIC enablement is kept in common 'enable_apicv' variable,
there's no need to call kvm_apicv_init() from vendor specific code.
No functional change intended.
Reviewed-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210609150911.1471882-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Unify VMX and SVM code by moving APICv/AVIC enablement tracking to common
'enable_apicv' variable. Note: unlike APICv, AVIC is disabled by default.
No functional change intended.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210609150911.1471882-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently vmx_vcpu_load_vmcs() writes the TSC_MULTIPLIER field of the
VMCS every time the VMCS is loaded. Instead of doing this, set this
field from common code on initialization and whenever the scaling ratio
changes.
Additionally remove vmx->current_tsc_ratio. This field is redundant as
vcpu->arch.tsc_scaling_ratio already tracks the current TSC scaling
ratio. The vmx->current_tsc_ratio field is only used for avoiding
unnecessary writes but it is no longer needed after removing the code
from the VMCS load path.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ilias Stamatis <ilstam@amazon.com>
Message-Id: <20210607105438.16541-1-ilstam@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The write_l1_tsc_offset() callback has a misleading name. It does not
set L1's TSC offset, it rather updates the current TSC offset which
might be different if a nested guest is executing. Additionally, both
the vmx and svm implementations use the same logic for calculating the
current TSC before writing it to hardware.
Rename the function and move the common logic to the caller. The vmx/svm
specific code now merely sets the given offset to the corresponding
hardware structure.
Signed-off-by: Ilias Stamatis <ilstam@amazon.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210526184418.28881-9-ilstam@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When L2 is entered we need to "merge" the TSC multiplier and TSC offset
values of 01 and 12 together.
The merging is done using the following equations:
offset_02 = ((offset_01 * mult_12) >> shift_bits) + offset_12
mult_02 = (mult_01 * mult_12) >> shift_bits
Where shift_bits is kvm_tsc_scaling_ratio_frac_bits.
Signed-off-by: Ilias Stamatis <ilstam@amazon.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210526184418.28881-8-ilstam@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In order to implement as much of the nested TSC scaling logic as
possible in common code, we need these vendor callbacks for retrieving
the TSC offset and the TSC multiplier that L1 has set for L2.
Signed-off-by: Ilias Stamatis <ilstam@amazon.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210526184418.28881-7-ilstam@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Sometimes kvm_scale_tsc() needs to use the current scaling ratio and
other times (like when reading the TSC from user space) it needs to use
L1's scaling ratio. Have the caller specify this by passing the ratio as
a parameter.
Signed-off-by: Ilias Stamatis <ilstam@amazon.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210526184418.28881-5-ilstam@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Store L1's scaling ratio in the kvm_vcpu_arch struct like we already do
for L1's TSC offset. This allows for easy save/restore when we enter and
then exit the nested guest.
Signed-off-by: Ilias Stamatis <ilstam@amazon.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210526184418.28881-3-ilstam@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If the TDP MMU is in use, wait to allocate the rmaps until the shadow
MMU is actually used. (i.e. a nested VM is launched.) This saves memory
equal to 0.2% of guest memory in cases where the TDP MMU is used and
there are no nested guests involved.
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210518173414.450044-8-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a field to control whether new memslots should have rmaps allocated
for them. As of this change, it's not safe to skip allocating rmaps, so
the field is always set to allocate rmaps. Future changes will make it
safe to operate without rmaps, using the TDP MMU. Then further changes
will allow the rmaps to be allocated lazily when needed for nested
oprtation.
No functional change expected.
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210518173414.450044-6-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a start_assignment hook to kvm_x86_ops, which is called when
kvm_arch_start_assignment is done.
The hook is required to update the wakeup vector of a sleeping vCPU
when a device is assigned to the guest.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Message-Id: <20210525134321.254128742@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Disallow loading KVM SVM if 5-level paging is supported. In theory, NPT
for L1 should simply work, but there unknowns with respect to how the
guest's MAXPHYADDR will be handled by hardware.
Nested NPT is more problematic, as running an L1 VMM that is using
2-level page tables requires stacking single-entry PDP and PML4 tables in
KVM's NPT for L2, as there are no equivalent entries in L1's NPT to
shadow. Barring hardware magic, for 5-level paging, KVM would need stack
another layer to handle PML5.
Opportunistically rename the lm_root pointer, which is used for the
aforementioned stacking when shadowing 2-level L1 NPT, to pml4_root to
call out that it's specifically for PML4.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210505204221.1934471-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Bus lock debug exception introduces a new bit DR6_BUS_LOCK (bit 11 of
DR6) to indicate that bus lock #DB exception is generated. The set/clear
of DR6_BUS_LOCK is similar to the DR6_RTM. The processor clears
DR6_BUS_LOCK when the exception is generated. For all other #DB, the
processor sets this bit to 1. Software #DB handler should set this bit
before returning to the interrupted task.
In VMM, to avoid breaking the CPUs without bus lock #DB exception
support, activate the DR6_BUS_LOCK conditionally in DR6_FIXED_1 bits.
When intercepting the #DB exception caused by bus locks, bit 11 of the
exit qualification is set to identify it. The VMM should emulate the
exception by clearing the bit 11 of the guest DR6.
Co-developed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20210202090433.13441-3-chenyi.qiang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Squish the Intel and AMD emulation of MSR_TSC_AUX together and tie it to
the guest CPU model instead of the host CPU behavior. While not strictly
necessary to avoid guest breakage, emulating cross-vendor "architecture"
will provide consistent behavior for the guest, e.g. WRMSR fault behavior
won't change if the vCPU is migrated to a host with divergent behavior.
Note, the "new" kvm_is_supported_user_return_msr() checks do not add new
functionality on either SVM or VMX. On SVM, the equivalent was
"tsc_aux_uret_slot < 0", and on VMX the check was buried in the
vmx_find_uret_msr() call at the find_uret_msr label.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210504171734.1434054-15-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Now that SVM and VMX both probe MSRs before "defining" user return slots
for them, consolidate the code for probe+define into common x86 and
eliminate the odd behavior of having the vendor code define the slot for
a given MSR.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210504171734.1434054-14-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Split out and export the number of configured user return MSRs so that
VMX can iterate over the set of MSRs without having to do its own tracking.
Keep the list itself internal to x86 so that vendor code still has to go
through the "official" APIs to add/modify entries.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210504171734.1434054-13-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop VMX's global list of user return MSRs now that VMX doesn't resort said
list to isolate "active" MSRs, i.e. now that VMX's list and x86's list have
the same MSRs in the same order.
In addition to eliminating the redundant list, this will also allow moving
more of the list management into common x86.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210504171734.1434054-11-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Disable preemption when probing a user return MSR via RDSMR/WRMSR. If
the MSR holds a different value per logical CPU, the WRMSR could corrupt
the host's value if KVM is preempted between the RDMSR and WRMSR, and
then rescheduled on a different CPU.
Opportunistically land the helper in common x86, SVM will use the helper
in a future commit.
Fixes: 4be5341026 ("KVM: VMX: Initialize vmx->guest_msrs[] right after allocation")
Cc: stable@vger.kernel.org
Cc: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210504171734.1434054-6-seanjc@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
* Define and use an invalid GPA (all ones) for init value of last
and current nested vmcb physical addresses.
* Reset the current vmcb12 gpa to the invalid value when leaving
the nested mode, similar to what is done on nested vmexit.
* Reset the last seen vmcb12 address when disabling the nested SVM,
as it relies on vmcb02 fields which are freed at that point.
Fixes: 4995a3685f ("KVM: SVM: Use a separate vmcb for the nested L2 guest")
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210503125446.1353307-3-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
- Stage-2 isolation for the host kernel when running in protected mode
- Guest SVE support when running in nVHE mode
- Force W^X hypervisor mappings in nVHE mode
- ITS save/restore for guests using direct injection with GICv4.1
- nVHE panics now produce readable backtraces
- Guest support for PTP using the ptp_kvm driver
- Performance improvements in the S2 fault handler
x86:
- Optimizations and cleanup of nested SVM code
- AMD: Support for virtual SPEC_CTRL
- Optimizations of the new MMU code: fast invalidation,
zap under read lock, enable/disably dirty page logging under
read lock
- /dev/kvm API for AMD SEV live migration (guest API coming soon)
- support SEV virtual machines sharing the same encryption context
- support SGX in virtual machines
- add a few more statistics
- improved directed yield heuristics
- Lots and lots of cleanups
Generic:
- Rework of MMU notifier interface, simplifying and optimizing
the architecture-specific code
- Some selftests improvements
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmCJ13kUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroM1HAgAqzPxEtiTPTFeFJV5cnPPJ3dFoFDK
y/juZJUQ1AOtvuWzzwuf175ewkv9vfmtG6rVohpNSkUlJYeoc6tw7n8BTTzCVC1b
c/4Dnrjeycr6cskYlzaPyV6MSgjSv5gfyj1LA5UEM16LDyekmaynosVWY5wJhju+
Bnyid8l8Utgz+TLLYogfQJQECCrsU0Wm//n+8TWQgLf1uuiwshU5JJe7b43diJrY
+2DX+8p9yWXCTz62sCeDWNahUv8AbXpMeJ8uqZPYcN1P0gSEUGu8xKmLOFf9kR7b
M4U1Gyz8QQbjd2lqnwiWIkvRLX6gyGVbq2zH0QbhUe5gg3qGUX7JjrhdDQ==
=AXUi
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"This is a large update by KVM standards, including AMD PSP (Platform
Security Processor, aka "AMD Secure Technology") and ARM CoreSight
(debug and trace) changes.
ARM:
- CoreSight: Add support for ETE and TRBE
- Stage-2 isolation for the host kernel when running in protected
mode
- Guest SVE support when running in nVHE mode
- Force W^X hypervisor mappings in nVHE mode
- ITS save/restore for guests using direct injection with GICv4.1
- nVHE panics now produce readable backtraces
- Guest support for PTP using the ptp_kvm driver
- Performance improvements in the S2 fault handler
x86:
- AMD PSP driver changes
- Optimizations and cleanup of nested SVM code
- AMD: Support for virtual SPEC_CTRL
- Optimizations of the new MMU code: fast invalidation, zap under
read lock, enable/disably dirty page logging under read lock
- /dev/kvm API for AMD SEV live migration (guest API coming soon)
- support SEV virtual machines sharing the same encryption context
- support SGX in virtual machines
- add a few more statistics
- improved directed yield heuristics
- Lots and lots of cleanups
Generic:
- Rework of MMU notifier interface, simplifying and optimizing the
architecture-specific code
- a handful of "Get rid of oprofile leftovers" patches
- Some selftests improvements"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (379 commits)
KVM: selftests: Speed up set_memory_region_test
selftests: kvm: Fix the check of return value
KVM: x86: Take advantage of kvm_arch_dy_has_pending_interrupt()
KVM: SVM: Skip SEV cache flush if no ASIDs have been used
KVM: SVM: Remove an unnecessary prototype declaration of sev_flush_asids()
KVM: SVM: Drop redundant svm_sev_enabled() helper
KVM: SVM: Move SEV VMCB tracking allocation to sev.c
KVM: SVM: Explicitly check max SEV ASID during sev_hardware_setup()
KVM: SVM: Unconditionally invoke sev_hardware_teardown()
KVM: SVM: Enable SEV/SEV-ES functionality by default (when supported)
KVM: SVM: Condition sev_enabled and sev_es_enabled on CONFIG_KVM_AMD_SEV=y
KVM: SVM: Append "_enabled" to module-scoped SEV/SEV-ES control variables
KVM: SEV: Mask CPUID[0x8000001F].eax according to supported features
KVM: SVM: Move SEV module params/variables to sev.c
KVM: SVM: Disable SEV/SEV-ES if NPT is disabled
KVM: SVM: Free sev_asid_bitmap during init if SEV setup fails
KVM: SVM: Zero out the VMCB array used to track SEV ASID association
x86/sev: Drop redundant and potentially misleading 'sev_enabled'
KVM: x86: Move reverse CPUID helpers to separate header file
KVM: x86: Rename GPR accessors to make mode-aware variants the defaults
...
Add a capability for userspace to mirror SEV encryption context from
one vm to another. On our side, this is intended to support a
Migration Helper vCPU, but it can also be used generically to support
other in-guest workloads scheduled by the host. The intention is for
the primary guest and the mirror to have nearly identical memslots.
The primary benefits of this are that:
1) The VMs do not share KVM contexts (think APIC/MSRs/etc), so they
can't accidentally clobber each other.
2) The VMs can have different memory-views, which is necessary for post-copy
migration (the migration vCPUs on the target need to read and write to
pages, when the primary guest would VMEXIT).
This does not change the threat model for AMD SEV. Any memory involved
is still owned by the primary guest and its initial state is still
attested to through the normal SEV_LAUNCH_* flows. If userspace wanted
to circumvent SEV, they could achieve the same effect by simply attaching
a vCPU to the primary VM.
This patch deliberately leaves userspace in charge of the memslots for the
mirror, as it already has the power to mess with them in the primary guest.
This patch does not support SEV-ES (much less SNP), as it does not
handle handing off attested VMSAs to the mirror.
For additional context, we need a Migration Helper because SEV PSP
migration is far too slow for our live migration on its own. Using
an in-guest migrator lets us speed this up significantly.
Signed-off-by: Nathan Tempelman <natet@google.com>
Message-Id: <20210408223214.2582277-1-natet@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add an ECREATE handler that will be used to intercept ECREATE for the
purpose of enforcing and enclave's MISCSELECT, ATTRIBUTES and XFRM, i.e.
to allow userspace to restrict SGX features via CPUID. ECREATE will be
intercepted when any of the aforementioned masks diverges from hardware
in order to enforce the desired CPUID model, i.e. inject #GP if the
guest attempts to set a bit that hasn't been enumerated as allowed-1 in
CPUID.
Note, access to the PROVISIONKEY is not yet supported.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Co-developed-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Message-Id: <c3a97684f1b71b4f4626a1fc3879472a95651725.1618196135.git.kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Page faults that are signaled by the SGX Enclave Page Cache Map (EPCM),
as opposed to the traditional IA32/EPT page tables, set an SGX bit in
the error code to indicate that the #PF was induced by SGX. KVM will
need to emulate this behavior as part of its trap-and-execute scheme for
virtualizing SGX Launch Control, e.g. to inject SGX-induced #PFs if
EINIT faults in the host, and to support live migration.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Kai Huang <kai.huang@intel.com>
Message-Id: <e170c5175cb9f35f53218a7512c9e3db972b97a2.1618196135.git.kai.huang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_mmu_slot_largepage_remove_write_access() is decared but not used,
just remove it.
Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com>
Message-Id: <20210406063504.17552-1-zhukeqian1@huawei.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
To analyze some performance issues with lock contention and scheduling,
it is nice to know when directed yield are successful or failing.
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Message-Id: <1617941911-5338-2-git-send-email-wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Protect the contents of the TDP MMU roots list with RCU in preparation
for a future patch which will allow the iterator macro to be used under
the MMU lock in read mode.
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210401233736.638171-9-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Yank out the hva-based MMU notifier APIs now that all architectures that
use the notifiers have moved to the gfn-based APIs.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210402005658.3024832-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the hva->gfn lookup for MMU notifiers into common code. Every arch
does a similar lookup, and some arch code is all but identical across
multiple architectures.
In addition to consolidating code, this will allow introducing
optimizations that will benefit all architectures without incurring
multiple walks of the memslots, e.g. by taking mmu_lock if and only if a
relevant range exists in the memslots.
The use of __always_inline to avoid indirect call retpolines, as done by
x86, may also benefit other architectures.
Consolidating the lookups also fixes a wart in x86, where the legacy MMU
and TDP MMU each do their own memslot walks.
Lastly, future enhancements to the memslot implementation, e.g. to add an
interval tree to track host address, will need to touch far less arch
specific code.
MIPS, PPC, and arm64 will be converted one at a time in future patches.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210402005658.3024832-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Store the supported bits into KVM_GUESTDBG_VALID_MASK
macro, similar to how arm does this.
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20210401135451.1004564-4-mlevitsk@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the prototypes for the MMU notifier callbacks out of arch code and
into common code. There is no benefit to having each arch replicate the
prototypes since any deviation from the invocation in common code will
explode.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210326021957.1424875-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Fix a plethora of issues with MSR filtering by installing the resulting
filter as an atomic bundle instead of updating the live filter one range
at a time. The KVM_X86_SET_MSR_FILTER ioctl() isn't truly atomic, as
the hardware MSR bitmaps won't be updated until the next VM-Enter, but
the relevant software struct is atomically updated, which is what KVM
really needs.
Similar to the approach used for modifying memslots, make arch.msr_filter
a SRCU-protected pointer, do all the work configuring the new filter
outside of kvm->lock, and then acquire kvm->lock only when the new filter
has been vetted and created. That way vCPU readers either see the old
filter or the new filter in their entirety, not some half-baked state.
Yuan Yao pointed out a use-after-free in ksm_msr_allowed() due to a
TOCTOU bug, but that's just the tip of the iceberg...
- Nothing is __rcu annotated, making it nigh impossible to audit the
code for correctness.
- kvm_add_msr_filter() has an unpaired smp_wmb(). Violation of kernel
coding style aside, the lack of a smb_rmb() anywhere casts all code
into doubt.
- kvm_clear_msr_filter() has a double free TOCTOU bug, as it grabs
count before taking the lock.
- kvm_clear_msr_filter() also has memory leak due to the same TOCTOU bug.
The entire approach of updating the live filter is also flawed. While
installing a new filter is inherently racy if vCPUs are running, fixing
the above issues also makes it trivial to ensure certain behavior is
deterministic, e.g. KVM can provide deterministic behavior for MSRs with
identical settings in the old and new filters. An atomic update of the
filter also prevents KVM from getting into a half-baked state, e.g. if
installing a filter fails, the existing approach would leave the filter
in a half-baked state, having already committed whatever bits of the
filter were already processed.
[*] https://lkml.kernel.org/r/20210312083157.25403-1-yaoyuan0329os@gmail.com
Fixes: 1a155254ff ("KVM: x86: Introduce MSR filtering")
Cc: stable@vger.kernel.org
Cc: Alexander Graf <graf@amazon.com>
Reported-by: Yuan Yao <yaoyuan0329os@gmail.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210316184436.2544875-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Fix ~144 single-word typos in arch/x86/ code comments.
Doing this in a single commit should reduce the churn.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: linux-kernel@vger.kernel.org
Create an infrastructure for tracking Hyper-V TSC page status, i.e. if it
was updated from guest/host side or if we've failed to set it up (because
e.g. guest wrote some garbage to HV_X64_MSR_REFERENCE_TSC) and there's no
need to retry.
Also, in a hypothetical situation when we are in 'always catchup' mode for
TSC we can now avoid contending 'hv->hv_lock' on every guest enter by
setting the state to HV_TSC_PAGE_BROKEN after compute_tsc_page_parameters()
returns false.
Check for HV_TSC_PAGE_SET state instead of '!hv->tsc_ref.tsc_sequence' in
get_time_ref_counter() to properly handle the situation when we failed to
write the updated TSC page values to the guest.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210316143736.964151-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Retrieve the active PCID only when writing a guest CR3 value, i.e. don't
get the PCID when using EPT or NPT. The PCID is especially problematic
for EPT as the bits have different meaning, and so the PCID and must be
manually stripped, which is annoying and unnecessary. And on VMX,
getting the active PCID also involves reading the guest's CR3 and
CR4.PCIDE, i.e. may add pointless VMREADs.
Opportunistically rename the pgd/pgd_level params to root_hpa and
root_level to better reflect their new roles. Keep the function names,
as "load the guest PGD" is still accurate/correct.
Last, and probably least, pass root_hpa as a hpa_t/u64 instead of an
unsigned long. The EPTP holds a 64-bit value, even in 32-bit mode, so
in theory EPT could support HIGHMEM for 32-bit KVM. Never mind that
doing so would require changing the MMU page allocators and reworking
the MMU to use kmap().
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210305183123.3978098-2-seanjc@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Let the MMU deal with the SPTE masks to avoid splitting the logic and
knowledge across the MMU and VMX.
The SPTE masks that are used for EPT are very, very tightly coupled to
the MMU implementation. The use of available bits, the existence of A/D
types, the fact that shadow_x_mask even exists, and so on and so forth
are all baked into the MMU implementation. Cross referencing the params
to the masks is also a nightmare, as pretty much every param is a u64.
A future patch will make the location of the MMU_WRITABLE and
HOST_WRITABLE bits MMU specific, to free up bit 11 for a MMU_PRESENT bit.
Doing that change with the current kvm_mmu_set_mask_ptes() would be an
absolute mess.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210225204749.1512652-18-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the entirety of the accelerated RDPMC emulation to x86.c, and assign
the common handler directly to the exit handler array for VMX. SVM has
bizarre nrips behavior that prevents it from directly invoking the common
handler. The nrips goofiness will be addressed in a future patch.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210205005750.3841462-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the trivial exit handlers, e.g. for instructions that KVM
"emulates" as nops, to common x86 code. Assign the common handlers
directly to the exit handler arrays and drop the vendor trampolines.
Opportunistically use pr_warn_once() where appropriate.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210205005750.3841462-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Move the entirety of XSETBV emulation to x86.c, and assign the
function directly to both VMX's and SVM's exit handlers, i.e. drop the
unnecessary trampolines.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210205005750.3841462-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Synthesize a nested VM-Exit if L2 triggers an emulated triple fault
instead of exiting to userspace, which likely will kill L1. Any flow
that does KVM_REQ_TRIPLE_FAULT is suspect, but the most common scenario
for L2 killing L1 is if L0 (KVM) intercepts a contributory exception that
is _not_intercepted by L1. E.g. if KVM is intercepting #GPs for the
VMware backdoor, a #GP that occurs in L2 while vectoring an injected #DF
will cause KVM to emulate triple fault.
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Jim Mattson <jmattson@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210302174515.2812275-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Unexport the MMU load and unload helpers now that they are no longer
used (incorrectly) in vendor code.
Opportunistically move the kvm_mmu_sync_roots() declaration into mmu.h,
it should not be exposed to vendor code.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210305011101.3597423-16-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The new per-cpu stat 'nested_run' is introduced in order to track if L1 VM
is running or used to run L2 VM.
An example of the usage of 'nested_run' is to help the host administrator
to easily track if any L1 VM is used to run L2 VM. Suppose there is issue
that may happen with nested virtualization, the administrator will be able
to easily narrow down and confirm if the issue is due to nested
virtualization via 'nested_run'. For example, whether the fix like
commit 88dddc11a8 ("KVM: nVMX: do not use dangling shadow VMCS after
guest reset") is required.
Cc: Joe Jin <joe.jin@oracle.com>
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Message-Id: <20210305225747.7682-1-dongli.zhang@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This is how Xen guests do steal time accounting. The hypervisor records
the amount of time spent in each of running/runnable/blocked/offline
states.
In the Xen accounting, a vCPU is still in state RUNSTATE_running while
in Xen for a hypercall or I/O trap, etc. Only if Xen explicitly schedules
does the state become RUNSTATE_blocked. In KVM this means that even when
the vCPU exits the kvm_run loop, the state remains RUNSTATE_running.
The VMM can explicitly set the vCPU to RUNSTATE_blocked by using the
KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT attribute, and can also use
KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST to retrospectively add a given
amount of time to the blocked state and subtract it from the running
state.
The state_entry_time corresponds to get_kvmclock_ns() at the time the
vCPU entered the current state, and the total times of all four states
should always add up to state_entry_time.
Co-developed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20210301125309.874953-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The 'mmu_page_hash' is used as hash table while 'active_mmu_pages' is a
list. Remove the misplaced comment as it's mostly stating the obvious
anyways.
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210226061945.1222-1-dongli.zhang@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Remove several exports from the MMU that are no longer necessary.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210213005015.1651772-15-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Stop setting dirty bits for MMU pages when dirty logging is disabled for
a memslot, as PML is now completely disabled when there are no memslots
with dirty logging enabled.
This means that spurious PML entries will be created for memslots with
dirty logging disabled if at least one other memslot has dirty logging
enabled. However, spurious PML entries are already possible since
dirty bits are set only when a dirty logging is turned off, i.e. memslots
that are never dirty logged will have dirty bits cleared.
In the end, it's faster overall to eat a few spurious PML entries in the
window where dirty logging is being disabled across all memslots.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210213005015.1651772-13-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Currently, if enable_pml=1 PML remains enabled for the entire lifetime
of the VM irrespective of whether dirty logging is enable or disabled.
When dirty logging is disabled, all the pages of the VM are manually
marked dirty, so that PML is effectively non-operational. Setting
the dirty bits is an expensive operation which can cause severe MMU
lock contention in a performance sensitive path when dirty logging is
disabled after a failed or canceled live migration.
Manually setting dirty bits also fails to prevent PML activity if some
code path clears dirty bits, which can incur unnecessary VM-Exits.
In order to avoid this extra overhead, dynamically enable/disable PML
when dirty logging gets turned on/off for the first/last memslot.
Signed-off-by: Makarand Sonare <makarandsonare@google.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210213005015.1651772-12-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop the facade of KVM's PML logic being vendor specific and move the
bits that aren't truly VMX specific into common x86 code. The MMU logic
for dealing with PML is tightly coupled to the feature and to VMX's
implementation, bouncing through kvm_x86_ops obfuscates the code without
providing any meaningful separation of concerns or encapsulation.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210213005015.1651772-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Store the vendor-specific dirty log size in a variable, there's no need
to wrap it in a function since the value is constant after
hardware_setup() runs.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210213005015.1651772-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Hyper-V emulation is enabled in KVM unconditionally. This is bad at least
from security standpoint as it is an extra attack surface. Ideally, there
should be a per-VM capability explicitly enabled by VMM but currently it
is not the case and we can't mandate one without breaking backwards
compatibility. We can, however, check guest visible CPUIDs and only enable
Hyper-V emulation when "Hv#1" interface was exposed in
HYPERV_CPUID_INTERFACE.
Note, VMMs are free to act in any sequence they like, e.g. they can try
to set MSRs first and CPUIDs later so we still need to allow the host
to read/write Hyper-V specific MSRs unconditionally.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210126134816.1880136-14-vkuznets@redhat.com>
[Add selftest vcpu_set_hv_cpuid API to avoid breaking xen_vmcall_test. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Hyper-V context is only needed for guests which use Hyper-V emulation in
KVM (e.g. Windows/Hyper-V guests). 'struct kvm_vcpu_hv' is, however, quite
big, it accounts for more than 1/4 of the total 'struct kvm_vcpu_arch'
which is also quite big already. This all looks like a waste.
Allocate 'struct kvm_vcpu_hv' dynamically. This patch does not bring any
(intentional) functional change as we still allocate the context
unconditionally but it paves the way to doing that only when needed.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210126134816.1880136-13-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Current KVM_USER_MEM_SLOTS limits are arch specific (512 on Power, 509 on x86,
32 on s390, 16 on MIPS) but they don't really need to be. Memory slots are
allocated dynamically in KVM when added so the only real limitation is
'id_to_index' array which is 'short'. We don't have any other
KVM_MEM_SLOTS_NUM/KVM_USER_MEM_SLOTS-sized statically defined structures.
Low KVM_USER_MEM_SLOTS can be a limiting factor for some configurations.
In particular, when QEMU tries to start a Windows guest with Hyper-V SynIC
enabled and e.g. 256 vCPUs the limit is hit as SynIC requires two pages per
vCPU and the guest is free to pick any GFN for each of them, this fragments
memslots as QEMU wants to have a separate memslot for each of these pages
(which are supposed to act as 'overlay' pages).
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210127175731.2020089-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_get_dr and emulator_get_dr except an in-range value for the register
number so they cannot fail. Change the return type to void.
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The TDP MMU assumes that it can do atomic accesses to 64-bit PTEs.
Rather than just disabling it, compile it out completely so that it
is possible to use for example 64-bit xchg.
To limit the number of stubs, wrap all accesses to tdp_mmu_enabled
or tdp_mmu_page with a function. Calls to all other functions in
tdp_mmu.c are eliminated and do not even reach the linker.
Reviewed-by: Sean Christopherson <seanjc@google.com>
Tested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rename cr3_lm_rsvd_bits to reserved_gpa_bits, and use it for all GPA
legality checks. AMD's APM states:
If the C-bit is an address bit, this bit is masked from the guest
physical address when it is translated through the nested page tables.
Thus, any access that can conceivably be run through NPT should ignore
the C-bit when checking for validity.
For features that KVM emulates in software, e.g. MTRRs, there is no
clear direction in the APM for how the C-bit should be handled. For
such cases, follow the SME behavior inasmuch as possible, since SEV is
is essentially a VM-specific variant of SME. For SME, the APM states:
In this case the upper physical address bits are treated as reserved
when the feature is enabled except where otherwise indicated.
Collecting the various relavant SME snippets in the APM and cross-
referencing the omissions with Linux kernel code, this leaves MTTRs and
APIC_BASE as the only flows that KVM emulates that should _not_ ignore
the C-bit.
Note, this means the reserved bit checks in the page tables are
technically broken. This will be remedied in a future patch.
Although the page table checks are technically broken, in practice, it's
all but guaranteed to be irrelevant. NPT is required for SEV, i.e.
shadowing page tables isn't needed in the common case. Theoretically,
the checks could be in play for nested NPT, but it's extremely unlikely
that anyone is running nested VMs on SEV, as doing so would require L1
to expose sensitive data to L0, e.g. the entire VMCB. And if anyone is
running nested VMs, L0 can't read the guest's encrypted memory, i.e. L1
would need to put its NPT in shared memory, in which case the C-bit will
never be set. Or, L1 could use shadow paging, but again, if L0 needs to
read page tables, e.g. to load PDPTRs, the memory can't be encrypted if
L1 has any expectation of L0 doing the right thing.
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210204000117.3303214-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
It turns out that we can't handle event channels *entirely* in userspace
by delivering them as ExtINT, because KVM is a bit picky about when it
accepts ExtINT interrupts from a legacy PIC. The in-kernel local APIC
has to have LVT0 configured in APIC_MODE_EXTINT and unmasked, which
isn't necessarily the case for Xen guests especially on secondary CPUs.
To cope with this, add kvm_xen_get_interrupt() which checks the
evtchn_pending_upcall field in the Xen vcpu_info, and delivers the Xen
upcall vector (configured by KVM_XEN_ATTR_TYPE_UPCALL_VECTOR) if it's
set regardless of LAPIC LVT0 configuration. This gives us the minimum
support we need for completely userspace-based implementation of event
channels.
This does mean that vcpu_enter_guest() needs to check for the
evtchn_pending_upcall flag being set, because it can't rely on someone
having set KVM_REQ_EVENT unless we were to add some way for userspace to
do so manually.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Allow the Xen emulated guest the ability to register secondary
vcpu time information. On Xen guests this is used in order to be
mapped to userspace and hence allow vdso gettimeofday to work.
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
The vcpu info supersedes the per vcpu area of the shared info page and
the guest vcpus will use this instead.
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Add KVM_XEN_ATTR_TYPE_SHARED_INFO to allow hypervisor to know where the
guest's shared info page is.
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Add a new exit reason for emulator to handle Xen hypercalls.
Since this means KVM owns the ABI, dispense with the facility for the
VMM to provide its own copy of the hypercall pages; just fill them in
directly using VMCALL/VMMCALL as we do for the Hyper-V hypercall page.
This behaviour is enabled by a new INTERCEPT_HCALL flag in the
KVM_XEN_HVM_CONFIG ioctl structure, and advertised by the same flag
being returned from the KVM_CAP_XEN_HVM check.
Rename xen_hvm_config() to kvm_xen_write_hypercall_page() and move it
to the nascent xen.c while we're at it, and add a test case.
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
To prepare for handling page faults in parallel, change the TDP MMU
page fault handler to use atomic operations to set SPTEs so that changes
are not lost if multiple threads attempt to modify the same SPTE.
Reviewed-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210202185734.1680553-21-bgardon@google.com>
[Document new locking rules. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a read / write lock to be used in place of the MMU spinlock on x86.
The rwlock will enable the TDP MMU to handle page faults, and other
operations in parallel in future commits.
Reviewed-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210202185734.1680553-19-bgardon@google.com>
[Introduce virt/kvm/mmu_lock.h - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Convert kvm_x86_ops to use static calls. Note that all kvm_x86_ops are
covered here except for 'pmu_ops and 'nested ops'.
Here are some numbers running cpuid in a loop of 1 million calls averaged
over 5 runs, measured in the vm (lower is better).
Intel Xeon 3000MHz:
|default |mitigations=off
-------------------------------------
vanilla |.671s |.486s
static call|.573s(-15%)|.458s(-6%)
AMD EPYC 2500MHz:
|default |mitigations=off
-------------------------------------
vanilla |.710s |.609s
static call|.664s(-6%) |.609s(0%)
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Message-Id: <e057bf1b8a7ad15652df6eeba3f907ae758d3399.1610680941.git.jbaron@akamai.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Use static calls to improve kvm_x86_ops performance. Introduce the
definitions that will be used by a subsequent patch to actualize the
savings. Add a new kvm-x86-ops.h header that can be used for the
definition of static calls. This header is also intended to be
used to simplify the defition of svm_kvm_ops and vmx_x86_ops.
Note that all functions in kvm_x86_ops are covered here except for
'pmu_ops' and 'nested ops'. I think they can be covered by static
calls in a simlilar manner, but were omitted from this series to
reduce scope and because I don't think they have as large of a
performance impact.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Message-Id: <e5cc82ead7ab37b2dceb0837a514f3f8bea4f8d1.1610680941.git.jbaron@akamai.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
DR6_INIT contains the 1-reserved bits as well as the bit that is cleared
to 0 when the condition (e.g. RTM) happens. The value can be used to
initialize dr6 and also be the XOR mask between the #DB exit
qualification (or payload) and DR6.
Concerning that DR6_INIT is used as initial value only once, rename it
to DR6_ACTIVE_LOW and apply it in other places, which would make the
incoming changes for bus lock debug exception more simple.
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20210202090433.13441-2-chenyi.qiang@intel.com>
[Define DR6_FIXED_1 from DR6_ACTIVE_LOW and DR6_VOLATILE. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Virtual Machine can exploit bus locks to degrade the performance of
system. Bus lock can be caused by split locked access to writeback(WB)
memory or by using locks on uncacheable(UC) memory. The bus lock is
typically >1000 cycles slower than an atomic operation within a cache
line. It also disrupts performance on other cores (which must wait for
the bus lock to be released before their memory operations can
complete).
To address the threat, bus lock VM exit is introduced to notify the VMM
when a bus lock was acquired, allowing it to enforce throttling or other
policy based mitigations.
A VMM can enable VM exit due to bus locks by setting a new "Bus Lock
Detection" VM-execution control(bit 30 of Secondary Processor-based VM
execution controls). If delivery of this VM exit was preempted by a
higher priority VM exit (e.g. EPT misconfiguration, EPT violation, APIC
access VM exit, APIC write VM exit, exception bitmap exiting), bit 26 of
exit reason in vmcs field is set to 1.
In current implementation, the KVM exposes this capability through
KVM_CAP_X86_BUS_LOCK_EXIT. The user can get the supported mode bitmap
(i.e. off and exit) and enable it explicitly (disabled by default). If
bus locks in guest are detected by KVM, exit to user space even when
current exit reason is handled by KVM internally. Set a new field
KVM_RUN_BUS_LOCK in vcpu->run->flags to inform the user space that there
is a bus lock detected in guest.
Document for Bus Lock VM exit is now available at the latest "Intel
Architecture Instruction Set Extensions Programming Reference".
Document Link:
https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html
Co-developed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20201106090315.18606-4-chenyi.qiang@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Remove the update_pte() shadow paging logic, which was obsoleted by
commit 4731d4c7a0 ("KVM: MMU: out of sync shadow core"), but never
removed. As pointed out by Yu, KVM never write protects leaf page
tables for the purposes of shadow paging, and instead marks their
associated shadow page as unsync so that the guest can write PTEs at
will.
The update_pte() path, which predates the unsync logic, optimizes COW
scenarios by refreshing leaf SPTEs when they are written, as opposed to
zapping the SPTE, restarting the guest, and installing the new SPTE on
the subsequent fault. Since KVM no longer write-protects leaf page
tables, update_pte() is unreachable and can be dropped.
Reported-by: Yu Zhang <yu.c.zhang@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210115004051.4099250-1-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Typically under KVM, an AP is booted using the INIT-SIPI-SIPI sequence,
where the guest vCPU register state is updated and then the vCPU is VMRUN
to begin execution of the AP. For an SEV-ES guest, this won't work because
the guest register state is encrypted.
Following the GHCB specification, the hypervisor must not alter the guest
register state, so KVM must track an AP/vCPU boot. Should the guest want
to park the AP, it must use the AP Reset Hold exit event in place of, for
example, a HLT loop.
First AP boot (first INIT-SIPI-SIPI sequence):
Execute the AP (vCPU) as it was initialized and measured by the SEV-ES
support. It is up to the guest to transfer control of the AP to the
proper location.
Subsequent AP boot:
KVM will expect to receive an AP Reset Hold exit event indicating that
the vCPU is being parked and will require an INIT-SIPI-SIPI sequence to
awaken it. When the AP Reset Hold exit event is received, KVM will place
the vCPU into a simulated HLT mode. Upon receiving the INIT-SIPI-SIPI
sequence, KVM will make the vCPU runnable. It is again up to the guest
to then transfer control of the AP to the proper location.
To differentiate between an actual HLT and an AP Reset Hold, a new MP
state is introduced, KVM_MP_STATE_AP_RESET_HOLD, which the vCPU is
placed in upon receiving the AP Reset Hold exit event. Additionally, to
communicate the AP Reset Hold exit event up to userspace (if needed), a
new exit reason is introduced, KVM_EXIT_AP_RESET_HOLD.
A new x86 ops function is introduced, vcpu_deliver_sipi_vector, in order
to accomplish AP booting. For VMX, vcpu_deliver_sipi_vector is set to the
original SIPI delivery function, kvm_vcpu_deliver_sipi_vector(). SVM adds
a new function that, for non SEV-ES guests, invokes the original SIPI
delivery function, kvm_vcpu_deliver_sipi_vector(), but for SEV-ES guests,
implements the logic above.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Message-Id: <e8fbebe8eb161ceaabdad7c01a5859a78b424d5e.1609791600.git.thomas.lendacky@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The tdp_mmu_roots and tdp_mmu_pages in struct kvm_arch should only contain
pages with tdp_mmu_page set to true. tdp_mmu_pages should not contain any
pages with a non-zero root_count and tdp_mmu_roots should only contain
pages with a positive root_count, unless a thread holds the MMU lock and
is in the process of modifying the list. Various functions expect these
invariants to be maintained, but they are not explictily documented. Add
to the comments on both fields to document the above invariants.
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20210107001935.3732070-2-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Sean Christopherson
Like Xu
Paolo Bonzini
Vitaly Kuznetsov
Paul Durrant
Maxim Levitsky
David Woodhouse
Peter Gonda
Linus Torvalds
David Woodhouse
David Edmondson
Thomas Gleixner
Wanpeng Li
David Stevens
Oliver Upton
Juergen Gross
Eduardo Habkost
Wei Huang
Mingwei Zhang
Peter Xu
Uros Bizjak
Lai Jiangshan
Like Xu
Hamza Mahfooz
Aaron Lewis
Jing Zhang
Ashish Kalra
Vineeth Pillai
Krish Sadhukhan
Ilias Stamatis
Ben Gardon
Marcelo Tosatti
Chenyi Qiang
Nathan Tempelman
Sean Christopherson
Keqian Zhu
Ingo Molnar
Dongli Zhang
Muhammad Usama Anjum
Makarand Sonare
Joao Martins
Jason Baron
Tom Lendacky