Prior to commit 0baedd7927 ("KVM: x86: make Hyper-V PV TLB flush use
tlb_flush_guest()"), kvm_hv_flush_tlb() was using 'KVM_REQ_TLB_FLUSH |
KVM_REQUEST_NO_WAKEUP' when making a request to flush TLBs on other vCPUs
and KVM_REQ_TLB_FLUSH is/was defined as:
(0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
so KVM_REQUEST_WAIT was lost. Hyper-V TLFS, however, requires that
"This call guarantees that by the time control returns back to the
caller, the observable effects of all flushes on the specified virtual
processors have occurred." and without KVM_REQUEST_WAIT there's a small
chance that the vCPU making the TLB flush will resume running before
all IPIs get delivered to other vCPUs and a stale mapping can get read
there.
Fix the issue by adding KVM_REQUEST_WAIT flag to KVM_REQ_TLB_FLUSH_GUEST:
kvm_hv_flush_tlb() is the sole caller which uses it for
kvm_make_all_cpus_request()/kvm_make_vcpus_request_mask() where
KVM_REQUEST_WAIT makes a difference.
Cc: stable@kernel.org
Fixes: 0baedd7927 ("KVM: x86: make Hyper-V PV TLB flush use tlb_flush_guest()")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211209102937.584397-1-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull x86 fixes from Borislav Petkov:
- Fix a couple of SWAPGS fencing issues in the x86 entry code
- Use the proper operand types in __{get,put}_user() to prevent
truncation in SEV-ES string io
- Make sure the kernel mappings are present in trampoline_pgd in order
to prevent any potential accesses to unmapped memory after switching
to it
- Fix a trivial list corruption in objtool's pv_ops validation
- Disable the clocksource watchdog for TSC on platforms which claim
that the TSC is constant, doesn't stop in sleep states, CPU has TSC
adjust and the number of sockets of the platform are max 2, to
prevent erroneous markings of the TSC as unstable.
- Make sure TSC adjust is always checked not only when going idle
- Prevent a stack leak by initializing struct _fpx_sw_bytes properly in
the FPU code
- Fix INTEL_FAM6_RAPTORLAKE define naming to adhere to the convention
* tag 'x86_urgent_for_v5.16_rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/xen: Add xenpv_restore_regs_and_return_to_usermode()
x86/entry: Use the correct fence macro after swapgs in kernel CR3
x86/entry: Add a fence for kernel entry SWAPGS in paranoid_entry()
x86/sev: Fix SEV-ES INS/OUTS instructions for word, dword, and qword
x86/64/mm: Map all kernel memory into trampoline_pgd
objtool: Fix pv_ops noinstr validation
x86/tsc: Disable clocksource watchdog for TSC on qualified platorms
x86/tsc: Add a timer to make sure TSC_adjust is always checked
x86/fpu/signal: Initialize sw_bytes in save_xstate_epilog()
x86/cpu: Drop spurious underscore from RAPTOR_LAKE #define
Pull more kvm fixes from Paolo Bonzini:
- Static analysis fix
- New SEV-ES protocol for communicating invalid VMGEXIT requests
- Ensure APICv is considered inactive if there is no APIC
- Fix reserved bits for AMD PerfEvtSeln register
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: SVM: Do not terminate SEV-ES guests on GHCB validation failure
KVM: SEV: Fall back to vmalloc for SEV-ES scratch area if necessary
KVM: SEV: Return appropriate error codes if SEV-ES scratch setup fails
KVM: x86/mmu: Retry page fault if root is invalidated by memslot update
KVM: VMX: Set failure code in prepare_vmcs02()
KVM: ensure APICv is considered inactive if there is no APIC
KVM: x86/pmu: Fix reserved bits for AMD PerfEvtSeln register
Currently, an SEV-ES guest is terminated if the validation of the VMGEXIT
exit code or exit parameters fails.
The VMGEXIT instruction can be issued from userspace, even though
userspace (likely) can't update the GHCB. To prevent userspace from being
able to kill the guest, return an error through the GHCB when validation
fails rather than terminating the guest. For cases where the GHCB can't be
updated (e.g. the GHCB can't be mapped, etc.), just return back to the
guest.
The new error codes are documented in the lasest update to the GHCB
specification.
Fixes: 291bd20d5d ("KVM: SVM: Add initial support for a VMGEXIT VMEXIT")
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Message-Id: <b57280b5562893e2616257ac9c2d4525a9aeeb42.1638471124.git.thomas.lendacky@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_vcpu_apicv_active() returns false if a virtual machine has no in-kernel
local APIC, however kvm_apicv_activated might still be true if there are
no reasons to disable APICv; in fact it is quite likely that there is none
because APICv is inhibited by specific configurations of the local APIC
and those configurations cannot be programmed. This triggers a WARN:
WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu));
To avoid this, introduce another cause for APICv inhibition, namely the
absence of an in-kernel local APIC. This cause is enabled by default,
and is dropped by either KVM_CREATE_IRQCHIP or the enabling of
KVM_CAP_IRQCHIP_SPLIT.
Reported-by: Ignat Korchagin <ignat@cloudflare.com>
Fixes: ee49a89329 ("KVM: x86: Move SVM's APICv sanity check to common x86", 2021-10-22)
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Tested-by: Ignat Korchagin <ignat@cloudflare.com>
Message-Id: <20211130123746.293379-1-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull xen fixes from Juergen Gross:
- Kconfig fix to make it possible to control building of the privcmd
driver
- three fixes for issues identified by the kernel test robot
- a five-patch series to simplify timeout handling for Xen PV driver
initialization
- two patches to fix error paths in xenstore/xenbus driver
initialization
* tag 'for-linus-5.16c-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
xen: make HYPERVISOR_set_debugreg() always_inline
xen: make HYPERVISOR_get_debugreg() always_inline
xen: detect uninitialized xenbus in xenbus_init
xen: flag xen_snd_front to be not essential for system boot
xen: flag pvcalls-front to be not essential for system boot
xen: flag hvc_xen to be not essential for system boot
xen: flag xen_drm_front to be not essential for system boot
xen: add "not_essential" flag to struct xenbus_driver
xen/pvh: add missing prototype to header
xen: don't continue xenstore initialization in case of errors
xen/privcmd: make option visible in Kconfig
Pull KVM fixes from Paolo Bonzini:
"Selftest changes:
- Cleanups for the perf test infrastructure and mapping hugepages
- Avoid contention on mmap_sem when the guests start to run
- Add event channel upcall support to xen_shinfo_test
x86 changes:
- Fixes for Xen emulation
- Kill kvm_map_gfn() / kvm_unmap_gfn() and broken gfn_to_pfn_cache
- Fixes for migration of 32-bit nested guests on 64-bit hypervisor
- Compilation fixes
- More SEV cleanups
Generic:
- Cap the return value of KVM_CAP_NR_VCPUS to both KVM_CAP_MAX_VCPUS
and num_online_cpus(). Most architectures were only using one of
the two"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (42 commits)
KVM: x86: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
KVM: s390: Cap KVM_CAP_NR_VCPUS by num_online_cpus()
KVM: RISC-V: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
KVM: PPC: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
KVM: MIPS: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
KVM: arm64: Cap KVM_CAP_NR_VCPUS by kvm_arm_default_max_vcpus()
KVM: x86: Assume a 64-bit hypercall for guests with protected state
selftests: KVM: Add /x86_64/sev_migrate_tests to .gitignore
riscv: kvm: fix non-kernel-doc comment block
KVM: SEV: Fix typo in and tweak name of cmd_allowed_from_miror()
KVM: SEV: Drop a redundant setting of sev->asid during initialization
KVM: SEV: WARN if SEV-ES is marked active but SEV is not
KVM: SEV: Set sev_info.active after initial checks in sev_guest_init()
KVM: SEV: Disallow COPY_ENC_CONTEXT_FROM if target has created vCPUs
KVM: Kill kvm_map_gfn() / kvm_unmap_gfn() and gfn_to_pfn_cache
KVM: nVMX: Use a gfn_to_hva_cache for vmptrld
KVM: nVMX: Use kvm_read_guest_offset_cached() for nested VMCS check
KVM: x86/xen: Use sizeof_field() instead of open-coding it
KVM: nVMX: Use kvm_{read,write}_guest_cached() for shadow_vmcs12
KVM: x86/xen: Fix get_attr of KVM_XEN_ATTR_TYPE_SHARED_INFO
...
* Fixes for Xen emulation
* Kill kvm_map_gfn() / kvm_unmap_gfn() and broken gfn_to_pfn_cache
* Fixes for migration of 32-bit nested guests on 64-bit hypervisor
* Compilation fixes
* More SEV cleanups
Incorporate EFER.LMA into kvm_mmu_extended_role, as it used to compute the
guest root level and is not reflected in kvm_mmu_page_role.level when TDP
is in use. When simply running the guest, it is impossible for EFER.LMA
and kvm_mmu.root_level to get out of sync, as the guest cannot transition
from PAE paging to 64-bit paging without toggling CR0.PG, i.e. without
first bouncing through a different MMU context. And stuffing guest state
via KVM_SET_SREGS{,2} also ensures a full MMU context reset.
However, if KVM_SET_SREGS{,2} is followed by KVM_SET_NESTED_STATE, e.g. to
set guest state when migrating the VM while L2 is active, the vCPU state
will reflect L2, not L1. If L1 is using TDP for L2, then root_mmu will
have been configured using L2's state, despite not being used for L2. If
L2.EFER.LMA != L1.EFER.LMA, and L2 is using PAE paging, then root_mmu will
be configured for guest PAE paging, but will match the mmu_role for 64-bit
paging and cause KVM to not reconfigure root_mmu on the next nested VM-Exit.
Alternatively, the root_mmu's role could be invalidated after a successful
KVM_SET_NESTED_STATE that yields vcpu->arch.mmu != vcpu->arch.root_mmu,
i.e. that switches the active mmu to guest_mmu, but doing so is unnecessarily
tricky, and not even needed if L1 and L2 do have the same role (e.g., they
are both 64-bit guests and run with the same CR4).
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211115131837.195527-3-mlevitsk@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull x86 static call update from Thomas Gleixner:
"A single fix for static calls to make the trampoline patching more
robust by placing explicit signature bytes after the call trampoline
to prevent patching random other jumps like the CFI jump table
entries"
* tag 'locking-urgent-2021-11-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
static_call,x86: Robustify trampoline patching
Pull scheduler fixes from Borislav Petkov:
- Avoid touching ~100 config files in order to be able to select the
preemption model
- clear cluster CPU masks too, on the CPU unplug path
- prevent use-after-free in cfs
- Prevent a race condition when updating CPU cache domains
- Factor out common shared part of smp_prepare_cpus() into a common
helper which can be called by both baremetal and Xen, in order to fix
a booting of Xen PV guests
* tag 'sched_urgent_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
preempt: Restore preemption model selection configs
arch_topology: Fix missing clear cluster_cpumask in remove_cpu_topology()
sched/fair: Prevent dead task groups from regaining cfs_rq's
sched/core: Mitigate race cpus_share_cache()/update_top_cache_domain()
x86/smp: Factor out parts of native_smp_prepare_cpus()
Pull x86 fixes from Borislav Petkov:
- Add the model number of a new, Raptor Lake CPU, to intel-family.h
- Do not log spurious corrected MCEs on SKL too, due to an erratum
- Clarify the path of paravirt ops patches upstream
- Add an optimization to avoid writing out AMX components to sigframes
when former are in init state
* tag 'x86_urgent_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/cpu: Add Raptor Lake to Intel family
x86/mce: Add errata workaround for Skylake SKX37
MAINTAINERS: Add some information to PARAVIRT_OPS entry
x86/fpu: Optimize out sigframe xfeatures when in init state
* 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>
