KVM SVM changes for 6.15
- Ensure the PSP driver is initialized when both the PSP and KVM modules are
built-in (the initcall framework doesn't handle dependencies).
- Use long-term pins when registering encrypted memory regions, so that the
pages are migrated out of MIGRATE_CMA/ZONE_MOVABLE and don't lead to
excessive fragmentation.
- Add macros and helpers for setting GHCB return/error codes.
- Add support for Idle HLT interception, which elides interception if the vCPU
has a pending, unmasked virtual IRQ when HLT is executed.
- Fix a bug in INVPCID emulation where KVM fails to check for a non-canonical
address.
- Don't attempt VMRUN for SEV-ES+ guests if the vCPU's VMSA is invalid, e.g.
because the vCPU was "destroyed" via SNP's AP Creation hypercall.
- Reject SNP AP Creation if the requested SEV features for the vCPU don't
match the VM's configured set of features.
- Misc cleanups
KVM x86 misc changes for 6.15:
- Fix a bug in PIC emulation that caused KVM to emit a spurious KVM_REQ_EVENT.
- Add a helper to consolidate handling of mp_state transitions, and use it to
clear pv_unhalted whenever a vCPU is made RUNNABLE.
- Defer runtime CPUID updates until KVM emulates a CPUID instruction, to
coalesce updates when multiple pieces of vCPU state are changing, e.g. as
part of a nested transition.
- Fix a variety of nested emulation bugs, and add VMX support for synthesizing
nested VM-Exit on interception (instead of injecting #UD into L2).
- Drop "support" for PV Async #PF with proctected guests without SEND_ALWAYS,
as KVM can't get the current CPL.
- Misc cleanups
KVM x86 fixes for 6.14-rcN #2
- Set RFLAGS.IF in C code on SVM to get VMRUN out of the STI shadow.
- Ensure DEBUGCTL is context switched on AMD to avoid running the guest with
the host's value, which can lead to unexpected bus lock #DBs.
- Suppress DEBUGCTL.BTF on AMD (to match Intel), as KVM doesn't properly
emulate BTF. KVM's lack of context switching has meant BTF has always been
broken to some extent.
- Always save DR masks for SNP vCPUs if DebugSwap is *supported*, as the guest
can enable DebugSwap without KVM's knowledge.
- Fix a bug in mmu_stress_tests where a vCPU could finish the "writes to RO
memory" phase without actually generating a write-protection fault.
- Fix a printf() goof in the SEV smoke test that causes build failures with
-Werror.
- Explicitly zero EAX and EBX in CPUID.0x8000_0022 output when PERFMON_V2
isn't supported by KVM.
When processing an SNP AP Creation event, invalidate the "next" VMSA GPA
even if acquiring the page/pfn for the new VMSA fails. In practice, the
next GPA will never be used regardless of whether or not its invalidated,
as the entire flow is guarded by snp_ap_waiting_for_reset, and said guard
and snp_vmsa_gpa are always written as a pair. But that's really hard to
see in the code.
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Use guard(mutex) in sev_snp_init_protected_guest_state() and pull in its
lock-protected inner helper. Without an unlock trampoline (and even with
one), there is no real need for an inner helper. Eliminating the helper
also avoids having to fixup the open coded "lockdep" WARN_ON().
Opportunistically drop the error message if KVM can't obtain the pfn for
the new target VMSA. The error message provides zero information that
can't be gleaned from the fact that the vCPU is stuck.
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Mark the VMCB dirty, i.e. zero control.clean, prior to handling the new
VMSA. Nothing in the VALID_PAGE() case touches control.clean, and
isolating the VALID_PAGE() code will allow simplifying the overall logic.
Note, the VMCB probably doesn't need to be marked dirty when the VMSA is
invalid, as KVM will disallow running the vCPU in such a state. But it
also doesn't hurt anything.
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
When handling an "AP Create" event, return an error if the "requested" SEV
features for the vCPU don't exactly match KVM's view of the VM-scoped
features. There is no known use case for heterogeneous SEV features across
vCPUs, and while KVM can't actually enforce an exact match since the value
in RAX isn't guaranteed to match what the guest shoved into the VMSA, KVM
can at least avoid knowingly letting the guest run in an unsupported state.
E.g. if a VM is created with DebugSwap disabled, KVM will intercept #DBs
and DRs for all vCPUs, even if an AP is "created" with DebugSwap enabled in
its VMSA.
Note, the GHCB spec only "requires" that "AP use the same interrupt
injection mechanism as the BSP", but given the disaster that is DebugSwap
and SEV_FEATURES in general, it's safe to say that AMD didn't consider all
possible complications with mismatching features between the BSP and APs.
Opportunistically fold the check into the relevant request flavors; the
"request < AP_DESTROY" check is just a bizarre way of implementing the
AP_CREATE_ON_INIT => AP_CREATE fallthrough.
Fixes: e366f92ea9 ("KVM: SEV: Support SEV-SNP AP Creation NAE event")
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
If KVM rejects an AP Creation event, leave the target vCPU state as-is.
Nothing in the GHCB suggests the hypervisor is *allowed* to muck with vCPU
state on failure, let alone required to do so. Furthermore, kicking only
in the !ON_INIT case leads to divergent behavior, and even the "kick" case
is non-deterministic.
E.g. if an ON_INIT request fails, the guest can successfully retry if the
fixed AP Creation request is made prior to sending INIT. And if a !ON_INIT
fails, the guest can successfully retry if the fixed AP Creation request is
handled before the target vCPU processes KVM's
KVM_REQ_UPDATE_PROTECTED_GUEST_STATE.
Fixes: e366f92ea9 ("KVM: SEV: Support SEV-SNP AP Creation NAE event")
Cc: stable@vger.kernel.org
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Explicitly reject KVM_RUN with KVM_EXIT_FAIL_ENTRY if userspace "coerces"
KVM into running an SEV-ES+ guest with an invalid VMSA, e.g. by modifying
a vCPU's mp_state to be RUNNABLE after an SNP vCPU has undergone a Destroy
event. On Destroy or failed Create, KVM marks the vCPU HALTED so that
*KVM* doesn't run the vCPU, but nothing prevents a misbehaving VMM from
manually making the vCPU RUNNABLE via KVM_SET_MP_STATE.
Attempting VMRUN with an invalid VMSA should be harmless, but knowingly
executing VMRUN with bad control state is at best dodgy.
Fixes: e366f92ea9 ("KVM: SEV: Support SEV-SNP AP Creation NAE event")
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Never rely on the CPU to restore/load host DR0..DR3 values, even if the
CPU supports DebugSwap, as there are no guarantees that SNP guests will
actually enable DebugSwap on APs. E.g. if KVM were to rely on the CPU to
load DR0..DR3 and skipped them during hw_breakpoint_restore(), KVM would
run with clobbered-to-zero DRs if an SNP guest created APs without
DebugSwap enabled.
Update the comment to explain the dangers, and hopefully prevent breaking
KVM in the future.
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
When running SEV-SNP guests on a CPU that supports DebugSwap, always save
the host's DR0..DR3 mask MSR values irrespective of whether or not
DebugSwap is enabled, to ensure the host values aren't clobbered by the
CPU. And for now, also save DR0..DR3, even though doing so isn't
necessary (see below).
SVM_VMGEXIT_AP_CREATE is deeply flawed in that it allows the *guest* to
create a VMSA with guest-controlled SEV_FEATURES. A well behaved guest
can inform the hypervisor, i.e. KVM, of its "requested" features, but on
CPUs without ALLOWED_SEV_FEATURES support, nothing prevents the guest from
lying about which SEV features are being enabled (or not!).
If a misbehaving guest enables DebugSwap in a secondary vCPU's VMSA, the
CPU will load the DR0..DR3 mask MSRs on #VMEXIT, i.e. will clobber the
MSRs with '0' if KVM doesn't save its desired value.
Note, DR0..DR3 themselves are "ok", as DR7 is reset on #VMEXIT, and KVM
restores all DRs in common x86 code as needed via hw_breakpoint_restore().
I.e. there is no risk of host DR0..DR3 being clobbered (when it matters).
However, there is a flaw in the opposite direction; because the guest can
lie about enabling DebugSwap, i.e. can *disable* DebugSwap without KVM's
knowledge, KVM must not rely on the CPU to restore DRs. Defer fixing
that wart, as it's more of a documentation issue than a bug in the code.
Note, KVM added support for DebugSwap on commit d1f85fbe83 ("KVM: SEV:
Enable data breakpoints in SEV-ES"), but that is not an appropriate Fixes,
as the underlying flaw exists in hardware, not in KVM. I.e. all kernels
that support SEV-SNP need to be patched, not just kernels with KVM's full
support for DebugSwap (ignoring that DebugSwap support landed first).
Opportunistically fix an incorrect statement in the comment; on CPUs
without DebugSwap, the CPU does NOT save or load debug registers, i.e.
Fixes: e366f92ea9 ("KVM: SEV: Support SEV-SNP AP Creation NAE event")
Cc: stable@vger.kernel.org
Cc: Naveen N Rao <naveen@kernel.org>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Convert VMGEXIT SW_EXITINFO1 codes from plain numbers to proper defines.
Opportunistically update the comment for the malformed input "sub-error"
codes to state that they are defined by the GHCB, and to capure the
relationship to the malformed input response.
No functional change intended.
Signed-off-by: Melody Wang <huibo.wang@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Pavan Kumar Paluri <papaluri@amd.com>
Link: https://lore.kernel.org/r/20250225213937.2471419-2-huibo.wang@amd.com
[sean: update comments]
Signed-off-by: Sean Christopherson <seanjc@google.com>
The kernel's initcall infrastructure lacks the ability to express
dependencies between initcalls, whereas the modules infrastructure
automatically handles dependencies via symbol loading. Ensure the
PSP SEV driver is initialized before proceeding in sev_hardware_setup()
if KVM is built-in as the dependency isn't handled by the initcall
infrastructure.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Message-ID: <f78ddb64087df27e7bcb1ae0ab53f55aa0804fab.1739226950.git.ashish.kalra@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When registering an encrypted memory region for SEV-MEM/SEV-ES guests,
pin the pages with FOLL_TERM so that the pages are migrated out of
MIGRATE_CMA/ZONE_MOVABLE. Failure to do so violates the CMA/MOVABLE
mechanisms and can result in fragmentation due to unmovable pages, e.g.
can make CMA allocations fail.
Signed-off-by: Ge Yang <yangge1116@126.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Acked-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/1739241423-14326-1-git-send-email-yangge1116@126.com
[sean: massage changelog, make @flags an unsigned int]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Defer runtime CPUID updates until the next non-faulting CPUID emulation
or KVM_GET_CPUID2, which are the only paths in KVM that consume the
dynamic entries. Deferring the updates is especially beneficial to
nested VM-Enter/VM-Exit, as KVM will almost always detect multiple state
changes, not to mention the updates don't need to be realized while L2 is
active if CPUID is being intercepted by L1 (CPUID is a mandatory intercept
on Intel, but not AMD).
Deferring CPUID updates shaves several hundred cycles from nested VMX
roundtrips, as measured from L2 executing CPUID in a tight loop:
SKX 6850 => 6450
ICX 9000 => 8800
EMR 7900 => 7700
Alternatively, KVM could update only the CPUID leaves that are affected
by the state change, e.g. update XSAVE info only if XCR0 or XSS changes,
but that adds non-trivial complexity and doesn't solve the underlying
problem of nested transitions potentially changing both XCR0 and XSS, on
both nested VM-Enter and VM-Exit.
Skipping updates entirely if L2 is active and CPUID is being intercepted
by L1 could work for the common case. However, simply skipping updates if
L2 is active is *very* subtly dangerous and complex. Most KVM updates are
triggered by changes to the current vCPU state, which may be L2 state,
whereas performing updates only for L1 would requiring detecting changes
to L1 state. KVM would need to either track relevant L1 state, or defer
runtime CPUID updates until the next nested VM-Exit. The former is ugly
and complex, while the latter comes with similar dangers to deferring all
CPUID updates, and would only address the nested VM-Enter path.
To guard against using stale data, disallow querying dynamic CPUID feature
bits, i.e. features that KVM updates at runtime, via a compile-time
assertion in guest_cpu_cap_has(). Exempt MWAIT from the rule, as the
MISC_ENABLE_NO_MWAIT means that MWAIT is _conditionally_ a dynamic CPUID
feature.
Note, the rule could be enforced for MWAIT as well, e.g. by querying guest
CPUID in kvm_emulate_monitor_mwait, but there's no obvious advtantage to
doing so, and allowing MWAIT for guest_cpuid_has() opens up a different can
of worms. MONITOR/MWAIT can't be virtualized (for a reasonable definition),
and the nature of the MWAIT_NEVER_UD_FAULTS and MISC_ENABLE_NO_MWAIT quirks
means checking X86_FEATURE_MWAIT outside of kvm_emulate_monitor_mwait() is
wrong for other reasons.
Beyond the aforementioned feature bits, the only other dynamic CPUID
(sub)leaves are the XSAVE sizes, and similar to MWAIT, consuming those
CPUID entries in KVM is all but guaranteed to be a bug. The layout for an
actual XSAVE buffer depends on the format (compacted or not) and
potentially the features that are actually enabled. E.g. see the logic in
fpstate_clear_xstate_component() needed to poke into the guest's effective
XSAVE state to clear MPX state on INIT. KVM does consume
CPUID.0xD.0.{EAX,EDX} in kvm_check_cpuid() and cpuid_get_supported_xcr0(),
but not EBX, which is the only dynamic output register in the leaf.
Link: https://lore.kernel.org/r/20241211013302.1347853-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
In kvm_set_mp_state(), ensure that vcpu->arch.pv.pv_unhalted is always
cleared on a transition to KVM_MP_STATE_RUNNABLE, so that the next HLT
instruction will be respected.
Fixes: 6aef266c6e ("kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks")
Fixes: b6b8a1451f ("KVM: nVMX: Rework interception of IRQs and NMIs")
Fixes: 38c0b192bd ("KVM: SVM: leave halted state on vmexit")
Fixes: 1a65105a5a ("KVM: x86/xen: handle PV spinlocks slowpath")
Signed-off-by: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20250113200150.487409-3-jmattson@google.com
[sean: add Xen PV spinlocks to the list of Fixes, tweak changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>
Pull kvm updates from Paolo Bonzini:
"Loongarch:
- Clear LLBCTL if secondary mmu mapping changes
- Add hypercall service support for usermode VMM
x86:
- Add a comment to kvm_mmu_do_page_fault() to explain why KVM
performs a direct call to kvm_tdp_page_fault() when RETPOLINE is
enabled
- Ensure that all SEV code is compiled out when disabled in Kconfig,
even if building with less brilliant compilers
- Remove a redundant TLB flush on AMD processors when guest CR4.PGE
changes
- Use str_enabled_disabled() to replace open coded strings
- Drop kvm_x86_ops.hwapic_irr_update() as KVM updates hardware's
APICv cache prior to every VM-Enter
- Overhaul KVM's CPUID feature infrastructure to track all vCPU
capabilities instead of just those where KVM needs to manage state
and/or explicitly enable the feature in hardware. Along the way,
refactor the code to make it easier to add features, and to make it
more self-documenting how KVM is handling each feature
- Rework KVM's handling of VM-Exits during event vectoring; this
plugs holes where KVM unintentionally puts the vCPU into infinite
loops in some scenarios (e.g. if emulation is triggered by the
exit), and brings parity between VMX and SVM
- Add pending request and interrupt injection information to the
kvm_exit and kvm_entry tracepoints respectively
- Fix a relatively benign flaw where KVM would end up redoing RDPKRU
when loading guest/host PKRU, due to a refactoring of the kernel
helpers that didn't account for KVM's pre-checking of the need to
do WRPKRU
- Make the completion of hypercalls go through the complete_hypercall
function pointer argument, no matter if the hypercall exits to
userspace or not.
Previously, the code assumed that KVM_HC_MAP_GPA_RANGE specifically
went to userspace, and all the others did not; the new code need
not special case KVM_HC_MAP_GPA_RANGE and in fact does not care at
all whether there was an exit to userspace or not
- As part of enabling TDX virtual machines, support support
separation of private/shared EPT into separate roots.
When TDX will be enabled, operations on private pages will need to
go through the privileged TDX Module via SEAMCALLs; as a result,
they are limited and relatively slow compared to reading a PTE.
The patches included in 6.14 allow KVM to keep a mirror of the
private EPT in host memory, and define entries in kvm_x86_ops to
operate on external page tables such as the TDX private EPT
- The recently introduced conversion of the NX-page reclamation
kthread to vhost_task moved the task under the main process. The
task is created as soon as KVM_CREATE_VM was invoked and this, of
course, broke userspace that didn't expect to see any child task of
the VM process until it started creating its own userspace threads.
In particular crosvm refuses to fork() if procfs shows any child
task, so unbreak it by creating the task lazily. This is arguably a
userspace bug, as there can be other kinds of legitimate worker
tasks and they wouldn't impede fork(); but it's not like userspace
has a way to distinguish kernel worker tasks right now. Should they
show as "Kthread: 1" in proc/.../status?
x86 - Intel:
- Fix a bug where KVM updates hardware's APICv cache of the highest
ISR bit while L2 is active, while ultimately results in a
hardware-accelerated L1 EOI effectively being lost
- Honor event priority when emulating Posted Interrupt delivery
during nested VM-Enter by queueing KVM_REQ_EVENT instead of
immediately handling the interrupt
- Rework KVM's processing of the Page-Modification Logging buffer to
reap entries in the same order they were created, i.e. to mark gfns
dirty in the same order that hardware marked the page/PTE dirty
- Misc cleanups
Generic:
- Cleanup and harden kvm_set_memory_region(); add proper lockdep
assertions when setting memory regions and add a dedicated API for
setting KVM-internal memory regions. The API can then explicitly
disallow all flags for KVM-internal memory regions
- Explicitly verify the target vCPU is online in kvm_get_vcpu() to
fix a bug where KVM would return a pointer to a vCPU prior to it
being fully online, and give kvm_for_each_vcpu() similar treatment
to fix a similar flaw
- Wait for a vCPU to come online prior to executing a vCPU ioctl, to
fix a bug where userspace could coerce KVM into handling the ioctl
on a vCPU that isn't yet onlined
- Gracefully handle xarray insertion failures; even though such
failures are impossible in practice after xa_reserve(), reserving
an entry is always followed by xa_store() which does not know (or
differentiate) whether there was an xa_reserve() before or not
RISC-V:
- Zabha, Svvptc, and Ziccrse extension support for guests. None of
them require anything in KVM except for detecting them and marking
them as supported; Zabha adds byte and halfword atomic operations,
while the others are markers for specific operation of the TLB and
of LL/SC instructions respectively
- Virtualize SBI system suspend extension for Guest/VM
- Support firmware counters which can be used by the guests to
collect statistics about traps that occur in the host
Selftests:
- Rework vcpu_get_reg() to return a value instead of using an
out-param, and update all affected arch code accordingly
- Convert the max_guest_memory_test into a more generic
mmu_stress_test. The basic gist of the "conversion" is to have the
test do mprotect() on guest memory while vCPUs are accessing said
memory, e.g. to verify KVM and mmu_notifiers are working as
intended
- Play nice with treewrite builds of unsupported architectures, e.g.
arm (32-bit), as KVM selftests' Makefile doesn't do anything to
ensure the target architecture is actually one KVM selftests
supports
- Use the kernel's $(ARCH) definition instead of the target triple
for arch specific directories, e.g. arm64 instead of aarch64,
mainly so as not to be different from the rest of the kernel
- Ensure that format strings for logging statements are checked by
the compiler even when the logging statement itself is disabled
- Attempt to whack the last LLC references/misses mole in the Intel
PMU counters test by adding a data load and doing CLFLUSH{OPT} on
the data instead of the code being executed. It seems that modern
Intel CPUs have learned new code prefetching tricks that bypass the
PMU counters
- Fix a flaw in the Intel PMU counters test where it asserts that
events are counting correctly without actually knowing what the
events count given the underlying hardware; this can happen if
Intel reuses a formerly microarchitecture-specific event encoding
as an architectural event, as was the case for Top-Down Slots"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (151 commits)
kvm: defer huge page recovery vhost task to later
KVM: x86/mmu: Return RET_PF* instead of 1 in kvm_mmu_page_fault()
KVM: Disallow all flags for KVM-internal memslots
KVM: x86: Drop double-underscores from __kvm_set_memory_region()
KVM: Add a dedicated API for setting KVM-internal memslots
KVM: Assert slots_lock is held when setting memory regions
KVM: Open code kvm_set_memory_region() into its sole caller (ioctl() API)
LoongArch: KVM: Add hypercall service support for usermode VMM
LoongArch: KVM: Clear LLBCTL if secondary mmu mapping is changed
KVM: SVM: Use str_enabled_disabled() helper in svm_hardware_setup()
KVM: VMX: read the PML log in the same order as it was written
KVM: VMX: refactor PML terminology
KVM: VMX: Fix comment of handle_vmx_instruction()
KVM: VMX: Reinstate __exit attribute for vmx_exit()
KVM: SVM: Use str_enabled_disabled() helper in sev_hardware_setup()
KVM: x86: Avoid double RDPKRU when loading host/guest PKRU
KVM: x86: Use LVT_TIMER instead of an open coded literal
RISC-V: KVM: Add new exit statstics for redirected traps
RISC-V: KVM: Update firmware counters for various events
RISC-V: KVM: Redirect instruction access fault trap to guest
...
Make the completion of hypercalls go through the complete_hypercall
function pointer argument, no matter if the hypercall exits to
userspace or not. Previously, the code assumed that KVM_HC_MAP_GPA_RANGE
specifically went to userspace, and all the others did not; the new code
need not special case KVM_HC_MAP_GPA_RANGE and in fact does not care at
all whether there was an exit to userspace or not.
KVM x86 misc changes for 6.14:
- Overhaul KVM's CPUID feature infrastructure to track all vCPU capabilities
instead of just those where KVM needs to manage state and/or explicitly
enable the feature in hardware. Along the way, refactor the code to make
it easier to add features, and to make it more self-documenting how KVM
is handling each feature.
- Rework KVM's handling of VM-Exits during event vectoring; this plugs holes
where KVM unintentionally puts the vCPU into infinite loops in some scenarios
(e.g. if emulation is triggered by the exit), and brings parity between VMX
and SVM.
- Add pending request and interrupt injection information to the kvm_exit and
kvm_entry tracepoints respectively.
- Fix a relatively benign flaw where KVM would end up redoing RDPKRU when
loading guest/host PKRU, due to a refactoring of the kernel helpers that
didn't account for KVM's pre-checking of the need to do WRPKRU.
QEMU up to 9.2.0 is assuming that vcpu->run->hypercall.ret is 0 on exit and
it never modifies it when processing KVM_EXIT_HYPERCALL. Make this explicit
in the code, to avoid breakage when KVM starts modifying that field.
This in principle is not a good idea... It would have been much better if
KVM had set the field to -KVM_ENOSYS from the beginning, so that a dumb
userspace that does nothing on KVM_EXIT_HYPERCALL would tell the guest it
does not support KVM_HC_MAP_GPA_RANGE. However, breaking userspace is
a Very Bad Thing, as everybody should know.
Reported-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Switch all queries (except XSAVES) of guest features from guest CPUID to
guest capabilities, i.e. replace all calls to guest_cpuid_has() with calls
to guest_cpu_cap_has().
Keep guest_cpuid_has() around for XSAVES, but subsume its helper
guest_cpuid_get_register() and add a compile-time assertion to prevent
using guest_cpuid_has() for any other feature. Add yet another comment
for XSAVE to explain why KVM is allowed to query its raw guest CPUID.
Opportunistically drop the unused guest_cpuid_clear(), as there should be
no circumstance in which KVM needs to _clear_ a guest CPUID feature now
that everything is tracked via cpu_caps. E.g. KVM may need to _change_
a feature to emulate dynamic CPUID flags, but KVM should never need to
clear a feature in guest CPUID to prevent it from being used by the guest.
Delete the last remnants of the governed features framework, as the lone
holdout was vmx_adjust_secondary_exec_control()'s divergent behavior for
governed vs. ungoverned features.
Note, replacing guest_cpuid_has() checks with guest_cpu_cap_has() when
computing reserved CR4 bits is a nop when viewed as a whole, as KVM's
capabilities are already incorporated into the calculation, i.e. if a
feature is present in guest CPUID but unsupported by KVM, its CR4 bit
was already being marked as reserved, checking guest_cpu_cap_has() simply
double-stamps that it's a reserved bit.
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20241128013424.4096668-51-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
As the first step toward replacing KVM's so-called "governed features"
framework with a more comprehensive, less poorly named implementation,
replace the "kvm_governed_feature" function prefix with "guest_cpu_cap"
and rename guest_can_use() to guest_cpu_cap_has().
The "guest_cpu_cap" naming scheme mirrors that of "kvm_cpu_cap", and
provides a more clear distinction between guest capabilities, which are
KVM controlled (heh, or one might say "governed"), and guest CPUID, which
with few exceptions is fully userspace controlled.
Opportunistically rewrite the comment about XSS passthrough for SEV-ES
guests to avoid referencing so many functions, as such comments are prone
to becoming stale (case in point...).
No functional change intended.
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Link: https://lore.kernel.org/r/20241128013424.4096668-40-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
Pull kvm updates from Paolo Bonzini:
"The biggest change here is eliminating the awful idea that KVM had of
essentially guessing which pfns are refcounted pages.
The reason to do so was that KVM needs to map both non-refcounted
pages (for example BARs of VFIO devices) and VM_PFNMAP/VM_MIXMEDMAP
VMAs that contain refcounted pages.
However, the result was security issues in the past, and more recently
the inability to map VM_IO and VM_PFNMAP memory that _is_ backed by
struct page but is not refcounted. In particular this broke virtio-gpu
blob resources (which directly map host graphics buffers into the
guest as "vram" for the virtio-gpu device) with the amdgpu driver,
because amdgpu allocates non-compound higher order pages and the tail
pages could not be mapped into KVM.
This requires adjusting all uses of struct page in the
per-architecture code, to always work on the pfn whenever possible.
The large series that did this, from David Stevens and Sean
Christopherson, also cleaned up substantially the set of functions
that provided arch code with the pfn for a host virtual addresses.
The previous maze of twisty little passages, all different, is
replaced by five functions (__gfn_to_page, __kvm_faultin_pfn, the
non-__ versions of these two, and kvm_prefetch_pages) saving almost
200 lines of code.
ARM:
- Support for stage-1 permission indirection (FEAT_S1PIE) and
permission overlays (FEAT_S1POE), including nested virt + the
emulated page table walker
- Introduce PSCI SYSTEM_OFF2 support to KVM + client driver. This
call was introduced in PSCIv1.3 as a mechanism to request
hibernation, similar to the S4 state in ACPI
- Explicitly trap + hide FEAT_MPAM (QoS controls) from KVM guests. As
part of it, introduce trivial initialization of the host's MPAM
context so KVM can use the corresponding traps
- PMU support under nested virtualization, honoring the guest
hypervisor's trap configuration and event filtering when running a
nested guest
- Fixes to vgic ITS serialization where stale device/interrupt table
entries are not zeroed when the mapping is invalidated by the VM
- Avoid emulated MMIO completion if userspace has requested
synchronous external abort injection
- Various fixes and cleanups affecting pKVM, vCPU initialization, and
selftests
LoongArch:
- Add iocsr and mmio bus simulation in kernel.
- Add in-kernel interrupt controller emulation.
- Add support for virtualization extensions to the eiointc irqchip.
PPC:
- Drop lingering and utterly obsolete references to PPC970 KVM, which
was removed 10 years ago.
- Fix incorrect documentation references to non-existing ioctls
RISC-V:
- Accelerate KVM RISC-V when running as a guest
- Perf support to collect KVM guest statistics from host side
s390:
- New selftests: more ucontrol selftests and CPU model sanity checks
- Support for the gen17 CPU model
- List registers supported by KVM_GET/SET_ONE_REG in the
documentation
x86:
- Cleanup KVM's handling of Accessed and Dirty bits to dedup code,
improve documentation, harden against unexpected changes.
Even if the hardware A/D tracking is disabled, it is possible to
use the hardware-defined A/D bits to track if a PFN is Accessed
and/or Dirty, and that removes a lot of special cases.
- Elide TLB flushes when aging secondary PTEs, as has been done in
x86's primary MMU for over 10 years.
- Recover huge pages in-place in the TDP MMU when dirty page logging
is toggled off, instead of zapping them and waiting until the page
is re-accessed to create a huge mapping. This reduces vCPU jitter.
- Batch TLB flushes when dirty page logging is toggled off. This
reduces the time it takes to disable dirty logging by ~3x.
- Remove the shrinker that was (poorly) attempting to reclaim shadow
page tables in low-memory situations.
- Clean up and optimize KVM's handling of writes to
MSR_IA32_APICBASE.
- Advertise CPUIDs for new instructions in Clearwater Forest
- Quirk KVM's misguided behavior of initialized certain feature MSRs
to their maximum supported feature set, which can result in KVM
creating invalid vCPU state. E.g. initializing PERF_CAPABILITIES to
a non-zero value results in the vCPU having invalid state if
userspace hides PDCM from the guest, which in turn can lead to
save/restore failures.
- Fix KVM's handling of non-canonical checks for vCPUs that support
LA57 to better follow the "architecture", in quotes because the
actual behavior is poorly documented. E.g. most MSR writes and
descriptor table loads ignore CR4.LA57 and operate purely on
whether the CPU supports LA57.
- Bypass the register cache when querying CPL from kvm_sched_out(),
as filling the cache from IRQ context is generally unsafe; harden
the cache accessors to try to prevent similar issues from occuring
in the future. The issue that triggered this change was already
fixed in 6.12, but was still kinda latent.
- Advertise AMD_IBPB_RET to userspace, and fix a related bug where
KVM over-advertises SPEC_CTRL when trying to support cross-vendor
VMs.
- Minor cleanups
- Switch hugepage recovery thread to use vhost_task.
These kthreads can consume significant amounts of CPU time on
behalf of a VM or in response to how the VM behaves (for example
how it accesses its memory); therefore KVM tried to place the
thread in the VM's cgroups and charge the CPU time consumed by that
work to the VM's container.
However the kthreads did not process SIGSTOP/SIGCONT, and therefore
cgroups which had KVM instances inside could not complete freezing.
Fix this by replacing the kthread with a PF_USER_WORKER thread, via
the vhost_task abstraction. Another 100+ lines removed, with
generally better behavior too like having these threads properly
parented in the process tree.
- Revert a workaround for an old CPU erratum (Nehalem/Westmere) that
didn't really work; there was really nothing to work around anyway:
the broken patch was meant to fix nested virtualization, but the
PERF_GLOBAL_CTRL MSR is virtualized and therefore unaffected by the
erratum.
- Fix 6.12 regression where CONFIG_KVM will be built as a module even
if asked to be builtin, as long as neither KVM_INTEL nor KVM_AMD is
'y'.
x86 selftests:
- x86 selftests can now use AVX.
Documentation:
- Use rST internal links
- Reorganize the introduction to the API document
Generic:
- Protect vcpu->pid accesses outside of vcpu->mutex with a rwlock
instead of RCU, so that running a vCPU on a different task doesn't
encounter long due to having to wait for all CPUs become quiescent.
In general both reads and writes are rare, but userspace that
supports confidential computing is introducing the use of "helper"
vCPUs that may jump from one host processor to another. Those will
be very happy to trigger a synchronize_rcu(), and the effect on
performance is quite the disaster"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (298 commits)
KVM: x86: Break CONFIG_KVM_X86's direct dependency on KVM_INTEL || KVM_AMD
KVM: x86: add back X86_LOCAL_APIC dependency
Revert "KVM: VMX: Move LOAD_IA32_PERF_GLOBAL_CTRL errata handling out of setup_vmcs_config()"
KVM: x86: switch hugepage recovery thread to vhost_task
KVM: x86: expose MSR_PLATFORM_INFO as a feature MSR
x86: KVM: Advertise CPUIDs for new instructions in Clearwater Forest
Documentation: KVM: fix malformed table
irqchip/loongson-eiointc: Add virt extension support
LoongArch: KVM: Add irqfd support
LoongArch: KVM: Add PCHPIC user mode read and write functions
LoongArch: KVM: Add PCHPIC read and write functions
LoongArch: KVM: Add PCHPIC device support
LoongArch: KVM: Add EIOINTC user mode read and write functions
LoongArch: KVM: Add EIOINTC read and write functions
LoongArch: KVM: Add EIOINTC device support
LoongArch: KVM: Add IPI user mode read and write function
LoongArch: KVM: Add IPI read and write function
LoongArch: KVM: Add IPI device support
LoongArch: KVM: Add iocsr and mmio bus simulation in kernel
KVM: arm64: Pass on SVE mapping failures
...
Pull 'struct fd' class updates from Al Viro:
"The bulk of struct fd memory safety stuff
Making sure that struct fd instances are destroyed in the same scope
where they'd been created, getting rid of reassignments and passing
them by reference, converting to CLASS(fd{,_pos,_raw}).
We are getting very close to having the memory safety of that stuff
trivial to verify"
* tag 'pull-fd' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (28 commits)
deal with the last remaing boolean uses of fd_file()
css_set_fork(): switch to CLASS(fd_raw, ...)
memcg_write_event_control(): switch to CLASS(fd)
assorted variants of irqfd setup: convert to CLASS(fd)
do_pollfd(): convert to CLASS(fd)
convert do_select()
convert vfs_dedupe_file_range().
convert cifs_ioctl_copychunk()
convert media_request_get_by_fd()
convert spu_run(2)
switch spufs_calls_{get,put}() to CLASS() use
convert cachestat(2)
convert do_preadv()/do_pwritev()
fdget(), more trivial conversions
fdget(), trivial conversions
privcmd_ioeventfd_assign(): don't open-code eventfd_ctx_fdget()
o2hb_region_dev_store(): avoid goto around fdget()/fdput()
introduce "fd_pos" class, convert fdget_pos() users to it.
fdget_raw() users: switch to CLASS(fd_raw)
convert vmsplice() to CLASS(fd)
...
- Drop obsolete references to PPC970 KVM, which was removed 10 years ago.
- Fix incorrect references to non-existing ioctls
- List registers supported by KVM_GET/SET_ONE_REG on s390
- Use rST internal links
- Reorganize the introduction to the API document
fdget() is the first thing done in scope, all matching fdput() are
immediately followed by leaving the scope.
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Now that all kvm_vcpu_{,un}map() users pass "true" for @dirty, have them
pass "true" as a @writable param to kvm_vcpu_map(), and thus create a
read-only mapping when possible.
Note, creating read-only mappings can be theoretically slower, as they
don't play nice with fast GUP due to the need to break CoW before mapping
the underlying PFN. But practically speaking, creating a mapping isn't
a super hot path, and getting a writable mapping for reading is weird and
confusing.
Tested-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Tested-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20241010182427.1434605-34-seanjc@google.com>
Pull 'struct fd' updates from Al Viro:
"Just the 'struct fd' layout change, with conversion to accessor
helpers"
* tag 'pull-stable-struct_fd' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
add struct fd constructors, get rid of __to_fd()
struct fd: representation change
introduce fd_file(), convert all accessors to it.
For any changes of struct fd representation we need to
turn existing accesses to fields into calls of wrappers.
Accesses to struct fd::flags are very few (3 in linux/file.h,
1 in net/socket.c, 3 in fs/overlayfs/file.c and 3 more in
explicit initializers).
Those can be dealt with in the commit converting to
new layout; accesses to struct fd::file are too many for that.
This commit converts (almost) all of f.file to
fd_file(f). It's not entirely mechanical ('file' is used as
a member name more than just in struct fd) and it does not
even attempt to distinguish the uses in pointer context from
those in boolean context; the latter will be eventually turned
into a separate helper (fd_empty()).
NOTE: mass conversion to fd_empty(), tempting as it
might be, is a bad idea; better do that piecewise in commit
that convert from fdget...() to CLASS(...).
[conflicts in fs/fhandle.c, kernel/bpf/syscall.c, mm/memcontrol.c
caught by git; fs/stat.c one got caught by git grep]
[fs/xattr.c conflict]
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
This check is currently performed by sev_gmem_post_populate(), but it
applies to all callers of kvm_gmem_populate(): the point of the function
is that the memory is being encrypted and some work has to be done
on all the gfns in order to encrypt them.
Therefore, check the KVM_MEMORY_ATTRIBUTE_PRIVATE attribute prior
to invoking the callback, and stop the operation if a shared page
is encountered. Because CONFIG_KVM_PRIVATE_MEM in principle does
not require attributes, this makes kvm_gmem_populate() depend on
CONFIG_KVM_GENERIC_PRIVATE_MEM (which does require them).
Reviewed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Do not allow populating the same page twice with startup data. In the
case of SEV-SNP, for example, the firmware does not allow it anyway,
since the launch-update operation is only possible on pages that are
still shared in the RMP.
Even if it worked, kvm_gmem_populate()'s callback is meant to have side
effects such as updating launch measurements, and updating the same
page twice is unlikely to have the desired results.
Races between calls to the ioctl are not possible because
kvm_gmem_populate() holds slots_lock and the VM should not be running.
But again, even if this worked on other confidential computing technology,
it doesn't matter to guest_memfd.c whether this is something fishy
such as missing synchronization in userspace, or rather something
intentional. One of the racers wins, and the page is initialized by
either kvm_gmem_prepare_folio() or kvm_gmem_populate().
Anyway, out of paranoia, adjust sev_gmem_post_populate() anyway to use
the same errno that kvm_gmem_populate() is using.
Reviewed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM_PRE_FAULT_MEMORY for an SNP guest can race with
sev_gmem_post_populate() in bad ways. The following sequence for
instance can potentially trigger an RMP fault:
thread A, sev_gmem_post_populate: called
thread B, sev_gmem_prepare: places below 'pfn' in a private state in RMP
thread A, sev_gmem_post_populate: *vaddr = kmap_local_pfn(pfn + i);
thread A, sev_gmem_post_populate: copy_from_user(vaddr, src + i * PAGE_SIZE, PAGE_SIZE);
RMP #PF
Fix this by only allowing KVM_PRE_FAULT_MEMORY to run after a guest's
initial private memory contents have been finalized via
KVM_SEV_SNP_LAUNCH_FINISH.
Beyond fixing this issue, it just sort of makes sense to enforce this,
since the KVM_PRE_FAULT_MEMORY documentation states:
"KVM maps memory as if the vCPU generated a stage-2 read page fault"
which sort of implies we should be acting on the same guest state that a
vCPU would see post-launch after the initial guest memory is all set up.
Co-developed-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The GHCB 2.0 specification defines 2 GHCB request types to allow SNP guests
to send encrypted messages/requests to firmware: SNP Guest Requests and SNP
Extended Guest Requests. These encrypted messages are used for things like
servicing attestation requests issued by the guest. Implementing support for
these is required to be fully GHCB-compliant.
For the most part, KVM only needs to handle forwarding these requests to
firmware (to be issued via the SNP_GUEST_REQUEST firmware command defined
in the SEV-SNP Firmware ABI), and then forwarding the encrypted response to
the guest.
However, in the case of SNP Extended Guest Requests, the host is also
able to provide the certificate data corresponding to the endorsement key
used by firmware to sign attestation report requests. This certificate data
is provided by userspace because:
1) It allows for different keys/key types to be used for each particular
guest with requiring any sort of KVM API to configure the certificate
table in advance on a per-guest basis.
2) It provides additional flexibility with how attestation requests might
be handled during live migration where the certificate data for
source/dest might be different.
3) It allows all synchronization between certificates and firmware/signing
key updates to be handled purely by userspace rather than requiring
some in-kernel mechanism to facilitate it. [1]
To support fetching certificate data from userspace, a new KVM exit type will
be needed to handle fetching the certificate from userspace. An attempt to
define a new KVM_EXIT_COCO/KVM_EXIT_COCO_REQ_CERTS exit type to handle this
was introduced in v1 of this patchset, but is still being discussed by
community, so for now this patchset only implements a stub version of SNP
Extended Guest Requests that does not provide certificate data, but is still
enough to provide compliance with the GHCB 2.0 spec.
Version 2 of GHCB specification added support for the SNP Extended Guest
Request Message NAE event. This event serves a nearly identical purpose
to the previously-added SNP_GUEST_REQUEST event, but for certain message
types it allows the guest to supply a buffer to be used for additional
information in some cases.
Currently the GHCB spec only defines extended handling of this sort in
the case of attestation requests, where the additional buffer is used to
supply a table of certificate data corresponding to the attestion
report's signing key. Support for this extended handling will require
additional KVM APIs to handle coordinating with userspace.
Whether or not the hypervisor opts to provide this certificate data is
optional. However, support for processing SNP_EXTENDED_GUEST_REQUEST
GHCB requests is required by the GHCB 2.0 specification for SNP guests,
so for now implement a stub implementation that provides an empty
certificate table to the guest if it supplies an additional buffer, but
otherwise behaves identically to SNP_GUEST_REQUEST.
Reviewed-by: Carlos Bilbao <carlos.bilbao.osdev@gmail.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240701223148.3798365-4-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Version 2 of GHCB specification added support for the SNP Guest Request
Message NAE event. The event allows for an SEV-SNP guest to make
requests to the SEV-SNP firmware through the hypervisor using the
SNP_GUEST_REQUEST API defined in the SEV-SNP firmware specification.
This is used by guests primarily to request attestation reports from
firmware. There are other request types are available as well, but the
specifics of what guest requests are being made generally does not
affect how they are handled by the hypervisor, which only serves as a
proxy for the guest requests and firmware responses.
Implement handling for these events.
When an SNP Guest Request is issued, the guest will provide its own
request/response pages, which could in theory be passed along directly
to firmware. However, these pages would need special care:
- Both pages are from shared guest memory, so they need to be
protected from migration/etc. occurring while firmware reads/writes
to them. At a minimum, this requires elevating the ref counts and
potentially needing an explicit pinning of the memory. This places
additional restrictions on what type of memory backends userspace
can use for shared guest memory since there would be some reliance
on using refcounted pages.
- The response page needs to be switched to Firmware-owned state
before the firmware can write to it, which can lead to potential
host RMP #PFs if the guest is misbehaved and hands the host a
guest page that KVM is writing to for other reasons (e.g. virtio
buffers).
Both of these issues can be avoided completely by using
separately-allocated bounce pages for both the request/response pages
and passing those to firmware instead. So that's the approach taken
here.
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Co-developed-by: Alexey Kardashevskiy <aik@amd.com>
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Co-developed-by: Ashish Kalra <ashish.kalra@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
[mdr: ensure FW command failures are indicated to guest, drop extended
request handling to be re-written as separate patch, massage commit]
Signed-off-by: Michael Roth <michael.roth@amd.com>
Message-ID: <20240701223148.3798365-2-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM SVM changes for 6.11
- Make per-CPU save_area allocations NUMA-aware.
- Force sev_es_host_save_area() to be inlined to avoid calling into an
instrumentable function from noinstr code.
