| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
apic-access-page
According to Intel SDM section 28.3.3.3/28.3.3.4 Guidelines for Use
of the INVVPID/INVEPT Instruction, the hypervisor needs to execute
INVVPID/INVEPT X in case CPU executes VMEntry with VPID/EPTP X and
either: "Virtualize APIC accesses" VM-execution control was changed
from 0 to 1, OR the value of apic_access_page was changed.
In the nested case, the burden falls on L1, unless L0 enables EPT in
vmcs02 but L1 enables neither EPT nor VPID in vmcs12. For this reason
prepare_vmcs02() and load_vmcs12_host_state() have special code to
request a TLB flush in case L1 does not use EPT but it uses
"virtualize APIC accesses".
This special case however is not necessary. On a nested vmentry the
physical TLB will already be flushed except if all the following apply:
* L0 uses VPID
* L1 uses VPID
* L0 can guarantee TLB entries populated while running L1 are tagged
differently than TLB entries populated while running L2.
If the first condition is false, the processor will flush the TLB
on vmentry to L2. If the second or third condition are false,
prepare_vmcs02() will request KVM_REQ_TLB_FLUSH. However, even
if both are true, no extra TLB flush is needed to handle the APIC
access page:
* if L1 doesn't use VPID, the second condition doesn't hold and the
TLB will be flushed anyway.
* if L1 uses VPID, it has to flush the TLB itself with INVVPID and
section 28.3.3.3 doesn't apply to L0.
* even INVEPT is not needed because, if L0 uses EPT, it uses different
EPTP when running L2 than L1 (because guest_mode is part of mmu-role).
In this case SDM section 28.3.3.4 doesn't apply.
Similarly, examining nested_vmx_vmexit()->load_vmcs12_host_state(),
one could note that L0 won't flush TLB only in cases where SDM sections
28.3.3.3 and 28.3.3.4 don't apply. In particular, if L0 uses different
VPIDs for L1 and L2 (i.e. vmx->vpid != vmx->nested.vpid02), section
28.3.3.3 doesn't apply.
Thus, remove this flush from prepare_vmcs02() and nested_vmx_vmexit().
Side-note: This patch can be viewed as removing parts of commit
fb6c81984313 ("kvm: vmx: Flush TLB when the APIC-access address changes”)
that is not relevant anymore since commit
1313cc2bd8f6 ("kvm: mmu: Add guest_mode to kvm_mmu_page_role”).
i.e. The first commit assumes that if L0 use EPT and L1 doesn’t use EPT,
then L0 will use same EPTP for both L0 and L1. Which indeed required
L0 to execute INVEPT before entering L2 guest. This assumption is
not true anymore since when guest_mode was added to mmu-role.
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
vmcs->apic_access_page is simply a token that the hypervisor puts into
the PFN of a 4KB EPTE (or PTE if using shadow-paging) that triggers
APIC-access VMExit or APIC virtualization logic whenever a CPU running
in VMX non-root mode read/write from/to this PFN.
As every write either triggers an APIC-access VMExit or write is
performed on vmcs->virtual_apic_page, the PFN pointed to by
vmcs->apic_access_page should never actually be touched by CPU.
Therefore, there is no need to mark vmcs02->apic_access_page as dirty
after unpin it on L2->L1 emulated VMExit or when L1 exit VMX operation.
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Conflicts:
arch/x86/kvm/vmx/vmx.c
|
|
Since commit 1313cc2bd8f6 ("kvm: mmu: Add guest_mode to kvm_mmu_page_role"),
guest_mode was added to mmu-role and therefore if L0 use EPT, it will
always run L1 and L2 with different EPTP. i.e. EPTP01!=EPTP02.
Because TLB entries are tagged with EP4TA, KVM can assume
TLB entries populated while running L2 are tagged differently
than TLB entries populated while running L1.
Therefore, update nested_has_guest_tlb_tag() to consider if
L0 use EPT instead of if L1 use EPT.
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Reviewed-by: Mark Kanda <mark.kanda@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The L1 hypervisor may include the IA32_TIME_STAMP_COUNTER MSR in the
vmcs12 MSR VM-exit MSR-store area as a way of determining the highest
TSC value that might have been observed by L2 prior to VM-exit. The
current implementation does not capture a very tight bound on this
value. To tighten the bound, add the IA32_TIME_STAMP_COUNTER MSR to the
vmcs02 VM-exit MSR-store area whenever it appears in the vmcs12 VM-exit
MSR-store area. When L0 processes the vmcs12 VM-exit MSR-store area
during the emulation of an L2->L1 VM-exit, special-case the
IA32_TIME_STAMP_COUNTER MSR, using the value stored in the vmcs02
VM-exit MSR-store area to derive the value to be stored in the vmcs12
VM-exit MSR-store area.
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add the function read_and_check_msr_entry() which just pulls some code
out of nested_vmx_store_msr(). This will be useful as reusable code in
upcoming patches.
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The "load IA32_PERF_GLOBAL_CTRL" bit for VM-entry and VM-exit should
only be exposed to the guest if IA32_PERF_GLOBAL_CTRL is a valid MSR.
Create a new helper to allow pmu_refresh() to update the VM-Entry and
VM-Exit controls to ensure PMU values are initialized when performing
the is_valid_msr() check.
Suggested-by: Jim Mattson <jmattson@google.com>
Co-developed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add condition to prepare_vmcs02 which loads IA32_PERF_GLOBAL_CTRL on
VM-entry if the "load IA32_PERF_GLOBAL_CTRL" bit on the VM-entry control
is set. Use SET_MSR_OR_WARN() rather than directly writing to the field
to avoid overwrite by atomic_switch_perf_msrs().
Suggested-by: Jim Mattson <jmattson@google.com>
Co-developed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The existing implementation for loading the IA32_PERF_GLOBAL_CTRL MSR
on VM-exit was incorrect, as the next call to atomic_switch_perf_msrs()
could cause this value to be overwritten. Instead, call kvm_set_msr()
which will allow atomic_switch_perf_msrs() to correctly set the values.
Define a macro, SET_MSR_OR_WARN(), to set the MSR with kvm_set_msr()
and WARN on failure.
Suggested-by: Jim Mattson <jmattson@google.com>
Co-developed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add a consistency check on nested vm-entry for host's
IA32_PERF_GLOBAL_CTRL from vmcs12. Per Intel's SDM Vol 3 26.2.2:
If the "load IA32_PERF_GLOBAL_CTRL"
VM-exit control is 1, bits reserved in the IA32_PERF_GLOBAL_CTRL
MSR must be 0 in the field for that register"
Suggested-by: Jim Mattson <jmattson@google.com>
Co-developed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add condition to nested_vmx_check_guest_state() to check the validity of
GUEST_IA32_PERF_GLOBAL_CTRL. Per Intel's SDM Vol 3 26.3.1.1:
If the "load IA32_PERF_GLOBAL_CTRL" VM-entry control is 1, bits
reserved in the IA32_PERF_GLOBAL_CTRL MSR must be 0 in the field for that
register.
Suggested-by: Jim Mattson <jmattson@google.com>
Co-developed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When L1 don't use TPR-Shadow to run L2, L0 configures vmcs02 without
TPR-Shadow and install intercepts on CR8 access (load and store).
If L1 do not intercept L2 CR8 access, L0 intercepts on those accesses
will emulate load/store on L1's LAPIC TPR. If in this case L2 lowers
TPR such that there is now an injectable interrupt to L1,
apic_update_ppr() will request a KVM_REQ_EVENT which will trigger a call
to update_cr8_intercept() to update TPR-Threshold to highest pending IRR
priority.
However, this update to TPR-Threshold is done while active vmcs is
vmcs02 instead of vmcs01. Thus, when later at some point L0 will
emulate an exit from L2 to L1, L1 will still run with high
TPR-Threshold. This will result in every VMEntry to L1 to immediately
exit on TPR_BELOW_THRESHOLD and continue to do so infinitely until
some condition will cause KVM_REQ_EVENT to be set.
(Note that TPR_BELOW_THRESHOLD exit handler do not set KVM_REQ_EVENT
until apic_update_ppr() will notice a new injectable interrupt for PPR)
To fix this issue, change update_cr8_intercept() such that if L2 lowers
L1's TPR in a way that requires to lower L1's TPR-Threshold, save update
to TPR-Threshold and apply it to vmcs01 when L0 emulates an exit from
L2 to L1.
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Intel SDM section 25.2 OTHER CAUSES OF VM EXITS specifies the following
on INIT signals: "Such exits do not modify register state or clear pending
events as they would outside of VMX operation."
When commit 4b9852f4f389 ("KVM: x86: Fix INIT signal handling in various CPU states")
was applied, I interepted above Intel SDM statement such that
INIT_SIGNAL exit don’t consume the LAPIC INIT pending event.
However, when Nadav Amit run matching kvm-unit-test on a bare-metal
machine, it turned out my interpetation was wrong. i.e. INIT_SIGNAL
exit does consume the LAPIC INIT pending event.
(See: https://www.spinics.net/lists/kvm/msg196757.html)
Therefore, fix KVM code to behave as observed on bare-metal.
Fixes: 4b9852f4f389 ("KVM: x86: Fix INIT signal handling in various CPU states")
Reported-by: Nadav Amit <nadav.amit@gmail.com>
Reviewed-by: Mihai Carabas <mihai.carabas@oracle.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If the "virtualize APIC accesses" VM-execution control is set in the
VMCS, the APIC virtualization hardware is triggered when a page walk
in VMX non-root mode terminates at a PTE wherein the address of the 4k
page frame matches the APIC-access address specified in the VMCS. On
hardware, the APIC-access address may be any valid 4k-aligned physical
address.
KVM's nVMX implementation enforces the additional constraint that the
APIC-access address specified in the vmcs12 must be backed by
a "struct page" in L1. If not, L0 will simply clear the "virtualize
APIC accesses" VM-execution control in the vmcs02.
The problem with this approach is that the L1 guest has arranged the
vmcs12 EPT tables--or shadow page tables, if the "enable EPT"
VM-execution control is clear in the vmcs12--so that the L2 guest
physical address(es)--or L2 guest linear address(es)--that reference
the L2 APIC map to the APIC-access address specified in the
vmcs12. Without the "virtualize APIC accesses" VM-execution control in
the vmcs02, the APIC accesses in the L2 guest will directly access the
APIC-access page in L1.
When there is no mapping whatsoever for the APIC-access address in L1,
the L2 VM just loses the intended APIC virtualization. However, when
the APIC-access address is mapped to an MMIO region in L1, the L2
guest gets direct access to the L1 MMIO device. For example, if the
APIC-access address specified in the vmcs12 is 0xfee00000, then L2
gets direct access to L1's APIC.
Since this vmcs12 configuration is something that KVM cannot
faithfully emulate, the appropriate response is to exit to userspace
with KVM_INTERNAL_ERROR_EMULATION.
Fixes: fe3ef05c7572 ("KVM: nVMX: Prepare vmcs02 from vmcs01 and vmcs12")
Reported-by: Dan Cross <dcross@google.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Rename {vmx,nested_vmx}_vcpu_setup() to match what they really do.
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add helpers to prettify code that tests and/or marks whether or not a
register is available and/or dirty.
Suggested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Write the desired L2 CR3 into vmcs02.GUEST_CR3 during nested VM-Enter
instead of deferring the VMWRITE until vmx_set_cr3(). If the VMWRITE
is deferred, then KVM can consume a stale vmcs02.GUEST_CR3 when it
refreshes vmcs12->guest_cr3 during nested_vmx_vmexit() if the emulated
VM-Exit occurs without actually entering L2, e.g. if the nested run
is squashed because nested VM-Enter (from L1) is putting L2 into HLT.
Note, the above scenario can occur regardless of whether L1 is
intercepting HLT, e.g. L1 can intercept HLT and then re-enter L2 with
vmcs.GUEST_ACTIVITY_STATE=HALTED. But practically speaking, a VMM will
likely put a guest into HALTED if and only if it's not intercepting HLT.
In an ideal world where EPT *requires* unrestricted guest (and vice
versa), VMX could handle CR3 similar to how it handles RSP and RIP,
e.g. mark CR3 dirty and conditionally load it at vmx_vcpu_run(). But
the unrestricted guest silliness complicates the dirty tracking logic
to the point that explicitly handling vmcs02.GUEST_CR3 during nested
VM-Enter is a simpler overall implementation.
Cc: stable@vger.kernel.org
Reported-and-tested-by: Reto Buerki <reet@codelabs.ch>
Tested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Current versions of Intel's SDM incorrectly state that "bits 31:15 of
the VM-Entry exception error-code field" must be zero. In reality, bits
31:16 must be zero, i.e. error codes are 16-bit values.
The bogus error code check manifests as an unexpected VM-Entry failure
due to an invalid code field (error number 7) in L1, e.g. when injecting
a #GP with error_code=0x9f00.
Nadav previously reported the bug[*], both to KVM and Intel, and fixed
the associated kvm-unit-test.
[*] https://patchwork.kernel.org/patch/11124749/
Reported-by: Nadav Amit <namit@vmware.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
KVM was incorrectly checking vmcs12->host_ia32_efer even if the "load
IA32_EFER" exit control was reset. Also, some checks were not using
the new CC macro for tracing.
Cleanup everything so that the vCPU's 64-bit mode is determined
directly from EFER_LMA and the VMCS checks are based on that, which
matches section 26.2.4 of the SDM.
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Fixes: 5845038c111db27902bc220a4f70070fe945871c
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Allowing an unlimited number of MSRs to be specified via the VMX
load/store MSR lists (e.g., vm-entry MSR load list) is bad for two
reasons. First, a guest can specify an unreasonable number of MSRs,
forcing KVM to process all of them in software. Second, the SDM bounds
the number of MSRs allowed to be packed into the atomic switch MSR lists.
Quoting the "Miscellaneous Data" section in the "VMX Capability
Reporting Facility" appendix:
"Bits 27:25 is used to compute the recommended maximum number of MSRs
that should appear in the VM-exit MSR-store list, the VM-exit MSR-load
list, or the VM-entry MSR-load list. Specifically, if the value bits
27:25 of IA32_VMX_MISC is N, then 512 * (N + 1) is the recommended
maximum number of MSRs to be included in each list. If the limit is
exceeded, undefined processor behavior may result (including a machine
check during the VMX transition)."
Because KVM needs to protect itself and can't model "undefined processor
behavior", arbitrarily force a VM-entry to fail due to MSR loading when
the MSR load list is too large. Similarly, trigger an abort during a VM
exit that encounters an MSR load list or MSR store list that is too large.
The MSR list size is intentionally not pre-checked so as to maintain
compatibility with hardware inasmuch as possible.
Test these new checks with the kvm-unit-test "x86: nvmx: test max atomic
switch MSRs".
Suggested-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Marc Orr <marcorr@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
As the latest Intel 64 and IA-32 Architectures Software Developer's
Manual, UMWAIT and TPAUSE instructions cause a VM exit if the
RDTSC exiting and enable user wait and pause VM-execution
controls are both 1.
Because KVM never enable RDTSC exiting, the vm-exit for UMWAIT and TPAUSE
should never happen. Considering EXIT_REASON_XSAVES and
EXIT_REASON_XRSTORS is also unexpected VM-exit for KVM. Introduce a common
exit helper handle_unexpected_vmexit() to handle these unexpected VM-exit.
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Co-developed-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
UMONITOR, UMWAIT and TPAUSE are a set of user wait instructions.
This patch adds support for user wait instructions in KVM. Availability
of the user wait instructions is indicated by the presence of the CPUID
feature flag WAITPKG CPUID.0x07.0x0:ECX[5]. User wait instructions may
be executed at any privilege level, and use 32bit IA32_UMWAIT_CONTROL MSR
to set the maximum time.
The behavior of user wait instructions in VMX non-root operation is
determined first by the setting of the "enable user wait and pause"
secondary processor-based VM-execution control bit 26.
If the VM-execution control is 0, UMONITOR/UMWAIT/TPAUSE cause
an invalid-opcode exception (#UD).
If the VM-execution control is 1, treatment is based on the
setting of the “RDTSC exiting†VM-execution control. Because KVM never
enables RDTSC exiting, if the instruction causes a delay, the amount of
time delayed is called here the physical delay. The physical delay is
first computed by determining the virtual delay. If
IA32_UMWAIT_CONTROL[31:2] is zero, the virtual delay is the value in
EDX:EAX minus the value that RDTSC would return; if
IA32_UMWAIT_CONTROL[31:2] is not zero, the virtual delay is the minimum
of that difference and AND(IA32_UMWAIT_CONTROL,FFFFFFFCH).
Because umwait and tpause can put a (psysical) CPU into a power saving
state, by default we dont't expose it to kvm and enable it only when
guest CPUID has it.
Detailed information about user wait instructions can be found in the
latest Intel 64 and IA-32 Architectures Software Developer's Manual.
Co-developed-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Jingqi Liu <jingqi.liu@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
According to section "Checks Related to Address-Space Size" in Intel SDM
vol 3C, the following checks are performed on vmentry of nested guests:
If the logical processor is outside IA-32e mode (if IA32_EFER.LMA = 0)
at the time of VM entry, the following must hold:
- The "IA-32e mode guest" VM-entry control is 0.
- The "host address-space size" VM-exit control is 0.
If the logical processor is in IA-32e mode (if IA32_EFER.LMA = 1) at the
time of VM entry, the "host address-space size" VM-exit control must be 1.
If the "host address-space size" VM-exit control is 0, the following must
hold:
- The "IA-32e mode guest" VM-entry control is 0.
- Bit 17 of the CR4 field (corresponding to CR4.PCIDE) is 0.
- Bits 63:32 in the RIP field are 0.
If the "host address-space size" VM-exit control is 1, the following must
hold:
- Bit 5 of the CR4 field (corresponding to CR4.PAE) is 1.
- The RIP field contains a canonical address.
On processors that do not support Intel 64 architecture, checks are
performed to ensure that the "IA-32e mode guest" VM-entry control and the
"host address-space size" VM-exit control are both 0.
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Pull KVM updates from Paolo Bonzini:
"s390:
- ioctl hardening
- selftests
ARM:
- ITS translation cache
- support for 512 vCPUs
- various cleanups and bugfixes
PPC:
- various minor fixes and preparation
x86:
- bugfixes all over the place (posted interrupts, SVM, emulation
corner cases, blocked INIT)
- some IPI optimizations"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (75 commits)
KVM: X86: Use IPI shorthands in kvm guest when support
KVM: x86: Fix INIT signal handling in various CPU states
KVM: VMX: Introduce exit reason for receiving INIT signal on guest-mode
KVM: VMX: Stop the preemption timer during vCPU reset
KVM: LAPIC: Micro optimize IPI latency
kvm: Nested KVM MMUs need PAE root too
KVM: x86: set ctxt->have_exception in x86_decode_insn()
KVM: x86: always stop emulation on page fault
KVM: nVMX: trace nested VM-Enter failures detected by H/W
KVM: nVMX: add tracepoint for failed nested VM-Enter
x86: KVM: svm: Fix a check in nested_svm_vmrun()
KVM: x86: Return to userspace with internal error on unexpected exit reason
KVM: x86: Add kvm_emulate_{rd,wr}msr() to consolidate VXM/SVM code
KVM: x86: Refactor up kvm_{g,s}et_msr() to simplify callers
doc: kvm: Fix return description of KVM_SET_MSRS
KVM: X86: Tune PLE Window tracepoint
KVM: VMX: Change ple_window type to unsigned int
KVM: X86: Remove tailing newline for tracepoints
KVM: X86: Trace vcpu_id for vmexit
KVM: x86: Manually calculate reserved bits when loading PDPTRS
...
|
|
The implementation of vmread to memory is still incomplete, as it
lacks the ability to do vmread to I/O memory just like vmptrst.
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Commit cd7764fe9f73 ("KVM: x86: latch INITs while in system management mode")
changed code to latch INIT while vCPU is in SMM and process latched INIT
when leaving SMM. It left a subtle remark in commit message that similar
treatment should also be done while vCPU is in VMX non-root-mode.
However, INIT signals should actually be latched in various vCPU states:
(*) For both Intel and AMD, INIT signals should be latched while vCPU
is in SMM.
(*) For Intel, INIT should also be latched while vCPU is in VMX
operation and later processed when vCPU leaves VMX operation by
executing VMXOFF.
(*) For AMD, INIT should also be latched while vCPU runs with GIF=0
or in guest-mode with intercept defined on INIT signal.
To fix this:
1) Add kvm_x86_ops->apic_init_signal_blocked() such that each CPU vendor
can define the various CPU states in which INIT signals should be
blocked and modify kvm_apic_accept_events() to use it.
2) Modify vmx_check_nested_events() to check for pending INIT signal
while vCPU in guest-mode. If so, emualte vmexit on
EXIT_REASON_INIT_SIGNAL. Note that nSVM should have similar behaviour
but is currently left as a TODO comment to implement in the future
because nSVM don't yet implement svm_check_nested_events().
Note: Currently KVM nVMX implementation don't support VMX wait-for-SIPI
activity state as specified in MSR_IA32_VMX_MISC bits 6:8 exposed to
guest (See nested_vmx_setup_ctls_msrs()).
If and when support for this activity state will be implemented,
kvm_check_nested_events() would need to avoid emulating vmexit on
INIT signal in case activity-state is wait-for-SIPI. In addition,
kvm_apic_accept_events() would need to be modified to avoid discarding
SIPI in case VMX activity-state is wait-for-SIPI but instead delay
SIPI processing to vmx_check_nested_events() that would clear
pending APIC events and emulate vmexit on SIPI.
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Co-developed-by: Nikita Leshenko <nikita.leshchenko@oracle.com>
Signed-off-by: Nikita Leshenko <nikita.leshchenko@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Use the recently added tracepoint for logging nested VM-Enter failures
instead of spamming the kernel log when hardware detects a consistency
check failure. Take the opportunity to print the name of the error code
instead of dumping the raw hex number, but limit the symbol table to
error codes that can reasonably be encountered by KVM.
Add an equivalent tracepoint in nested_vmx_check_vmentry_hw(), e.g. so
that tracing of "invalid control field" errors isn't suppressed when
nested early checks are enabled.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Debugging a failed VM-Enter is often like searching for a needle in a
haystack, e.g. there are over 80 consistency checks that funnel into
the "invalid control field" error code. One way to expedite debug is
to run the buggy code as an L1 guest under KVM (and pray that the
failing check is detected by KVM). However, extracting useful debug
information out of L0 KVM requires attaching a debugger to KVM and/or
modifying the source, e.g. to log which check is failing.
Make life a little less painful for VMM developers and add a tracepoint
for failed VM-Enter consistency checks. Ideally the tracepoint would
capture both what check failed and precisely why it failed, but logging
why a checked failed is difficult to do in a generic tracepoint without
resorting to invasive techniques, e.g. generating a custom string on
failure. That being said, for the vast majority of VM-Enter failures
the most difficult step is figuring out exactly what to look at, e.g.
figuring out which bit was incorrectly set in a control field is usually
not too painful once the guilty field as been identified.
To reach a happy medium between precision and ease of use, simply log
the code that detected a failed check, using a macro to execute the
check and log the trace event on failure. This approach enables tracing
arbitrary code, e.g. it's not limited to function calls or specific
formats of checks, and the changes to the existing code are minimally
invasive. A macro with a two-character name is desirable as usage of
the macro doesn't result in overly long lines or confusing alignment,
while still retaining some amount of readability. I.e. a one-character
name is a little too terse, and a three-character name results in the
contents being passed to the macro aligning with an indented line when
the macro is used an in if-statement, e.g.:
if (VCC(nested_vmx_check_long_line_one(...) &&
nested_vmx_check_long_line_two(...)))
return -EINVAL;
And that is the story of how the CC(), a.k.a. Consistency Check, macro
got its name.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Refactor the top-level MSR accessors to take/return the index and value
directly instead of requiring the caller to dump them into a msr_data
struct.
No functional change intended.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Shall help finding use-after-free bugs earlier.
Suggested-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Letting this pend may cause nested_get_vmcs12_pages to run against an
invalid state, corrupting the effective vmcs of L1.
This was triggerable in QEMU after a guest corruption in L2, followed by
a L1 reset.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Cc: stable@vger.kernel.org
Fixes: 7f7f1ba33cf2 ("KVM: x86: do not load vmcs12 pages while still in SMM")
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If a KVM guest is reset while running a nested guest, free_nested will
disable the shadow VMCS execution control in the vmcs01. However,
on the next KVM_RUN vmx_vcpu_run would nevertheless try to sync
the VMCS12 to the shadow VMCS which has since been freed.
This causes a vmptrld of a NULL pointer on my machime, but Jan reports
the host to hang altogether. Let's see how much this trivial patch fixes.
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Liran Alon <liran.alon@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
As reported by Maxime at
https://bugzilla.kernel.org/show_bug.cgi?id=204175:
In vmx/nested.c::get_vmx_mem_address(), when the guest runs in long mode,
the base address of the memory operand is computed with a simple:
*ret = s.base + off;
This is incorrect, the base applies only to FS and GS, not to the others.
Because of that, if the guest uses a VMX instruction based on DS and has
a DS.base that is non-zero, KVM wrongfully adds the base to the
resulting address.
Reported-by: Maxime Villard <max@m00nbsd.net>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Pull KVM updates from Paolo Bonzini:
"ARM:
- support for chained PMU counters in guests
- improved SError handling
- handle Neoverse N1 erratum #1349291
- allow side-channel mitigation status to be migrated
- standardise most AArch64 system register accesses to msr_s/mrs_s
- fix host MPIDR corruption on 32bit
- selftests ckleanups
x86:
- PMU event {white,black}listing
- ability for the guest to disable host-side interrupt polling
- fixes for enlightened VMCS (Hyper-V pv nested virtualization),
- new hypercall to yield to IPI target
- support for passing cstate MSRs through to the guest
- lots of cleanups and optimizations
Generic:
- Some txt->rST conversions for the documentation"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (128 commits)
Documentation: virtual: Add toctree hooks
Documentation: kvm: Convert cpuid.txt to .rst
Documentation: virtual: Convert paravirt_ops.txt to .rst
KVM: x86: Unconditionally enable irqs in guest context
KVM: x86: PMU Event Filter
kvm: x86: Fix -Wmissing-prototypes warnings
KVM: Properly check if "page" is valid in kvm_vcpu_unmap
KVM: arm/arm64: Initialise host's MPIDRs by reading the actual register
KVM: LAPIC: Retry tune per-vCPU timer_advance_ns if adaptive tuning goes insane
kvm: LAPIC: write down valid APIC registers
KVM: arm64: Migrate _elx sysreg accessors to msr_s/mrs_s
KVM: doc: Add API documentation on the KVM_REG_ARM_WORKAROUNDS register
KVM: arm/arm64: Add save/restore support for firmware workaround state
arm64: KVM: Propagate full Spectre v2 workaround state to KVM guests
KVM: arm/arm64: Support chained PMU counters
KVM: arm/arm64: Remove pmc->bitmask
KVM: arm/arm64: Re-create event when setting counter value
KVM: arm/arm64: Extract duplicated code to own function
KVM: arm/arm64: Rename kvm_pmu_{enable/disable}_counter functions
KVM: LAPIC: ARBPRI is a reserved register for x2APIC
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm updates for 5.3
- Add support for chained PMU counters in guests
- Improve SError handling
- Handle Neoverse N1 erratum #1349291
- Allow side-channel mitigation status to be migrated
- Standardise most AArch64 system register accesses to msr_s/mrs_s
- Fix host MPIDR corruption on 32bit
|
|
nested guests
According to section "Checks on Host Segment and Descriptor-Table
Registers" in Intel SDM vol 3C, the following checks are performed on
vmentry of nested guests:
- In the selector field for each of CS, SS, DS, ES, FS, GS and TR, the
RPL (bits 1:0) and the TI flag (bit 2) must be 0.
- The selector fields for CS and TR cannot be 0000H.
- The selector field for SS cannot be 0000H if the "host address-space
size" VM-exit control is 0.
- On processors that support Intel 64 architecture, the base-address
fields for FS, GS and TR must contain canonical addresses.
Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
KVM does not have 100% coverage of VMX consistency checks, i.e. some
checks that cause VM-Fail may only be detected by hardware during a
nested VM-Entry. In such a case, KVM must restore L1's state to the
pre-VM-Enter state as L2's state has already been loaded into KVM's
software model.
L1's CR3 and PDPTRs in particular are loaded from vmcs01.GUEST_*. But
when EPT is disabled, the associated fields hold KVM's shadow values,
not L1's "real" values. Fortunately, when EPT is disabled the PDPTRs
come from memory, i.e. are not cached in the VMCS. Which leaves CR3
as the sole anomaly.
A previously applied workaround to handle CR3 was to force nested early
checks if EPT is disabled:
commit 2b27924bb1d48 ("KVM: nVMX: always use early vmcs check when EPT
is disabled")
Forcing nested early checks is undesirable as doing so adds hundreds of
cycles to every nested VM-Entry. Rather than take this performance hit,
handle CR3 by overwriting vmcs01.GUEST_CR3 with L1's CR3 during nested
VM-Entry when EPT is disabled *and* nested early checks are disabled.
By stuffing vmcs01.GUEST_CR3, nested_vmx_restore_host_state() will
naturally restore the correct vcpu->arch.cr3 from vmcs01.GUEST_CR3.
These shenanigans work because nested_vmx_restore_host_state() does a
full kvm_mmu_reset_context(), i.e. unloads the current MMU, which
guarantees vmcs01.GUEST_CR3 will be rewritten with a new shadow CR3
prior to re-entering L1.
vcpu->arch.root_mmu.root_hpa is set to INVALID_PAGE via:
nested_vmx_restore_host_state() ->
kvm_mmu_reset_context() ->
kvm_mmu_unload() ->
kvm_mmu_free_roots()
kvm_mmu_unload() has WARN_ON(root_hpa != INVALID_PAGE), i.e. we can bank
on 'root_hpa == INVALID_PAGE' unless the implementation of
kvm_mmu_reset_context() is changed.
On the way into L1, VMCS.GUEST_CR3 is guaranteed to be written (on a
successful entry) via:
vcpu_enter_guest() ->
kvm_mmu_reload() ->
kvm_mmu_load() ->
kvm_mmu_load_cr3() ->
vmx_set_cr3()
Stuff vmcs01.GUEST_CR3 if and only if nested early checks are disabled
as a "late" VM-Fail should never happen win that case (KVM WARNs), and
the conditional write avoids the need to restore the correct GUEST_CR3
when nested_vmx_check_vmentry_hw() fails.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20190607185534.24368-1-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Currently KVM_STATE_NESTED_EVMCS is used to signal that eVMCS
capability is enabled on vCPU.
As indicated by vmx->nested.enlightened_vmcs_enabled.
This is quite bizarre as userspace VMM should make sure to expose
same vCPU with same CPUID values in both source and destination.
In case vCPU is exposed with eVMCS support on CPUID, it is also
expected to enable KVM_CAP_HYPERV_ENLIGHTENED_VMCS capability.
Therefore, KVM_STATE_NESTED_EVMCS is redundant.
KVM_STATE_NESTED_EVMCS is currently used on restore path
(vmx_set_nested_state()) only to enable eVMCS capability in KVM
and to signal need_vmcs12_sync such that on next VMEntry to guest
nested_sync_from_vmcs12() will be called to sync vmcs12 content
into eVMCS in guest memory.
However, because restore nested-state is rare enough, we could
have just modified vmx_set_nested_state() to always signal
need_vmcs12_sync.
From all the above, it seems that we could have just removed
the usage of KVM_STATE_NESTED_EVMCS. However, in order to preserve
backwards migration compatibility, we cannot do that.
(vmx_get_nested_state() needs to signal flag when migrating from
new kernel to old kernel).
Returning KVM_STATE_NESTED_EVMCS when just vCPU have eVMCS enabled
have a bad side-effect of userspace VMM having to send nested-state
from source to destination as part of migration stream. Even if
guest have never used eVMCS as it doesn't even run a nested
hypervisor workload. This requires destination userspace VMM and
KVM to support setting nested-state. Which make it more difficult
to migrate from new host to older host.
To avoid this, change KVM_STATE_NESTED_EVMCS to signal eVMCS is
not only enabled but also active. i.e. Guest have made some
eVMCS active via an enlightened VMEntry. i.e. vmcs12 is copied
from eVMCS and therefore should be restored into eVMCS resident
in memory (by copy_vmcs12_to_enlightened()).
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Maran Wilson <maran.wilson@oracle.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
As comment in code specifies, SMM temporarily disables VMX so we cannot
be in guest mode, nor can VMLAUNCH/VMRESUME be pending.
However, code currently assumes that these are the only flags that can be
set on kvm_state->flags. This is not true as KVM_STATE_NESTED_EVMCS
can also be set on this field to signal that eVMCS should be enabled.
Therefore, fix code to check for guest-mode and pending VMLAUNCH/VMRESUME
explicitly.
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When L0 is executing handle_invept(), the TDP MMU is active. Emulating
an L1 INVEPT does require synchronizing the appropriate shadow EPT
root(s), but a call to kvm_mmu_sync_roots in this context won't do
that. Similarly, the hardware TLB and paging-structure-cache entries
associated with the appropriate shadow EPT root(s) must be flushed,
but requesting a TLB_FLUSH from this context won't do that either.
How did this ever work? KVM always does a sync_roots and TLB flush (in
the correct context) when transitioning from L1 to L2. That isn't the
best choice for nested VM performance, but it effectively papers over
the mistakes here.
Remove the unnecessary operations and leave a comment to try to do
better in the future.
Reported-by: Junaid Shahid <junaids@google.com>
Fixes: bfd0a56b90005f ("nEPT: Nested INVEPT")
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Nadav Har'El <nyh@il.ibm.com>
Cc: Jun Nakajima <jun.nakajima@intel.com>
Cc: Xinhao Xu <xinhao.xu@intel.com>
Cc: Yang Zhang <yang.z.zhang@Intel.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by Peter Shier <pshier@google.com>
Reviewed-by: Junaid Shahid <junaids@google.com>
Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When Enlightened VMCS is in use, it is valid to do VMCLEAR and,
according to TLFS, this should "transition an enlightened VMCS from the
active to the non-active state". It is, however, wrong to assume that
it is only valid to do VMCLEAR for the eVMCS which is currently active
on the vCPU performing VMCLEAR.
Currently, the logic in handle_vmclear() is broken: in case, there is no
active eVMCS on the vCPU doing VMCLEAR we treat the argument as a 'normal'
VMCS and kvm_vcpu_write_guest() to the 'launch_state' field irreversibly
corrupts the memory area.
So, in case the VMCLEAR argument is not the current active eVMCS on the
vCPU, how can we know if the area it is pointing to is a normal or an
enlightened VMCS?
Thanks to the bug in Hyper-V (see commit 72aeb60c52bf7 ("KVM: nVMX: Verify
eVMCS revision id match supported eVMCS version on eVMCS VMPTRLD")) we can
not, the revision can't be used to distinguish between them. So let's
assume it is always enlightened in case enlightened vmentry is enabled in
the assist page. Also, check if vmx->nested.enlightened_vmcs_enabled to
minimize the impact for 'unenlightened' workloads.
Fixes: b8bbab928fb1 ("KVM: nVMX: implement enlightened VMPTRLD and VMCLEAR")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Apparently, Windows doesn't maintain clean fields data after it does
VMCLEAR for an enlightened VMCS so we can only use it on VMRESUME.
The issue went unnoticed because currently we do nested_release_evmcs()
in handle_vmclear() and the consecutive enlightened VMPTRLD invalidates
clean fields when a new eVMCS is mapped but we're going to change the
logic.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Allow userspace to set a custom value for the VMFUNC controls MSR, as long
as the capabilities it advertises do not exceed those of the host.
Fixes: 27c42a1bb ("KVM: nVMX: Enable VMFUNC for the L1 hypervisor", 2017-08-03)
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Some secondary controls are automatically enabled/disabled based on the CPUID
values that are set for the guest. However, they are still available at a
global level and therefore should be present when KVM_GET_MSRS is sent to
/dev/kvm.
Fixes: 1389309c811 ("KVM: nVMX: expose VMX capabilities for nested hypervisors to userspace", 2018-02-26)
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Commit 332d079735f5 ("KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS
state before setting new state", 2019-05-02) broke evmcs_test because the
eVMCS setup must be performed even if there is no VMXON region defined,
as long as the eVMCS bit is set in the assist page.
While the simplest possible fix would be to add a check on
kvm_state->flags & KVM_STATE_NESTED_EVMCS in the initial "if" that
covers kvm_state->hdr.vmx.vmxon_pa == -1ull, that is quite ugly.
Instead, this patch moves checks earlier in the function and
conditionalizes them on kvm_state->hdr.vmx.vmxon_pa, so that
vmx_set_nested_state always goes through vmx_leave_nested
and nested_enable_evmcs.
Fixes: 332d079735f5 ("KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state")
Cc: Aaron Lewis <aaronlewis@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Improve the KVM_{GET,SET}_NESTED_STATE structs by detailing the format
of VMX nested state data in a struct.
In order to avoid changing the ioctl values of
KVM_{GET,SET}_NESTED_STATE, there is a need to preserve
sizeof(struct kvm_nested_state). This is done by defining the data
struct as "data.vmx[0]". It was the most elegant way I found to
preserve struct size while still keeping struct readable and easy to
maintain. It does have a misfortunate side-effect that now it has to be
accessed as "data.vmx[0]" rather than just "data.vmx".
Because we are already modifying these structs, I also modified the
following:
* Define the "format" field values as macros.
* Rename vmcs_pa to vmcs12_pa for better readability.
Signed-off-by: Liran Alon <liran.alon@oracle.com>
[Remove SVM stubs, add KVM_STATE_NESTED_VMX_VMCS12_SIZE. - Paolo]
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
VMWRITEs to the major VMCS controls, pin controls included, are
deceptively expensive. CPUs with VMCS caching (Westmere and later) also
optimize away consistency checks on VM-Entry, i.e. skip consistency
checks if the relevant fields have not changed since the last successful
VM-Entry (of the cached VMCS). Because uops are a precious commodity,
uCode's dirty VMCS field tracking isn't as precise as software would
prefer. Notably, writing any of the major VMCS fields effectively marks
the entire VMCS dirty, i.e. causes the next VM-Entry to perform all
consistency checks, which consumes several hundred cycles.
As it pertains to KVM, toggling PIN_BASED_VMX_PREEMPTION_TIMER more than
doubles the latency of the next VM-Entry (and again when/if the flag is
toggled back). In a non-nested scenario, running a "standard" guest
with the preemption timer enabled, toggling the timer flag is uncommon
but not rare, e.g. roughly 1 in 10 entries. Disabling the preemption
timer can change these numbers due to its use for "immediate exits",
even when explicitly disabled by userspace.
Nested virtualization in particular is painful, as the timer flag is set
for the majority of VM-Enters, but prepare_vmcs02() initializes vmcs02's
pin controls to *clear* the flag since its the timer's final state isn't
known until vmx_vcpu_run(). I.e. the majority of nested VM-Enters end
up unnecessarily writing pin controls *twice*.
Rather than toggle the timer flag in pin controls, set the timer value
itself to the largest allowed value to put it into a "soft disabled"
state, and ignore any spurious preemption timer exits.
Sadly, the timer is a 32-bit value and so theoretically it can fire
before the head death of the universe, i.e. spurious exits are possible.
But because KVM does *not* save the timer value on VM-Exit and because
the timer runs at a slower rate than the TSC, the maximuma timer value
is still sufficiently large for KVM's purposes. E.g. on a modern CPU
with a timer that runs at 1/32 the frequency of a 2.4ghz constant-rate
TSC, the timer will fire after ~55 seconds of *uninterrupted* guest
execution. In other words, spurious VM-Exits are effectively only
possible if the host is completely tickless on the logical CPU, the
guest is not using the preemption timer, and the guest is not generating
VM-Exits for any other reason.
To be safe from bad/weird hardware, disable the preemption timer if its
maximum delay is less than ten seconds. Ten seconds is mostly arbitrary
and was selected in no small part because it's a nice round number.
For simplicity and paranoia, fall back to __kvm_request_immediate_exit()
if the preemption timer is disabled by KVM or userspace. Previously
KVM continued to use the preemption timer to force immediate exits even
when the timer was disabled by userspace. Now that KVM leaves the timer
running instead of truly disabling it, allow userspace to kill it
entirely in the unlikely event the timer (or KVM) malfunctions.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
... now that it is fully redundant with the pin controls shadow.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
KVM dynamically toggles SECONDARY_EXEC_DESC to intercept (a subset of)
instructions that are subject to User-Mode Instruction Prevention, i.e.
VMCS.SECONDARY_EXEC_DESC == CR4.UMIP when emulating UMIP. Preset the
VMCS control when preparing vmcs02 to avoid unnecessarily VMWRITEs,
e.g. KVM will clear VMCS.SECONDARY_EXEC_DESC in prepare_vmcs02_early()
and then set it in vmx_set_cr4().
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
