Age | Commit message (Collapse) | Author |
|
commit 2ebac8bb3c2d35f5135466490fc8eeaf3f3e2d37 upstream.
Consult only the basic exit reason, i.e. bits 15:0 of vmcs.EXIT_REASON,
when determining whether a nested VM-Exit should be reflected into L1 or
handled by KVM in L0.
For better or worse, the switch statement in nested_vmx_exit_reflected()
currently defaults to "true", i.e. reflects any nested VM-Exit without
dedicated logic. Because the case statements only contain the basic
exit reason, any VM-Exit with modifier bits set will be reflected to L1,
even if KVM intended to handle it in L0.
Practically speaking, this only affects EXIT_REASON_MCE_DURING_VMENTRY,
i.e. a #MC that occurs on nested VM-Enter would be incorrectly routed to
L1, as "failed VM-Entry" is the only modifier that KVM can currently
encounter. The SMM modifiers will never be generated as KVM doesn't
support/employ a SMI Transfer Monitor. Ditto for "exit from enclave",
as KVM doesn't yet support virtualizing SGX, i.e. it's impossible to
enter an enclave in a KVM guest (L1 or L2).
Fixes: 644d711aa0e1 ("KVM: nVMX: Deciding if L0 or L1 should handle an L2 exit")
Cc: Jim Mattson <jmattson@google.com>
Cc: Xiaoyao Li <xiaoyao.li@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200227174430.26371-1-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 5c911beff20aa8639e7a1f28988736c13e03ed54 upstream.
Skip the Indirect Branch Prediction Barrier that is triggered on a VMCS
switch when running with spectre_v2_user=on/auto if the switch is
between two VMCSes in the same guest, i.e. between vmcs01 and vmcs02.
The IBPB is intended to prevent one guest from attacking another, which
is unnecessary in the nested case as it's the same guest from KVM's
perspective.
This all but eliminates the overhead observed for nested VMX transitions
when running with CONFIG_RETPOLINE=y and spectre_v2_user=on/auto, which
can be significant, e.g. roughly 3x on current systems.
Reported-by: Alexander Graf <graf@amazon.com>
Cc: KarimAllah Raslan <karahmed@amazon.de>
Cc: stable@vger.kernel.org
Fixes: 15d45071523d ("KVM/x86: Add IBPB support")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200501163117.4655-1-sean.j.christopherson@intel.com>
[Invert direction of bool argument. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 37486135d3a7b03acc7755b63627a130437f066a upstream.
Though rdpkru and wrpkru are contingent upon CR4.PKE, the PKRU
resource isn't. It can be read with XSAVE and written with XRSTOR.
So, if we don't set the guest PKRU value here(kvm_load_guest_xsave_state),
the guest can read the host value.
In case of kvm_load_host_xsave_state, guest with CR4.PKE clear could
potentially use XRSTOR to change the host PKRU value.
While at it, move pkru state save/restore to common code and the
host_pkru field to kvm_vcpu_arch. This will let SVM support protection keys.
Cc: stable@vger.kernel.org
Reported-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Message-Id: <158932794619.44260.14508381096663848853.stgit@naples-babu.amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit b045ae906b42afb361dc7ecf1a3cea110fb0a65f ]
According to SDM 26.6.2, it is possible to inject an MTF VM-exit via the
VM-entry interruption-information field regardless of the 'monitor trap
flag' VM-execution control. KVM appropriately copies the VM-entry
interruption-information field from vmcs12 to vmcs02. However, if L1
has not set the 'monitor trap flag' VM-execution control, KVM fails to
reflect the subsequent MTF VM-exit into L1.
Fix this by consulting the VM-entry interruption-information field of
vmcs12 to determine if L1 has injected the MTF VM-exit. If so, reflect
the exit, regardless of the 'monitor trap flag' VM-execution control.
Fixes: 5f3d45e7f282 ("kvm/x86: add support for MONITOR_TRAP_FLAG")
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20200414224746.240324-1-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 212617dbb6bac2a21dec6ef7d6012d96bb6dbb5d ]
commit 5ef8acbdd687 ("KVM: nVMX: Emulate MTF when performing
instruction emulation") introduced a helper to check the MTF
VM-execution control in vmcs12. Change pre-existing check in
nested_vmx_exit_reflected() to instead use the helper.
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
commit c7cb2d650c9e78c03bd2d1c0db89891825f8c0f4 upstream.
Clear CF and ZF in the VM-Exit path after doing __FILL_RETURN_BUFFER so
that KVM doesn't interpret clobbered RFLAGS as a VM-Fail. Filling the
RSB has always clobbered RFLAGS, its current incarnation just happens
clear CF and ZF in the processs. Relying on the macro to clear CF and
ZF is extremely fragile, e.g. commit 089dd8e53126e ("x86/speculation:
Change FILL_RETURN_BUFFER to work with objtool") tweaks the loop such
that the ZF flag is always set.
Reported-by: Qian Cai <cai@lca.pw>
Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: stable@vger.kernel.org
Fixes: f2fde6a5bcfcf ("KVM: VMX: Move RSB stuffing to before the first RET after VM-Exit")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200506035355.2242-1-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 514ccc194971d0649e4e7ec8a9b3a6e33561d7bf upstream.
The commit 842f4be95899 ("KVM: VMX: Add a trampoline to fix VMREAD error
handling") removed the declaration of vmread_error() causes a W=1 build
failure with KVM_WERROR=y. Fix it by adding it back.
arch/x86/kvm/vmx/vmx.c:359:17: error: no previous prototype for 'vmread_error' [-Werror=missing-prototypes]
asmlinkage void vmread_error(unsigned long field, bool fault)
^~~~~~~~~~~~
Signed-off-by: Qian Cai <cai@lca.pw>
Message-Id: <20200402153955.1695-1-cai@lca.pw>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit fb56baae5ea509e63c2a068d66a4d8ea91969fca upstream.
There is no reason to limit the use of do_machine_check
to 64bit targets. MCE handling works for both target familes.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: stable@vger.kernel.org
Fixes: a0861c02a981 ("KVM: Add VT-x machine check support")
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Message-Id: <20200414071414.45636-1-ubizjak@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit dbef2808af6c594922fe32833b30f55f35e9da6d upstream.
If KVM wasn't used at all before we crash the cleanup procedure fails with
BUG: unable to handle page fault for address: ffffffffffffffc8
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 23215067 P4D 23215067 PUD 23217067 PMD 0
Oops: 0000 [#8] SMP PTI
CPU: 0 PID: 3542 Comm: bash Kdump: loaded Tainted: G D 5.6.0-rc2+ #823
RIP: 0010:crash_vmclear_local_loaded_vmcss.cold+0x19/0x51 [kvm_intel]
The root cause is that loaded_vmcss_on_cpu list is not yet initialized,
we initialize it in hardware_enable() but this only happens when we start
a VM.
Previously, we used to have a bitmap with enabled CPUs and that was
preventing [masking] the issue.
Initialized loaded_vmcss_on_cpu list earlier, right before we assign
crash_vmclear_loaded_vmcss pointer. blocked_vcpu_on_cpu list and
blocked_vcpu_on_cpu_lock are moved altogether for consistency.
Fixes: 31603d4fc2bb ("KVM: VMX: Always VMCLEAR in-use VMCSes during crash with kexec support")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200401081348.1345307-1-vkuznets@redhat.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 842f4be95899df22b5843ba1a7c8cf37e831a6e8 upstream.
Add a hand coded assembly trampoline to preserve volatile registers
across vmread_error(), and to handle the calling convention differences
between 64-bit and 32-bit due to asmlinkage on vmread_error(). Pass
@field and @fault on the stack when invoking the trampoline to avoid
clobbering volatile registers in the context of the inline assembly.
Calling vmread_error() directly from inline assembly is partially broken
on 64-bit, and completely broken on 32-bit. On 64-bit, it will clobber
%rdi and %rsi (used to pass @field and @fault) and any volatile regs
written by vmread_error(). On 32-bit, asmlinkage means vmread_error()
expects the parameters to be passed on the stack, not via regs.
Opportunistically zero out the result in the trampoline to save a few
bytes of code for every VMREAD. A happy side effect of the trampoline
is that the inline code footprint is reduced by three bytes on 64-bit
due to PUSH/POP being more efficent (in terms of opcode bytes) than MOV.
Fixes: 6e2020977e3e6 ("KVM: VMX: Add error handling to VMREAD helper")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200326160712.28803-1-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit d18b2f43b9147c8005ae0844fb445d8cc6a87e31 upstream.
Check the result of __vmalloc() to avoid dereferencing a NULL pointer in
the event that allocation failres.
Fixes: d1e5b0e98ea27 ("kvm: Make VM ioctl do valloc for some archs")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit 31603d4fc2bb4f0815245d496cb970b27b4f636a upstream.
VMCLEAR all in-use VMCSes during a crash, even if kdump's NMI shootdown
interrupted a KVM update of the percpu in-use VMCS list.
Because NMIs are not blocked by disabling IRQs, it's possible that
crash_vmclear_local_loaded_vmcss() could be called while the percpu list
of VMCSes is being modified, e.g. in the middle of list_add() in
vmx_vcpu_load_vmcs(). This potential corner case was called out in the
original commit[*], but the analysis of its impact was wrong.
Skipping the VMCLEARs is wrong because it all but guarantees that a
loaded, and therefore cached, VMCS will live across kexec and corrupt
memory in the new kernel. Corruption will occur because the CPU's VMCS
cache is non-coherent, i.e. not snooped, and so the writeback of VMCS
memory on its eviction will overwrite random memory in the new kernel.
The VMCS will live because the NMI shootdown also disables VMX, i.e. the
in-progress VMCLEAR will #UD, and existing Intel CPUs do not flush the
VMCS cache on VMXOFF.
Furthermore, interrupting list_add() and list_del() is safe due to
crash_vmclear_local_loaded_vmcss() using forward iteration. list_add()
ensures the new entry is not visible to forward iteration unless the
entire add completes, via WRITE_ONCE(prev->next, new). A bad "prev"
pointer could be observed if the NMI shootdown interrupted list_del() or
list_add(), but list_for_each_entry() does not consume ->prev.
In addition to removing the temporary disabling of VMCLEAR, open code
loaded_vmcs_init() in __loaded_vmcs_clear() and reorder VMCLEAR so that
the VMCS is deleted from the list only after it's been VMCLEAR'd.
Deleting the VMCS before VMCLEAR would allow a race where the NMI
shootdown could arrive between list_del() and vmcs_clear() and thus
neither flow would execute a successful VMCLEAR. Alternatively, more
code could be moved into loaded_vmcs_init(), but that gets rather silly
as the only other user, alloc_loaded_vmcs(), doesn't need the smp_wmb()
and would need to work around the list_del().
Update the smp_*() comments related to the list manipulation, and
opportunistically reword them to improve clarity.
[*] https://patchwork.kernel.org/patch/1675731/#3720461
Fixes: 8f536b7697a0 ("KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200321193751.24985-2-sean.j.christopherson@intel.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
commit a1c77abb8d93381e25a8d2df3a917388244ba776 upstream.
Return true for vmx_interrupt_allowed() if the vCPU is in L2 and L1 has
external interrupt exiting enabled. IRQs are never blocked in hardware
if the CPU is in the guest (L2 from L1's perspective) when IRQs trigger
VM-Exit.
The new check percolates up to kvm_vcpu_ready_for_interrupt_injection()
and thus vcpu_run(), and so KVM will exit to userspace if userspace has
requested an interrupt window (to inject an IRQ into L1).
Remove the @external_intr param from vmx_check_nested_events(), which is
actually an indicator that userspace wants an interrupt window, e.g.
it's named @req_int_win further up the stack. Injecting a VM-Exit into
L1 to try and bounce out to L0 userspace is all kinds of broken and is
no longer necessary.
Remove the hack in nested_vmx_vmexit() that attempted to workaround the
breakage in vmx_check_nested_events() by only filling interrupt info if
there's an actual interrupt pending. The hack actually made things
worse because it caused KVM to _never_ fill interrupt info when the
LAPIC resides in userspace (kvm_cpu_has_interrupt() queries
interrupt.injected, which is always cleared by prepare_vmcs12() before
reaching the hack in nested_vmx_vmexit()).
Fixes: 6550c4df7e50 ("KVM: nVMX: Fix interrupt window request with "Acknowledge interrupt on exit"")
Cc: stable@vger.kernel.org
Cc: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
THUNK_TARGET defines [thunk_target] as having "rm" input constraints
when CONFIG_RETPOLINE is not set, which isn't constrained enough for
this specific case.
For inline assembly that modifies the stack pointer before using this
input, the underspecification of constraints is dangerous, and results
in an indirect call to a previously pushed flags register.
In this case `entry`'s stack slot is good enough to satisfy the "m"
constraint in "rm", but the inline assembly in
handle_external_interrupt_irqoff() modifies the stack pointer via
push+pushf before using this input, which in this case results in
calling what was the previous state of the flags register, rather than
`entry`.
Be more specific in the constraints by requiring `entry` be in a
register, and not a memory operand.
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Reported-by: syzbot+3f29ca2efb056a761e38@syzkaller.appspotmail.com
Debugged-by: Alexander Potapenko <glider@google.com>
Debugged-by: Paolo Bonzini <pbonzini@redhat.com>
Debugged-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Message-Id: <20200323191243.30002-1-ndesaulniers@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
|
When an EVMCS enabled L1 guest on KVM will tries doing enlightened VMEnter
with EVMCS GPA = 0 the host crashes because the
evmcs_gpa != vmx->nested.hv_evmcs_vmptr
condition in nested_vmx_handle_enlightened_vmptrld() will evaluate to
false (as nested.hv_evmcs_vmptr is zeroed after init). The crash will
happen on vmx->nested.hv_evmcs pointer dereference.
Another problematic EVMCS ptr value is '-1' but it only causes host crash
after nested_release_evmcs() invocation. The problem is exactly the same as
with '0', we mistakenly think that the EVMCS pointer hasn't changed and
thus nested.hv_evmcs_vmptr is valid.
Resolve the issue by adding an additional !vmx->nested.hv_evmcs
check to nested_vmx_handle_enlightened_vmptrld(), this way we will
always be trying kvm_vcpu_map() when nested.hv_evmcs is NULL
and this is supposed to catch all invalid EVMCS GPAs.
Also, initialize hv_evmcs_vmptr to '0' in nested_release_evmcs()
to be consistent with initialization where we don't currently
set hv_evmcs_vmptr to '-1'.
Cc: stable@vger.kernel.org
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Enable ENCLS-exiting (and thus set vmcs.ENCLS_EXITING_BITMAP) only if
the CPU supports SGX1. Per Intel's SDM, all ENCLS leafs #UD if SGX1
is not supported[*], i.e. intercepting ENCLS to inject a #UD is
unnecessary.
Avoiding ENCLS-exiting even when it is reported as supported by the CPU
works around a reported issue where SGX is "hard" disabled after an S3
suspend/resume cycle, i.e. CPUID.0x7.SGX=0 and the VMCS field/control
are enumerated as unsupported. While the root cause of the S3 issue is
unknown, it's definitely _not_ a KVM (or kernel) bug, i.e. this is a
workaround for what is most likely a hardware or firmware issue. As a
bonus side effect, KVM saves a VMWRITE when first preparing vmcs01 and
vmcs02.
Note, SGX must be disabled in BIOS to take advantage of this workaround
[*] The additional ENCLS CPUID check on SGX1 exists so that SGX can be
globally "soft" disabled post-reset, e.g. if #MC bits in MCi_CTL are
cleared. Soft disabled meaning disabling SGX without clearing the
primary CPUID bit (in leaf 0x7) and without poking into non-SGX
CPU paths, e.g. for the VMCS controls.
Fixes: 0b665d304028 ("KVM: vmx: Inject #UD for SGX ENCLS instruction in guest")
Reported-by: Toni Spets <toni.spets@iki.fi>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
KVM emulates UMIP on hardware that doesn't support it by setting the
'descriptor table exiting' VM-execution control and performing
instruction emulation. When running nested, this emulation is broken as
KVM refuses to emulate L2 instructions by default.
Correct this regression by allowing the emulation of descriptor table
instructions if L1 hasn't requested 'descriptor table exiting'.
Fixes: 07721feee46b ("KVM: nVMX: Don't emulate instructions in guest mode")
Reported-by: Jan Kiszka <jan.kiszka@web.de>
Cc: stable@vger.kernel.org
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Jim Mattson <jmattson@google.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Compile error with CONFIG_KVM_INTEL=y and W=1:
CC arch/x86/kvm/vmx/vmx.o
arch/x86/kvm/vmx/vmx.c:68:32: error: 'vmx_cpu_id' defined but not used [-Werror=unused-const-variable=]
68 | static const struct x86_cpu_id vmx_cpu_id[] = {
| ^~~~~~~~~~
cc1: all warnings being treated as errors
When building with =y, the MODULE_DEVICE_TABLE macro doesn't generate a
reference to the structure (or any code at all). This makes W=1 compiles
unhappy.
Wrap both in a #ifdef to avoid the issue.
Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
[Do the same for CONFIG_KVM_AMD. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Consult the 'unconditional IO exiting' and 'use IO bitmaps' VM-execution
controls when checking instruction interception. If the 'use IO bitmaps'
VM-execution control is 1, check the instruction access against the IO
bitmaps to determine if the instruction causes a VM-exit.
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Checks against the IO bitmap are useful for both instruction emulation
and VM-exit reflection. Refactor the IO bitmap checks into a helper
function.
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
vmx_check_intercept is not yet fully implemented. To avoid emulating
instructions disallowed by the L1 hypervisor, refuse to emulate
instructions by default.
Cc: stable@vger.kernel.org
[Made commit, added commit msg - Oliver]
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Since commit 5f3d45e7f282 ("kvm/x86: add support for
MONITOR_TRAP_FLAG"), KVM has allowed an L1 guest to use the monitor trap
flag processor-based execution control for its L2 guest. KVM simply
forwards any MTF VM-exits to the L1 guest, which works for normal
instruction execution.
However, when KVM needs to emulate an instruction on the behalf of an L2
guest, the monitor trap flag is not emulated. Add the necessary logic to
kvm_skip_emulated_instruction() to synthesize an MTF VM-exit to L1 upon
instruction emulation for L2.
Fixes: 5f3d45e7f282 ("kvm/x86: add support for MONITOR_TRAP_FLAG")
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
apicv is globally disabled
When apicv is disabled on a vCPU (e.g. by enabling KVM_CAP_HYPERV_SYNIC*),
nothing happens to VMX MSRs on the already existing vCPUs, however, all new
ones are created with PIN_BASED_POSTED_INTR filtered out. This is very
confusing and results in the following picture inside the guest:
$ rdmsr -ax 0x48d
ff00000016
7f00000016
7f00000016
7f00000016
This is observed with QEMU and 4-vCPU guest: QEMU creates vCPU0, does
KVM_CAP_HYPERV_SYNIC2 and then creates the remaining three.
L1 hypervisor may only check CPU0's controls to find out what features
are available and it will be very confused later. Switch to setting
PIN_BASED_POSTED_INTR control based on global 'enable_apicv' setting.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Even when APICv is disabled for L1 it can (and, actually, is) still
available for L2, this means we need to always call
vmx_deliver_nested_posted_interrupt() when attempting an interrupt
delivery.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
For the duration of mapping eVMCS, it derefences ->memslots without holding
->srcu or ->slots_lock when accessing hv assist page. This patch fixes it by
moving nested_sync_vmcs12_to_shadow to prepare_guest_switch, where the SRCU
is already taken.
It can be reproduced by running kvm's evmcs_test selftest.
=============================
warning: suspicious rcu usage
5.6.0-rc1+ #53 tainted: g w ioe
-----------------------------
./include/linux/kvm_host.h:623 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by evmcs_test/8507:
#0: ffff9ddd156d00d0 (&vcpu->mutex){+.+.}, at:
kvm_vcpu_ioctl+0x85/0x680 [kvm]
stack backtrace:
cpu: 6 pid: 8507 comm: evmcs_test tainted: g w ioe 5.6.0-rc1+ #53
hardware name: dell inc. optiplex 7040/0jctf8, bios 1.4.9 09/12/2016
call trace:
dump_stack+0x68/0x9b
kvm_read_guest_cached+0x11d/0x150 [kvm]
kvm_hv_get_assist_page+0x33/0x40 [kvm]
nested_enlightened_vmentry+0x2c/0x60 [kvm_intel]
nested_vmx_handle_enlightened_vmptrld.part.52+0x32/0x1c0 [kvm_intel]
nested_sync_vmcs12_to_shadow+0x439/0x680 [kvm_intel]
vmx_vcpu_run+0x67a/0xe60 [kvm_intel]
vcpu_enter_guest+0x35e/0x1bc0 [kvm]
kvm_arch_vcpu_ioctl_run+0x40b/0x670 [kvm]
kvm_vcpu_ioctl+0x370/0x680 [kvm]
ksys_ioctl+0x235/0x850
__x64_sys_ioctl+0x16/0x20
do_syscall_64+0x77/0x780
entry_syscall_64_after_hwframe+0x49/0xbe
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Fix wrong variable names and grammar error in comment.
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Hardcode the EPT page-walk level for L2 to be 4 levels, as KVM's MMU
currently also hardcodes the page walk level for nested EPT to be 4
levels. The L2 guest is all but guaranteed to soft hang on its first
instruction when L1 is using EPT, as KVM will construct 4-level page
tables and then tell hardware to use 5-level page tables.
Fixes: 855feb673640 ("KVM: MMU: Add 5 level EPT & Shadow page table support.")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Fix some typos in the comments. Also fix coding style.
[Sean Christopherson rewrites the comment of write_fault_to_shadow_pgtable
field in struct kvm_vcpu_arch.]
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
SDM 27.3.4 states that the 'pending debug exceptions' VMCS field will
be populated if a VM-exit caused by an INIT signal takes priority over a
debug-trap. Emulate this behavior when synthesizing an INIT signal
VM-exit into L1.
Fixes: 4b9852f4f389 ("KVM: x86: Fix INIT signal handling in various CPU states")
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Do not initialize the microcode version at RESET or INIT, only on vCPU
creation. Microcode updates are not lost during INIT, and exact
behavior across a warm RESET is not specified by the architecture.
Since we do not support a microcode update directly from the hypervisor,
but only as a result of userspace setting the microcode version MSR,
it's simpler for userspace if we do nothing in KVM and let userspace
emulate behavior for RESET as it sees fit.
Userspace can tie the fix to the availability of MSR_IA32_UCODE_REV in
the list of emulated MSRs.
Reported-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The function vmx_decache_cr0_guest_bits() is only called below its
implementation. So this is meaningless and should be removed.
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Correct the logic in intel_pmu_set_msr() for fixed and general purpose
counters. This was recently changed to set pmc->counter without taking
in to account the value of pmc_read_counter() which will be incorrect if
the counter is currently running and non-zero; this changes back to the
old logic which accounted for the value of currently running counters.
Signed-off-by: Eric Hankland <ehankland@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
guests
Sane L1 hypervisors are not supposed to turn any of the unsupported VMX
controls on for its guests and nested_vmx_check_controls() checks for
that. This is, however, not the case for the controls which are supported
on the host but are missing in enlightened VMCS and when eVMCS is in use.
It would certainly be possible to add these missing checks to
nested_check_vm_execution_controls()/_vm_exit_controls()/.. but it seems
preferable to keep eVMCS-specific stuff in eVMCS and reduce the impact on
non-eVMCS guests by doing less unrelated checks. Create a separate
nested_evmcs_check_controls() for this purpose.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
With fine grained VMX feature enablement QEMU>=4.2 tries to do KVM_SET_MSRS
with default (matching CPU model) values and in case eVMCS is also enabled,
fails.
It would be possible to drop VMX feature filtering completely and make
this a guest's responsibility: if it decides to use eVMCS it should know
which fields are available and which are not. Hyper-V mostly complies to
this, however, there are some problematic controls:
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES
VM_{ENTRY,EXIT}_LOAD_IA32_PERF_GLOBAL_CTRL
which Hyper-V enables. As there are no corresponding fields in eVMCS, we
can't handle this properly in KVM. This is a Hyper-V issue.
Move VMX controls sanitization from nested_enable_evmcs() to vmx_get_msr(),
and do the bare minimum (only clear controls which are known to cause issues).
This allows userspace to keep setting controls it wants and at the same
time hides them from the guest.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The blurb pertaining to the return value of nested_vmx_load_cr3() no
longer matches reality, remove it entirely as the behavior it is
attempting to document is quite obvious when reading the actual code.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The function nested_vmx_run() declaration is below its implementation. So
this is meaningless and should be removed.
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Since disabling APICv has to be done for all vcpus on AMD-based
system, adopt the newly introduced kvm_request_apicv_update()
interface, and introduce a new APICV_INHIBIT_REASON_HYPERV.
Also, remove the kvm_vcpu_deactivate_apicv() since no longer used.
Cc: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Inibit reason bits are used to determine if APICv deactivation is
applicable for a particular hardware virtualization architecture.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
It is unused now.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
There are several reasons in which a VM needs to deactivate APICv
e.g. disable APICv via parameter during module loading, or when
enable Hyper-V SynIC support. Additional inhibit reasons will be
introduced later on when dynamic APICv is supported,
Introduce KVM APICv inhibit reason bits along with a new variable,
apicv_inhibit_reasons, to help keep track of APICv state for each VM,
Initially, the APICV_INHIBIT_REASON_DISABLE bit is used to indicate
the case where APICv is disabled during KVM module load.
(e.g. insmod kvm_amd avic=0 or insmod kvm_intel enable_apicv=0).
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
[Do not use get_enable_apicv; consider irqchip_split in svm.c. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Pull KVM updates from Paolo Bonzini:
"This is the first batch of KVM changes.
ARM:
- cleanups and corner case fixes.
PPC:
- Bugfixes
x86:
- Support for mapping DAX areas with large nested page table entries.
- Cleanups and bugfixes here too. A particularly important one is a
fix for FPU load when the thread has TIF_NEED_FPU_LOAD. There is
also a race condition which could be used in guest userspace to
exploit the guest kernel, for which the embargo expired today.
- Fast path for IPI delivery vmexits, shaving about 200 clock cycles
from IPI latency.
- Protect against "Spectre-v1/L1TF" (bring data in the cache via
speculative out of bound accesses, use L1TF on the sibling
hyperthread to read it), which unfortunately is an even bigger
whack-a-mole game than SpectreV1.
Sean continues his mission to rewrite KVM. In addition to a sizable
number of x86 patches, this time he contributed a pretty large
refactoring of vCPU creation that affects all architectures but should
not have any visible effect.
s390 will come next week together with some more x86 patches"
* tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
x86/KVM: Clean up host's steal time structure
x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed
x86/kvm: Cache gfn to pfn translation
x86/kvm: Introduce kvm_(un)map_gfn()
x86/kvm: Be careful not to clear KVM_VCPU_FLUSH_TLB bit
KVM: PPC: Book3S PR: Fix -Werror=return-type build failure
KVM: PPC: Book3S HV: Release lock on page-out failure path
KVM: arm64: Treat emulated TVAL TimerValue as a signed 32-bit integer
KVM: arm64: pmu: Only handle supported event counters
KVM: arm64: pmu: Fix chained SW_INCR counters
KVM: arm64: pmu: Don't mark a counter as chained if the odd one is disabled
KVM: arm64: pmu: Don't increment SW_INCR if PMCR.E is unset
KVM: x86: Use a typedef for fastop functions
KVM: X86: Add 'else' to unify fastop and execute call path
KVM: x86: inline memslot_valid_for_gpte
KVM: x86/mmu: Use huge pages for DAX-backed files
KVM: x86/mmu: Remove lpage_is_disallowed() check from set_spte()
KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust()
KVM: x86/mmu: Zap any compound page when collapsing sptes
KVM: x86/mmu: Remove obsolete gfn restoration in FNAME(fetch)
...
|
|
vmx_set_segment() clears segment cache unconditionally, so we should not
clear it again by calling vmx_segment_cache_clear().
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
According to section "Checks on Guest Control Registers, Debug Registers, and
and MSRs" in Intel SDM vol 3C, the following checks are performed on vmentry
of nested guests:
If the "load debug controls" VM-entry control is 1, bits 63:32 in the DR7
field must be 0.
In KVM, GUEST_DR7 is set prior to the vmcs02 VM-entry by kvm_set_dr() and the
latter synthesizes a #GP if any bit in the high dword in the former is set.
Hence this field needs to be checked in software.
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>
|
|
The helper x86_set_memory_region() is only used in vmx_set_tss_addr()
and kvm_arch_destroy_vm(). Push the lock upper in both cases. With
that, drop x86_set_memory_region().
This prepares to allow __x86_set_memory_region() to return a HVA
mapped, because the HVA will need to be protected by the lock too even
after __x86_set_memory_region() returns.
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
We've already got the slots_lock, so we should be safe.
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
nested_enable_evmcs()
In nested_enable_evmcs() evmcs_already_enabled check doesn't really do
anything: controls are already sanitized and we return '0' regardless.
Just drop the check.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Liran Alon <liran.alon@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Remove the CONFIG_X86_64 condition from the low level non-canonical
helpers to effectively enable non-canonical checks on 32-bit KVM.
Non-canonical checks are performed by hardware if the CPU *supports*
64-bit mode, whether or not the CPU is actually in 64-bit mode is
irrelevant.
For the most part, skipping non-canonical checks on 32-bit KVM is ok-ish
because 32-bit KVM always (hopefully) drops bits 63:32 of whatever value
it's checking before propagating it to hardware, and architecturally,
the expected behavior for the guest is a bit of a grey area since the
vCPU itself doesn't support 64-bit mode. I.e. a 32-bit KVM guest can
observe the missed checks in several paths, e.g. INVVPID and VM-Enter,
but it's debatable whether or not the missed checks constitute a bug
because technically the vCPU doesn't support 64-bit mode.
The primary motivation for enabling the non-canonical checks is defense
in depth. As mentioned above, a guest can trigger a missed check via
INVVPID or VM-Enter. INVVPID is straightforward as it takes a 64-bit
virtual address as part of its 128-bit INVVPID descriptor and fails if
the address is non-canonical, even if INVVPID is executed in 32-bit PM.
Nested VM-Enter is a bit more convoluted as it requires the guest to
write natural width VMCS fields via memory accesses and then VMPTRLD the
VMCS, but it's still possible. In both cases, KVM is saved from a true
bug only because its flows that propagate values to hardware (correctly)
take "unsigned long" parameters and so drop bits 63:32 of the bad value.
Explicitly performing the non-canonical checks makes it less likely that
a bad value will be propagated to hardware, e.g. in the INVVPID case,
if __invvpid() didn't implicitly drop bits 63:32 then KVM would BUG() on
the resulting unexpected INVVPID failure due to hardware rejecting the
non-canonical address.
The only downside to enabling the non-canonical checks is that it adds a
relatively small amount of overhead, but the affected flows are not hot
paths, i.e. the overhead is negligible.
Note, KVM technically could gate the non-canonical checks on 32-bit KVM
with static_cpu_has(X86_FEATURE_LM), but on bare metal that's an even
bigger waste of code for everyone except the 0.00000000000001% of the
population running on Yonah, and nested 32-bit on 64-bit already fudges
things with respect to 64-bit CPU behavior.
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
[Also do so in nested_vmx_check_host_state as reported by Krish. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Writes to MSR_CORE_PERF_GLOBAL_CONTROL should never fail if the VM-exit
and VM-entry controls are exposed to L1. Promote the checks to perform a
full WARN if kvm_set_msr() fails and remove the now unused macro
SET_MSR_OR_WARN().
Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This fixes Spectre-v1/L1TF vulnerabilities in intel_find_fixed_event()
and intel_rdpmc_ecx_to_pmc().
kvm_rdpmc() (ancestor of intel_find_fixed_event()) and
reprogram_fixed_counter() (ancestor of intel_rdpmc_ecx_to_pmc()) are
exported symbols so KVM should treat them conservatively from a security
perspective.
Fixes: 25462f7f5295 ("KVM: x86/vPMU: Define kvm_pmu_ops to support vPMU function dispatch")
Signed-off-by: Nick Finco <nifi@google.com>
Signed-off-by: Marios Pomonis <pomonis@google.com>
Reviewed-by: Andrew Honig <ahonig@google.com>
Cc: stable@vger.kernel.org
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|