A guest can cause a BUG_ON() leading to a host kernel crash.
When the guest writes to the ICR to request an IPI, while in x2apic
mode the following things happen, the destination is read from
ICR2, which is a register that the guest can control.
kvm_irq_delivery_to_apic_fast uses the high 16 bits of ICR2 as the
cluster id. A BUG_ON is triggered, which is a protection against
accessing map->logical_map with an out-of-bounds access and manages
to avoid that anything really unsafe occurs.
The logic in the code is correct from real HW point of view. The problem
is that KVM supports only one cluster with ID 0 in clustered mode, but
the code that has the bug does not take this into account.
Reported-by: Lars Bull <larsbull@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In kvm_lapic_sync_from_vapic and kvm_lapic_sync_to_vapic there is the
potential to corrupt kernel memory if userspace provides an address that
is at the end of a page. This patches concerts those functions to use
kvm_write_guest_cached and kvm_read_guest_cached. It also checks the
vapic_address specified by userspace during ioctl processing and returns
an error to userspace if the address is not a valid GPA.
This is generally not guest triggerable, because the required write is
done by firmware that runs before the guest. Also, it only affects AMD
processors and oldish Intel that do not have the FlexPriority feature
(unless you disable FlexPriority, of course; then newer processors are
also affected).
Fixes: b93463aa59 ('KVM: Accelerated apic support')
Reported-by: Andrew Honig <ahonig@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Honig <ahonig@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Under guest controllable circumstances apic_get_tmcct will execute a
divide by zero and cause a crash. If the guest cpuid support
tsc deadline timers and performs the following sequence of requests
the host will crash.
- Set the mode to periodic
- Set the TMICT to 0
- Set the mode bits to 11 (neither periodic, nor one shot, nor tsc deadline)
- Set the TMICT to non-zero.
Then the lapic_timer.period will be 0, but the TMICT will not be. If the
guest then reads from the TMCCT then the host will perform a divide by 0.
This patch ensures that if the lapic_timer.period is 0, then the division
does not occur.
Reported-by: Andrew Honig <ahonig@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Honig <ahonig@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We should not be using jump labels before they were initialized. Push back
the callback to until after jump label initialization.
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
If a nested guest does a NM fault but its CR0 doesn't contain the TS
flag (because it was already cleared by the guest with L1 aid) then we
have to activate FPU ourselves in L0 and then continue to L2. If TS flag
is set then we fallback on the previous behavior, forward the fault to
L1 if it asked for.
Signed-off-by: Anthoine Bourgeois <bourgeois@bertin.fr>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We need to copy padding to kernel space first before looking at it.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
I noticed that srcu_read_lock/unlock both have a memory barrier,
so just by moving srcu_read_unlock earlier we can get rid of
one call to smp_mb() using smp_mb__after_srcu_read_unlock instead.
Unsurprisingly, the gain is small but measureable using the unit test
microbenchmark:
before
vmcall in the ballpark of 1410 cycles
after
vmcall in the ballpark of 1360 cycles
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Currently cpuid emulation is traced only when executed by intercept.
Move trace point so that emulator invocation is traced too.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
All decode_register() callers check if instruction has rex prefix
to properly decode one byte operand. It make sense to move the check
inside.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
When I was looking at RHEL5.9's failure to start with
unrestricted_guest=0/emulate_invalid_guest_state=1, I got it working with a
slightly older tree than kvm.git. I now debugged the remaining failure,
which was introduced by commit 660696d1 (KVM: X86 emulator: fix
source operand decoding for 8bit mov[zs]x instructions, 2013-04-24)
introduced a similar mis-emulation to the one in commit 8acb4207 (KVM:
fix sil/dil/bpl/spl in the mod/rm fields, 2013-05-30). The incorrect
decoding occurs in 8-bit movzx/movsx instructions whose 8-bit operand
is sil/dil/bpl/spl.
Needless to say, "movzbl %bpl, %eax" does occur in RHEL5.9's decompression
prolog, just a handful of instructions before finally giving control to
the decompressed vmlinux and getting out of the invalid guest state.
Because OpMem8 bypasses decode_modrm, the same handling of the REX prefix
must be applied to OpMem8.
Reported-by: Michele Baldessari <michele@redhat.com>
Cc: stable@vger.kernel.org
Cc: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Yet another instruction that we fail to emulate, this time found
in Windows 2008R2 32-bit.
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
mst can't be blamed for lack of switch entries: the
issue is with msrs actually.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The loop was always using 0 as the index. This means that
any rubbish after the first element of the array went undetected.
It seems reasonable to assume that no KVM userspace did that.
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The KVM_SET_XCRS ioctl must accept anything that KVM_GET_XCRS
could return. XCR0's bit 0 is always 1 in real processors with
XSAVE, and KVM_GET_XCRS will always leave bit 0 set even if the
emulated processor does not have XSAVE. So, KVM_SET_XCRS must
ignore that bit when checking for attempts to enable unsupported
save states.
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We currently use some ad-hoc arch variables tied to legacy KVM device
assignment to manage emulation of instructions that depend on whether
non-coherent DMA is present. Create an interface for this, adapting
legacy KVM device assignment and adding VFIO via the KVM-VFIO device.
For now we assume that non-coherent DMA is possible any time we have a
VFIO group. Eventually an interface can be developed as part of the
VFIO external user interface to query the coherency of a group.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Default to operating in coherent mode. This simplifies the logic when
we switch to a model of registering and unregistering noncoherent I/O
with KVM.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
So far we've succeeded at making KVM and VFIO mostly unaware of each
other, but areas are cropping up where a connection beyond eventfds
and irqfds needs to be made. This patch introduces a KVM-VFIO device
that is meant to be a gateway for such interaction. The user creates
the device and can add and remove VFIO groups to it via file
descriptors. When a group is added, KVM verifies the group is valid
and gets a reference to it via the VFIO external user interface.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This basically came from the need to be able to boot 32-bit Atom SMP
guests on an AMD host, i.e. a host which doesn't support MOVBE. As a
matter of fact, qemu has since recently received MOVBE support but we
cannot share that with kvm emulation and thus we have to do this in the
host. We're waay faster in kvm anyway. :-)
So, we piggyback on the #UD path and emulate the MOVBE functionality.
With it, an 8-core SMP guest boots in under 6 seconds.
Also, requesting MOVBE emulation needs to happen explicitly to work,
i.e. qemu -cpu n270,+movbe...
Just FYI, a fairly straight-forward boot of a MOVBE-enabled 3.9-rc6+
kernel in kvm executes MOVBE ~60K times.
Signed-off-by: Andre Przywara <andre@andrep.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add initial support for handling three-byte instructions in the
emulator.
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Call it EmulateOnUD which is exactly what we're trying to do with
vendor-specific instructions.
Rename ->only_vendor_specific_insn to something shorter, while at it.
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a field to the current emulation context which contains the
instruction opcode length. This will streamline handling of opcodes of
different length.
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Add a kvm ioctl which states which system functionality kvm emulates.
The format used is that of CPUID and we return the corresponding CPUID
bits set for which we do emulate functionality.
Make sure ->padding is being passed on clean from userspace so that we
can use it for something in the future, after the ioctl gets cast in
stone.
s/kvm_dev_ioctl_get_supported_cpuid/kvm_dev_ioctl_get_cpuid/ while at
it.
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If the host supports it, we can and should expose it to the guest as
well, just like we already do with PIN_BASED_VIRTUAL_NMIS.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
__vmx_complete_interrupts stored uninjected NMIs in arch.nmi_injected,
not arch.nmi_pending. So we actually need to check the former field in
vmcs12_save_pending_event. This fixes the eventinj unit test when run
in nested KVM.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
As long as the hardware provides us 2MB EPT pages, we can also expose
them to the guest because our shadow EPT code already supports this
feature.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We will use that in the later patch to find the kvm ops handler
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Page pinning is not mandatory in kvm async page fault processing since
after async page fault event is delivered to a guest it accesses page once
again and does its own GUP. Drop the FOLL_GET flag in GUP in async_pf
code, and do some simplifying in check/clear processing.
Suggested-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Gu zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: chai wen <chaiw.fnst@cn.fujitsu.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
This patch contains the following two changes:
1. Fix the bug in nested preemption timer support. If vmexit L2->L0
with some reasons not emulated by L1, preemption timer value should
be save in such exits.
2. Add support of "Save VMX-preemption timer value" VM-Exit controls
to nVMX.
With this patch, nested VMX preemption timer features are fully
supported.
Signed-off-by: Arthur Chunqi Li <yzt356@gmail.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
72f857950f broke shadow on EPT. This patch reverts it and fixes PAE
on nEPT (which reverted commit fixed) in other way.
Shadow on EPT is now broken because while L1 builds shadow page table
for L2 (which is PAE while L2 is in real mode) it never loads L2's
GUEST_PDPTR[0-3]. They do not need to be loaded because without nested
virtualization HW does this during guest entry if EPT is disabled,
but in our case L0 emulates L2's vmentry while EPT is enables, so we
cannot rely on vmcs12->guest_pdptr[0-3] to contain up-to-date values
and need to re-read PDPTEs from L2 memory. This is what kvm_set_cr3()
is doing, but by clearing cache bits during L2 vmentry we drop values
that kvm_set_cr3() read from memory.
So why the same code does not work for PAE on nEPT? kvm_set_cr3()
reads pdptes into vcpu->arch.walk_mmu->pdptrs[]. walk_mmu points to
vcpu->arch.nested_mmu while nested guest is running, but ept_load_pdptrs()
uses vcpu->arch.mmu which contain incorrect values. Fix that by using
walk_mmu in ept_(load|save)_pdptrs.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_mmu initialization is mostly filling in function pointers, there is
no way for it to fail. Clean up unused return values.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
They do the same thing, and destroy_kvm_mmu can be confused with
kvm_mmu_destroy.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
The new_cr3 MMU callback has been a wrapper for mmu_free_roots since commit
e676505 (KVM: MMU: Force cr3 reload with two dimensional paging on mov
cr3 emulation, 2012-07-08).
The commit message mentioned that "mmu_free_roots() is somewhat of an overkill,
but fixing that is more complicated and will be done after this minimal fix".
One year has passed, and no one really felt the need to do a different fix.
Wrap the call with a kvm_mmu_new_cr3 function for clarity, but remove the
callback.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
The free MMU callback has been a wrapper for mmu_free_roots since mmu_free_roots
itself was introduced (commit 17ac10a, [PATCH] KVM: MU: Special treatment
for shadow pae root pages, 2007-01-05), and has always been the same for all
MMU cases. Remove the indirection as it is useless.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
This makes the interface more deterministic for userspace, which can expect
(after configuring only the features it supports) to get exactly the same
state from the kernel, independent of the host CPU and kernel version.
Suggested-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
A guest can still attempt to save and restore XSAVE states even if they
have been masked in CPUID leaf 0Dh. This usually is not visible to
the guest, but is still wrong: "Any attempt to set a reserved bit (as
determined by the contents of EAX and EDX after executing CPUID with
EAX=0DH, ECX= 0H) in XCR0 for a given processor will result in a #GP
exception".
The patch also performs the same checks as __kvm_set_xcr in KVM_SET_XSAVE.
This catches migration from newer to older kernel/processor before the
guest starts running.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
XSAVE entries that KVM does not support are reported by
KVM_GET_SUPPORTED_CPUID for leaf 0Dh index 0 if the host supports them;
they should be left out unless there is also hypervisor support for them.
Sub-leafs are correctly handled in supported_xcr0_bit, fix index 0
to match.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
In commit e935b8372c ("KVM: Convert kvm_lock to raw_spinlock"),
the kvm_lock was made a raw lock. However, the kvm mmu_shrink()
function tries to grab the (non-raw) mmu_lock within the scope of
the raw locked kvm_lock being held. This leads to the following:
BUG: sleeping function called from invalid context at kernel/rtmutex.c:659
in_atomic(): 1, irqs_disabled(): 0, pid: 55, name: kswapd0
Preemption disabled at:[<ffffffffa0376eac>] mmu_shrink+0x5c/0x1b0 [kvm]
Pid: 55, comm: kswapd0 Not tainted 3.4.34_preempt-rt
Call Trace:
[<ffffffff8106f2ad>] __might_sleep+0xfd/0x160
[<ffffffff817d8d64>] rt_spin_lock+0x24/0x50
[<ffffffffa0376f3c>] mmu_shrink+0xec/0x1b0 [kvm]
[<ffffffff8111455d>] shrink_slab+0x17d/0x3a0
[<ffffffff81151f00>] ? mem_cgroup_iter+0x130/0x260
[<ffffffff8111824a>] balance_pgdat+0x54a/0x730
[<ffffffff8111fe47>] ? set_pgdat_percpu_threshold+0xa7/0xd0
[<ffffffff811185bf>] kswapd+0x18f/0x490
[<ffffffff81070961>] ? get_parent_ip+0x11/0x50
[<ffffffff81061970>] ? __init_waitqueue_head+0x50/0x50
[<ffffffff81118430>] ? balance_pgdat+0x730/0x730
[<ffffffff81060d2b>] kthread+0xdb/0xe0
[<ffffffff8106e122>] ? finish_task_switch+0x52/0x100
[<ffffffff817e1e94>] kernel_thread_helper+0x4/0x10
[<ffffffff81060c50>] ? __init_kthread_worker+0x
After the previous patch, kvm_lock need not be a raw spinlock anymore,
so change it back.
Reported-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: kvm@vger.kernel.org
Cc: gleb@redhat.com
Cc: jan.kiszka@siemens.com
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If #PF happens during delivery of an exception into L2 and L1 also do
not have the page mapped in its shadow page table then L0 needs to
generate vmexit to L2 with original event in IDT_VECTORING_INFO, but
current code combines both exception and generates #DF instead. Fix that
by providing nVMX specific function to handle page faults during page
table walk that handles this case correctly.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
All exceptions should be checked for intercept during delivery to L2,
but we check only #PF currently. Drop nested_run_pending while we are
at it since exception cannot be injected during vmentry anyway.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
[Renamed the nested_vmx_check_exception function. - Paolo]
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If an exception causes vmexit directly it should not be reported in
IDT_VECTORING_INFO during the exit. For that we need to be able to
distinguish between exception that is injected into nested VM and one that
is reinjected because its delivery failed. Fortunately we already have
mechanism to do so for nested SVM, so here we just use correct function
to requeue exceptions and make sure that reinjected exception is not
moved to IDT_VECTORING_INFO during vmexit emulation and not re-checked
for interception during delivery.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
EXIT_REASON_VMLAUNCH/EXIT_REASON_VMRESUME exit does not mean that nested
VM will actually run during next entry. Move setting nested_run_pending
closer to vmentry emulation code and move its clearing close to vmexit to
minimize amount of code that will erroneously run with nested_run_pending
set.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Bit 12 is undefined in any of the following cases:
- If the "NMI exiting" VM-execution control is 1 and the "virtual NMIs"
VM-execution control is 0.
- If the VM exit sets the valid bit in the IDT-vectoring information field
Signed-off-by: Gleb Natapov <gleb@redhat.com>
[Add parentheses around & within && - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Now that we provide EPT support, there is no reason to torture our
guests by hiding the relieving unrestricted guest mode feature. We just
need to relax CR0 checks for always-on bits as PE and PG can now be
switched off.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Implement and advertise VM_EXIT_SAVE_IA32_EFER. L0 traps EFER writes
unconditionally, so we always find the current L2 value in the
architectural state.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Fiddling with CR3 for L2 is L1's job. It may set its own, different
identity map or simple leave it alone if unrestricted guest mode is
enabled. This also fixes reading back the current CR3 on L2 exits for
reporting it to L1.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
kvm_set_cr0 performs checks on the state transition that may prevent
loading L1's cr0. For now we rely on the hardware to catch invalid
states loaded by L1 into its VMCS. Still, consistency checks on the host
state part of the VMCS on guest entry will have to be improved later on.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Set "blocked by NMI" flag if EPT violation happens during IRET from NMI
otherwise NMI can be called recursively causing stack corruption.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
