Vitaly Kuznetsov [Thu, 25 Jan 2018 15:37:07 +0000 (16:37 +0100)]
x86/kvm/vmx: do not use vm-exit instruction length for fast MMIO when running nested
I was investigating an issue with seabios >= 1.10 which stopped working
for nested KVM on Hyper-V. The problem appears to be in
handle_ept_violation() function: when we do fast mmio we need to skip
the instruction so we do kvm_skip_emulated_instruction(). This, however,
depends on VM_EXIT_INSTRUCTION_LEN field being set correctly in VMCS.
However, this is not the case.
Intel's manual doesn't mandate VM_EXIT_INSTRUCTION_LEN to be set when
EPT MISCONFIG occurs. While on real hardware it was observed to be set,
some hypervisors follow the spec and don't set it; we end up advancing
IP with some random value.
I checked with Microsoft and they confirmed they don't fill
VM_EXIT_INSTRUCTION_LEN on EPT MISCONFIG.
Fix the issue by doing instruction skip through emulator when running
nested.
Fixes: 68c3b4d1676d870f0453c31d5a52e7e65c7448ae Suggested-by: Radim Krčmář <rkrcmar@redhat.com> Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Masatake YAMATO [Fri, 19 Jan 2018 19:04:22 +0000 (04:04 +0900)]
kvm: embed vcpu id to dentry of vcpu anon inode
All d-entries for vcpu have the same, "anon_inode:kvm-vcpu". That means
it is impossible to know the mapping between fds for vcpu and vcpu
from userland.
# LC_ALL=C ls -l /proc/617/fd | grep vcpu
lrwx------. 1 qemu qemu 64 Jan 7 16:50 18 -> anon_inode:kvm-vcpu
lrwx------. 1 qemu qemu 64 Jan 7 16:50 19 -> anon_inode:kvm-vcpu
It is also impossible to know the mapping between vma for kvm_run
structure and vcpu from userland.
With the mappings known from the output, a tool like strace can report more details
of qemu-kvm process activities. Here is the strace output of my local prototype:
KarimAllah Ahmed [Wed, 17 Jan 2018 18:18:56 +0000 (19:18 +0100)]
kvm: Map PFN-type memory regions as writable (if possible)
For EPT-violations that are triggered by a read, the pages are also mapped with
write permissions (if their memory region is also writable). That would avoid
getting yet another fault on the same page when a write occurs.
This optimization only happens when you have a "struct page" backing the memory
region. So also enable it for memory regions that do not have a "struct page".
Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: KarimAllah Ahmed <karahmed@amazon.de> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Radim Krčmář [Wed, 31 Jan 2018 12:34:41 +0000 (13:34 +0100)]
Merge tag 'kvm-arm-for-v4.16' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm
KVM/ARM Changes for v4.16
The changes for this version include icache invalidation optimizations
(improving VM startup time), support for forwarded level-triggered
interrupts (improved performance for timers and passthrough platform
devices), a small fix for power-management notifiers, and some cosmetic
changes.
When I introduced a static key to avoid work in the critical path for
userspace irqchips which is very rarely used, I accidentally messed up
my logic and used && where I should have used ||, because the point was
to short-circuit the evaluation in case userspace irqchips weren't even
in use.
This fixes an issue when running in-kernel irqchip VMs alongside
userspace irqchip VMs.
Acked-by: Marc Zyngier <marc.zyngier@arm.com> Fixes: c44c232ee2d3 ("KVM: arm/arm64: Avoid work when userspace iqchips are not used") Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
We were not decrementing the static key count in the right location.
kvm_arch_vcpu_destroy() is only called to clean up after a failed
VCPU create attempt, whereas kvm_arch_vcpu_free() is called on teardown
of the VM as well. Move the static key decrement call to
kvm_arch_vcpu_free().
Acked-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
After the recently introduced support for level-triggered mapped
interrupt, I accidentally left the VCPU thread busily going back and
forward between the guest and the hypervisor whenever the guest was
blocking, because I would always incorrectly report that a timer
interrupt was pending.
This is because the timer->irq.level field is not valid for mapped
interrupts, where we offload the level state to the hardware, and as a
result this field is always true.
Luckily the problem can be relatively easily solved by not checking the
cached signal state of either timer in kvm_timer_should_fire() but
instead compute the timer state on the fly, which we do already if the
cached signal state wasn't high. In fact, the only reason for checking
the cached signal state was a tiny optimization which would only be
potentially faster when the polling loop detects a pending timer
interrupt, which is quite unlikely.
Instead of duplicating the logic from kvm_arch_timer_handler(), we
enlighten kvm_timer_should_fire() to report something valid when the
timer state is loaded onto the hardware. We can then call this from
kvm_arch_timer_handler() as well and avoid the call to
__timer_snapshot_state() in kvm_arch_timer_get_input_level().
Reported-by: Tomasz Nowicki <tn@semihalf.com> Tested-by: Tomasz Nowicki <tn@semihalf.com> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Cornelia Huck [Fri, 12 Jan 2018 14:53:34 +0000 (15:53 +0100)]
MAINTAINERS: update KVM/s390 maintainers
As I have neither too much time nor access to the architecture
documentation anymore, let's switch my status from maintainer to
reviewer. Janosch will step in as second maintainer.
Acked-by: Janosch Frank <frankja@linux.vnet.ibm.com> Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Michael Mueller [Fri, 23 Jun 2017 11:51:25 +0000 (13:51 +0200)]
KVM: s390: introduce the format-1 GISA
The patch modifies the previously defined GISA data structure to be
able to store two GISA formats, format-0 and format-1. Additionally,
it verifies the availability of the GISA format facility and enables
the use of a format-1 GISA in the SIE control block accordingly.
A format-1 can do everything that format-0 can and we will need it
for real HW passthrough. As there are systems with only format-0
we keep both variants.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Pierre Morel <pmorel@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Mon, 12 Jun 2017 11:49:28 +0000 (13:49 +0200)]
s390/sclp: expose the GISA format facility
The GISA format facility is required by the host to be able to process
a format-1 GISA. If not available, the used GISA format will be format-0.
All format-1 related extension will not be available in this case.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Pierre Morel <pmorel@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Acked-by: David Hildenbrand <david@redhat.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Fri, 23 Jun 2017 12:46:21 +0000 (14:46 +0200)]
KVM: s390: activate GISA for emulated interrupts
If the AIV facility is available, a GISA will be used to manage emulated
adapter interrupts.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Fri, 7 Jul 2017 13:27:31 +0000 (15:27 +0200)]
KVM: s390: make kvm_s390_get_io_int() aware of GISA
The function returns a pending I/O interrupt with the highest
priority defined by its ISC.
Together with AIV activation, pending adapter interrupts are
managed by the GISA IPM. Thus kvm_s390_get_io_int() needs to
inspect the IPM as well when the interrupt with the highest
priority has to be identified.
In case classic and adapter interrupts with the same ISC are
pending, the classic interrupt will be returned first.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Wed, 14 Jun 2017 11:21:32 +0000 (13:21 +0200)]
KVM: s390: add GISA interrupts to FLIC ioctl interface
Pending interrupts marked in the GISA IPM are required to
become part of the answer of ioctl KVM_DEV_FLIC_GET_ALL_IRQS.
The ioctl KVM_DEV_FLIC_ENQUEUE is already capable to enqueue
adapter interrupts when a GISA is present.
With ioctl KVM_DEV_FLIC_CLEAR_IRQS the GISA IPM wil be cleared
now as well.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Pierre Morel <pmorel@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Thu, 31 Aug 2017 09:10:28 +0000 (11:10 +0200)]
KVM: s390: abstract adapter interruption word generation from ISC
The function isc_to_int_word() allows the generation of interruption
words for adapter interrupts.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Mon, 12 Jun 2017 12:15:19 +0000 (14:15 +0200)]
KVM: s390: exploit GISA and AIV for emulated interrupts
The adapter interruption virtualization (AIV) facility is an
optional facility that comes with functionality expected to increase
the performance of adapter interrupt handling for both emulated and
passed-through adapter interrupts. With AIV, adapter interrupts can be
delivered to the guest without exiting SIE.
This patch provides some preparations for using AIV for emulated adapter
interrupts (including virtio) if it's available. When using AIV, the
interrupts are delivered at the so called GISA by setting the bit
corresponding to its Interruption Subclass (ISC) in the Interruption
Pending Mask (IPM) instead of inserting a node into the floating interrupt
list.
To keep the change reasonably small, the handling of this new state is
deferred in get_all_floating_irqs and handle_tpi. This patch concentrates
on the code handling enqueuement of emulated adapter interrupts, and their
delivery to the guest.
Note that care is still required for adapter interrupts using AIV,
because there is no guarantee that AIV is going to deliver the adapter
interrupts pending at the GISA (consider all vcpus idle). When delivering
GISA adapter interrupts by the host (usual mechanism) special attention
is required to honor interrupt priorities.
Empirical results show that the time window between making an interrupt
pending at the GISA and doing kvm_s390_deliver_pending_interrupts is
sufficient for a guest with at least moderate cpu activity to get adapter
interrupts delivered within the SIE, and potentially save some SIE exits
(if not other deliverable interrupts).
The code will be activated with a follow-up patch.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Mon, 10 Jul 2017 09:03:42 +0000 (11:03 +0200)]
s390/css: indicate the availability of the AIV facility
The patch adds an indication for the presence Adapter Interruption
Virtualization facility (AIV) of the general channel subsystem
characteristics.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Acked-by: Cornelia Huck <cohuck@redhat.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
[change wording]
Michael Mueller [Mon, 12 Jun 2017 10:37:57 +0000 (12:37 +0200)]
KVM: s390: implement GISA IPM related primitives
The patch implements routines to access the GISA to test and modify
its Interruption Pending Mask (IPM) from the host side.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Pierre Morel <pmorel@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Tue, 30 May 2017 12:26:02 +0000 (14:26 +0200)]
KVM: s390: define GISA format-0 data structure
In preperation to support pass-through adapter interrupts, the Guest
Interruption State Area (GISA) and the Adapter Interruption Virtualization
(AIV) features will be introduced here.
This patch introduces format-0 GISA (that is defines the struct describing
the GISA, allocates storage for it, and introduces fields for the
GISA address in kvm_s390_sie_block and kvm_s390_vsie).
As the GISA requires storage below 2GB, it is put in sie_page2, which is
already allocated in ZONE_DMA. In addition, The GISA requires alignment to
its integral boundary. This is already naturally aligned via the
padding in the sie_page2.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Pierre Morel <pmorel@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Michael Mueller [Thu, 29 Jun 2017 16:39:27 +0000 (18:39 +0200)]
KVM: s390: reverse bit ordering of irqs in pending mask
This patch prepares a simplification of bit operations between the irq
pending mask for emulated interrupts and the Interruption Pending Mask
(IPM) which is part of the Guest Interruption State Area (GISA), a feature
that allows interrupt delivery to guests by means of the SIE instruction.
Without that change, a bit-wise *or* operation on parts of these two masks
would either require a look-up table of size 256 bytes to map the IPM
to the emulated irq pending mask bit orientation (all bits mirrored at half
byte) or a sequence of up to 8 condidional branches to perform tests of
single bit positions. Both options are to be rejected either by performance
or space utilization reasons.
Beyond that this change will be transparent.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Pierre Morel <pmorel@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
KVM: s390: add vcpu stat counters for many instruction
The overall instruction counter is larger than the sum of the
single counters. We should try to catch all instruction handlers
to make this match the summary counter.
Let us add sck,tb,sske,iske,rrbe,tb,tpi,tsch,lpsw,pswe....
and remove other unused ones.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Acked-by: Janosch Frank <frankja@linux.vnet.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com>
We never call it with anything but PROT_READ. This is a left over from
an old prototype. For creation of shadow page tables, we always only
have to protect the original table in guest memory from write accesses,
so we can properly invalidate the shadow on writes. Other protections
are not needed.
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20180123212618.32611-1-david@redhat.com> Reviewed-by: Janosch Frank <frankja@linux.vnet.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
KVM: s390: vsie: use READ_ONCE to access some SCB fields
Another VCPU might try to modify the SCB while we are creating the
shadow SCB. In general this is no problem - unless the compiler decides
to not load values once, but e.g. twice.
For us, this is only relevant when checking/working with such values.
E.g. the prefix value, the mso, state of transactional execution and
addresses of satellite blocks.
E.g. if we blindly forward values (e.g. general purpose registers or
execution controls after masking), we don't care.
Leaving unpin_blocks() untouched for now, will handle it separately.
The worst thing right now that I can see would be a missed prefix
un/remap (mso, prefix, tx) or using wrong guest addresses. Nothing
critical, but let's try to avoid unpredictable behavior.
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20180116171526.12343-2-david@redhat.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Acked-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
James Morse [Mon, 22 Jan 2018 18:19:06 +0000 (18:19 +0000)]
KVM: arm/arm64: Handle CPU_PM_ENTER_FAILED
cpu_pm_enter() calls the pm notifier chain with CPU_PM_ENTER, then if
there is a failure: CPU_PM_ENTER_FAILED.
When KVM receives CPU_PM_ENTER it calls cpu_hyp_reset() which will
return us to the hyp-stub. If we subsequently get a CPU_PM_ENTER_FAILED,
KVM does nothing, leaving the CPU running with the hyp-stub, at odds
with kvm_arm_hardware_enabled.
Add CPU_PM_ENTER_FAILED as a fallthrough for CPU_PM_EXIT, this reloads
KVM based on kvm_arm_hardware_enabled. This is safe even if CPU_PM_ENTER
never gets as far as KVM, as cpu_hyp_reinit() calls cpu_hyp_reset()
to make sure the hyp-stub is loaded before reloading KVM.
Fixes: 67f691976662 ("arm64: kvm: allows kvm cpu hotplug") Cc: <stable@vger.kernel.org> # v4.7+ CC: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: James Morse <james.morse@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Janosch Frank [Wed, 13 Dec 2017 12:53:22 +0000 (13:53 +0100)]
s390/mm: Remove superfluous parameter
It seems it hasn't even been used before the last cleanup and was
overlooked.
Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Message-Id: <1513169613-13509-12-git-send-email-frankja@linux.vnet.ibm.com> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Christoffer Dall [Wed, 17 Jan 2018 11:35:27 +0000 (12:35 +0100)]
arm64: mm: Add additional parameter to uaccess_ttbr0_disable
Add an extra temporary register parameter to uaccess_ttbr0_disable which
is about to be required for arm64 PAN support.
This patch doesn't introduce any functional change but ensures that the
kernel compiles once the KVM/ARM tree is merged with the arm64 tree by
ensuring a trivially mergable conflict with commit 6b88a32c7af68895134872cdec3b6bfdb532d94e
("arm64: kpti: Fix the interaction between ASID switching and software PAN").
Cc: Will Deacon <will.deacon@arm.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Acked-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Paolo Bonzini [Wed, 20 Dec 2017 23:47:55 +0000 (00:47 +0100)]
KVM: VMX: introduce X2APIC_MSR macro
Remove duplicate expression in nested_vmx_prepare_msr_bitmap, and make
the register names clearer in hardware_setup.
Suggested-by: Jim Mattson <jmattson@google.com> Reviewed-by: Jim Mattson <jmattson@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
[Resolved rebase conflict after removing Intel PT. - Radim] Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Paolo Bonzini [Wed, 13 Dec 2017 13:16:30 +0000 (14:16 +0100)]
KVM: vmx: speed up MSR bitmap merge
The bulk of the MSR bitmap is either immutable, or can be copied from
the L1 bitmap. By initializing it at VMXON time, and copying the mutable
parts one long at a time on vmentry (rather than one bit), about 4000
clock cycles (30%) can be saved on a nested VMLAUNCH/VMRESUME.
The resulting for loop only has four iterations, so it is cheap enough
to reinitialize the MSR write bitmaps on every iteration, and it makes
the code simpler.
Suggested-by: Jim Mattson <jmattson@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Paolo Bonzini [Wed, 20 Dec 2017 10:32:16 +0000 (11:32 +0100)]
KVM: vmx: simplify MSR bitmap setup
The APICv-enabled MSR bitmap is a superset of the APICv-disabled bitmap.
Make that obvious in vmx_disable_intercept_msr_x2apic.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
[Resolved rebase conflict after removing Intel PT. - Radim] Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Paolo Bonzini [Wed, 20 Dec 2017 13:05:21 +0000 (14:05 +0100)]
KVM: nVMX: initialize more non-shadowed fields in prepare_vmcs02_full
These fields are also simple copies of the data in the vmcs12 struct.
For some of them, prepare_vmcs02 was skipping the copy when the field
was unused. In prepare_vmcs02_full, we copy them always as long as the
field exists on the host, because the corresponding execution control
might be one of the shadowed fields.
Optimization opportunities remain for MSRs that, depending on the
entry/exit controls, have to be copied from either the vmcs01 or
the vmcs12: EFER (whose value is partly stored in the entry controls
too), PAT, DEBUGCTL (and also DR7). Before moving these three and
the entry/exit controls to prepare_vmcs02_full, KVM would have to set
dirty_vmcs12 on writes to the L1 MSRs.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Paolo Bonzini [Wed, 20 Dec 2017 12:55:39 +0000 (13:55 +0100)]
KVM: nVMX: track dirty state of non-shadowed VMCS fields
VMCS12 fields that are not handled through shadow VMCS are rarely
written, and thus they are also almost constant in the vmcs02. We can
thus optimize prepare_vmcs02 by skipping all the work for non-shadowed
fields in the common case.
This patch introduces the (pretty simple) tracking infrastructure; the
next patches will move work to prepare_vmcs02_full and save a few hundred
clock cycles per VMRESUME on a Haswell Xeon E5 system:
Jim Mattson [Fri, 22 Dec 2017 20:13:13 +0000 (12:13 -0800)]
kvm: vmx: Reduce size of vmcs_field_to_offset_table
The vmcs_field_to_offset_table was a rather sparse table of short
integers with a maximum index of 0x6c16, amounting to 55342 bytes. Now
that we are considering support for multiple VMCS12 formats, it would
be unfortunate to replicate that large, sparse table. Rotating the
field encoding (as a 16-bit integer) left by 6 reduces that table to
5926 bytes.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Jim Mattson <jmattson@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Jim Mattson [Fri, 22 Dec 2017 20:12:16 +0000 (12:12 -0800)]
kvm: vmx: Change vmcs_field_type to vmcs_field_width
Per the SDM, "[VMCS] Fields are grouped by width (16-bit, 32-bit,
etc.) and type (guest-state, host-state, etc.)." Previously, the width
was indicated by vmcs_field_type. To avoid confusion when we start
dealing with both field width and field type, change vmcs_field_type
to vmcs_field_width.
Signed-off-by: Jim Mattson <jmattson@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Paolo Bonzini [Wed, 13 Dec 2017 11:58:02 +0000 (12:58 +0100)]
KVM: VMX: optimize shadow VMCS copying
Because all fields can be read/written with a single vmread/vmwrite on
64-bit kernels, the switch statements in copy_vmcs12_to_shadow and
copy_shadow_to_vmcs12 are unnecessary.
What I did in this patch is to copy the two parts of 64-bit fields
separately on 32-bit kernels, to keep all complicated #ifdef-ery
in init_vmcs_shadow_fields. The disadvantage is that 64-bit fields
have to be listed separately in shadow_read_only/read_write_fields,
but those are few and we can validate the arrays when building the
VMREAD and VMWRITE bitmaps. This saves a few hundred clock cycles
per nested vmexit.
However there is still a "switch" in vmcs_read_any and vmcs_write_any.
So, while at it, this patch reorders the fields by type, hoping that
the branch predictor appreciates it.
Cc: Jim Mattson <jmattson@google.com> Cc: Wanpeng Li <wanpeng.li@hotmail.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Paolo Bonzini [Wed, 13 Dec 2017 10:05:19 +0000 (11:05 +0100)]
KVM: vmx: shadow more fields that are read/written on every vmexits
Compared to when VMCS shadowing was added to KVM, we are reading/writing
a few more fields: the PML index, the interrupt status and the preemption
timer value. The first two are because we are exposing more features
to nested guests, the preemption timer is simply because we have grown
a new optimization. Adding them to the shadow VMCS field lists reduces
the cost of a vmexit by about 1000 clock cycles for each field that exists
on bare metal.
On the other hand, the guest BNDCFGS and TSC offset are not written on
fast paths, so remove them.
Suggested-by: Jim Mattson <jmattson@google.com> Cc: Jim Mattson <jmattson@google.com> Cc: Wanpeng Li <wanpeng.li@hotmail.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Liran Alon [Thu, 9 Nov 2017 18:27:20 +0000 (20:27 +0200)]
KVM: nVMX: Fix races when sending nested PI while dest enters/leaves L2
Consider the following scenario:
1. CPU A calls vmx_deliver_nested_posted_interrupt() to send an IPI
to CPU B via virtual posted-interrupt mechanism.
2. CPU B is currently executing L2 guest.
3. vmx_deliver_nested_posted_interrupt() calls
kvm_vcpu_trigger_posted_interrupt() which will note that
vcpu->mode == IN_GUEST_MODE.
4. Assume that before CPU A sends the physical POSTED_INTR_NESTED_VECTOR
IPI, CPU B exits from L2 to L0 during event-delivery
(valid IDT-vectoring-info).
5. CPU A now sends the physical IPI. The IPI is received in host and
it's handler (smp_kvm_posted_intr_nested_ipi()) does nothing.
6. Assume that before CPU A sets pi_pending=true and KVM_REQ_EVENT,
CPU B continues to run in L0 and reach vcpu_enter_guest(). As
KVM_REQ_EVENT is not set yet, vcpu_enter_guest() will continue and resume
L2 guest.
7. At this point, CPU A sets pi_pending=true and KVM_REQ_EVENT but
it's too late! CPU B already entered L2 and KVM_REQ_EVENT will only be
consumed at next L2 entry!
Another scenario to consider:
1. CPU A calls vmx_deliver_nested_posted_interrupt() to send an IPI
to CPU B via virtual posted-interrupt mechanism.
2. Assume that before CPU A calls kvm_vcpu_trigger_posted_interrupt(),
CPU B is at L0 and is about to resume into L2. Further assume that it is
in vcpu_enter_guest() after check for KVM_REQ_EVENT.
3. At this point, CPU A calls kvm_vcpu_trigger_posted_interrupt() which
will note that vcpu->mode != IN_GUEST_MODE. Therefore, do nothing and
return false. Then, will set pi_pending=true and KVM_REQ_EVENT.
4. Now CPU B continue and resumes into L2 guest without processing
the posted-interrupt until next L2 entry!
To fix both issues, we just need to change
vmx_deliver_nested_posted_interrupt() to set pi_pending=true and
KVM_REQ_EVENT before calling kvm_vcpu_trigger_posted_interrupt().
It will fix the first scenario by chaging step (6) to note that
KVM_REQ_EVENT and pi_pending=true and therefore process
nested posted-interrupt.
It will fix the second scenario by two possible ways:
1. If kvm_vcpu_trigger_posted_interrupt() is called while CPU B has changed
vcpu->mode to IN_GUEST_MODE, physical IPI will be sent and will be received
when CPU resumes into L2.
2. If kvm_vcpu_trigger_posted_interrupt() is called while CPU B hasn't yet
changed vcpu->mode to IN_GUEST_MODE, then after CPU B will change
vcpu->mode it will call kvm_request_pending() which will return true and
therefore force another round of vcpu_enter_guest() which will note that
KVM_REQ_EVENT and pi_pending=true and therefore process nested
posted-interrupt.
Cc: stable@vger.kernel.org Fixes: 705699a13994 ("KVM: nVMX: Enable nested posted interrupt processing") Signed-off-by: Liran Alon <liran.alon@oracle.com> Reviewed-by: Nikita Leshenko <nikita.leshchenko@oracle.com> Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
[Add kvm_vcpu_kick to also handle the case where L1 doesn't intercept L2 HLT
and L2 executes HLT instruction. - Paolo] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Liran Alon [Sun, 24 Dec 2017 16:12:56 +0000 (18:12 +0200)]
KVM: nVMX: Fix injection to L2 when L1 don't intercept external-interrupts
Before each vmentry to guest, vcpu_enter_guest() calls sync_pir_to_irr()
which calls vmx_hwapic_irr_update() to update RVI.
Currently, vmx_hwapic_irr_update() contains a tweak in case it is called
when CPU is running L2 and L1 don't intercept external-interrupts.
In that case, code injects interrupt directly into L2 instead of
updating RVI.
Besides being hacky (wouldn't expect function updating RVI to also
inject interrupt), it also doesn't handle this case correctly.
The code contains several issues:
1. When code calls kvm_queue_interrupt() it just passes it max_irr which
represents the highest IRR currently pending in L1 LAPIC.
This is problematic as interrupt was injected to guest but it's bit is
still set in LAPIC IRR instead of being cleared from IRR and set in ISR.
2. Code doesn't check if LAPIC PPR is set to accept an interrupt of
max_irr priority. It just checks if interrupts are enabled in guest with
vmx_interrupt_allowed().
To fix the above issues:
1. Simplify vmx_hwapic_irr_update() to just update RVI.
Note that this shouldn't happen when CPU is running L2
(See comment in code).
2. Since now vmx_hwapic_irr_update() only does logic for L1
virtual-interrupt-delivery, inject_pending_event() should be the
one responsible for injecting the interrupt directly into L2.
Therefore, change kvm_cpu_has_injectable_intr() to check L1
LAPIC when CPU is running L2.
3. Change vmx_sync_pir_to_irr() to set KVM_REQ_EVENT when L1
has a pending injectable interrupt.
Liran Alon [Sun, 24 Dec 2017 16:12:55 +0000 (18:12 +0200)]
KVM: nVMX: Re-evaluate L1 pending events when running L2 and L1 got posted-interrupt
In case posted-interrupt was delivered to CPU while it is in host
(outside guest), then posted-interrupt delivery will be done by
calling sync_pir_to_irr() at vmentry after interrupts are disabled.
sync_pir_to_irr() will check vmx->pi_desc.control ON bit and if
set, it will sync vmx->pi_desc.pir to IRR and afterwards update RVI to
ensure virtual-interrupt-delivery will dispatch interrupt to guest.
However, it is possible that L1 will receive a posted-interrupt while
CPU runs at host and is about to enter L2. In this case, the call to
sync_pir_to_irr() will indeed update the L1's APIC IRR but
vcpu_enter_guest() will then just resume into L2 guest without
re-evaluating if it should exit from L2 to L1 as a result of this
new pending L1 event.
To address this case, if sync_pir_to_irr() has a new L1 injectable
interrupt and CPU is running L2, we force exit GUEST_MODE which will
result in another iteration of vcpu_run() run loop which will call
kvm_vcpu_running() which will call check_nested_events() which will
handle the pending L1 event properly.
Liran Alon [Sun, 19 Nov 2017 16:25:43 +0000 (18:25 +0200)]
KVM: nVMX: Fix bug of injecting L2 exception into L1
kvm_clear_exception_queue() should clear pending exception.
This also includes exceptions which were only marked pending but not
yet injected. This is because exception.pending is used for both L1
and L2 to determine if an exception should be raised to guest.
Note that an exception which is pending but not yet injected will
be raised again once the guest will be resumed.
Consider the following scenario:
1) L0 KVM with ignore_msrs=false.
2) L1 prepare vmcs12 with the following:
a) No intercepts on MSR (MSR_BITMAP exist and is filled with 0).
b) No intercept for #GP.
c) vmx-preemption-timer is configured.
3) L1 enters into L2.
4) L2 reads an unhandled MSR that exists in MSR_BITMAP
(such as 0x1fff).
L2 RDMSR could be handled as described below:
1) L2 exits to L0 on RDMSR and calls handle_rdmsr().
2) handle_rdmsr() calls kvm_inject_gp() which sets
KVM_REQ_EVENT, exception.pending=true and exception.injected=false.
3) vcpu_enter_guest() consumes KVM_REQ_EVENT and calls
inject_pending_event() which calls vmx_check_nested_events()
which sees that exception.pending=true but
nested_vmx_check_exception() returns 0 and therefore does nothing at
this point. However let's assume it later sees vmx-preemption-timer
expired and therefore exits from L2 to L1 by calling
nested_vmx_vmexit().
4) nested_vmx_vmexit() calls prepare_vmcs12()
which calls vmcs12_save_pending_event() but it does nothing as
exception.injected is false. Also prepare_vmcs12() calls
kvm_clear_exception_queue() which does nothing as
exception.injected is already false.
5) We now return from vmx_check_nested_events() with 0 while still
having exception.pending=true!
6) Therefore inject_pending_event() continues
and we inject L2 exception to L1!...
This commit will fix above issue by changing step (4) to
clear exception.pending in kvm_clear_exception_queue().
Fixes: 664f8e26b00c ("KVM: X86: Fix loss of exception which has not yet been injected") Signed-off-by: Liran Alon <liran.alon@oracle.com> Reviewed-by: Nikita Leshenko <nikita.leshchenko@oracle.com> Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com> Signed-off-by: Krish Sadhukhan <krish.sadhukhan@oracle.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Haozhong Zhang [Wed, 20 Dec 2017 07:29:29 +0000 (15:29 +0800)]
KVM: MMU: consider host cache mode in MMIO page check
Some reserved pages, such as those from NVDIMM DAX devices, are not
for MMIO, and can be mapped with cached memory type for better
performance. However, the above check misconceives those pages as
MMIO. Because KVM maps MMIO pages with UC memory type, the
performance of guest accesses to those pages would be harmed.
Therefore, we check the host memory type in addition and only treat
UC/UC-/WC pages as MMIO.
Signed-off-by: Haozhong Zhang <haozhong.zhang@intel.com> Reported-by: Cuevas Escareno, Ivan D <ivan.d.cuevas.escareno@intel.com> Reported-by: Kumar, Karthik <karthik.kumar@intel.com> Reviewed-by: Xiao Guangrong <xiaoguangrong@tencent.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Haozhong Zhang [Wed, 20 Dec 2017 07:29:28 +0000 (15:29 +0800)]
x86/mm: add a function to check if a pfn is UC/UC-/WC
Check whether the PAT memory type of a pfn cannot be overridden by
MTRR UC memory type, i.e. the PAT memory type is UC, UC- or WC. This
function will be used by KVM to distinguish MMIO pfns and give them
UC memory type in the EPT page tables (on Intel processors, EPT
memory types work like MTRRs).
Paolo Bonzini [Tue, 16 Jan 2018 15:34:48 +0000 (16:34 +0100)]
Merge branch 'sev-v9-p2' of https://github.com/codomania/kvm
This part of Secure Encrypted Virtualization (SEV) patch series focuses on KVM
changes required to create and manage SEV guests.
SEV is an extension to the AMD-V architecture which supports running encrypted
virtual machine (VMs) under the control of a hypervisor. Encrypted VMs have their
pages (code and data) secured such that only the guest itself has access to
unencrypted version. Each encrypted VM is associated with a unique encryption key;
if its data is accessed to a different entity using a different key the encrypted
guest's data will be incorrectly decrypted, leading to unintelligible data.
This security model ensures that hypervisor will no longer able to inspect or
alter any guest code or data.
The key management of this feature is handled by a separate processor known as
the AMD Secure Processor (AMD-SP) which is present on AMD SOCs. The SEV Key
Management Specification (see below) provides a set of commands which can be
used by hypervisor to load virtual machine keys through the AMD-SP driver.
The patch series adds a new ioctl in KVM driver (KVM_MEMORY_ENCRYPT_OP). The
ioctl will be used by qemu to issue SEV guest-specific commands defined in Key
Management Specification.
The following links provide additional details:
AMD Memory Encryption white paper:
http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf
AMD64 Architecture Programmer's Manual:
http://support.amd.com/TechDocs/24593.pdf
SME is section 7.10
SEV is section 15.34
SEV Key Management:
http://support.amd.com/TechDocs/55766_SEV-KM API_Specification.pdf
KVM Forum Presentation:
http://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf
SEV Guest BIOS support:
SEV support has been add to EDKII/OVMF BIOS
https://github.com/tianocore/edk2
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Paolo Bonzini [Wed, 13 Dec 2017 12:51:32 +0000 (13:51 +0100)]
KVM: x86: avoid unnecessary XSETBV on guest entry
xsetbv can be expensive when running on nested virtualization, try to
avoid it.
Reviewed-by: Jim Mattson <jmattson@google.com> Reviewed-by: Wanpeng Li <wanpeng.li@hotmail.com> Reviewed-by: Quan Xu <quan.xu0@gmail.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
The testcase sets a watchpoint (with perf_event_open) on a buffer that is
passed to timer_create() as the struct sigevent argument. In timer_create(),
copy_from_user()'s rep movsb triggers the BP. The testcase also sets
the debug registers for the guest.
However, KVM only restores host debug registers when the host has active
watchpoints, which triggers a race condition when running the testcase with
multiple threads. The guest's DR6.BS bit can escape to the host before
another thread invokes timer_create(), and do_debug() complains.
The fix is to respect do_debug()'s dr6 invariant when leaving KVM.
Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Dmitry Vyukov <dvyukov@google.com> Reviewed-by: David Hildenbrand <david@redhat.com> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Wanpeng Li [Wed, 13 Dec 2017 01:33:04 +0000 (17:33 -0800)]
KVM: X86: support paravirtualized help for TLB shootdowns
When running on a virtual machine, IPIs are expensive when the target
CPU is sleeping. Thus, it is nice to be able to avoid them for TLB
shootdowns. KVM can just do the flush via INVVPID on the guest's behalf
the next time the CPU is scheduled.
Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krčmář <rkrcmar@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
[Use "&" to test the bit instead of "==". - Paolo] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Wanpeng Li [Wed, 13 Dec 2017 01:33:02 +0000 (17:33 -0800)]
KVM: X86: use paravirtualized TLB Shootdown
Remote TLB flush does a busy wait which is fine in bare-metal
scenario. But with-in the guest, the vcpus might have been pre-empted or
blocked. In this scenario, the initator vcpu would end up busy-waiting
for a long amount of time; it also consumes CPU unnecessarily to wake
up the target of the shootdown.
This patch set adds support for KVM's new paravirtualized TLB flush;
remote TLB flush does not wait for vcpus that are sleeping, instead
KVM will flush the TLB as soon as the vCPU starts running again.
The improvement is clearly visible when the host is overcommitted; in this
case, the PV TLB flush (in addition to avoiding the wait on the main CPU)
prevents preempted vCPUs from stealing precious execution time from the
running ones.
Testing on a Xeon Gold 6142 2.6GHz 2 sockets, 32 cores, 64 threads,
so 64 pCPUs, and each VM is 64 vCPUs.
"wq" is not used at all. "cpuflags" can be access directly via the vcpu,
just as "float_int" via vcpu->kvm.
While at it, reuse _set_cpuflag() to make the code look nicer.
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20180108193747.10818-1-david@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
make kvmconfig currently does not select CONFIG_S390_GUEST. Since
the virtio-ccw transport depends on CONFIG_S390_GUEST, we want
to add CONFIG_S390_GUEST to kvmconfig.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Acked-by: Cornelia Huck <cohuck@redhat.com>
Michael Mueller [Mon, 20 Nov 2017 09:37:30 +0000 (10:37 +0100)]
KVM: s390: drop use of spin lock in __floating_irq_kick
It is not required to take to a lock to protect access to the cpuflags
of the local interrupt structure of a vcpu as the performed operation
is an atomic_or.
Signed-off-by: Michael Mueller <mimu@linux.vnet.ibm.com> Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
commit a03825bbd0c3 ("KVM: s390: use kvm->created_vcpus") introduced
kvm->created_vcpus to avoid races with the existing kvm->online_vcpus
scheme. One place was "forgotten" and one new place was "added".
Let's fix those.
Reported-by: Halil Pasic <pasic@linux.vnet.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: David Hildenbrand <david@redhat.com> Fixes: 4e0b1ab72b8a ("KVM: s390: gs support for kvm guests") Fixes: a03825bbd0c3 ("KVM: s390: use kvm->created_vcpus")
gmap_mprotect_notify() refuses shadow gmaps. Turns out that
a) gmap_protect_range()
b) gmap_read_table()
c) gmap_pte_op_walk()
Are never called for gmap shadows. And never should be. This dates back
to gmap shadow prototypes where we allowed to call mprotect_notify() on
the gmap shadow (to get notified about the prefix pages getting removed).
This is avoided by always getting notified about any change on the gmap
shadow.
The only real function for walking page tables on shadow gmaps is
gmap_table_walk().
So, essentially, these functions should never get called and
gmap_pte_op_walk() can be cleaned up. Add some checks to callers of
gmap_pte_op_walk().
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20171110151805.7541-1-david@redhat.com> Reviewed-by: Janosch Frank <frankja@linux.vnet.ibm.com> Acked-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Andrew Honig [Wed, 10 Jan 2018 18:12:03 +0000 (10:12 -0800)]
KVM: x86: Add memory barrier on vmcs field lookup
This adds a memory barrier when performing a lookup into
the vmcs_field_to_offset_table. This is related to
CVE-2017-5753.
Signed-off-by: Andrew Honig <ahonig@google.com> Reviewed-by: Jim Mattson <jmattson@google.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
arm64: mm: Add additional parameter to uaccess_ttbr0_enable
Add an extra temporary register parameter to uaccess_ttbr0_enable which
is about to be required for arm64 PAN support.
This patch doesn't introduce any functional change but ensures that the
kernel compiles once the KVM/ARM tree is merged with the arm64 tree by
ensuring a trivially mergable conflict with commit 27a921e75711d924617269e0ba4adb8bae9fd0d1
("arm64: mm: Fix and re-enable ARM64_SW_TTBR0_PAN").
Cc: Will Deacon <will.deacon@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:22 +0000 (17:11 +0100)]
KVM: arm/arm64: Drop vcpu parameter from guest cache maintenance operartions
The vcpu parameter isn't used for anything, and gets in the way of
further cleanups. Let's get rid of it.
Acked-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:21 +0000 (17:11 +0100)]
KVM: arm/arm64: Preserve Exec permission across R/W permission faults
So far, we loose the Exec property whenever we take permission
faults, as we always reconstruct the PTE/PMD from scratch. This
can be counter productive as we can end-up with the following
fault sequence:
X -> RO -> ROX -> RW -> RWX
Instead, we can lookup the existing PTE/PMD and clear the XN bit in the
new entry if it was already cleared in the old one, leadig to a much
nicer fault sequence:
X -> ROX -> RWX
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:20 +0000 (17:11 +0100)]
KVM: arm/arm64: Only clean the dcache on translation fault
The only case where we actually need to perform a dcache maintenance
is when we map the page for the first time, and subsequent permission
faults do not require cache maintenance. Let's make it conditional
on not being a permission fault (and thus a translation fault).
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:19 +0000 (17:11 +0100)]
KVM: arm/arm64: Limit icache invalidation to prefetch aborts
We've so far eagerly invalidated the icache, no matter how
the page was faulted in (data or prefetch abort).
But we can easily track execution by setting the XN bits
in the S2 page tables, get the prefetch abort at HYP and
perform the icache invalidation at that time only.
As for most VMs, the instruction working set is pretty
small compared to the data set, this is likely to save
some traffic (specially as the invalidation is broadcast).
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:18 +0000 (17:11 +0100)]
arm64: KVM: PTE/PMD S2 XN bit definition
As we're about to make S2 page-tables eXecute Never by default,
add the required bits for both PMDs and PTEs.
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:17 +0000 (17:11 +0100)]
arm: KVM: Add optimized PIPT icache flushing
Calling __cpuc_coherent_user_range to invalidate the icache on
a PIPT icache machine has some pointless overhead, as it starts
by cleaning the dcache to the PoU, while we're guaranteed to
have already cleaned it to the PoC.
As KVM is the only user of such a feature, let's implement some
ad-hoc cache flushing in kvm_mmu.h. Should it become useful to
other subsystems, it can be moved to a more global location.
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:16 +0000 (17:11 +0100)]
arm64: KVM: Add invalidate_icache_range helper
We currently tightly couple dcache clean with icache invalidation,
but KVM could do without the initial flush to PoU, as we've
already flushed things to PoC.
Let's introduce invalidate_icache_range which is limited to
invalidating the icache from the linear mapping (and thus
has none of the userspace fault handling complexity), and
wire it in KVM instead of flush_icache_range.
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:15 +0000 (17:11 +0100)]
KVM: arm/arm64: Split dcache/icache flushing
As we're about to introduce opportunistic invalidation of the icache,
let's split dcache and icache flushing.
Acked-by: Christoffer Dall <cdall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Marc Zyngier [Mon, 23 Oct 2017 16:11:14 +0000 (17:11 +0100)]
KVM: arm/arm64: Detangle kvm_mmu.h from kvm_hyp.h
kvm_hyp.h has an odd dependency on kvm_mmu.h, which makes the
opposite inclusion impossible. Let's start with breaking that
useless dependency.
Acked-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Revert "arm64: KVM: Hide PMU from guests when disabled"
Commit 0c0543a128bd1c6a4c8610d0d9d869053fa2fbf5 breaks migration and
introduces a regression with existing userspace because it introduces an
ordering requirement of setting up all VCPU features before writing ID
registers which we didn't have before.
Revert this commit for now until we have a proper fix.
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
The reason I added this documentation originally was that the concept of
"never taking the interrupt", but just use the timer to generate an exit
from the guest, was confusing to most, and we had to explain it several
times over. But as we can clearly see, we've failed to update the
documentation as the code has evolved, and people who need to understand
these details are probably better off reading the code.
Let's lighten our maintenance burden slightly and just get rid of this.
Acked-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Christoffer Dall [Fri, 27 Oct 2017 17:57:51 +0000 (19:57 +0200)]
KVM: arm/arm64: Avoid work when userspace iqchips are not used
We currently check if the VM has a userspace irqchip in several places
along the critical path, and if so, we do some work which is only
required for having an irqchip in userspace. This is unfortunate, as we
could avoid doing any work entirely, if we didn't have to support
irqchip in userspace.
Realizing the userspace irqchip on ARM is mostly a developer or hobby
feature, and is unlikely to be used in servers or other scenarios where
performance is a priority, we can use a refcounted static key to only
check the irqchip configuration when we have at least one VM that uses
an irqchip in userspace.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Christoffer Dall [Fri, 27 Oct 2017 17:34:30 +0000 (19:34 +0200)]
KVM: arm/arm64: Provide a get_input_level for the arch timer
The VGIC can now support the life-cycle of mapped level-triggered
interrupts, and we no longer have to read back the timer state on every
exit from the VM if we had an asserted timer interrupt signal, because
the VGIC already knows if we hit the unlikely case where the guest
disables the timer without ACKing the virtual timer interrupt.
This means we rework a bit of the code to factor out the functionality
to snapshot the timer state from vtimer_save_state(), and we can reuse
this functionality in the sync path when we have an irqchip in
userspace, and also to support our implementation of the
get_input_level() function for the timer.
This change also means that we can no longer rely on the timer's view of
the interrupt line to set the active state, because we no longer
maintain this state for mapped interrupts when exiting from the guest.
Instead, we only set the active state if the virtual interrupt is
active, and otherwise we simply let the timer fire again and raise the
virtual interrupt from the ISR.
Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
KVM: arm/arm64: Support VGIC dist pend/active changes for mapped IRQs
For mapped IRQs (with the HW bit set in the LR) we have to follow some
rules of the architecture. One of these rules is that VM must not be
allowed to deactivate a virtual interrupt with the HW bit set unless the
physical interrupt is also active.
This works fine when injecting mapped interrupts, because we leave it up
to the injector to either set EOImode==1 or manually set the active
state of the physical interrupt.
However, the guest can set virtual interrupt to be pending or active by
writing to the virtual distributor, which could lead to deactivating a
virtual interrupt with the HW bit set without the physical interrupt
being active.
We could set the physical interrupt to active whenever we are about to
enter the VM with a HW interrupt either pending or active, but that
would be really slow, especially on GICv2. So we take the long way
around and do the hard work when needed, which is expected to be
extremely rare.
When the VM sets the pending state for a HW interrupt on the virtual
distributor we set the active state on the physical distributor, because
the virtual interrupt can become active and then the guest can
deactivate it.
When the VM clears the pending state we also clear it on the physical
side, because the injector might otherwise raise the interrupt. We also
clear the physical active state when the virtual interrupt is not
active, since otherwise a SPEND/CPEND sequence from the guest would
prevent signaling of future interrupts.
Changing the state of mapped interrupts from userspace is not supported,
and it's expected that userspace unmaps devices from VFIO before
attempting to set the interrupt state, because the interrupt state is
driven by hardware.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Christoffer Dall [Fri, 27 Oct 2017 17:30:09 +0000 (19:30 +0200)]
KVM: arm/arm64: Support a vgic interrupt line level sample function
The GIC sometimes need to sample the physical line of a mapped
interrupt. As we know this to be notoriously slow, provide a callback
function for devices (such as the timer) which can do this much faster
than talking to the distributor, for example by comparing a few
in-memory values. Fall back to the good old method of poking the
physical GIC if no callback is provided.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Christoffer Dall [Tue, 29 Aug 2017 08:40:44 +0000 (10:40 +0200)]
KVM: arm/arm64: vgic: Support level-triggered mapped interrupts
Level-triggered mapped IRQs are special because we only observe rising
edges as input to the VGIC, and we don't set the EOI flag and therefore
are not told when the level goes down, so that we can re-queue a new
interrupt when the level goes up.
One way to solve this problem is to side-step the logic of the VGIC and
special case the validation in the injection path, but it has the
unfortunate drawback of having to peak into the physical GIC state
whenever we want to know if the interrupt is pending on the virtual
distributor.
Instead, we can maintain the current semantics of a level triggered
interrupt by sort of treating it as an edge-triggered interrupt,
following from the fact that we only observe an asserting edge. This
requires us to be a bit careful when populating the LRs and when folding
the state back in though:
* We lower the line level when populating the LR, so that when
subsequently observing an asserting edge, the VGIC will do the right
thing.
* If the guest never acked the interrupt while running (for example if
it had masked interrupts at the CPU level while running), we have
to preserve the pending state of the LR and move it back to the
line_level field of the struct irq when folding LR state.
If the guest never acked the interrupt while running, but changed the
device state and lowered the line (again with interrupts masked) then
we need to observe this change in the line_level.
Both of the above situations are solved by sampling the physical line
and set the line level when folding the LR back.
* Finally, if the guest never acked the interrupt while running and
sampling the line reveals that the device state has changed and the
line has been lowered, we must clear the physical active state, since
we will otherwise never be told when the interrupt becomes asserted
again.
This has the added benefit of making the timer optimization patches
(https://lists.cs.columbia.edu/pipermail/kvmarm/2017-July/026343.html) a
bit simpler, because the timer code doesn't have to clear the active
state on the sync anymore. It also potentially improves the performance
of the timer implementation because the GIC knows the state or the LR
and only needs to clear the
active state when the pending bit in the LR is still set, where the
timer has to always clear it when returning from running the guest with
an injected timer interrupt.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
The timer logic was designed after a strict idea of modeling an
interrupt line level in software, meaning that only transitions in the
level need to be reported to the VGIC. This works well for the timer,
because the arch timer code is in complete control of the device and can
track the transitions of the line.
However, as we are about to support using the HW bit in the VGIC not
just for the timer, but also for VFIO which cannot track transitions of
the interrupt line, we have to decide on an interface between the GIC
and other subsystems for level triggered mapped interrupts, which both
the timer and VFIO can use.
VFIO only sees an asserting transition of the physical interrupt line,
and tells the VGIC when that happens. That means that part of the
interrupt flow is offloaded to the hardware.
To use the same interface for VFIO devices and the timer, we therefore
have to change the timer (we cannot change VFIO because it doesn't know
the details of the device it is assigning to a VM).
Luckily, changing the timer is simple, we just need to stop 'caching'
the line level, but instead let the VGIC know the state of the timer
every time there is a potential change in the line level, and when the
line level should be asserted from the timer ISR. The VGIC can ignore
extra notifications using its validate mechanism.
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com> Reviewed-by: Andre Przywara <andre.przywara@arm.com> Reviewed-by: Julien Thierry <julien.thierry@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Christoffer Dall [Thu, 14 Sep 2017 18:08:45 +0000 (11:08 -0700)]
KVM: arm/arm64: Factor out functionality to get vgic mmio requester_vcpu
We are about to distinguish between userspace accesses and mmio traps
for a number of the mmio handlers. When the requester vcpu is NULL, it
means we are handling a userspace access.
Factor out the functionality to get the request vcpu into its own
function, mostly so we have a common place to document the semantics of
the return value.
Also take the chance to move the functionality outside of holding a
spinlock and instead explicitly disable and enable preemption. This
supports PREEMPT_RT kernels as well.
Acked-by: Marc Zyngier <marc.zyngier@arm.com> Reviewed-by: Andre Przywara <andre.przywara@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
The __this_cpu_read() and __this_cpu_write() functions already implement
checks for the required preemption levels when using
CONFIG_DEBUG_PREEMPT which gives you nice error messages and such.
Therefore there is no need to explicitly check this using a BUG_ON() in
the code (which we don't do for other uses of per cpu variables either).
Acked-by: Marc Zyngier <marc.zyngier@arm.com> Reviewed-by: Andre Przywara <andre.przywara@arm.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Andrew Jones [Sat, 25 Nov 2017 17:40:31 +0000 (18:40 +0100)]
arm64: KVM: Hide PMU from guests when disabled
Since commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU
features from guests") we can hide cpu features from guests. Apply
this to a long standing issue where guests see a PMU available, but
it's not, because it was not enabled by KVM's userspace.
Signed-off-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Paolo Bonzini [Tue, 12 Dec 2017 16:41:34 +0000 (17:41 +0100)]
KVM: introduce kvm_arch_vcpu_async_ioctl
After the vcpu_load/vcpu_put pushdown, the handling of asynchronous VCPU
ioctl is already much clearer in that it is obvious that they bypass
vcpu_load and vcpu_put.
However, it is still not perfect in that the different state of the VCPU
mutex is still hidden in the caller. Separate those ioctls into a new
function kvm_arch_vcpu_async_ioctl that returns -ENOIOCTLCMD for more
"traditional" synchronous ioctls.
Cc: James Hogan <jhogan@kernel.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Suggested-by: Cornelia Huck <cohuck@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
KVM: Move vcpu_load to arch-specific kvm_arch_vcpu_ioctl
Move the calls to vcpu_load() and vcpu_put() in to the architecture
specific implementations of kvm_arch_vcpu_ioctl() which dispatches
further architecture-specific ioctls on to other functions.
Some architectures support asynchronous vcpu ioctls which cannot call
vcpu_load() or take the vcpu->mutex, because that would prevent
concurrent execution with a running VCPU, which is the intended purpose
of these ioctls, for example because they inject interrupts.
We repeat the separate checks for these specifics in the architecture
code for MIPS, S390 and PPC, and avoid taking the vcpu->mutex and
calling vcpu_load for these ioctls.
Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
projects / linux.git / log