Initialize the default ID register values upon the first call to
KVM_ARM_VCPU_INIT. The vCPU feature flags are finalized at that point,
so it is possible to determine the maximum feature set supported by a
particular VM configuration. Do nothing with these values for now, as we
need to rework the plumbing of what's already writable to be compatible
with the generic infrastructure.
Co-developed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Link: https://lore.kernel.org/r/20230609190054.1542113-7-oliver.upton@linux.dev
[Oliver: Hoist everything into KVM_ARM_VCPU_INIT time, so the features
are final]
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
KVM allows userspace to write an IMPDEF PMU version to the corresponding
32bit and 64bit ID register fields for the sake of backwards
compatibility with kernels that lacked commit 3d0dba5764 ("KVM: arm64:
PMU: Move the ID_AA64DFR0_EL1.PMUver limit to VM creation"). Plumbing
that IMPDEF PMU version through to the gues is getting in the way of
progress, and really doesn't any sense in the first place.
Bite the bullet and reinterpret the IMPDEF PMU version as NI (0) for
userspace writes. Additionally, spill the dirty details into a comment.
Link: https://lore.kernel.org/r/20230609190054.1542113-5-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
To date KVM has allowed userspace to construct asymmetric VMs where
particular features may only be supported on a subset of vCPUs. This
wasn't really the intened usage pattern, and it is a total pain in the
ass to keep working in the kernel. What's more, this is at odds with CPU
features in host userspace, where asymmetric features are largely hidden
or disabled.
It's time to put an end to the whole game. Require all vCPUs in the VM
to have the same feature set, rejecting deviants in the
KVM_ARM_VCPU_INIT ioctl. Preserve some of the vestiges of per-vCPU
feature flags in case we need to reinstate the old behavior for some
limited configurations. Yes, this is a sign of cowardice around a
user-visibile change.
Hoist all of the 32-bit limitations into kvm_vcpu_init_check_features()
to avoid nested attempts to acquire the config_lock, which won't end
well.
Link: https://lore.kernel.org/r/20230609190054.1542113-4-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
kvm_vcpu_set_target() iteratively sanitises and copies feature flags in
one go. This is rather odd, especially considering the fact that bitmap
accessors can do the heavy lifting. A subsequent change will make vCPU
features VM-wide, and fitting that into the present implementation is
just a chore.
Rework the whole thing to use bitmap accessors to sanitise and copy
flags.
Link: https://lore.kernel.org/r/20230609190054.1542113-2-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Our standard scheme for naming the constants for bitfields in system
registers includes _ELx in the name but not the SYS_, update the
constants for OSL[AS]R_EL1 to follow this convention.
Reviewed-by: Shaoqin Huang <shahuang@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20230419-arm64-syreg-gen-v2-3-4c6add1f6257@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Define the new system registers that PIE introduces and context switch them.
The PIE feature is still hidden from the ID register, and not exposed to a VM.
Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Zenghui Yu <yuzenghui@huawei.com>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230606145859.697944-10-joey.gouly@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Define the new system register TCR2_EL1 and context switch it.
Signed-off-by: Joey Gouly <joey.gouly@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Zenghui Yu <yuzenghui@huawei.com>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230606145859.697944-9-joey.gouly@arm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Currently, with VHE, KVM sets ER, CR, SW and EN bits of
PMUSERENR_EL0 to 1 on vcpu_load(), and saves and restores
the register value for the host on vcpu_load() and vcpu_put().
If the value of those bits are cleared on a pCPU with a vCPU
loaded (armv8pmu_start() would do that when PMU counters are
programmed for the guest), PMU access from the guest EL0 might
be trapped to the guest EL1 directly regardless of the current
PMUSERENR_EL0 value of the vCPU.
Fix this by not letting armv8pmu_start() overwrite PMUSERENR_EL0
on the pCPU where PMUSERENR_EL0 for the guest is loaded, and
instead updating the saved shadow register value for the host
so that the value can be restored on vcpu_put() later.
While vcpu_{put,load}() are manipulating PMUSERENR_EL0, disable
IRQs to prevent a race condition between these processes and IPIs
that attempt to update PMUSERENR_EL0 for the host EL0.
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Suggested-by: Marc Zyngier <maz@kernel.org>
Fixes: 83a7a4d643 ("arm64: perf: Enable PMU counter userspace access for perf event")
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230603025035.3781797-3-reijiw@google.com
Probe FF-A during pKVM initialisation so that we can detect any
inconsistencies in the version or partition ID early on.
Signed-off-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20230523101828.7328-3-will@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Add a capability for userspace to specify the eager split chunk size.
The chunk size specifies how many pages to break at a time, using a
single allocation. Bigger the chunk size, more pages need to be
allocated ahead of time.
Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Link: https://lore.kernel.org/r/20230426172330.1439644-6-ricarkol@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
* More phys_to_virt conversions
* Improvement of AP management for VSIE (nested virtualization)
ARM64:
* Numerous fixes for the pathological lock inversion issue that
plagued KVM/arm64 since... forever.
* New framework allowing SMCCC-compliant hypercalls to be forwarded
to userspace, hopefully paving the way for some more features
being moved to VMMs rather than be implemented in the kernel.
* Large rework of the timer code to allow a VM-wide offset to be
applied to both virtual and physical counters as well as a
per-timer, per-vcpu offset that complements the global one.
This last part allows the NV timer code to be implemented on
top.
* A small set of fixes to make sure that we don't change anything
affecting the EL1&0 translation regime just after having having
taken an exception to EL2 until we have executed a DSB. This
ensures that speculative walks started in EL1&0 have completed.
* The usual selftest fixes and improvements.
KVM x86 changes for 6.4:
* Optimize CR0.WP toggling by avoiding an MMU reload when TDP is enabled,
and by giving the guest control of CR0.WP when EPT is enabled on VMX
(VMX-only because SVM doesn't support per-bit controls)
* Add CR0/CR4 helpers to query single bits, and clean up related code
where KVM was interpreting kvm_read_cr4_bits()'s "unsigned long" return
as a bool
* Move AMD_PSFD to cpufeatures.h and purge KVM's definition
* Avoid unnecessary writes+flushes when the guest is only adding new PTEs
* Overhaul .sync_page() and .invlpg() to utilize .sync_page()'s optimizations
when emulating invalidations
* Clean up the range-based flushing APIs
* Revamp the TDP MMU's reaping of Accessed/Dirty bits to clear a single
A/D bit using a LOCK AND instead of XCHG, and skip all of the "handle
changed SPTE" overhead associated with writing the entire entry
* Track the number of "tail" entries in a pte_list_desc to avoid having
to walk (potentially) all descriptors during insertion and deletion,
which gets quite expensive if the guest is spamming fork()
* Disallow virtualizing legacy LBRs if architectural LBRs are available,
the two are mutually exclusive in hardware
* Disallow writes to immutable feature MSRs (notably PERF_CAPABILITIES)
after KVM_RUN, similar to CPUID features
* Overhaul the vmx_pmu_caps selftest to better validate PERF_CAPABILITIES
* Apply PMU filters to emulated events and add test coverage to the
pmu_event_filter selftest
x86 AMD:
* Add support for virtual NMIs
* Fixes for edge cases related to virtual interrupts
x86 Intel:
* Don't advertise XTILE_CFG in KVM_GET_SUPPORTED_CPUID if XTILE_DATA is
not being reported due to userspace not opting in via prctl()
* Fix a bug in emulation of ENCLS in compatibility mode
* Allow emulation of NOP and PAUSE for L2
* AMX selftests improvements
* Misc cleanups
MIPS:
* Constify MIPS's internal callbacks (a leftover from the hardware enabling
rework that landed in 6.3)
Generic:
* Drop unnecessary casts from "void *" throughout kvm_main.c
* Tweak the layout of "struct kvm_mmu_memory_cache" to shrink the struct
size by 8 bytes on 64-bit kernels by utilizing a padding hole
Documentation:
* Fix goof introduced by the conversion to rST
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmRNExkUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroNyjwf+MkzDael9y9AsOZoqhEZ5OsfQYJ32
Im5ZVYsPRU2K5TuoWql6meIihgclCj1iIU32qYHa2F1WYt2rZ72rJp+HoY8b+TaI
WvF0pvNtqQyg3iEKUBKPA4xQ6mj7RpQBw86qqiCHmlfNt0zxluEGEPxH8xrWcfhC
huDQ+NUOdU7fmJ3rqGitCvkUbCuZNkw3aNPR8dhU8RAWrwRzP2hBOmdxIeo81WWY
XMEpJSijbGpXL9CvM0Jz9nOuMJwZwCCBGxg1vSQq0xTfLySNMxzvWZC2GFaBjucb
j0UOQ7yE0drIZDVhd3sdNslubXXU6FcSEzacGQb9aigMUon3Tem9SHi7Kw==
=S2Hq
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"s390:
- More phys_to_virt conversions
- Improvement of AP management for VSIE (nested virtualization)
ARM64:
- Numerous fixes for the pathological lock inversion issue that
plagued KVM/arm64 since... forever.
- New framework allowing SMCCC-compliant hypercalls to be forwarded
to userspace, hopefully paving the way for some more features being
moved to VMMs rather than be implemented in the kernel.
- Large rework of the timer code to allow a VM-wide offset to be
applied to both virtual and physical counters as well as a
per-timer, per-vcpu offset that complements the global one. This
last part allows the NV timer code to be implemented on top.
- A small set of fixes to make sure that we don't change anything
affecting the EL1&0 translation regime just after having having
taken an exception to EL2 until we have executed a DSB. This
ensures that speculative walks started in EL1&0 have completed.
- The usual selftest fixes and improvements.
x86:
- Optimize CR0.WP toggling by avoiding an MMU reload when TDP is
enabled, and by giving the guest control of CR0.WP when EPT is
enabled on VMX (VMX-only because SVM doesn't support per-bit
controls)
- Add CR0/CR4 helpers to query single bits, and clean up related code
where KVM was interpreting kvm_read_cr4_bits()'s "unsigned long"
return as a bool
- Move AMD_PSFD to cpufeatures.h and purge KVM's definition
- Avoid unnecessary writes+flushes when the guest is only adding new
PTEs
- Overhaul .sync_page() and .invlpg() to utilize .sync_page()'s
optimizations when emulating invalidations
- Clean up the range-based flushing APIs
- Revamp the TDP MMU's reaping of Accessed/Dirty bits to clear a
single A/D bit using a LOCK AND instead of XCHG, and skip all of
the "handle changed SPTE" overhead associated with writing the
entire entry
- Track the number of "tail" entries in a pte_list_desc to avoid
having to walk (potentially) all descriptors during insertion and
deletion, which gets quite expensive if the guest is spamming
fork()
- Disallow virtualizing legacy LBRs if architectural LBRs are
available, the two are mutually exclusive in hardware
- Disallow writes to immutable feature MSRs (notably
PERF_CAPABILITIES) after KVM_RUN, similar to CPUID features
- Overhaul the vmx_pmu_caps selftest to better validate
PERF_CAPABILITIES
- Apply PMU filters to emulated events and add test coverage to the
pmu_event_filter selftest
- AMD SVM:
- Add support for virtual NMIs
- Fixes for edge cases related to virtual interrupts
- Intel AMX:
- Don't advertise XTILE_CFG in KVM_GET_SUPPORTED_CPUID if
XTILE_DATA is not being reported due to userspace not opting in
via prctl()
- Fix a bug in emulation of ENCLS in compatibility mode
- Allow emulation of NOP and PAUSE for L2
- AMX selftests improvements
- Misc cleanups
MIPS:
- Constify MIPS's internal callbacks (a leftover from the hardware
enabling rework that landed in 6.3)
Generic:
- Drop unnecessary casts from "void *" throughout kvm_main.c
- Tweak the layout of "struct kvm_mmu_memory_cache" to shrink the
struct size by 8 bytes on 64-bit kernels by utilizing a padding
hole
Documentation:
- Fix goof introduced by the conversion to rST"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (211 commits)
KVM: s390: pci: fix virtual-physical confusion on module unload/load
KVM: s390: vsie: clarifications on setting the APCB
KVM: s390: interrupt: fix virtual-physical confusion for next alert GISA
KVM: arm64: Have kvm_psci_vcpu_on() use WRITE_ONCE() to update mp_state
KVM: arm64: Acquire mp_state_lock in kvm_arch_vcpu_ioctl_vcpu_init()
KVM: selftests: Test the PMU event "Instructions retired"
KVM: selftests: Copy full counter values from guest in PMU event filter test
KVM: selftests: Use error codes to signal errors in PMU event filter test
KVM: selftests: Print detailed info in PMU event filter asserts
KVM: selftests: Add helpers for PMC asserts in PMU event filter test
KVM: selftests: Add a common helper for the PMU event filter guest code
KVM: selftests: Fix spelling mistake "perrmited" -> "permitted"
KVM: arm64: vhe: Drop extra isb() on guest exit
KVM: arm64: vhe: Synchronise with page table walker on MMU update
KVM: arm64: pkvm: Document the side effects of kvm_flush_dcache_to_poc()
KVM: arm64: nvhe: Synchronise with page table walker on TLBI
KVM: arm64: Handle 32bit CNTPCTSS traps
KVM: arm64: nvhe: Synchronise with page table walker on vcpu run
KVM: arm64: vgic: Don't acquire its_lock before config_lock
KVM: selftests: Add test to verify KVM's supported XCR0
...
- Numerous fixes for the pathological lock inversion issue that
plagued KVM/arm64 since... forever.
- New framework allowing SMCCC-compliant hypercalls to be forwarded
to userspace, hopefully paving the way for some more features
being moved to VMMs rather than be implemented in the kernel.
- Large rework of the timer code to allow a VM-wide offset to be
applied to both virtual and physical counters as well as a
per-timer, per-vcpu offset that complements the global one.
This last part allows the NV timer code to be implemented on
top.
- A small set of fixes to make sure that we don't change anything
affecting the EL1&0 translation regime just after having having
taken an exception to EL2 until we have executed a DSB. This
ensures that speculative walks started in EL1&0 have completed.
- The usual selftest fixes and improvements.
-----BEGIN PGP SIGNATURE-----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=Bhta
-----END PGP SIGNATURE-----
Merge tag 'kvmarm-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for 6.4
- Numerous fixes for the pathological lock inversion issue that
plagued KVM/arm64 since... forever.
- New framework allowing SMCCC-compliant hypercalls to be forwarded
to userspace, hopefully paving the way for some more features
being moved to VMMs rather than be implemented in the kernel.
- Large rework of the timer code to allow a VM-wide offset to be
applied to both virtual and physical counters as well as a
per-timer, per-vcpu offset that complements the global one.
This last part allows the NV timer code to be implemented on
top.
- A small set of fixes to make sure that we don't change anything
affecting the EL1&0 translation regime just after having having
taken an exception to EL2 until we have executed a DSB. This
ensures that speculative walks started in EL1&0 have completed.
- The usual selftest fixes and improvements.
* kvm-arm64/smccc-filtering:
: .
: SMCCC call filtering and forwarding to userspace, courtesy of
: Oliver Upton. From the cover letter:
:
: "The Arm SMCCC is rather prescriptive in regards to the allocation of
: SMCCC function ID ranges. Many of the hypercall ranges have an
: associated specification from Arm (FF-A, PSCI, SDEI, etc.) with some
: room for vendor-specific implementations.
:
: The ever-expanding SMCCC surface leaves a lot of work within KVM for
: providing new features. Furthermore, KVM implements its own
: vendor-specific ABI, with little room for other implementations (like
: Hyper-V, for example). Rather than cramming it all into the kernel we
: should provide a way for userspace to handle hypercalls."
: .
KVM: selftests: Fix spelling mistake "KVM_HYPERCAL_EXIT_SMC" -> "KVM_HYPERCALL_EXIT_SMC"
KVM: arm64: Test that SMC64 arch calls are reserved
KVM: arm64: Prevent userspace from handling SMC64 arch range
KVM: arm64: Expose SMC/HVC width to userspace
KVM: selftests: Add test for SMCCC filter
KVM: selftests: Add a helper for SMCCC calls with SMC instruction
KVM: arm64: Let errors from SMCCC emulation to reach userspace
KVM: arm64: Return NOT_SUPPORTED to guest for unknown PSCI version
KVM: arm64: Introduce support for userspace SMCCC filtering
KVM: arm64: Add support for KVM_EXIT_HYPERCALL
KVM: arm64: Use a maple tree to represent the SMCCC filter
KVM: arm64: Refactor hvc filtering to support different actions
KVM: arm64: Start handling SMCs from EL1
KVM: arm64: Rename SMC/HVC call handler to reflect reality
KVM: arm64: Add vm fd device attribute accessors
KVM: arm64: Add a helper to check if a VM has ran once
KVM: x86: Redefine 'longmode' as a flag for KVM_EXIT_HYPERCALL
Signed-off-by: Marc Zyngier <maz@kernel.org>
* kvm-arm64/timer-vm-offsets: (21 commits)
: .
: This series aims at satisfying multiple goals:
:
: - allow a VMM to atomically restore a timer offset for a whole VM
: instead of updating the offset each time a vcpu get its counter
: written
:
: - allow a VMM to save/restore the physical timer context, something
: that we cannot do at the moment due to the lack of offsetting
:
: - provide a framework that is suitable for NV support, where we get
: both global and per timer, per vcpu offsetting, and manage
: interrupts in a less braindead way.
:
: Conflict resolution involves using the new per-vcpu config lock instead
: of the home-grown timer lock.
: .
KVM: arm64: Handle 32bit CNTPCTSS traps
KVM: arm64: selftests: Augment existing timer test to handle variable offset
KVM: arm64: selftests: Deal with spurious timer interrupts
KVM: arm64: selftests: Add physical timer registers to the sysreg list
KVM: arm64: nv: timers: Support hyp timer emulation
KVM: arm64: nv: timers: Add a per-timer, per-vcpu offset
KVM: arm64: Document KVM_ARM_SET_CNT_OFFSETS and co
KVM: arm64: timers: Abstract the number of valid timers per vcpu
KVM: arm64: timers: Fast-track CNTPCT_EL0 trap handling
KVM: arm64: Elide kern_hyp_va() in VHE-specific parts of the hypervisor
KVM: arm64: timers: Move the timer IRQs into arch_timer_vm_data
KVM: arm64: timers: Abstract per-timer IRQ access
KVM: arm64: timers: Rationalise per-vcpu timer init
KVM: arm64: timers: Allow save/restoring of the physical timer
KVM: arm64: timers: Allow userspace to set the global counter offset
KVM: arm64: Expose {un,}lock_all_vcpus() to the rest of KVM
KVM: arm64: timers: Allow physical offset without CNTPOFF_EL2
KVM: arm64: timers: Use CNTPOFF_EL2 to offset the physical timer
arm64: Add HAS_ECV_CNTPOFF capability
arm64: Add CNTPOFF_EL2 register definition
...
Signed-off-by: Marc Zyngier <maz@kernel.org>
Per-vcpu flags are updated using a non-atomic RMW operation.
Which means it is possible to get preempted between the read and
write operations.
Another interesting thing to note is that preemption also updates
flags, as we have some flag manipulation in both the load and put
operations.
It is thus possible to lose information communicated by either
load or put, as the preempted flag update will overwrite the flags
when the thread is resumed. This is specially critical if either
load or put has stored information which depends on the physical
CPU the vcpu runs on.
This results in really elusive bugs, and kudos must be given to
Mostafa for the long hours of debugging, and finally spotting
the problem.
Fix it by disabling preemption during the RMW operation, which
ensures that the state stays consistent. Also upgrade vcpu_get_flag
path to use READ_ONCE() to make sure the field is always atomically
accessed.
Fixes: e87abb73e5 ("KVM: arm64: Add helpers to manipulate vcpu flags among a set")
Reported-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20230418125737.2327972-1-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Maple tree is an efficient B-tree implementation that is intended for
storing non-overlapping intervals. Such a data structure is a good fit
for the SMCCC filter as it is desirable to sparsely allocate the 32 bit
function ID space.
To that end, add a maple tree to kvm_arch and correctly init/teardown
along with the VM. Wire in a test against the hypercall filter for HVCs
which does nothing until the controls are exposed to userspace.
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230404154050.2270077-8-oliver.upton@linux.dev
The test_bit(...) pattern is quite a lot of keystrokes. Replace
existing callsites with a helper.
No functional change intended.
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230404154050.2270077-3-oliver.upton@linux.dev
Emulating EL2 also means emulating the EL2 timers. To do so, we expand
our timer framework to deal with at most 4 timers. At any given time,
two timers are using the HW timers, and the two others are purely
emulated.
The role of deciding which is which at any given time is left to a
mapping function which is called every time we need to make such a
decision.
Reviewed-by: Colton Lewis <coltonlewis@google.com>
Co-developed-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230330174800.2677007-18-maz@kernel.org
Having the timer IRQs duplicated into each vcpu isn't great, and
becomes absolutely awful with NV. So let's move these into
the per-VM arch_timer_vm_data structure.
This simplifies a lot of code, but requires us to introduce a
mutex so that we can reason about userspace trying to change
an interrupt number while another vcpu is running, something
that wasn't really well handled so far.
Reviewed-by: Colton Lewis <coltonlewis@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230330174800.2677007-12-maz@kernel.org
And this is the moment you have all been waiting for: setting the
counter offset from userspace.
We expose a brand new capability that reports the ability to set
the offset for both the virtual and physical sides.
In keeping with the architecture, the offset is expressed as
a delta that is substracted from the physical counter value.
Once this new API is used, there is no going back, and the counters
cannot be written to to set the offsets implicitly (the writes
are instead ignored).
Reviewed-by: Colton Lewis <coltonlewis@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230330174800.2677007-8-maz@kernel.org
Being able to lock/unlock all vcpus in one go is a feature that
only the vgic has enjoyed so far. Let's be brave and expose it
to the world.
Reviewed-by: Colton Lewis <coltonlewis@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230330174800.2677007-7-maz@kernel.org
kvm->lock must be taken outside of the vcpu->mutex. Of course, the
locking documentation for KVM makes this abundantly clear. Nonetheless,
the locking order in KVM/arm64 has been wrong for quite a while; we
acquire the kvm->lock while holding the vcpu->mutex all over the shop.
All was seemingly fine until commit 42a90008f8 ("KVM: Ensure lockdep
knows about kvm->lock vs. vcpu->mutex ordering rule") caught us with our
pants down, leading to lockdep barfing:
======================================================
WARNING: possible circular locking dependency detected
6.2.0-rc7+ #19 Not tainted
------------------------------------------------------
qemu-system-aar/859 is trying to acquire lock:
ffff5aa69269eba0 (&host_kvm->lock){+.+.}-{3:3}, at: kvm_reset_vcpu+0x34/0x274
but task is already holding lock:
ffff5aa68768c0b8 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x8c/0xba0
which lock already depends on the new lock.
Add a dedicated lock to serialize writes to VM-scoped configuration from
the context of a vCPU. Protect the register width flags with the new
lock, thus avoiding the need to grab the kvm->lock while holding
vcpu->mutex in kvm_reset_vcpu().
Cc: stable@vger.kernel.org
Reported-by: Jeremy Linton <jeremy.linton@arm.com>
Link: https://lore.kernel.org/kvmarm/f6452cdd-65ff-34b8-bab0-5c06416da5f6@arm.com/
Tested-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230327164747.2466958-3-oliver.upton@linux.dev
KVM/arm64 had the lock ordering backwards on vcpu->mutex and kvm->lock
from the very beginning. One such example is the way vCPU resets are
handled: the kvm->lock is acquired while handling a guest CPU_ON PSCI
call.
Add a dedicated lock to serialize writes to kvm_vcpu_arch::{mp_state,
reset_state}. Promote all accessors of mp_state to {READ,WRITE}_ONCE()
as readers do not acquire the mp_state_lock. While at it, plug yet
another race by taking the mp_state_lock in the KVM_SET_MP_STATE ioctl
handler.
As changes to MP state are now guarded with a dedicated lock, drop the
kvm->lock acquisition from the PSCI CPU_ON path. Similarly, move the
reader of reset_state outside of the kvm->lock and instead protect it
with the mp_state_lock. Note that writes to reset_state::reset have been
demoted to regular stores as both readers and writers acquire the
mp_state_lock.
While the kvm->lock inversion still exists in kvm_reset_vcpu(), at least
now PSCI CPU_ON no longer depends on it for serializing vCPU reset.
Cc: stable@vger.kernel.org
Tested-by: Jeremy Linton <jeremy.linton@arm.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230327164747.2466958-2-oliver.upton@linux.dev
In case of success, this function returns the amount of handled bytes.
However, this does not work for large values: The function is called
from kvm_arch_vm_ioctl() (which still returns a long), which in turn
is called from kvm_vm_ioctl() in virt/kvm/kvm_main.c. And that function
stores the return value in an "int r" variable. So the upper 32-bits
of the "long" return value are lost there.
KVM ioctl functions should only return "int" values, so let's limit
the amount of bytes that can be requested here to INT_MAX to avoid
the problem with the truncated return value. We can then also change
the return type of the function to "int" to make it clearer that it
is not possible to return a "long" here.
Fixes: f0376edb1d ("KVM: arm64: Add ioctl to fetch/store tags in a guest")
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Message-Id: <20230208140105.655814-5-thuth@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Having a per-vcpu virtual offset is a pain. It needs to be synchronized
on each update, and expands badly to a setup where different timers can
have different offsets, or have composite offsets (as with NV).
So let's start by replacing the use of the CNTVOFF_EL2 shadow register
(which we want to reclaim for NV anyway), and make the virtual timer
carry a pointer to a VM-wide offset.
This simplifies the code significantly. It also addresses two terrible bugs:
- The use of CNTVOFF_EL2 leads to some nice offset corruption
when the sysreg gets reset, as reported by Joey.
- The kvm mutex is taken from a vcpu ioctl, which goes against
the locking rules...
Reported-by: Joey Gouly <joey.gouly@arm.com>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230224173915.GA17407@e124191.cambridge.arm.com
Tested-by: Joey Gouly <joey.gouly@arm.com>
Link: https://lore.kernel.org/r/20230224191640.3396734-1-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
* kvm-arm64/nv-prefix:
: Preamble to NV support, courtesy of Marc Zyngier.
:
: This brings in a set of prerequisite patches for supporting nested
: virtualization in KVM/arm64. Of course, there is a long way to go until
: NV is actually enabled in KVM.
:
: - Introduce cpucap / vCPU feature flag to pivot the NV code on
:
: - Add support for EL2 vCPU register state
:
: - Basic nested exception handling
:
: - Hide unsupported features from the ID registers for NV-capable VMs
KVM: arm64: nv: Use reg_to_encoding() to get sysreg ID
KVM: arm64: nv: Only toggle cache for virtual EL2 when SCTLR_EL2 changes
KVM: arm64: nv: Filter out unsupported features from ID regs
KVM: arm64: nv: Emulate EL12 register accesses from the virtual EL2
KVM: arm64: nv: Allow a sysreg to be hidden from userspace only
KVM: arm64: nv: Emulate PSTATE.M for a guest hypervisor
KVM: arm64: nv: Add accessors for SPSR_EL1, ELR_EL1 and VBAR_EL1 from virtual EL2
KVM: arm64: nv: Handle SMCs taken from virtual EL2
KVM: arm64: nv: Handle trapped ERET from virtual EL2
KVM: arm64: nv: Inject HVC exceptions to the virtual EL2
KVM: arm64: nv: Support virtual EL2 exceptions
KVM: arm64: nv: Handle HCR_EL2.NV system register traps
KVM: arm64: nv: Add nested virt VCPU primitives for vEL2 VCPU state
KVM: arm64: nv: Add EL2 system registers to vcpu context
KVM: arm64: nv: Allow userspace to set PSR_MODE_EL2x
KVM: arm64: nv: Reset VCPU to EL2 registers if VCPU nested virt is set
KVM: arm64: nv: Introduce nested virtualization VCPU feature
KVM: arm64: Use the S2 MMU context to iterate over S2 table
arm64: Add ARM64_HAS_NESTED_VIRT cpufeature
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
* kvm-arm64/misc:
: Miscellaneous updates
:
: - Convert CPACR_EL1_TTA to the new, generated system register
: definitions.
:
: - Serialize toggling CPACR_EL1.SMEN to avoid unexpected exceptions when
: accessing SVCR in the host.
:
: - Avoid quiescing the guest if a vCPU accesses its own redistributor's
: SGIs/PPIs, eliminating the need to IPI. Largely an optimization for
: nested virtualization, as the L1 accesses the affected registers
: rather often.
:
: - Conversion to kstrtobool()
:
: - Common definition of INVALID_GPA across architectures
:
: - Enable CONFIG_USERFAULTFD for CI runs of KVM selftests
KVM: arm64: Fix non-kerneldoc comments
KVM: selftests: Enable USERFAULTFD
KVM: selftests: Remove redundant setbuf()
arm64/sysreg: clean up some inconsistent indenting
KVM: MMU: Make the definition of 'INVALID_GPA' common
KVM: arm64: vgic-v3: Use kstrtobool() instead of strtobool()
KVM: arm64: vgic-v3: Limit IPI-ing when accessing GICR_{C,S}ACTIVER0
KVM: arm64: Synchronize SMEN on vcpu schedule out
KVM: arm64: Kill CPACR_EL1_TTA definition
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
* kvm-arm64/virtual-cache-geometry:
: Virtualized cache geometry for KVM guests, courtesy of Akihiko Odaki.
:
: KVM/arm64 has always exposed the host cache geometry directly to the
: guest, even though non-secure software should never perform CMOs by
: Set/Way. This was slightly wrong, as the cache geometry was derived from
: the PE on which the vCPU thread was running and not a sanitized value.
:
: All together this leads to issues migrating VMs on heterogeneous
: systems, as the cache geometry saved/restored could be inconsistent.
:
: KVM/arm64 now presents 1 level of cache with 1 set and 1 way. The cache
: geometry is entirely controlled by userspace, such that migrations from
: older kernels continue to work.
KVM: arm64: Mark some VM-scoped allocations as __GFP_ACCOUNT
KVM: arm64: Normalize cache configuration
KVM: arm64: Mask FEAT_CCIDX
KVM: arm64: Always set HCR_TID2
arm64/cache: Move CLIDR macro definitions
arm64/sysreg: Add CCSIDR2_EL1
arm64/sysreg: Convert CCSIDR_EL1 to automatic generation
arm64: Allow the definition of UNKNOWN system register fields
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
We can no longer blindly copy the VCPU's PSTATE into SPSR_EL2 and return
to the guest and vice versa when taking an exception to the hypervisor,
because we emulate virtual EL2 in EL1 and therefore have to translate
the mode field from EL2 to EL1 and vice versa.
This requires keeping track of the state we enter the guest, for which
we transiently use a dedicated flag.
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Alexandru Elisei <alexandru.elisei@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230209175820.1939006-15-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Support injecting exceptions and performing exception returns to and
from virtual EL2. This must be done entirely in software except when
taking an exception from vEL0 to vEL2 when the virtual HCR_EL2.{E2H,TGE}
== {1,1} (a VHE guest hypervisor).
[maz: switch to common exception injection framework, illegal exeption
return handling]
Reviewed-by: Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230209175820.1939006-10-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Add the minimal set of EL2 system registers to the vcpu context.
Nothing uses them just yet.
Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230209175820.1939006-7-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Add a new ARM64_HAS_NESTED_VIRT feature to indicate that the
CPU has the ARMv8.3 nested virtualization capability, together
with the 'kvm-arm.mode=nested' command line option.
This will be used to support nested virtualization in KVM.
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Jintack Lim <jintack.lim@linaro.org>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>
[maz: moved the command-line option to kvm-arm.mode]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20230209175820.1939006-2-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Before this change, the cache configuration of the physical CPU was
exposed to vcpus. This is problematic because the cache configuration a
vcpu sees varies when it migrates between vcpus with different cache
configurations.
Fabricate cache configuration from the sanitized value, which holds the
CTR_EL0 value the userspace sees regardless of which physical CPU it
resides on.
CLIDR_EL1 and CCSIDR_EL1 are now writable from the userspace so that
the VMM can restore the values saved with the old kernel.
Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Link: https://lore.kernel.org/r/20230112023852.42012-8-akihiko.odaki@daynix.com
[ Oliver: Squash Marc's fix for CCSIDR_EL1.LineSize when set from userspace ]
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
KVM already has a 'GPA_INVALID' defined as (~(gpa_t)0) in kvm_types.h,
and it is used by ARM code. We do not need another definition of
'INVALID_GPA' for X86 specifically.
Instead of using the common 'GPA_INVALID' for X86, replace it with
'INVALID_GPA', and change the users of 'GPA_INVALID' so that the diff
can be smaller. Also because the name 'INVALID_GPA' tells the user we
are using an invalid GPA, while the name 'GPA_INVALID' is emphasizing
the GPA is an invalid one.
No functional change intended.
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Reviewed-by: Paul Durrant <paul@xen.org>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20230105130127.866171-1-yu.c.zhang@linux.intel.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Always set HCR_TID2 to trap CTR_EL0, CCSIDR2_EL1, CLIDR_EL1, and
CSSELR_EL1. This saves a few lines of code and allows to employ their
access trap handlers for more purposes anticipated by the old
condition for setting HCR_TID2.
Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Link: https://lore.kernel.org/r/20230112023852.42012-6-akihiko.odaki@daynix.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Define pr_fmt using KBUILD_MODNAME for all KVM x86 code so that printks
use consistent formatting across common x86, Intel, and AMD code. In
addition to providing consistent print formatting, using KBUILD_MODNAME,
e.g. kvm_amd and kvm_intel, allows referencing SVM and VMX (and SEV and
SGX and ...) as technologies without generating weird messages, and
without causing naming conflicts with other kernel code, e.g. "SEV: ",
"tdx: ", "sgx: " etc.. are all used by the kernel for non-KVM subsystems.
Opportunistically move away from printk() for prints that need to be
modified anyways, e.g. to drop a manual "kvm: " prefix.
Opportunistically convert a few SGX WARNs that are similarly modified to
WARN_ONCE; in the very unlikely event that the WARNs fire, odds are good
that they would fire repeatedly and spam the kernel log without providing
unique information in each print.
Note, defining pr_fmt yields undesirable results for code that uses KVM's
printk wrappers, e.g. vcpu_unimpl(). But, that's a pre-existing problem
as SVM/kvm_amd already defines a pr_fmt, and thankfully use of KVM's
wrappers is relatively limited in KVM x86 code.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Paul Durrant <paul@xen.org>
Message-Id: <20221130230934.1014142-35-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Drop kvm_arch_hardware_setup() and kvm_arch_hardware_unsetup() now that
all implementations are nops.
No functional change intended.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com> # s390
Acked-by: Anup Patel <anup@brainfault.org>
Message-Id: <20221130230934.1014142-10-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
* Enable the per-vcpu dirty-ring tracking mechanism, together with an
option to keep the good old dirty log around for pages that are
dirtied by something other than a vcpu.
* Switch to the relaxed parallel fault handling, using RCU to delay
page table reclaim and giving better performance under load.
* Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping option,
which multi-process VMMs such as crosvm rely on (see merge commit 382b5b87a9:
"Fix a number of issues with MTE, such as races on the tags being
initialised vs the PG_mte_tagged flag as well as the lack of support
for VM_SHARED when KVM is involved. Patches from Catalin Marinas and
Peter Collingbourne").
* Merge the pKVM shadow vcpu state tracking that allows the hypervisor
to have its own view of a vcpu, keeping that state private.
* Add support for the PMUv3p5 architecture revision, bringing support
for 64bit counters on systems that support it, and fix the
no-quite-compliant CHAIN-ed counter support for the machines that
actually exist out there.
* Fix a handful of minor issues around 52bit VA/PA support (64kB pages
only) as a prefix of the oncoming support for 4kB and 16kB pages.
* Pick a small set of documentation and spelling fixes, because no
good merge window would be complete without those.
s390:
* Second batch of the lazy destroy patches
* First batch of KVM changes for kernel virtual != physical address support
* Removal of a unused function
x86:
* Allow compiling out SMM support
* Cleanup and documentation of SMM state save area format
* Preserve interrupt shadow in SMM state save area
* Respond to generic signals during slow page faults
* Fixes and optimizations for the non-executable huge page errata fix.
* Reprogram all performance counters on PMU filter change
* Cleanups to Hyper-V emulation and tests
* Process Hyper-V TLB flushes from a nested guest (i.e. from a L2 guest
running on top of a L1 Hyper-V hypervisor)
* Advertise several new Intel features
* x86 Xen-for-KVM:
** Allow the Xen runstate information to cross a page boundary
** Allow XEN_RUNSTATE_UPDATE flag behaviour to be configured
** Add support for 32-bit guests in SCHEDOP_poll
* Notable x86 fixes and cleanups:
** One-off fixes for various emulation flows (SGX, VMXON, NRIPS=0).
** Reinstate IBPB on emulated VM-Exit that was incorrectly dropped a few
years back when eliminating unnecessary barriers when switching between
vmcs01 and vmcs02.
** Clean up vmread_error_trampoline() to make it more obvious that params
must be passed on the stack, even for x86-64.
** Let userspace set all supported bits in MSR_IA32_FEAT_CTL irrespective
of the current guest CPUID.
** Fudge around a race with TSC refinement that results in KVM incorrectly
thinking a guest needs TSC scaling when running on a CPU with a
constant TSC, but no hardware-enumerated TSC frequency.
** Advertise (on AMD) that the SMM_CTL MSR is not supported
** Remove unnecessary exports
Generic:
* Support for responding to signals during page faults; introduces
new FOLL_INTERRUPTIBLE flag that was reviewed by mm folks
Selftests:
* Fix an inverted check in the access tracking perf test, and restore
support for asserting that there aren't too many idle pages when
running on bare metal.
* Fix build errors that occur in certain setups (unsure exactly what is
unique about the problematic setup) due to glibc overriding
static_assert() to a variant that requires a custom message.
* Introduce actual atomics for clear/set_bit() in selftests
* Add support for pinning vCPUs in dirty_log_perf_test.
* Rename the so called "perf_util" framework to "memstress".
* Add a lightweight psuedo RNG for guest use, and use it to randomize
the access pattern and write vs. read percentage in the memstress tests.
* Add a common ucall implementation; code dedup and pre-work for running
SEV (and beyond) guests in selftests.
* Provide a common constructor and arch hook, which will eventually be
used by x86 to automatically select the right hypercall (AMD vs. Intel).
* A bunch of added/enabled/fixed selftests for ARM64, covering memslots,
breakpoints, stage-2 faults and access tracking.
* x86-specific selftest changes:
** Clean up x86's page table management.
** Clean up and enhance the "smaller maxphyaddr" test, and add a related
test to cover generic emulation failure.
** Clean up the nEPT support checks.
** Add X86_PROPERTY_* framework to retrieve multi-bit CPUID values.
** Fix an ordering issue in the AMX test introduced by recent conversions
to use kvm_cpu_has(), and harden the code to guard against similar bugs
in the future. Anything that tiggers caching of KVM's supported CPUID,
kvm_cpu_has() in this case, effectively hides opt-in XSAVE features if
the caching occurs before the test opts in via prctl().
Documentation:
* Remove deleted ioctls from documentation
* Clean up the docs for the x86 MSR filter.
* Various fixes
-----BEGIN PGP SIGNATURE-----
iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmOaFrcUHHBib256aW5p
QHJlZGhhdC5jb20ACgkQv/vSX3jHroPemQgAq49excg2Cc+EsHnZw3vu/QWdA0Rt
KhL3OgKxuHNjCbD2O9n2t5di7eJOTQ7F7T0eDm3xPTr4FS8LQ2327/mQePU/H2CF
mWOpq9RBWLzFsSTeVA2Mz9TUTkYSnDHYuRsBvHyw/n9cL76BWVzjImldFtjYjjex
yAwl8c5itKH6bc7KO+5ydswbvBzODkeYKUSBNdbn6m0JGQST7XppNwIAJvpiHsii
Qgpk0e4Xx9q4PXG/r5DedI6BlufBsLhv0aE9SHPzyKH3JbbUFhJYI8ZD5OhBQuYW
MwxK2KlM5Jm5ud2NZDDlsMmmvd1lnYCFDyqNozaKEWC1Y5rq1AbMa51fXA==
=QAYX
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"ARM64:
- Enable the per-vcpu dirty-ring tracking mechanism, together with an
option to keep the good old dirty log around for pages that are
dirtied by something other than a vcpu.
- Switch to the relaxed parallel fault handling, using RCU to delay
page table reclaim and giving better performance under load.
- Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping
option, which multi-process VMMs such as crosvm rely on (see merge
commit 382b5b87a9: "Fix a number of issues with MTE, such as
races on the tags being initialised vs the PG_mte_tagged flag as
well as the lack of support for VM_SHARED when KVM is involved.
Patches from Catalin Marinas and Peter Collingbourne").
- Merge the pKVM shadow vcpu state tracking that allows the
hypervisor to have its own view of a vcpu, keeping that state
private.
- Add support for the PMUv3p5 architecture revision, bringing support
for 64bit counters on systems that support it, and fix the
no-quite-compliant CHAIN-ed counter support for the machines that
actually exist out there.
- Fix a handful of minor issues around 52bit VA/PA support (64kB
pages only) as a prefix of the oncoming support for 4kB and 16kB
pages.
- Pick a small set of documentation and spelling fixes, because no
good merge window would be complete without those.
s390:
- Second batch of the lazy destroy patches
- First batch of KVM changes for kernel virtual != physical address
support
- Removal of a unused function
x86:
- Allow compiling out SMM support
- Cleanup and documentation of SMM state save area format
- Preserve interrupt shadow in SMM state save area
- Respond to generic signals during slow page faults
- Fixes and optimizations for the non-executable huge page errata
fix.
- Reprogram all performance counters on PMU filter change
- Cleanups to Hyper-V emulation and tests
- Process Hyper-V TLB flushes from a nested guest (i.e. from a L2
guest running on top of a L1 Hyper-V hypervisor)
- Advertise several new Intel features
- x86 Xen-for-KVM:
- Allow the Xen runstate information to cross a page boundary
- Allow XEN_RUNSTATE_UPDATE flag behaviour to be configured
- Add support for 32-bit guests in SCHEDOP_poll
- Notable x86 fixes and cleanups:
- One-off fixes for various emulation flows (SGX, VMXON, NRIPS=0).
- Reinstate IBPB on emulated VM-Exit that was incorrectly dropped
a few years back when eliminating unnecessary barriers when
switching between vmcs01 and vmcs02.
- Clean up vmread_error_trampoline() to make it more obvious that
params must be passed on the stack, even for x86-64.
- Let userspace set all supported bits in MSR_IA32_FEAT_CTL
irrespective of the current guest CPUID.
- Fudge around a race with TSC refinement that results in KVM
incorrectly thinking a guest needs TSC scaling when running on a
CPU with a constant TSC, but no hardware-enumerated TSC
frequency.
- Advertise (on AMD) that the SMM_CTL MSR is not supported
- Remove unnecessary exports
Generic:
- Support for responding to signals during page faults; introduces
new FOLL_INTERRUPTIBLE flag that was reviewed by mm folks
Selftests:
- Fix an inverted check in the access tracking perf test, and restore
support for asserting that there aren't too many idle pages when
running on bare metal.
- Fix build errors that occur in certain setups (unsure exactly what
is unique about the problematic setup) due to glibc overriding
static_assert() to a variant that requires a custom message.
- Introduce actual atomics for clear/set_bit() in selftests
- Add support for pinning vCPUs in dirty_log_perf_test.
- Rename the so called "perf_util" framework to "memstress".
- Add a lightweight psuedo RNG for guest use, and use it to randomize
the access pattern and write vs. read percentage in the memstress
tests.
- Add a common ucall implementation; code dedup and pre-work for
running SEV (and beyond) guests in selftests.
- Provide a common constructor and arch hook, which will eventually
be used by x86 to automatically select the right hypercall (AMD vs.
Intel).
- A bunch of added/enabled/fixed selftests for ARM64, covering
memslots, breakpoints, stage-2 faults and access tracking.
- x86-specific selftest changes:
- Clean up x86's page table management.
- Clean up and enhance the "smaller maxphyaddr" test, and add a
related test to cover generic emulation failure.
- Clean up the nEPT support checks.
- Add X86_PROPERTY_* framework to retrieve multi-bit CPUID values.
- Fix an ordering issue in the AMX test introduced by recent
conversions to use kvm_cpu_has(), and harden the code to guard
against similar bugs in the future. Anything that tiggers
caching of KVM's supported CPUID, kvm_cpu_has() in this case,
effectively hides opt-in XSAVE features if the caching occurs
before the test opts in via prctl().
Documentation:
- Remove deleted ioctls from documentation
- Clean up the docs for the x86 MSR filter.
- Various fixes"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (361 commits)
KVM: x86: Add proper ReST tables for userspace MSR exits/flags
KVM: selftests: Allocate ucall pool from MEM_REGION_DATA
KVM: arm64: selftests: Align VA space allocator with TTBR0
KVM: arm64: Fix benign bug with incorrect use of VA_BITS
KVM: arm64: PMU: Fix period computation for 64bit counters with 32bit overflow
KVM: x86: Advertise that the SMM_CTL MSR is not supported
KVM: x86: remove unnecessary exports
KVM: selftests: Fix spelling mistake "probabalistic" -> "probabilistic"
tools: KVM: selftests: Convert clear/set_bit() to actual atomics
tools: Drop "atomic_" prefix from atomic test_and_set_bit()
tools: Drop conflicting non-atomic test_and_{clear,set}_bit() helpers
KVM: selftests: Use non-atomic clear/set bit helpers in KVM tests
perf tools: Use dedicated non-atomic clear/set bit helpers
tools: Take @bit as an "unsigned long" in {clear,set}_bit() helpers
KVM: arm64: selftests: Enable single-step without a "full" ucall()
KVM: x86: fix APICv/x2AVIC disabled when vm reboot by itself
KVM: Remove stale comment about KVM_REQ_UNHALT
KVM: Add missing arch for KVM_CREATE_DEVICE and KVM_{SET,GET}_DEVICE_ATTR
KVM: Reference to kvm_userspace_memory_region in doc and comments
KVM: Delete all references to removed KVM_SET_MEMORY_ALIAS ioctl
...
* kvm-arm64/pmu-unchained:
: .
: PMUv3 fixes and improvements:
:
: - Make the CHAIN event handling strictly follow the architecture
:
: - Add support for PMUv3p5 (64bit counters all the way)
:
: - Various fixes and cleanups
: .
KVM: arm64: PMU: Fix period computation for 64bit counters with 32bit overflow
KVM: arm64: PMU: Sanitise PMCR_EL0.LP on first vcpu run
KVM: arm64: PMU: Simplify PMCR_EL0 reset handling
KVM: arm64: PMU: Replace version number '0' with ID_AA64DFR0_EL1_PMUVer_NI
KVM: arm64: PMU: Make kvm_pmc the main data structure
KVM: arm64: PMU: Simplify vcpu computation on perf overflow notification
KVM: arm64: PMU: Allow PMUv3p5 to be exposed to the guest
KVM: arm64: PMU: Implement PMUv3p5 long counter support
KVM: arm64: PMU: Allow ID_DFR0_EL1.PerfMon to be set from userspace
KVM: arm64: PMU: Allow ID_AA64DFR0_EL1.PMUver to be set from userspace
KVM: arm64: PMU: Move the ID_AA64DFR0_EL1.PMUver limit to VM creation
KVM: arm64: PMU: Do not let AArch32 change the counters' top 32 bits
KVM: arm64: PMU: Simplify setting a counter to a specific value
KVM: arm64: PMU: Add counter_index_to_*reg() helpers
KVM: arm64: PMU: Only narrow counters that are not 64bit wide
KVM: arm64: PMU: Narrow the overflow checking when required
KVM: arm64: PMU: Distinguish between 64bit counter and 64bit overflow
KVM: arm64: PMU: Always advertise the CHAIN event
KVM: arm64: PMU: Align chained counter implementation with architecture pseudocode
arm64: Add ID_DFR0_EL1.PerfMon values for PMUv3p7 and IMP_DEF
Signed-off-by: Marc Zyngier <maz@kernel.org>
When we save the state for the floating point registers this can be done
in the form visible through either the FPSIMD V registers or the SVE Z and
P registers. At present we track which format is currently used based on
TIF_SVE and the SME streaming mode state but particularly in the SVE case
this limits our options for optimising things, especially around syscalls.
Introduce a new enum which we place together with saved floating point
state in both thread_struct and the KVM guest state which explicitly
states which format is active and keep it up to date when we change it.
At present we do not use this state except to verify that it has the
expected value when loading the state, future patches will introduce
functional changes.
Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221115094640.112848-3-broonie@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
As further patches will enable the selection of a PMU revision
from userspace, sample the supported PMU revision at VM creation
time, rather than building each time the ID_AA64DFR0_EL1 register
is accessed.
This shouldn't result in any change in behaviour.
Reviewed-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221113163832.3154370-11-maz@kernel.org
Rather than relying on the host to free the previously-donated pKVM
hypervisor VM pages explicitly on teardown, introduce a dedicated
teardown memcache which allows the host to reclaim guest memory
resources without having to keep track of all of the allocations made by
the pKVM hypervisor at EL2.
Tested-by: Vincent Donnefort <vdonnefort@google.com>
Co-developed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
[maz: dropped __maybe_unused from unmap_donated_memory_noclear()]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110190259.26861-21-will@kernel.org
The initialisation of guest stage-2 page-tables is currently split
across two functions: kvm_init_stage2_mmu() and kvm_arm_setup_stage2().
That is presumably for historical reasons as kvm_arm_setup_stage2()
originates from the (now defunct) KVM port for 32-bit Arm.
Simplify this code path by merging both functions into one, taking care
to map the 'struct kvm' into the hypervisor stage-1 early on in order to
simplify the failure path.
Tested-by: Vincent Donnefort <vdonnefort@google.com>
Co-developed-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110190259.26861-19-will@kernel.org
The host at EL1 and the pKVM hypervisor at EL2 will soon need to
exchange memory pages dynamically for creating and destroying VM state.
Indeed, the hypervisor will rely on the host to donate memory pages it
can use to create guest stage-2 page-tables and to store VM and vCPU
metadata. In order to ease this process, introduce a
'struct hyp_memcache' which is essentially a linked list of available
pages, indexed by physical addresses so that it can be passed
meaningfully between the different virtual address spaces configured at
EL1 and EL2.
Tested-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110190259.26861-18-will@kernel.org
With the pKVM hypervisor at EL2 now offering hypercalls to the host for
creating and destroying VM and vCPU structures, plumb these in to the
existing arm64 KVM backend to ensure that the hypervisor data structures
are allocated and initialised on first vCPU run for a pKVM guest.
In the host, 'struct kvm_protected_vm' is introduced to hold the handle
of the pKVM VM instance as well as to track references to the memory
donated to the hypervisor so that it can be freed back to the host
allocator following VM teardown. The stage-2 page-table, hypervisor VM
and vCPU structures are allocated separately so as to avoid the need for
a large physically-contiguous allocation in the host at run-time.
Tested-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110190259.26861-14-will@kernel.org
Introduce a global table (and lock) to track pKVM instances at EL2, and
provide hypercalls that can be used by the untrusted host to create and
destroy pKVM VMs and their vCPUs. pKVM VM/vCPU state is directly
accessible only by the trusted hypervisor (EL2).
Each pKVM VM is directly associated with an untrusted host KVM instance,
and is referenced by the host using an opaque handle. Future patches
will provide hypercalls to allow the host to initialize/set/get pKVM
VM/vCPU state using the opaque handle.
Tested-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Co-developed-by: Will Deacon <will@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
[maz: silence warning on unmap_donated_memory_noclear()]
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110190259.26861-13-will@kernel.org
While userspace enables single-step, if the Software Step state at the
last guest exit was "Active-pending", clear PSTATE.SS on guest entry
to restore the state.
Currently, KVM sets PSTATE.SS to 1 on every guest entry while userspace
enables single-step for the vCPU (with KVM_GUESTDBG_SINGLESTEP).
It means KVM always makes the vCPU's Software Step state
"Active-not-pending" on the guest entry, which lets the VCPU perform
single-step (then Software Step exception is taken). This could cause
extra single-step (without returning to userspace) if the Software Step
state at the last guest exit was "Active-pending" (i.e. the last
exit was triggered by an asynchronous exception after the single-step
is performed, but before the Software Step exception is taken.
See "Figure D2-3 Software step state machine" and "D2.12.7 Behavior
in the active-pending state" in ARM DDI 0487I.a for more info about
this behavior).
Fix this by clearing PSTATE.SS on guest entry if the Software Step state
at the last exit was "Active-pending" so that KVM restore the state (and
the exception is taken before further single-step is performed).
Fixes: 337b99bf7e ("KVM: arm64: guest debug, add support for single-step")
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220917010600.532642-3-reijiw@google.com
Preserve the PSTATE.SS value for the guest while userspace enables
single-step (i.e. while KVM manipulates the PSTATE.SS) for the vCPU.
Currently, while userspace enables single-step for the vCPU
(with KVM_GUESTDBG_SINGLESTEP), KVM sets PSTATE.SS to 1 on every
guest entry, not saving its original value.
When userspace disables single-step, KVM doesn't restore the original
value for the subsequent guest entry (use the current value instead).
Exception return instructions copy PSTATE.SS from SPSR_ELx.SS
only in certain cases when single-step is enabled (and set it to 0
in other cases). So, the value matters only when the guest enables
single-step (and when the guest's Software step state isn't affected
by single-step enabled by userspace, practically), though.
Fix this by preserving the original PSTATE.SS value while userspace
enables single-step, and restoring the value once it is disabled.
This fix modifies the behavior of GET_ONE_REG/SET_ONE_REG for the
PSTATE.SS while single-step is enabled by userspace.
Presently, GET_ONE_REG/SET_ONE_REG gets/sets the current PSTATE.SS
value, which KVM will override on the next guest entry (i.e. the
value userspace gets/sets is not used for the next guest entry).
With this patch, GET_ONE_REG/SET_ONE_REG will get/set the guest's
preserved value, which KVM will preserve and try to restore after
single-step is disabled.
Fixes: 337b99bf7e ("KVM: arm64: guest debug, add support for single-step")
Signed-off-by: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220917010600.532642-2-reijiw@google.com
KVM does not support AArch32 on asymmetric systems. To that end, enforce
AArch64-only behavior on PMCR_EL1.LC when on an asymmetric system.
Fixes: 2122a83331 ("arm64: Allow mismatched 32-bit EL0 support")
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220816192554.1455559-2-oliver.upton@linux.dev
* kvm-arm64/sysreg-cleanup-5.20:
: .
: Long overdue cleanup of the sysreg userspace access,
: with extra scrubbing on the vgic side of things.
: From the cover letter:
:
: "Schspa Shi recently reported[1] that some of the vgic code interacting
: with userspace was reading uninitialised stack memory, and although
: that read wasn't used any further, it prompted me to revisit this part
: of the code.
:
: Needless to say, this area of the kernel is pretty crufty, and shows a
: bunch of issues in other parts of the KVM/arm64 infrastructure. This
: series tries to remedy a bunch of them:
:
: - Sanitise the way we deal with sysregs from userspace: at the moment,
: each and every .set_user/.get_user callback has to implement its own
: userspace accesses (directly or indirectly). It'd be much better if
: that was centralised so that we can reason about it.
:
: - Enforce that all AArch64 sysregs are 64bit. Always. This was sort of
: implied by the code, but it took some effort to convince myself that
: this was actually the case.
:
: - Move the vgic-v3 sysreg userspace accessors to the userspace
: callbacks instead of hijacking the vcpu trap callback. This allows
: us to reuse the sysreg infrastructure.
:
: - Consolidate userspace accesses for both GICv2, GICv3 and common code
: as much as possible.
:
: - Cleanup a bunch of not-very-useful helpers, tidy up some of the code
: as we touch it.
:
: [1] https://lore.kernel.org/r/m2h740zz1i.fsf@gmail.com"
: .
KVM: arm64: Get rid or outdated comments
KVM: arm64: Descope kvm_arm_sys_reg_{get,set}_reg()
KVM: arm64: Get rid of find_reg_by_id()
KVM: arm64: vgic: Tidy-up calls to vgic_{get,set}_common_attr()
KVM: arm64: vgic: Consolidate userspace access for base address setting
KVM: arm64: vgic-v2: Add helper for legacy dist/cpuif base address setting
KVM: arm64: vgic: Use {get,put}_user() instead of copy_{from.to}_user
KVM: arm64: vgic-v2: Consolidate userspace access for MMIO registers
KVM: arm64: vgic-v3: Consolidate userspace access for MMIO registers
KVM: arm64: vgic-v3: Use u32 to manage the line level from userspace
KVM: arm64: vgic-v3: Convert userspace accessors over to FIELD_GET/FIELD_PREP
KVM: arm64: vgic-v3: Make the userspace accessors use sysreg API
KVM: arm64: vgic-v3: Push user access into vgic_v3_cpu_sysregs_uaccess()
KVM: arm64: vgic-v3: Simplify vgic_v3_has_cpu_sysregs_attr()
KVM: arm64: Get rid of reg_from/to_user()
KVM: arm64: Consolidate sysreg userspace accesses
KVM: arm64: Rely on index_to_param() for size checks on userspace access
KVM: arm64: Introduce generic get_user/set_user helpers for system registers
KVM: arm64: Reorder handling of invariant sysregs from userspace
KVM: arm64: Add get_reg_by_id() as a sys_reg_desc retrieving helper
Signed-off-by: Marc Zyngier <maz@kernel.org>
