KVM/arm64 fixes for 6.14, take #4

- Fix a couple of bugs affecting pKVM's PSCI relay implementation
when running in the hVHE mode, resulting in the host being entered
with the MMU in an unknown state, and EL2 being in the wrong mode.

A VMM may send a non-fatal signal to its threads, including vCPU tasks,
at any time, and thus may signal vCPU tasks during KVM_RUN. If a vCPU
task receives the signal while its trying to spawn the huge page recovery
vhost task, then KVM_RUN will fail due to copy_process() returning
-ERESTARTNOINTR.

Rework call_once() to mark the call complete if and only if the called
function succeeds, and plumb the function's true error code back to the
call_once() invoker. This provides userspace with the correct, non-fatal
error code so that the VMM doesn't terminate the VM on -ENOMEM, and allows
subsequent KVM_RUN a succeed by virtue of retrying creation of the NX huge
page task.

Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
[implemented the kvm user side]
Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250227230631.303431-3-kbusch@meta.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

When KVM is in protected mode, host calls to PSCI are proxied via EL2,
and cold entries from CPU_ON, CPU_SUSPEND, and SYSTEM_SUSPEND bounce
through __kvm_hyp_init_cpu() at EL2 before entering the host kernel's
entry point at EL1. While __kvm_hyp_init_cpu() initializes SPSR_EL2 for
the exception return to EL1, it does not initialize SCTLR_EL1.

Due to this, it's possible to enter EL1 with SCTLR_EL1 in an UNKNOWN
state. In practice this has been seen to result in kernel crashes after
CPU_ON as a result of SCTLR_EL1.M being 1 in violation of the initial
core configuration specified by PSCI.

Fix this by initializing SCTLR_EL1 for cold entry to the host kernel.
As it's necessary to write to SCTLR_EL12 in VHE mode, this
initialization is moved into __kvm_host_psci_cpu_entry() where we can
use write_sysreg_el1().

The remnants of the '__init_el2_nvhe_prepare_eret' macro are folded into
its only caller, as this is clearer than having the macro.

Fixes: cdf367192766ad11 ("KVM: arm64: Intercept host's CPU_ON SMCs")
Reported-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Ahmed Genidi <ahmed.genidi@arm.com>
[ Mark: clarify commit message, handle E2H, move to C, remove macro ]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ahmed Genidi <ahmed.genidi@arm.com>
Cc: Ben Horgan <ben.horgan@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Link: https://lore.kernel.org/r/20250227180526.1204723-3-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>

Lets callers distinguish why the vhost task creation failed. No one
currently cares why it failed, so no real runtime change from this
patch, but that will not be the case for long.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250227230631.303431-2-kbusch@meta.com>
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

On CPUs without FEAT_E2H0, HCR_EL2.E2H is RES1, but may reset to an
UNKNOWN value out of reset and consequently may not read as 1 unless it
has been explicitly initialized.

We handled this for the head.S boot code in commits:

3944382fa6f22b54 ("arm64: Treat HCR_EL2.E2H as RES1 when ID_AA64MMFR4_EL1.E2H0 is negative")
b3320142f3db9b3f ("arm64: Fix early handling of FEAT_E2H0 not being implemented")

Unfortunately, we forgot to apply a similar fix to the KVM PSCI entry
points used when relaying CPU_ON, CPU_SUSPEND, and SYSTEM SUSPEND. When
KVM is entered via these entry points, the value of HCR_EL2.E2H may be
consumed before it has been initialized (e.g. by the 'init_el2_state'
macro).

Initialize HCR_EL2.E2H early in these paths such that it can be consumed
reliably. The existing code in head.S is factored out into a new
'init_el2_hcr' macro, and this is used in the __kvm_hyp_init_cpu()
function common to all the relevant PSCI entry points.

For clarity, I've tweaked the assembly used to check whether
ID_AA64MMFR4_EL1.E2H0 is negative. The bitfield is extracted as a signed
value, and this is checked with a signed-greater-or-equal (GE) comparison.

As the hyp code will reconfigure HCR_EL2 later in ___kvm_hyp_init(), all
bits other than E2H are initialized to zero in __kvm_hyp_init_cpu().

Fixes: 3944382fa6f22b54 ("arm64: Treat HCR_EL2.E2H as RES1 when ID_AA64MMFR4_EL1.E2H0 is negative")
Fixes: b3320142f3db9b3f ("arm64: Fix early handling of FEAT_E2H0 not being implemented")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ahmed Genidi <ahmed.genidi@arm.com>
Cc: Ben Horgan <ben.horgan@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250227180526.1204723-2-mark.rutland@arm.com
[maz: fixed LT->GE thinko]
Signed-off-by: Marc Zyngier <maz@kernel.org>

Process pending events on nested VM-Exit if the vCPU has an injectable IRQ
or NMI, as the event may have become pending while L2 was active, i.e. may
not be tracked in the context of vmcs01. E.g. if L1 has passed its APIC
through to L2 and an IRQ arrives while L2 is active, then KVM needs to
request an IRQ window prior to running L1, otherwise delivery of the IRQ
will be delayed until KVM happens to process events for some other reason.

The missed failure is detected by vmx_apic_passthrough_tpr_threshold_test
in KVM-Unit-Tests, but has effectively been masked due to a flaw in KVM's
PIC emulation that causes KVM to make spurious KVM_REQ_EVENT requests (and
apparently no one ever ran the test with split IRQ chips).

Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20250224235542.2562848-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Vladimir reports that a race condition to attach a VMID to a stage-2 MMU
sometimes results in a vCPU entering the guest with a VMID of 0:

| CPU1 | CPU2
| |
| | kvm_arch_vcpu_ioctl_run
| | vcpu_load <= load VTTBR_EL2
| | kvm_vmid->id = 0
| |
| kvm_arch_vcpu_ioctl_run |
| vcpu_load <= load VTTBR_EL2 |
| with kvm_vmid->id = 0|
| kvm_arm_vmid_update <= allocates fresh |
| kvm_vmid->id and |
| reload VTTBR_EL2 |
| |
| | kvm_arm_vmid_update <= observes that kvm_vmid->id
| | already allocated,
| | skips reload VTTBR_EL2

Oh yeah, it's as bad as it looks. Remember that VHE loads the stage-2
MMU eagerly but a VMID only gets attached to the MMU later on in the
KVM_RUN loop.

Even in the "best case" where VTTBR_EL2 correctly gets reprogrammed
before entering the EL1&0 regime, there is a period of time where
hardware is configured with VMID 0. That's completely insane. So, rather
than decorating the 'late' binding with another hack, just allocate the
damn thing up front.

Attaching a VMID from vcpu_load() is still rollover safe since
(surprise!) it'll always get called after a vCPU was preempted.

Excuse me while I go find a brown paper bag.

Cc: stable@vger.kernel.org
Fixes: 934bf871f011 ("KVM: arm64: Load the stage-2 MMU context in kvm_vcpu_load_vhe()")
Reported-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250219220737.130842-1-oliver.upton@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>

Free vCPUs before freeing any VM state, as both SVM and VMX may access
VM state when "freeing" a vCPU that is currently "in" L2, i.e. that needs
to be kicked out of nested guest mode.

Commit 6fcee03df6a1 ("KVM: x86: avoid loading a vCPU after .vm_destroy was
called") partially fixed the issue, but for unknown reasons only moved the
MMU unloading before VM destruction. Complete the change, and free all
vCPU state prior to destroying VM state, as nVMX accesses even more state
than nSVM.

In addition to the AVIC, KVM can hit a use-after-free on MSR filters:

kvm_msr_allowed+0x4c/0xd0
__kvm_set_msr+0x12d/0x1e0
kvm_set_msr+0x19/0x40
load_vmcs12_host_state+0x2d8/0x6e0 [kvm_intel]
nested_vmx_vmexit+0x715/0xbd0 [kvm_intel]
nested_vmx_free_vcpu+0x33/0x50 [kvm_intel]
vmx_free_vcpu+0x54/0xc0 [kvm_intel]
kvm_arch_vcpu_destroy+0x28/0xf0
kvm_vcpu_destroy+0x12/0x50
kvm_arch_destroy_vm+0x12c/0x1c0
kvm_put_kvm+0x263/0x3c0
kvm_vm_release+0x21/0x30

and an upcoming fix to process injectable interrupts on nested VM-Exit
will access the PIC:

BUG: kernel NULL pointer dereference, address: 0000000000000090
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
CPU: 23 UID: 1000 PID: 2658 Comm: kvm-nx-lpage-re
RIP: 0010:kvm_cpu_has_extint+0x2f/0x60 [kvm]
Call Trace:
<TASK>
kvm_cpu_has_injectable_intr+0xe/0x60 [kvm]
nested_vmx_vmexit+0x2d7/0xdf0 [kvm_intel]
nested_vmx_free_vcpu+0x40/0x50 [kvm_intel]
vmx_vcpu_free+0x2d/0x80 [kvm_intel]
kvm_arch_vcpu_destroy+0x2d/0x130 [kvm]
kvm_destroy_vcpus+0x8a/0x100 [kvm]
kvm_arch_destroy_vm+0xa7/0x1d0 [kvm]
kvm_destroy_vm+0x172/0x300 [kvm]
kvm_vcpu_release+0x31/0x50 [kvm]

Inarguably, both nSVM and nVMX need to be fixed, but punt on those
cleanups for the moment. Conceptually, vCPUs should be freed before VM
state. Assets like the I/O APIC and PIC _must_ be allocated before vCPUs
are created, so it stands to reason that they must be freed _after_ vCPUs
are destroyed.

Reported-by: Aaron Lewis <aaronlewis@google.com>
Closes: https://lore.kernel.org/all/20240703175618.2304869-2-aaronlewis@google.com
Cc: Jim Mattson <jmattson@google.com>
Cc: Yan Zhao <yan.y.zhao@intel.com>
Cc: Rick P Edgecombe <rick.p.edgecombe@intel.com>
Cc: Kai Huang <kai.huang@intel.com>
Cc: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20250224235542.2562848-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

When not running in VHE mode, cpu_prepare_hyp_mode() computes the value
of TCR_EL2 using the host's TCR_EL1 settings as a starting point. For
nVHE, this amounts to masking out everything apart from the TG0, SH0,
ORGN0, IRGN0 and T0SZ fields before setting the RES1 bits, shifting the
IPS field down to the PS field and setting DS if LPA2 is enabled.

Unfortunately, for hVHE, things go slightly wonky: EPD1 is correctly set
to disable walks via TTBR1_EL2 but then the T1SZ and IPS fields are
corrupted when we mistakenly attempt to initialise the PS and DS fields
in their E2H=0 positions. Furthermore, many fields are retained from
TCR_EL1 which should not be propagated to TCR_EL2. Notably, this means
we can end up with A1 set despite not initialising TTBR1_EL2 at all.
This has been shown to cause unexpected translation faults at EL2 with
pKVM due to TLB invalidation not taking effect when running with a
non-zero ASID.

Fix the TCR_EL2 initialisation code to set PS and DS only when E2H=0,
masking out HD, HA and A1 when E2H=1.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Fixes: ad744e8cb346 ("arm64: Allow arm64_sw.hvhe on command line")
Signed-off-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250214133724.13179-1-will@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>

KVM/riscv fixes for 6.14, take #1

- Fix hart status check in SBI HSM extension
- Fix hart suspend_type usage in SBI HSM extension
- Fix error returned by SBI IPI and TIME extensions for
unsupported function IDs
- Fix suspend_type usage in SBI SUSP extension
- Remove unnecessary vcpu kick after injecting interrupt
via IMSIC guest file

KVM/arm64 fixes for 6.14, take #3

- Fix TCR_EL2 configuration to not use the ASID in TTBR1_EL2
and not mess-up T1SZ/PS by using the HCR_EL2.E2H==0 layout.

- Bring back the VMID allocation to the vcpu_load phase, ensuring
that we only setup VTTBR_EL2 once on VHE. This cures an ugly
race that would lead to running with an unallocated VMID.

Remove the unnecessary kick to the vCPU after writing to the vs_file
of IMSIC in kvm_riscv_vcpu_aia_imsic_inject.

For vCPUs that are running, writing to the vs_file directly forwards
the interrupt as an MSI to them and does not need an extra kick.

For vCPUs that are descheduled after emulating WFI, KVM will enable
the guest external interrupt for that vCPU in
kvm_riscv_aia_wakeon_hgei. This means that writing to the vs_file
will cause a guest external interrupt, which will cause KVM to wake
up the vCPU in hgei_interrupt to handle the interrupt properly.

Signed-off-by: BillXiang <xiangwencheng@lanxincomputing.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Link: https://lore.kernel.org/r/20250221104538.2147-1-xiangwencheng@lanxincomputing.com
Signed-off-by: Anup Patel <anup@brainfault.org>

Pull Kbuild fixes from Masahiro Yamada:

- Fix annoying logs when building tools in parallel

- Fix the Debian linux-headers package build again

- Fix the target triple detection for userspace programs on Clang

* tag 'kbuild-fixes-v6.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild:
modpost: Fix a few typos in a comment
kbuild: userprogs: fix bitsize and target detection on clang
kbuild: fix linux-headers package build when $(CC) cannot link userspace
tools: fix annoying "mkdir -p ..." logs when building tools in parallel

The spec says sleep_type is 32 bits wide and "In case the data is
defined as 32bit wide, higher privilege software must ensure that it
only uses 32 bit data." Mask off upper bits of sleep_type before
using it.

Fixes: 023c15151fbb ("RISC-V: KVM: Add SBI system suspend support")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-12-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>

Pull driver core api addition from Greg KH:
"Here is a driver core new api for 6.14-rc3 that is being added to
allow platform devices from stop being abused.

It adds a new 'faux_device' structure and bus and api to allow almost
a straight or simpler conversion from platform devices that were not
really a platform device. It also comes with a binding for rust, with
an example driver in rust showing how it's used.

I'm adding this now so that the patches that convert the different
drivers and subsystems can all start flowing into linux-next now
through their different development trees, in time for 6.15-rc1.

We have a number that are already reviewed and tested, but adding
those conversions now doesn't seem right. For now, no one is using
this, and it passes all build tests from 0-day and linux-next, so all
should be good"

* tag 'driver-core-6.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core:
rust/kernel: Add faux device bindings
driver core: add a faux bus for use when a simple device/bus is needed