linux-toradex.git/arch/x86, branch v6.16

Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

2025-07-23T22:04:27+00:00

Pull kvm fix from Paolo Bonzini:

 - Fix cleanup mistake (probably a cut-and-paste error) in a Xen
   hypercall

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86/xen: Fix cleanup logic in emulation of Xen schedop poll hypercalls

KVM: x86/xen: Fix cleanup logic in emulation of Xen schedop poll hypercalls

2025-07-23T21:48:54+00:00

kvm_xen_schedop_poll does a kmalloc_array() when a VM polls the host
for more than one event channel potr (nr_ports > 1).

After the kmalloc_array(), the error paths need to go through the
"out" label, but the call to kvm_read_guest_virt() does not.

Fixes: 92c58965e965 ("KVM: x86/xen: Use kvm_read_guest_virt() instead of open-coding it badly")
Reviewed-by: David Woodhouse 
Signed-off-by: Manuel Andreas 
[Adjusted commit message. - Paolo]
Signed-off-by: Paolo Bonzini

Merge tag 'x86-urgent-2025-07-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2025-07-20T18:27:52+00:00

Pull x86 bug fix from Thomas Gleixner:
 "A single fix for a GCC wreckage, which emits a KCSAN instrumentation
  call in __sev_es_nmi_complete() despite the function being annotated
  with 'noinstr'.

  As all functions in that source file are noinstr, exclude the whole
  file from KCSAN in the Makefile to cure it"

* tag 'x86-urgent-2025-07-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/sev: Work around broken noinstr on GCC

Merge tag 'hyperv-fixes-signed-20250718' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

2025-07-20T16:29:43+00:00

Pull hyperv fixes from Wei Liu:

 - Select use CONFIG_SYSFB only if EFI is enabled (Michael Kelley)

 - An assorted set of fixes to remove warnings for missing export.h
   header inclusion (Naman Jain)

 - An assorted set of fixes for when Linux run as the root partition
   for Microsoft Hypervisor (Mukesh Rathor, Nuno Das Neves, Stanislav
   Kinsburskii)

 - Fix the check for HYPERVISOR_CALLBACK_VECTOR (Naman Jain)

 - Fix fcopy tool to handle irregularities with size of ring buffer
   (Naman Jain)

 - Fix incorrect file path conversion in fcopy tool (Yasumasa Suenaga)

* tag 'hyperv-fixes-signed-20250718' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  tools/hv: fcopy: Fix irregularities with size of ring buffer
  PCI: hv: Use the correct hypercall for unmasking interrupts on nested
  x86/hyperv: Expose hv_map_msi_interrupt()
  Drivers: hv: Use nested hypercall for post message and signal event
  x86/hyperv: Clean up hv_map/unmap_interrupt() return values
  x86/hyperv: Fix usage of cpu_online_mask to get valid cpu
  PCI: hv: Don't load the driver for baremetal root partition
  net: mana: Fix warnings for missing export.h header inclusion
  PCI: hv: Fix warnings for missing export.h header inclusion
  clocksource: hyper-v: Fix warnings for missing export.h header inclusion
  x86/hyperv: Fix warnings for missing export.h header inclusion
  Drivers: hv: Fix warnings for missing export.h header inclusion
  Drivers: hv: Fix the check for HYPERVISOR_CALLBACK_VECTOR
  tools/hv: fcopy: Fix incorrect file path conversion
  Drivers: hv: Select CONFIG_SYSFB only if EFI is enabled

Merge tag 'kvm-x86-fixes-6.16-rc7' of https://github.com/kvm-x86/linux into HEAD

2025-07-17T15:06:13+00:00

KVM TDX fixes for 6.16

 - Fix a formatting goof in the TDX documentation.

 - Reject KVM_SET_TSC_KHZ for guests with a protected TSC (currently only TDX).

 - Ensure struct kvm_tdx_capabilities fields that are not explicitly set by KVM
   are zeroed.

KVM: TDX: Don't report base TDVMCALLs

2025-07-17T14:24:23+00:00

Remove TDVMCALLINFO_GET_QUOTE from user_tdvmcallinfo_1_r11 reported to
userspace to align with the direction of the GHCI spec.

Recently, concern was raised about a gap in the GHCI spec that left
ambiguity in how to expose to the guest that only a subset of GHCI
TDVMCalls were supported. During the back and forth on the spec details[0],
 was moved from an individually enumerable TDVMCall, to one that
is part of the 'base spec', meaning it doesn't have a specific bit in the
 return values. Although the spec[1] is still in draft
form, the GetQoute part has been agreed by the major TDX VMMs.

Unfortunately the commits that were upstreamed still treat  as
individually enumerable. They set bit 0 in the user_tdvmcallinfo_1_r11
which is reported to userspace to tell supported optional TDVMCalls,
intending to say that  is supported.

So stop reporting  in user_tdvmcallinfo_1_r11 to align with
the direction of the spec, and allow some future TDVMCall to use that bit.

[0] https://lore.kernel.org/all/aEmuKII8FGU4eQZz@google.com/
[1] https://cdrdv2.intel.com/v1/dl/getContent/858626

Fixes: 28224ef02b56 ("KVM: TDX: Report supported optional TDVMCALLs in TDX capabilities")
Signed-off-by: Xiaoyao Li 
Message-ID: <20250717022010.677645-1-xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini

KVM: VMX: Ensure unused kvm_tdx_capabilities fields are zeroed out

2025-07-15T21:04:39+00:00

Zero-allocate the kernel's kvm_tdx_capabilities structure and copy only
the number of CPUID entries from the userspace structure.  As is, KVM
doesn't ensure kernel_tdvmcallinfo_1_{r11,r12} and user_tdvmcallinfo_1_r12
are zeroed, i.e. KVM will reflect whatever happens to be in the userspace
structure back at userspace, and thus may report garbage to userspace.

Zeroing the entire kernel structure also provides better semantics for the
reserved field.  E.g. if KVM extends kvm_tdx_capabilities to enumerate new
information by repurposing bytes from the reserved field, userspace would
be required to zero the new field in order to get useful information back
(because older KVMs without support for the repurposed field would report
garbage, a la the aforementioned tdvmcallinfo bugs).

Fixes: 61bb28279623 ("KVM: TDX: Get system-wide info about TDX module on initialization")
Suggested-by: Rick Edgecombe 
Reported-by: Xiaoyao Li 
Closes: https://lore.kernel.org/all/3ef581f1-1ff1-4b99-b216-b316f6415318@intel.com
Tested-by: Xiaoyao Li 
Reviewed-by: Xiaoyao Li 
Reviewed-by: Rick Edgecombe 
Link: https://lore.kernel.org/r/20250714221928.1788095-1-seanjc@google.com
Signed-off-by: Sean Christopherson

KVM: x86: Reject KVM_SET_TSC_KHZ vCPU ioctl for TSC protected guest

2025-07-15T14:05:13+00:00

Reject KVM_SET_TSC_KHZ vCPU ioctl if guest's TSC is protected and not
changeable by KVM, and update the documentation to reflect it.

For such TSC protected guests, e.g. TDX guests, typically the TSC is
configured once at VM level before any vCPU are created and remains
unchanged during VM's lifetime.  KVM provides the KVM_SET_TSC_KHZ VM
scope ioctl to allow the userspace VMM to configure the TSC of such VM.
After that the userspace VMM is not supposed to call the KVM_SET_TSC_KHZ
vCPU scope ioctl anymore when creating the vCPU.

The de facto userspace VMM Qemu does this for TDX guests.  The upcoming
SEV-SNP guests with Secure TSC should follow.

Note, TDX support hasn't been fully released as of the "buggy" commit,
i.e. there is no established ABI to break.

Fixes: adafea110600 ("KVM: x86: Add infrastructure for secure TSC")
Suggested-by: Sean Christopherson 
Signed-off-by: Kai Huang 
Reviewed-by: Xiaoyao Li 
Reviewed-by: Nikunj A Dadhania 
Link: https://lore.kernel.org/r/71bbdf87fdd423e3ba3a45b57642c119ee2dd98c.1752444335.git.kai.huang@intel.com
Signed-off-by: Sean Christopherson

x86/sev: Work around broken noinstr on GCC

2025-07-15T08:12:25+00:00

Forcibly disable KCSAN for the sev-nmi.c source file, which only
contains functions annotated as 'noinstr' but is emitted with calls to
KCSAN instrumentation nonetheless. E.g.,

  vmlinux.o: error: objtool: __sev_es_nmi_complete+0x58: call to __kcsan_check_access() leaves .noinstr.text section
  make[2]: *** [/usr/local/google/home/ardb/linux/scripts/Makefile.vmlinux_o:72: vmlinux.o] Error 1

Fixes: a3cbbb4717e1 ("x86/boot: Move SEV startup code into startup/")
Reported-by: Randy Dunlap 
Signed-off-by: Ard Biesheuvel 
Signed-off-by: Borislav Petkov (AMD) 
Acked-by: Randy Dunlap 
Tested-by: Randy Dunlap 
Link: https://lore.kernel.org/20250714073402.4107091-2-ardb+git@google.com

x86/hyperv: Expose hv_map_msi_interrupt()

2025-07-15T06:24:16+00:00

Move some of the logic of hv_irq_compose_irq_message() into
hv_map_msi_interrupt(). Make hv_map_msi_interrupt() a globally-available
helper function, which will be used to map PCI interrupts when running
in the root partition.

Signed-off-by: Stanislav Kinsburskii 
Signed-off-by: Nuno Das Neves 
Reviewed-by: Roman Kisel 
Reviewed-by: Michael Kelley 
Link: https://lore.kernel.org/r/1752261532-7225-3-git-send-email-nunodasneves@linux.microsoft.com
Signed-off-by: Wei Liu 
Message-ID: <1752261532-7225-3-git-send-email-nunodasneves@linux.microsoft.com>