Skip to content

L
linux
Switch branch/tag
  1. 15 Nov, 2020 10 commits
    • David Woodhouse's avatar
      sched/wait: Add add_wait_queue_priority() · c4d51a52
      David Woodhouse authored 
      This allows an exclusive wait_queue_entry to be added at the head of the
queue, instead of the tail as normal. Thus, it gets to consume events
first without allowing non-exclusive waiters to be woken at all.

The (first) intended use is for KVM IRQFD, which currently has
inconsistent behaviour depending on whether posted interrupts are
available or not. If they are, KVM will bypass the eventfd completely
and deliver interrupts directly to the appropriate vCPU. If not, events
are delivered through the eventfd and userspace will receive them when
polling on the eventfd.

By using add_wait_queue_priority(), KVM will be able to consistently
consume events within the kernel without accidentally exposing them
to userspace when they're supposed to be bypassed. This, in turn, means
that userspace doesn't have to jump through hoops to avoid listening
on the erroneously noisy eventfd and injecting duplicate interrupts.
Signed-off-by: default avatarDavid Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20201027143944.648769-2-dwmw2@infradead.org>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      c4d51a52
    • Yadong Qi's avatar
      KVM: x86: emulate wait-for-SIPI and SIPI-VMExit · bf0cd88c
      Yadong Qi authored 
      Background: We have a lightweight HV, it needs INIT-VMExit and
SIPI-VMExit to wake-up APs for guests since it do not monitor
the Local APIC. But currently virtual wait-for-SIPI(WFS) state
is not supported in nVMX, so when running on top of KVM, the L1
HV cannot receive the INIT-VMExit and SIPI-VMExit which cause
the L2 guest cannot wake up the APs.

According to Intel SDM Chapter 25.2 Other Causes of VM Exits,
SIPIs cause VM exits when a logical processor is in
wait-for-SIPI state.

In this patch:
    1. introduce SIPI exit reason,
    2. introduce wait-for-SIPI state for nVMX,
    3. advertise wait-for-SIPI support to guest.

When L1 hypervisor is not monitoring Local APIC, L0 need to emulate
INIT-VMExit and SIPI-VMExit to L1 to emulate INIT-SIPI-SIPI for
L2. L2 LAPIC write would be traped by L0 Hypervisor(KVM), L0 should
emulate the INIT/SIPI vmexit to L1 hypervisor to set proper state
for L2's vcpu state.

Handle procdure:
Source vCPU:
    L2 write LAPIC.ICR(INIT).
    L0 trap LAPIC.ICR write(INIT): inject a latched INIT event to target
       vCPU.
Target vCPU:
    L0 emulate an INIT VMExit to L1 if is guest mode.
    L1 set guest VMCS, guest_activity_state=WAIT_SIPI, vmresume.
    L0 set vcpu.mp_state to INIT_RECEIVED if (vmcs12.guest_activity_state
       == WAIT_SIPI).

Source vCPU:
    L2 write LAPIC.ICR(SIPI).
    L0 trap LAPIC.ICR write(INIT): inject a latched SIPI event to traget
       vCPU.
Target vCPU:
    L0 emulate an SIPI VMExit to L1 if (vcpu.mp_state == INIT_RECEIVED).
    L1 set CS:IP, guest_activity_state=ACTIVE, vmresume.
    L0 resume to L2.
    L2 start-up.
Signed-off-by: default avatarYadong Qi <yadong.qi@intel.com>
Message-Id: <20200922052343.84388-1-yadong.qi@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
Message-Id: <20201106065122.403183-1-yadong.qi@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      bf0cd88c
    • Paolo Bonzini's avatar
      KVM: x86: fix apic_accept_events vs check_nested_events · 1c96dcce
      Paolo Bonzini authored 
      vmx_apic_init_signal_blocked is buggy in that it returns true
even in VMX non-root mode.  In non-root mode, however, INITs
are not latched, they just cause a vmexit.  Previously,
KVM was waiting for them to be processed when kvm_apic_accept_events
and in the meanwhile it ate the SIPIs that the processor received.

However, in order to implement the wait-for-SIPI activity state,
KVM will have to process KVM_APIC_SIPI in vmx_check_nested_events,
and it will not be possible anymore to disregard SIPIs in non-root
mode as the code is currently doing.

By calling kvm_x86_ops.nested_ops->check_events, we can force a vmexit
(with the side-effect of latching INITs) before incorrectly injecting
an INIT or SIPI in a guest, and therefore vmx_apic_init_signal_blocked
can do the right thing.
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      1c96dcce
    • Sean Christopherson's avatar
      KVM: selftests: Verify supported CR4 bits can be set before KVM_SET_CPUID2 · 7a873e45
      Sean Christopherson authored 
      Extend the KVM_SET_SREGS test to verify that all supported CR4 bits, as
enumerated by KVM, can be set before KVM_SET_CPUID2, i.e. without first
defining the vCPU model.  KVM is supposed to skip guest CPUID checks
when host userspace is stuffing guest state.

Check the inverse as well, i.e. that KVM rejects KVM_SET_REGS if CR4
has one or more unsupported bits set.
Signed-off-by: default avatarSean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201007014417.29276-7-sean.j.christopherson@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      7a873e45
    • Sean Christopherson's avatar
      KVM: x86: Return bool instead of int for CR4 and SREGS validity checks · ee69c92b
      Sean Christopherson authored 
      Rework the common CR4 and SREGS checks to return a bool instead of an
int, i.e. true/false instead of 0/-EINVAL, and add "is" to the name to
clarify the polarity of the return value (which is effectively inverted
by this change).

No functional changed intended.
Signed-off-by: default avatarSean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201007014417.29276-6-sean.j.christopherson@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      ee69c92b
    • Sean Christopherson's avatar
      KVM: x86: Move vendor CR4 validity check to dedicated kvm_x86_ops hook · c2fe3cd4
      Sean Christopherson authored 
      Split out VMX's checks on CR4.VMXE to a dedicated hook, .is_valid_cr4(),
and invoke the new hook from kvm_valid_cr4().  This fixes an issue where
KVM_SET_SREGS would return success while failing to actually set CR4.

Fixing the issue by explicitly checking kvm_x86_ops.set_cr4()'s return
in __set_sregs() is not a viable option as KVM has already stuffed a
variety of vCPU state.

Note, kvm_valid_cr4() and is_valid_cr4() have different return types and
inverted semantics.  This will be remedied in a future patch.

Fixes: 5e1746d6 ("KVM: nVMX: Allow setting the VMXE bit in CR4")
Signed-off-by: default avatarSean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201007014417.29276-5-sean.j.christopherson@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      c2fe3cd4
    • Sean Christopherson's avatar
      KVM: SVM: Drop VMXE check from svm_set_cr4() · 311a0659
      Sean Christopherson authored 
      Drop svm_set_cr4()'s explicit check CR4.VMXE now that common x86 handles
the check by incorporating VMXE into the CR4 reserved bits, via
kvm_cpu_caps.  SVM obviously does not set X86_FEATURE_VMX.

No functional change intended.
Signed-off-by: default avatarSean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201007014417.29276-4-sean.j.christopherson@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      311a0659
    • Sean Christopherson's avatar
      KVM: VMX: Drop explicit 'nested' check from vmx_set_cr4() · a447e38a
      Sean Christopherson authored 
      Drop vmx_set_cr4()'s explicit check on the 'nested' module param now
that common x86 handles the check by incorporating VMXE into the CR4
reserved bits, via kvm_cpu_caps.  X86_FEATURE_VMX is set in kvm_cpu_caps
(by vmx_set_cpu_caps()), if and only if 'nested' is true.

No functional change intended.
Signed-off-by: default avatarSean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201007014417.29276-3-sean.j.christopherson@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      a447e38a
    • Sean Christopherson's avatar
      KVM: VMX: Drop guest CPUID check for VMXE in vmx_set_cr4() · d3a9e414
      Sean Christopherson authored 
      Drop vmx_set_cr4()'s somewhat hidden guest_cpuid_has() check on VMXE now
that common x86 handles the check by incorporating VMXE into the CR4
reserved bits, i.e. in cr4_guest_rsvd_bits.  This fixes a bug where KVM
incorrectly rejects KVM_SET_SREGS with CR4.VMXE=1 if it's executed
before KVM_SET_CPUID{,2}.

Fixes: 5e1746d6 ("KVM: nVMX: Allow setting the VMXE bit in CR4")
Reported-by: default avatarStas Sergeev <stsp@users.sourceforge.net>
Signed-off-by: default avatarSean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201007014417.29276-2-sean.j.christopherson@intel.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      d3a9e414
    • Paolo Bonzini's avatar
      kvm: mmu: fix is_tdp_mmu_check when the TDP MMU is not in use · c887c9b9
      Paolo Bonzini authored 
      In some cases where shadow paging is in use, the root page will
be either mmu->pae_root or vcpu->arch.mmu->lm_root.  Then it will
not have an associated struct kvm_mmu_page, because it is allocated
with alloc_page instead of kvm_mmu_alloc_page.

Just return false quickly from is_tdp_mmu_root if the TDP MMU is
not in use, which also includes the case where shadow paging is
enabled.
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
      c887c9b9
  3. 13 Nov, 2020 6 commits
  5. 12 Nov, 2020 24 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7