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

Pull KVM updates from Paolo Bonzini:
 "PPC:
   - Better machine check handling for HV KVM
   - Ability to support guests with threads=2, 4 or 8 on POWER9
   - Fix for a race that could cause delayed recognition of signals
   - Fix for a bug where POWER9 guests could sleep with interrupts pending.

  ARM:
   - VCPU request overhaul
   - allow timer and PMU to have their interrupt number selected from userspace
   - workaround for Cavium erratum 30115
   - handling of memory poisonning
   - the usual crop of fixes and cleanups

  s390:
   - initial machine check forwarding
   - migration support for the CMMA page hinting information
   - cleanups and fixes

  x86:
   - nested VMX bugfixes and improvements
   - more reliable NMI window detection on AMD
   - APIC timer optimizations

  Generic:
   - VCPU request overhaul + documentation of common code patterns
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  Update my email address
  kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS
  x86: kvm: mmu: use ept a/d in vmcs02 iff used in vmcs12
  kvm: x86: mmu: allow A/D bits to be disabled in an mmu
  x86: kvm: mmu: make spte mmio mask more explicit
  x86: kvm: mmu: dead code thanks to access tracking
  KVM: PPC: Book3S: Fix typo in XICS-on-XIVE state saving code
  KVM: PPC: Book3S HV: Close race with testing for signals on guest entry
  KVM: PPC: Book3S HV: Simplify dynamic micro-threading code
  KVM: x86: remove ignored type attribute
  KVM: LAPIC: Fix lapic timer injection delay
  KVM: lapic: reorganize restart_apic_timer
  KVM: lapic: reorganize start_hv_timer
  kvm: nVMX: Check memory operand to INVVPID
  KVM: s390: Inject machine check into the nested guest
  KVM: s390: Inject machine check into the guest
  tools/kvm_stat: add new interactive command 'b'
  tools/kvm_stat: add new command line switch '-i'
  tools/kvm_stat: fix error on interactive command 'g'
  KVM: SVM: suppress unnecessary NMI singlestep on GIF=0 and nested exit
  ...
This commit is contained in:
Linus Torvalds
2017-07-06 18:38:31 -07:00
95 changed files with 4255 additions and 972 deletions

View File

@@ -190,6 +190,7 @@ struct vcpu_svm {
struct nested_state nested;
bool nmi_singlestep;
u64 nmi_singlestep_guest_rflags;
unsigned int3_injected;
unsigned long int3_rip;
@@ -964,6 +965,18 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
static void disable_nmi_singlestep(struct vcpu_svm *svm)
{
svm->nmi_singlestep = false;
if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) {
/* Clear our flags if they were not set by the guest */
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
svm->vmcb->save.rflags &= ~X86_EFLAGS_TF;
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
svm->vmcb->save.rflags &= ~X86_EFLAGS_RF;
}
}
/* Note:
* This hash table is used to map VM_ID to a struct kvm_arch,
* when handling AMD IOMMU GALOG notification to schedule in
@@ -1713,11 +1726,24 @@ static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
{
return to_svm(vcpu)->vmcb->save.rflags;
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long rflags = svm->vmcb->save.rflags;
if (svm->nmi_singlestep) {
/* Hide our flags if they were not set by the guest */
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF))
rflags &= ~X86_EFLAGS_TF;
if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF))
rflags &= ~X86_EFLAGS_RF;
}
return rflags;
}
static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
if (to_svm(vcpu)->nmi_singlestep)
rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
/*
* Any change of EFLAGS.VM is accompanied by a reload of SS
* (caused by either a task switch or an inter-privilege IRET),
@@ -2112,10 +2138,7 @@ static int db_interception(struct vcpu_svm *svm)
}
if (svm->nmi_singlestep) {
svm->nmi_singlestep = false;
if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
svm->vmcb->save.rflags &=
~(X86_EFLAGS_TF | X86_EFLAGS_RF);
disable_nmi_singlestep(svm);
}
if (svm->vcpu.guest_debug &
@@ -2370,8 +2393,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
static int nested_svm_check_permissions(struct vcpu_svm *svm)
{
if (!(svm->vcpu.arch.efer & EFER_SVME)
|| !is_paging(&svm->vcpu)) {
if (!(svm->vcpu.arch.efer & EFER_SVME) ||
!is_paging(&svm->vcpu)) {
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
}
@@ -2381,7 +2404,7 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm)
return 1;
}
return 0;
return 0;
}
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
@@ -2534,6 +2557,31 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}
/* DB exceptions for our internal use must not cause vmexit */
static int nested_svm_intercept_db(struct vcpu_svm *svm)
{
unsigned long dr6;
/* if we're not singlestepping, it's not ours */
if (!svm->nmi_singlestep)
return NESTED_EXIT_DONE;
/* if it's not a singlestep exception, it's not ours */
if (kvm_get_dr(&svm->vcpu, 6, &dr6))
return NESTED_EXIT_DONE;
if (!(dr6 & DR6_BS))
return NESTED_EXIT_DONE;
/* if the guest is singlestepping, it should get the vmexit */
if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) {
disable_nmi_singlestep(svm);
return NESTED_EXIT_DONE;
}
/* it's ours, the nested hypervisor must not see this one */
return NESTED_EXIT_HOST;
}
static int nested_svm_exit_special(struct vcpu_svm *svm)
{
u32 exit_code = svm->vmcb->control.exit_code;
@@ -2589,8 +2637,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
}
case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
if (svm->nested.intercept_exceptions & excp_bits)
vmexit = NESTED_EXIT_DONE;
if (svm->nested.intercept_exceptions & excp_bits) {
if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR)
vmexit = nested_svm_intercept_db(svm);
else
vmexit = NESTED_EXIT_DONE;
}
/* async page fault always cause vmexit */
else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) &&
svm->apf_reason != 0)
@@ -4627,10 +4679,17 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
== HF_NMI_MASK)
return; /* IRET will cause a vm exit */
if ((svm->vcpu.arch.hflags & HF_GIF_MASK) == 0)
return; /* STGI will cause a vm exit */
if (svm->nested.exit_required)
return; /* we're not going to run the guest yet */
/*
* Something prevents NMI from been injected. Single step over possible
* problem (IRET or exception injection or interrupt shadow)
*/
svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu);
svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
}
@@ -4771,6 +4830,22 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(svm->nested.exit_required))
return;
/*
* Disable singlestep if we're injecting an interrupt/exception.
* We don't want our modified rflags to be pushed on the stack where
* we might not be able to easily reset them if we disabled NMI
* singlestep later.
*/
if (svm->nmi_singlestep && svm->vmcb->control.event_inj) {
/*
* Event injection happens before external interrupts cause a
* vmexit and interrupts are disabled here, so smp_send_reschedule
* is enough to force an immediate vmexit.
*/
disable_nmi_singlestep(svm);
smp_send_reschedule(vcpu->cpu);
}
pre_svm_run(svm);
sync_lapic_to_cr8(vcpu);