diff options
| author |   Liang Li <liang.z.li@intel.com> | 2015-05-21 04:41:25 +0800 |
|---|---|---|
| committer |   Paolo Bonzini <pbonzini@redhat.com> | 2015-05-20 12:30:26 +0200 |
| commit | c447e76b4cabb49ddae8e49c5758f031f35d55fb (patch) | |
| tree | d19c11fe52ca9c9078676902fbf893517fe5c626 /arch/x86/kvm/x86.c | |
| parent | Revert "KVM: x86: drop fpu_activate hook" (diff) | |
| download | linux-dev-c447e76b4cabb49ddae8e49c5758f031f35d55fb.tar.xz linux-dev-c447e76b4cabb49ddae8e49c5758f031f35d55fb.zip | |
kvm/fpu: Enable eager restore kvm FPU for MPX
The MPX feature requires eager KVM FPU restore support. We have verified
that MPX cannot work correctly with the current lazy KVM FPU restore
mechanism. Eager KVM FPU restore should be enabled if the MPX feature is
exposed to VM.
Signed-off-by: Yang Zhang <yang.z.zhang@intel.com>
Signed-off-by: Liang Li <liang.z.li@intel.com>
[Also activate the FPU on AMD processors. - Paolo]
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to '')
| -rw-r--r-- | arch/x86/kvm/x86.c | 16 |
1 files changed, 14 insertions, 2 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5f3818846465..ea306adbbc13 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7060,7 +7060,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) fpu_save_init(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + if (!vcpu->arch.eager_fpu) + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + trace_kvm_fpu(0); } @@ -7076,11 +7078,21 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) { + struct kvm_vcpu *vcpu; + if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0) printk_once(KERN_WARNING "kvm: SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); - return kvm_x86_ops->vcpu_create(kvm, id); + + vcpu = kvm_x86_ops->vcpu_create(kvm, id); + + /* + * Activate fpu unconditionally in case the guest needs eager FPU. It will be + * deactivated soon if it doesn't. + */ + kvm_x86_ops->fpu_activate(vcpu); + return vcpu; } int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) |