summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorDavid Matlack <dmatlack@google.com>2016-03-30 12:24:47 -0700
committerPaolo Bonzini <pbonzini@redhat.com>2016-04-10 21:53:49 +0200
commitfc5b7f3bf1e1414bd4e91db6918c85ace0c873a5 (patch)
treeaae6c04ef461e36cf47fd6b04bbf459057fbfb33 /arch
parent7a98205deebfff9fc96f90d9e7b1a334b0bd3e2b (diff)
kvm: x86: do not leak guest xcr0 into host interrupt handlers
An interrupt handler that uses the fpu can kill a KVM VM, if it runs under the following conditions: - the guest's xcr0 register is loaded on the cpu - the guest's fpu context is not loaded - the host is using eagerfpu Note that the guest's xcr0 register and fpu context are not loaded as part of the atomic world switch into "guest mode". They are loaded by KVM while the cpu is still in "host mode". Usage of the fpu in interrupt context is gated by irq_fpu_usable(). The interrupt handler will look something like this: if (irq_fpu_usable()) { kernel_fpu_begin(); [... code that uses the fpu ...] kernel_fpu_end(); } As long as the guest's fpu is not loaded and the host is using eager fpu, irq_fpu_usable() returns true (interrupted_kernel_fpu_idle() returns true). The interrupt handler proceeds to use the fpu with the guest's xcr0 live. kernel_fpu_begin() saves the current fpu context. If this uses XSAVE[OPT], it may leave the xsave area in an undesirable state. According to the SDM, during XSAVE bit i of XSTATE_BV is not modified if bit i is 0 in xcr0. So it's possible that XSTATE_BV[i] == 1 and xcr0[i] == 0 following an XSAVE. kernel_fpu_end() restores the fpu context. Now if any bit i in XSTATE_BV == 1 while xcr0[i] == 0, XRSTOR generates a #GP. The fault is trapped and SIGSEGV is delivered to the current process. Only pre-4.2 kernels appear to be vulnerable to this sequence of events. Commit 653f52c ("kvm,x86: load guest FPU context more eagerly") from 4.2 forces the guest's fpu to always be loaded on eagerfpu hosts. This patch fixes the bug by keeping the host's xcr0 loaded outside of the interrupts-disabled region where KVM switches into guest mode. Cc: stable@vger.kernel.org Suggested-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: David Matlack <dmatlack@google.com> [Move load after goto cancel_injection. - Paolo] Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/kvm/x86.c10
1 files changed, 4 insertions, 6 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0a2c70e43bc8..9b7798c7b210 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -700,7 +700,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
return 1;
}
- kvm_put_guest_xcr0(vcpu);
vcpu->arch.xcr0 = xcr0;
if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
@@ -6590,8 +6589,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_x86_ops->prepare_guest_switch(vcpu);
if (vcpu->fpu_active)
kvm_load_guest_fpu(vcpu);
- kvm_load_guest_xcr0(vcpu);
-
vcpu->mode = IN_GUEST_MODE;
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6618,6 +6615,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
+ kvm_load_guest_xcr0(vcpu);
+
if (req_immediate_exit)
smp_send_reschedule(vcpu->cpu);
@@ -6667,6 +6666,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
+ kvm_put_guest_xcr0(vcpu);
+
/* Interrupt is enabled by handle_external_intr() */
kvm_x86_ops->handle_external_intr(vcpu);
@@ -7314,7 +7315,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
* and assume host would use all available bits.
* Guest xcr0 would be loaded later.
*/
- kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
__kernel_fpu_begin();
__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
@@ -7323,8 +7323,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
- kvm_put_guest_xcr0(vcpu);
-
if (!vcpu->guest_fpu_loaded) {
vcpu->fpu_counter = 0;
return;