KVM's "Lazy FPU loading" means that sometimes L0 needs to set CR0.TS, even
if a guest didn't set it. Moreover, L0 must also trap CR0.TS changes and
NM exceptions, even if we have a guest hypervisor (L1) who didn't want these
traps. And of course, conversely: If L1 wanted to trap these events, we
must let it, even if L0 is not interested in them.
This patch fixes some existing KVM code (in update_exception_bitmap(),
vmx_fpu_activate(), vmx_fpu_deactivate()) to do the correct merging of L0's
and L1's needs. Note that handle_cr() was already fixed in the above patch,
and that new code in introduced in previous patches already handles CR0
correctly (see prepare_vmcs02(), prepare_vmcs12(), and nested_vmx_vmexit()).
Signed-off-by: Nadav Har'El <nyh@xxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 31 ++++++++++++++++++++++++++++++-
1 file changed, 30 insertions(+), 1 deletion(-)
--- .before/arch/x86/kvm/vmx.c 2011-05-08 10:43:21.000000000 +0300
+++ .after/arch/x86/kvm/vmx.c 2011-05-08 10:43:21.000000000 +0300
@@ -1170,6 +1170,15 @@ static void update_exception_bitmap(stru
eb &= ~(1u << PF_VECTOR); /* bypass_guest_pf = 0 */
if (vcpu->fpu_active)
eb &= ~(1u << NM_VECTOR);
+
+ /* When we are running a nested L2 guest and L1 specified for it a
+ * certain exception bitmap, we must trap the same exceptions and pass
+ * them to L1. When running L2, we will only handle the exceptions
+ * specified above if L1 did not want them.
+ */
+ if (is_guest_mode(vcpu))
+ eb |= get_vmcs12(vcpu)->exception_bitmap;
+
vmcs_write32(EXCEPTION_BITMAP, eb);
}
@@ -1464,6 +1473,9 @@ static void vmx_fpu_activate(struct kvm_
vmcs_writel(GUEST_CR0, cr0);
update_exception_bitmap(vcpu);
vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ if (is_guest_mode(vcpu))
+ vcpu->arch.cr0_guest_owned_bits &=
+ ~get_vmcs12(vcpu)->cr0_guest_host_mask;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
}
@@ -1487,12 +1499,29 @@ static inline unsigned long guest_readab
static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
{
+ /* Note that there is no vcpu->fpu_active = 0 here. The caller must
+ * set this *before* calling this function.
+ */
vmx_decache_cr0_guest_bits(vcpu);
vmcs_set_bits(GUEST_CR0, X86_CR0_TS | X86_CR0_MP);
update_exception_bitmap(vcpu);
vcpu->arch.cr0_guest_owned_bits = 0;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
- vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
+ if (is_guest_mode(vcpu)) {
+ /*
+ * L1's specified read shadow might not contain the TS bit,
+ * so now that we turned on shadowing of this bit, we need to
+ * set this bit of the shadow. Like in nested_vmx_run we need
+ * guest_readable_cr0(vmcs12), but vmcs12->guest_cr0 is not
+ * yet up-to-date here because we just decached cr0.TS (and
+ * we'll only update vmcs12->guest_cr0 on nested exit).
+ */
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ vmcs12->guest_cr0 = (vmcs12->guest_cr0 & ~X86_CR0_TS) |
+ (vcpu->arch.cr0 & X86_CR0_TS);
+ vmcs_writel(CR0_READ_SHADOW, guest_readable_cr0(vmcs12));
+ } else
+ vmcs_writel(CR0_READ_SHADOW, vcpu->arch.cr0);
}
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
