Avi Kivity wrote:
>>
>> How about only update the shadow page which has the same pae set with
>> the written
>> vcpu? Just like this:
>>
>> @@ -3000,6 +3000,10 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu,
>> gpa_t gpa,
>> while (npte--) {
>> entry =
On 07/12/2010 05:37 AM, Xiao Guangrong wrote:
+if (is_rsvd_bits_set(vcpu, gentry, PT_PAGE_TABLE_LEVEL))
+gentry = 0;
+
That only works if the gpte is for the same mode as the current vcpu mmu
mode. In some cases it is too strict (vcpu in pae mode writing a 32-bit
gpte),
Avi Kivity wrote:
>> +if (is_rsvd_bits_set(vcpu, gentry, PT_PAGE_TABLE_LEVEL))
>> +gentry = 0;
>> +
>>
>
> That only works if the gpte is for the same mode as the current vcpu mmu
> mode. In some cases it is too strict (vcpu in pae mode writing a 32-bit
> gpte), which is not to
On 07/06/2010 01:44 PM, Xiao Guangrong wrote:
In the speculative path, we should check guest pte's reserved bits just as
the real processor does
Reported-by: Marcelo Tosatti
Signed-off-by: Xiao Guangrong
---
arch/x86/kvm/mmu.c |3 +++
arch/x86/kvm/paging_tmpl.h |3 ++-
2 file
In the speculative path, we should check guest pte's reserved bits just as
the real processor does
Reported-by: Marcelo Tosatti
Signed-off-by: Xiao Guangrong
---
arch/x86/kvm/mmu.c |3 +++
arch/x86/kvm/paging_tmpl.h |3 ++-
2 files changed, 5 insertions(+), 1 deletions(-)
diff