On Tue, 2018-09-25 at 12:33 -0700, Junaid Shahid wrote:
> On 09/25/2018 07:48 AM, Sean Christopherson wrote:
...
> > @@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
> >
> > static void kvm_mmu_reset_all_pte_masks(void)
> > {
> > + u8 low_gpa_bits;
> > +
> > shadow_user_mask = 0;
> > shadow_accessed_mask = 0;
> > shadow_dirty_mask = 0;
> > @@ -437,12 +448,16 @@ static void kvm_mmu_reset_all_pte_masks(void)
> > * appropriate mask to guard against L1TF attacks. Otherwise, it is
> > * assumed that the CPU is not vulnerable to L1TF.
> > */
> > + low_gpa_bits = boot_cpu_data.x86_phys_bits;
> > if (boot_cpu_data.x86_phys_bits <
> > - 52 - shadow_nonpresent_or_rsvd_mask_len)
> > + 52 - shadow_nonpresent_or_rsvd_mask_len) {
> > shadow_nonpresent_or_rsvd_mask =
> > rsvd_bits(boot_cpu_data.x86_phys_bits -
> > shadow_nonpresent_or_rsvd_mask_len,
> > boot_cpu_data.x86_phys_bits - 1);
> > + low_gpa_bits -= shadow_nonpresent_or_rsvd_mask_len;
> > + }
> > + shadow_nonpresent_or_rsvd_lower_gpa_mask = (1ULL << low_gpa_bits) - 1;
> I think that it might be slightly better to do something like:
>
> + shadow_nonpresent_or_rsvd_lower_gpa_mask = rsvd_bits(PAGE_SHIFT, low_gpa_bits - 1);
>
> Of course, it doesn't matter for get_mmio_spte_gfn() because that already shifts by PAGE_SHIFT, but could matter if this were to get used somewhere else.
Good point, we're providing a mask for the GFN, not the GPA. I'll
send a v2.
