KVM: MMU: Update shadow ptes on partial guest pte writes

A guest partial guest pte write will leave shadow_trap_nonpresent_pte
in spte, which generates a vmexit at the next guest access through that pte.

This patch improves this by reading the full guest pte in advance and thus
being able to update the spte and eliminate the vmexit.

This helps pae guests which use two 32-bit writes to set a single 64-bit pte.

[truncation fix by Eric]

Signed-off-by: Yaozu (Eddie) Dong <eddie.dong@intel.com>
Signed-off-by: Feng (Eric) Liu <eric.e.liu@intel.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>
This commit is contained in:
Dong, Eddie
2008-01-07 11:14:20 +02:00
committed by Avi Kivity
parent c3bf9bc243
commit 489f1d6526
2 changed files with 18 additions and 12 deletions

View File

@@ -243,8 +243,7 @@ err:
}
static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
u64 *spte, const void *pte, int bytes,
int offset_in_pte)
u64 *spte, const void *pte)
{
pt_element_t gpte;
unsigned pte_access;
@@ -252,12 +251,10 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
if (!offset_in_pte && !is_present_pte(gpte))
if (!is_present_pte(gpte))
set_shadow_pte(spte, shadow_notrap_nonpresent_pte);
return;
}
if (bytes < sizeof(pt_element_t))
return;
pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte);
pte_access = page->role.access & FNAME(gpte_access)(vcpu, gpte);
if (gpte_to_gfn(gpte) != vcpu->arch.update_pte.gfn)