[PATCH] KVM: MMU: Use the guest pdptrs instead of mapping cr3 in pae mode

This lets us not write protect a partial page, and is anyway what a real
processor does.

Signed-off-by: Avi Kivity <avi@qumranet.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index 4512d8c39c849cf4305e2d97a449ceef1a30fac4..68e121eeccbc60467a31bf1b3e48db4dd19d1a26 100644 (file)
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -1491,6 +1491,8 @@ static int kvm_dev_ioctl_set_sregs(struct kvm *kvm, struct kvm_sregs *sregs)
 
        mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
        kvm_arch_ops->set_cr4(vcpu, sregs->cr4);
+       if (!is_long_mode(vcpu) && is_pae(vcpu))
+               load_pdptrs(vcpu, vcpu->cr3);
 
        if (mmu_reset_needed)
                kvm_mmu_reset_context(vcpu);

diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 963d80e2271ffcf263f88bae7f2c2405a18a1972..3ade9445ab239da38ad4f8596186f2e922c9302c 100644 (file)
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -67,18 +67,28 @@ static void FNAME(walk_addr)(struct guest_walker *walker,
        hpa_t hpa;
        struct kvm_memory_slot *slot;
        pt_element_t *ptep;
+       pt_element_t root;
 
        walker->level = vcpu->mmu.root_level;
-       walker->table_gfn = (vcpu->cr3 & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
+       walker->table = NULL;
+       root = vcpu->cr3;
+#if PTTYPE == 64
+       if (!is_long_mode(vcpu)) {
+               walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
+               root = *walker->ptep;
+               if (!(root & PT_PRESENT_MASK))
+                       return;
+               --walker->level;
+       }
+#endif
+       walker->table_gfn = (root & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
        slot = gfn_to_memslot(vcpu->kvm, walker->table_gfn);
-       hpa = safe_gpa_to_hpa(vcpu, vcpu->cr3 & PT64_BASE_ADDR_MASK);
+       hpa = safe_gpa_to_hpa(vcpu, root & PT64_BASE_ADDR_MASK);
        walker->table = kmap_atomic(pfn_to_page(hpa >> PAGE_SHIFT), KM_USER0);
 
        ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
               (vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) == 0);
 
-       walker->table = (pt_element_t *)( (unsigned long)walker->table |
-               (unsigned long)(vcpu->cr3 & ~(PAGE_MASK | CR3_FLAGS_MASK)) );
        walker->inherited_ar = PT_USER_MASK | PT_WRITABLE_MASK;
 
        for (;;) {
@@ -89,11 +99,8 @@ static void FNAME(walk_addr)(struct guest_walker *walker,
                ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
                       ((unsigned long)ptep & PAGE_MASK));
 
-               /* Don't set accessed bit on PAE PDPTRs */
-               if (vcpu->mmu.root_level != 3 || walker->level != 3)
-                       if ((*ptep & (PT_PRESENT_MASK | PT_ACCESSED_MASK))
-                           == PT_PRESENT_MASK)
-                               *ptep |= PT_ACCESSED_MASK;
+               if (is_present_pte(*ptep) && !(*ptep &  PT_ACCESSED_MASK))
+                       *ptep |= PT_ACCESSED_MASK;
 
                if (!is_present_pte(*ptep) ||
                    walker->level == PT_PAGE_TABLE_LEVEL ||
@@ -116,7 +123,8 @@ static void FNAME(walk_addr)(struct guest_walker *walker,
 
 static void FNAME(release_walker)(struct guest_walker *walker)
 {
-       kunmap_atomic(walker->table, KM_USER0);
+       if (walker->table)
+               kunmap_atomic(walker->table, KM_USER0);
 }
 
 static void FNAME(set_pte)(struct kvm_vcpu *vcpu, u64 guest_pte,