pt_element_t *ptep;
pt_element_t inherited_ar;
gfn_t gfn;
+ u32 error_code;
};
/*
* Fetch a guest pte for a guest virtual address
*/
-static void FNAME(walk_addr)(struct guest_walker *walker,
- struct kvm_vcpu *vcpu, gva_t addr)
+static int FNAME(walk_addr)(struct guest_walker *walker,
+ struct kvm_vcpu *vcpu, gva_t addr,
+ int write_fault, int user_fault, int fetch_fault)
{
hpa_t hpa;
struct kvm_memory_slot *slot;
walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3];
root = *walker->ptep;
if (!(root & PT_PRESENT_MASK))
- return;
+ goto not_present;
--walker->level;
}
#endif
ASSERT(((unsigned long)walker->table & PAGE_MASK) ==
((unsigned long)ptep & PAGE_MASK));
- if (is_present_pte(*ptep) && !(*ptep & PT_ACCESSED_MASK))
- *ptep |= PT_ACCESSED_MASK;
-
if (!is_present_pte(*ptep))
- break;
+ goto not_present;
+
+ if (write_fault && !is_writeble_pte(*ptep))
+ if (user_fault || is_write_protection(vcpu))
+ goto access_error;
+
+ if (user_fault && !(*ptep & PT_USER_MASK))
+ goto access_error;
+
+#if PTTYPE == 64
+ if (fetch_fault && is_nx(vcpu) && (*ptep & PT64_NX_MASK))
+ goto access_error;
+#endif
+
+ if (!(*ptep & PT_ACCESSED_MASK))
+ *ptep |= PT_ACCESSED_MASK; /* avoid rmw */
if (walker->level == PT_PAGE_TABLE_LEVEL) {
walker->gfn = (*ptep & PT_BASE_ADDR_MASK)
}
walker->ptep = ptep;
pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep);
+ return 1;
+
+not_present:
+ walker->error_code = 0;
+ goto err;
+
+access_error:
+ walker->error_code = PFERR_PRESENT_MASK;
+
+err:
+ if (write_fault)
+ walker->error_code |= PFERR_WRITE_MASK;
+ if (user_fault)
+ walker->error_code |= PFERR_USER_MASK;
+ if (fetch_fault)
+ walker->error_code |= PFERR_FETCH_MASK;
+ return 0;
}
static void FNAME(release_walker)(struct guest_walker *walker)
}
shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1,
metaphysical, shadow_ent);
- if (!shadow_page)
- return ERR_PTR(-ENOMEM);
shadow_addr = shadow_page->page_hpa;
shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK
| PT_WRITABLE_MASK | PT_USER_MASK;
pt_element_t *guest_ent;
int writable_shadow;
gfn_t gfn;
+ struct kvm_mmu_page *page;
if (is_writeble_pte(*shadow_ent))
- return 0;
+ return !user || (*shadow_ent & PT_USER_MASK);
writable_shadow = *shadow_ent & PT_SHADOW_WRITABLE_MASK;
if (user) {
}
gfn = walker->gfn;
- if (kvm_mmu_lookup_page(vcpu, gfn)) {
+
+ if (user) {
+ /*
+ * Usermode page faults won't be for page table updates.
+ */
+ while ((page = kvm_mmu_lookup_page(vcpu, gfn)) != NULL) {
+ pgprintk("%s: zap %lx %x\n",
+ __FUNCTION__, gfn, page->role.word);
+ kvm_mmu_zap_page(vcpu, page);
+ }
+ } else if (kvm_mmu_lookup_page(vcpu, gfn)) {
pgprintk("%s: found shadow page for %lx, marking ro\n",
__FUNCTION__, gfn);
+ *guest_ent |= PT_DIRTY_MASK;
*write_pt = 1;
return 0;
}
mark_page_dirty(vcpu->kvm, gfn);
*shadow_ent |= PT_WRITABLE_MASK;
*guest_ent |= PT_DIRTY_MASK;
- rmap_add(vcpu->kvm, shadow_ent);
+ rmap_add(vcpu, shadow_ent);
return 1;
}
* - normal guest page fault due to the guest pte marked not present, not
* writable, or not executable
*
- * Returns: 1 if we need to emulate the instruction, 0 otherwise
+ * Returns: 1 if we need to emulate the instruction, 0 otherwise, or
+ * a negative value on error.
*/
static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
u32 error_code)
{
int write_fault = error_code & PFERR_WRITE_MASK;
- int pte_present = error_code & PFERR_PRESENT_MASK;
int user_fault = error_code & PFERR_USER_MASK;
+ int fetch_fault = error_code & PFERR_FETCH_MASK;
struct guest_walker walker;
u64 *shadow_pte;
int fixed;
int write_pt = 0;
+ int r;
pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code);
+ kvm_mmu_audit(vcpu, "pre page fault");
+
+ r = mmu_topup_memory_caches(vcpu);
+ if (r)
+ return r;
+
/*
* Look up the shadow pte for the faulting address.
*/
- for (;;) {
- FNAME(walk_addr)(&walker, vcpu, addr);
- shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
- if (IS_ERR(shadow_pte)) { /* must be -ENOMEM */
- printk("%s: oom\n", __FUNCTION__);
- nonpaging_flush(vcpu);
- FNAME(release_walker)(&walker);
- continue;
- }
- break;
- }
+ r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault,
+ fetch_fault);
/*
* The page is not mapped by the guest. Let the guest handle it.
*/
- if (!shadow_pte) {
- pgprintk("%s: not mapped\n", __FUNCTION__);
- inject_page_fault(vcpu, addr, error_code);
+ if (!r) {
+ pgprintk("%s: guest page fault\n", __FUNCTION__);
+ inject_page_fault(vcpu, addr, walker.error_code);
FNAME(release_walker)(&walker);
return 0;
}
+ shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
pgprintk("%s: shadow pte %p %llx\n", __FUNCTION__,
shadow_pte, *shadow_pte);
* mmio: emulate if accessible, otherwise its a guest fault.
*/
if (is_io_pte(*shadow_pte)) {
- if (may_access(*shadow_pte, write_fault, user_fault))
- return 1;
- pgprintk("%s: io work, no access\n", __FUNCTION__);
- inject_page_fault(vcpu, addr,
- error_code | PFERR_PRESENT_MASK);
- return 0;
- }
-
- /*
- * pte not present, guest page fault.
- */
- if (pte_present && !fixed && !write_pt) {
- inject_page_fault(vcpu, addr, error_code);
- return 0;
+ return 1;
}
++kvm_stat.pf_fixed;
+ kvm_mmu_audit(vcpu, "post page fault (fixed)");
return write_pt;
}
pt_element_t guest_pte;
gpa_t gpa;
- FNAME(walk_addr)(&walker, vcpu, vaddr);
+ FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0);
guest_pte = *walker.ptep;
FNAME(release_walker)(&walker);