KVM: MMU: Fold fix_read_pf() into set_pte_common()

[linux-2.6] / drivers / kvm / paging_tmpl.h

diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 65763007f04d98844f9a1bc0eaac273d40d296e0..869582befaf1fec68768db822b1d642d922ab756 100644 (file)
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -195,11 +195,13 @@ static void FNAME(mark_pagetable_dirty)(struct kvm *kvm,
 static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
                                  u64 *shadow_pte,
                                  gpa_t gaddr,
-                                 int dirty,
+                                 pt_element_t *gpte,
                                  u64 access_bits,
+                                 int write_fault,
                                  gfn_t gfn)
 {
        hpa_t paddr;
+       int dirty = *gpte & PT_DIRTY_MASK;
 
        *shadow_pte |= access_bits << PT_SHADOW_BITS_OFFSET;
        if (!dirty)
@@ -218,6 +220,17 @@ static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
 
        *shadow_pte |= paddr;
 
+       if (!write_fault && (*shadow_pte & PT_SHADOW_USER_MASK) &&
+           !(*shadow_pte & PT_USER_MASK)) {
+               /*
+                * If supervisor write protect is disabled, we shadow kernel
+                * pages as user pages so we can trap the write access.
+                */
+               *shadow_pte |= PT_USER_MASK;
+               *shadow_pte &= ~PT_WRITABLE_MASK;
+               access_bits &= ~PT_WRITABLE_MASK;
+       }
+
        if (access_bits & PT_WRITABLE_MASK) {
                struct kvm_mmu_page *shadow;
 
@@ -240,14 +253,15 @@ static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
        rmap_add(vcpu, shadow_pte);
 }
 
-static void FNAME(set_pte)(struct kvm_vcpu *vcpu, u64 guest_pte,
-                          u64 *shadow_pte, u64 access_bits, gfn_t gfn)
+static void FNAME(set_pte)(struct kvm_vcpu *vcpu, pt_element_t *gpte,
+                          u64 *shadow_pte, u64 access_bits,
+                          int write_fault, gfn_t gfn)
 {
        ASSERT(*shadow_pte == 0);
-       access_bits &= guest_pte;
-       *shadow_pte = (guest_pte & PT_PTE_COPY_MASK);
-       FNAME(set_pte_common)(vcpu, shadow_pte, guest_pte & PT_BASE_ADDR_MASK,
-                             guest_pte & PT_DIRTY_MASK, access_bits, gfn);
+       access_bits &= *gpte;
+       *shadow_pte = (*gpte & PT_PTE_COPY_MASK);
+       FNAME(set_pte_common)(vcpu, shadow_pte, *gpte & PT_BASE_ADDR_MASK,
+                             gpte, access_bits, write_fault, gfn);
 }
 
 static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
@@ -261,31 +275,32 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
        if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK))
                return;
        pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte);
-       FNAME(set_pte)(vcpu, gpte, spte, PT_USER_MASK | PT_WRITABLE_MASK,
+       FNAME(set_pte)(vcpu, &gpte, spte, PT_USER_MASK | PT_WRITABLE_MASK, 0,
                       (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT);
 }
 
-static void FNAME(set_pde)(struct kvm_vcpu *vcpu, u64 guest_pde,
-                          u64 *shadow_pte, u64 access_bits, gfn_t gfn)
+static void FNAME(set_pde)(struct kvm_vcpu *vcpu, pt_element_t *gpde,
+                          u64 *shadow_pte, u64 access_bits, int write_fault,
+                          gfn_t gfn)
 {
        gpa_t gaddr;
 
        ASSERT(*shadow_pte == 0);
-       access_bits &= guest_pde;
+       access_bits &= *gpde;
        gaddr = (gpa_t)gfn << PAGE_SHIFT;
        if (PTTYPE == 32 && is_cpuid_PSE36())
-               gaddr |= (guest_pde & PT32_DIR_PSE36_MASK) <<
+               gaddr |= (*gpde & PT32_DIR_PSE36_MASK) <<
                        (32 - PT32_DIR_PSE36_SHIFT);
-       *shadow_pte = guest_pde & PT_PTE_COPY_MASK;
+       *shadow_pte = *gpde & PT_PTE_COPY_MASK;
        FNAME(set_pte_common)(vcpu, shadow_pte, gaddr,
-                             guest_pde & PT_DIRTY_MASK, access_bits, gfn);
+                             gpde, access_bits, write_fault, gfn);
 }
 
 /*
  * Fetch a shadow pte for a specific level in the paging hierarchy.
  */
 static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
-                             struct guest_walker *walker)
+                        struct guest_walker *walker, int write_fault)
 {
        hpa_t shadow_addr;
        int level;
@@ -349,13 +364,13 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
        if (walker->level == PT_DIRECTORY_LEVEL) {
                if (prev_shadow_ent)
                        *prev_shadow_ent |= PT_SHADOW_PS_MARK;
-               FNAME(set_pde)(vcpu, *guest_ent, shadow_ent,
-                              walker->inherited_ar, walker->gfn);
+               FNAME(set_pde)(vcpu, guest_ent, shadow_ent,
+                              walker->inherited_ar, write_fault, walker->gfn);
        } else {
                ASSERT(walker->level == PT_PAGE_TABLE_LEVEL);
-               FNAME(set_pte)(vcpu, *guest_ent, shadow_ent,
+               FNAME(set_pte)(vcpu, guest_ent, shadow_ent,
                               walker->inherited_ar,
-                              walker->gfn);
+                              write_fault, walker->gfn);
        }
        return shadow_ent;
 }
@@ -488,7 +503,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
                return 0;
        }
 
-       shadow_pte = FNAME(fetch)(vcpu, addr, &walker);
+       shadow_pte = FNAME(fetch)(vcpu, addr, &walker, write_fault);
        pgprintk("%s: shadow pte %p %llx\n", __FUNCTION__,
                 shadow_pte, *shadow_pte);
 
@@ -498,8 +513,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
        if (write_fault)
                fixed = FNAME(fix_write_pf)(vcpu, shadow_pte, &walker, addr,
                                            user_fault, &write_pt);
-       else
-               fixed = fix_read_pf(shadow_pte);
 
        pgprintk("%s: updated shadow pte %p %llx\n", __FUNCTION__,
                 shadow_pte, *shadow_pte);