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

This prevents some work from being performed twice, and, more importantly,
reduces the number of places where we modify shadow ptes.

Signed-off-by: Avi Kivity <avi@qumranet.com>

2 files changed, 68 insertions, 111 deletions

diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index 2079d69f186a..3cdbf687df25 100644
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -731,6 +731,17 @@ static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn)
         return r;
 }
 
+static void mmu_unshadow(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+        struct kvm_mmu_page *page;
+
+        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);
+        }
+}
+
 static void page_header_update_slot(struct kvm *kvm, void *pte, gpa_t gpa)
 {
         int slot = memslot_id(kvm, gfn_to_memslot(kvm, gpa >> PAGE_SHIFT));
diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h
index 869582befaf1..c06720385551 100644
--- a/drivers/kvm/paging_tmpl.h
+++ b/drivers/kvm/paging_tmpl.h
@@ -197,11 +197,26 @@ static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
                                   gpa_t gaddr,
                                   pt_element_t *gpte,
                                   u64 access_bits,
+                                  int user_fault,
                                   int write_fault,
+                                  int *ptwrite,
+                                  struct guest_walker *walker,
                                   gfn_t gfn)
 {
         hpa_t paddr;
         int dirty = *gpte & PT_DIRTY_MASK;
+        int was_rmapped = is_rmap_pte(*shadow_pte);
+
+        pgprintk("%s: spte %llx gpte %llx access %llx write_fault %d"
+                 " user_fault %d gfn %lx\n",
+                 __FUNCTION__, *shadow_pte, (u64)*gpte, access_bits,
+                 write_fault, user_fault, gfn);
+
+        if (write_fault && !dirty) {
+                *gpte |= PT_DIRTY_MASK;
+                dirty = 1;
+                FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
+        }
 
         *shadow_pte |= access_bits << PT_SHADOW_BITS_OFFSET;
         if (!dirty)
@@ -209,7 +224,9 @@ static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
 
         paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK);
 
-        *shadow_pte |= access_bits;
+        *shadow_pte |= PT_PRESENT_MASK;
+        if (access_bits & PT_USER_MASK)
+                *shadow_pte |= PT_USER_MASK;
 
         if (is_error_hpa(paddr)) {
                 *shadow_pte |= gaddr;
@@ -231,37 +248,50 @@ static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu,
                 access_bits &= ~PT_WRITABLE_MASK;
         }
 
-        if (access_bits & PT_WRITABLE_MASK) {
+        if ((access_bits & PT_WRITABLE_MASK)
+            || (write_fault && !is_write_protection(vcpu) && !user_fault)) {
                 struct kvm_mmu_page *shadow;
 
+                *shadow_pte |= PT_WRITABLE_MASK;
+                if (user_fault) {
+                        mmu_unshadow(vcpu, gfn);
+                        goto unshadowed;
+                }
+
                 shadow = kvm_mmu_lookup_page(vcpu, gfn);
                 if (shadow) {
                         pgprintk("%s: found shadow page for %lx, marking ro\n",
                                  __FUNCTION__, gfn);
                         access_bits &= ~PT_WRITABLE_MASK;
                         if (is_writeble_pte(*shadow_pte)) {
-                                    *shadow_pte &= ~PT_WRITABLE_MASK;
-                                    kvm_arch_ops->tlb_flush(vcpu);
+                                *shadow_pte &= ~PT_WRITABLE_MASK;
+                                kvm_arch_ops->tlb_flush(vcpu);
                         }
+                        if (write_fault)
+                                *ptwrite = 1;
                 }
         }
 
+unshadowed:
+
         if (access_bits & PT_WRITABLE_MASK)
                 mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT);
 
         page_header_update_slot(vcpu->kvm, shadow_pte, gaddr);
-        rmap_add(vcpu, shadow_pte);
+        if (!was_rmapped)
+                rmap_add(vcpu, shadow_pte);
 }
 
 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)
+                           int user_fault, int write_fault, int *ptwrite,
+                           struct guest_walker *walker, gfn_t gfn)
 {
-        ASSERT(*shadow_pte == 0);
         access_bits &= *gpte;
-        *shadow_pte = (*gpte & PT_PTE_COPY_MASK);
+        *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);
+                              gpte, access_bits, user_fault, write_fault,
+                              ptwrite, walker, gfn);
 }
 
 static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
@@ -276,31 +306,34 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
                 return;
         pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte);
         FNAME(set_pte)(vcpu, &gpte, spte, PT_USER_MASK | PT_WRITABLE_MASK, 0,
+                       0, NULL, NULL,
                        (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT);
 }
 
 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)
+                           u64 *shadow_pte, u64 access_bits,
+                           int user_fault, int write_fault, int *ptwrite,
+                           struct guest_walker *walker, gfn_t gfn)
 {
         gpa_t gaddr;
 
-        ASSERT(*shadow_pte == 0);
         access_bits &= *gpde;
         gaddr = (gpa_t)gfn << PAGE_SHIFT;
         if (PTTYPE == 32 && is_cpuid_PSE36())
                 gaddr |= (*gpde & PT32_DIR_PSE36_MASK) <<
                         (32 - PT32_DIR_PSE36_SHIFT);
-        *shadow_pte = *gpde & PT_PTE_COPY_MASK;
+        *shadow_pte |= *gpde & PT_PTE_COPY_MASK;
         FNAME(set_pte_common)(vcpu, shadow_pte, gaddr,
-                              gpde, access_bits, write_fault, gfn);
+                              gpde, access_bits, user_fault, write_fault,
+                              ptwrite, walker, 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, int write_fault)
+                         struct guest_walker *walker,
+                         int user_fault, int write_fault, int *ptwrite)
 {
         hpa_t shadow_addr;
         int level;
@@ -330,7 +363,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
                 shadow_ent = ((u64 *)__va(shadow_addr)) + index;
                 if (is_present_pte(*shadow_ent) || is_io_pte(*shadow_ent)) {
                         if (level == PT_PAGE_TABLE_LEVEL)
-                                return shadow_ent;
+                                break;
                         shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK;
                         prev_shadow_ent = shadow_ent;
                         continue;
@@ -365,95 +398,18 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
                 if (prev_shadow_ent)
                         *prev_shadow_ent |= PT_SHADOW_PS_MARK;
                 FNAME(set_pde)(vcpu, guest_ent, shadow_ent,
-                               walker->inherited_ar, write_fault, walker->gfn);
+                               walker->inherited_ar, user_fault, write_fault,
+                               ptwrite, walker, walker->gfn);
         } else {
                 ASSERT(walker->level == PT_PAGE_TABLE_LEVEL);
                 FNAME(set_pte)(vcpu, guest_ent, shadow_ent,
-                               walker->inherited_ar,
-                               write_fault, walker->gfn);
+                               walker->inherited_ar, user_fault, write_fault,
+                               ptwrite, walker, walker->gfn);
         }
         return shadow_ent;
 }
 
 /*
- * The guest faulted for write.  We need to
- *
- * - check write permissions
- * - update the guest pte dirty bit
- * - update our own dirty page tracking structures
- */
-static int FNAME(fix_write_pf)(struct kvm_vcpu *vcpu,
-                               u64 *shadow_ent,
-                               struct guest_walker *walker,
-                               gva_t addr,
-                               int user,
-                               int *write_pt)
-{
-        pt_element_t *guest_ent;
-        int writable_shadow;
-        gfn_t gfn;
-        struct kvm_mmu_page *page;
-
-        if (is_writeble_pte(*shadow_ent))
-                return !user || (*shadow_ent & PT_USER_MASK);
-
-        writable_shadow = *shadow_ent & PT_SHADOW_WRITABLE_MASK;
-        if (user) {
-                /*
-                 * User mode access.  Fail if it's a kernel page or a read-only
-                 * page.
-                 */
-                if (!(*shadow_ent & PT_SHADOW_USER_MASK) || !writable_shadow)
-                        return 0;
-                ASSERT(*shadow_ent & PT_USER_MASK);
-        } else
-                /*
-                 * Kernel mode access.  Fail if it's a read-only page and
-                 * supervisor write protection is enabled.
-                 */
-                if (!writable_shadow) {
-                        if (is_write_protection(vcpu))
-                                return 0;
-                        *shadow_ent &= ~PT_USER_MASK;
-                }
-
-        guest_ent = walker->ptep;
-
-        if (!is_present_pte(*guest_ent)) {
-                *shadow_ent = 0;
-                return 0;
-        }
-
-        gfn = walker->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);
-                mark_page_dirty(vcpu->kvm, gfn);
-                FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
-                *guest_ent |= PT_DIRTY_MASK;
-                *write_pt = 1;
-                return 0;
-        }
-        mark_page_dirty(vcpu->kvm, gfn);
-        *shadow_ent |= PT_WRITABLE_MASK;
-        FNAME(mark_pagetable_dirty)(vcpu->kvm, walker);
-        *guest_ent |= PT_DIRTY_MASK;
-        rmap_add(vcpu, shadow_ent);
-
-        return 1;
-}
-
-/*
  * Page fault handler.  There are several causes for a page fault:
  *   - there is no shadow pte for the guest pte
  *   - write access through a shadow pte marked read only so that we can set
@@ -475,7 +431,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
         int fetch_fault = error_code & PFERR_FETCH_MASK;
         struct guest_walker walker;
         u64 *shadow_pte;
-        int fixed;
         int write_pt = 0;
         int r;
 
@@ -503,19 +458,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
                 return 0;
         }
 
-        shadow_pte = FNAME(fetch)(vcpu, addr, &walker, write_fault);
-        pgprintk("%s: shadow pte %p %llx\n", __FUNCTION__,
-                 shadow_pte, *shadow_pte);
-
-        /*
-         * Update the shadow pte.
-         */
-        if (write_fault)
-                fixed = FNAME(fix_write_pf)(vcpu, shadow_pte, &walker, addr,
-                                            user_fault, &write_pt);
-
-        pgprintk("%s: updated shadow pte %p %llx\n", __FUNCTION__,
-                 shadow_pte, *shadow_pte);
+        shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
+                                  &write_pt);
+        pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__,
+                 shadow_pte, *shadow_pte, write_pt);
 
         FNAME(release_walker)(&walker);