KVM: Modify guest segments after potentially switching modes

[linux-2.6-omap-h63xx.git] / drivers / kvm / mmu.c

diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c
index a1a93368f314d4e89226c3ab1b78dd9934135d42..2930d7cc7c0623fd301820f0013b0f217f28d6ca 100644 (file)
--- a/drivers/kvm/mmu.c
+++ b/drivers/kvm/mmu.c
@@ -131,7 +131,7 @@ static int dbg = 1;
        (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
 
 
-#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & PAGE_MASK)
+#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
 #define PT64_DIR_BASE_ADDR_MASK \
        (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
 
@@ -406,8 +406,8 @@ static void rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
                        spte = desc->shadow_ptes[0];
                }
                BUG_ON(!spte);
-               BUG_ON((*spte & PT64_BASE_ADDR_MASK) !=
-                      page_to_pfn(page) << PAGE_SHIFT);
+               BUG_ON((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT
+                      != page_to_pfn(page));
                BUG_ON(!(*spte & PT_PRESENT_MASK));
                BUG_ON(!(*spte & PT_WRITABLE_MASK));
                rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
@@ -461,7 +461,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
        list_add(&page->link, &vcpu->kvm->active_mmu_pages);
        ASSERT(is_empty_shadow_page(page->page_hpa));
        page->slot_bitmap = 0;
-       page->global = 1;
        page->multimapped = 0;
        page->parent_pte = parent_pte;
        --vcpu->kvm->n_free_mmu_pages;
@@ -735,6 +734,15 @@ hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva)
        return gpa_to_hpa(vcpu, gpa);
 }
 
+struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
+{
+       gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva);
+
+       if (gpa == UNMAPPED_GVA)
+               return NULL;
+       return pfn_to_page(gpa_to_hpa(vcpu, gpa) >> PAGE_SHIFT);
+}
+
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
 {
 }
@@ -918,11 +926,6 @@ static void paging_new_cr3(struct kvm_vcpu *vcpu)
        kvm_arch_ops->set_cr3(vcpu, vcpu->mmu.root_hpa);
 }
 
-static void mark_pagetable_nonglobal(void *shadow_pte)
-{
-       page_header(__pa(shadow_pte))->global = 0;
-}
-
 static inline void set_pte_common(struct kvm_vcpu *vcpu,
                             u64 *shadow_pte,
                             gpa_t gaddr,
@@ -940,9 +943,6 @@ static inline void set_pte_common(struct kvm_vcpu *vcpu,
 
        *shadow_pte |= access_bits;
 
-       if (!(*shadow_pte & PT_GLOBAL_MASK))
-               mark_pagetable_nonglobal(shadow_pte);
-
        if (is_error_hpa(paddr)) {
                *shadow_pte |= gaddr;
                *shadow_pte |= PT_SHADOW_IO_MARK;
@@ -1093,22 +1093,40 @@ out:
        return r;
 }
 
+static void mmu_pre_write_zap_pte(struct kvm_vcpu *vcpu,
+                                 struct kvm_mmu_page *page,
+                                 u64 *spte)
+{
+       u64 pte;
+       struct kvm_mmu_page *child;
+
+       pte = *spte;
+       if (is_present_pte(pte)) {
+               if (page->role.level == PT_PAGE_TABLE_LEVEL)
+                       rmap_remove(vcpu, spte);
+               else {
+                       child = page_header(pte & PT64_BASE_ADDR_MASK);
+                       mmu_page_remove_parent_pte(vcpu, child, spte);
+               }
+       }
+       *spte = 0;
+}
+
 void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
 {
        gfn_t gfn = gpa >> PAGE_SHIFT;
        struct kvm_mmu_page *page;
-       struct kvm_mmu_page *child;
        struct hlist_node *node, *n;
        struct hlist_head *bucket;
        unsigned index;
        u64 *spte;
-       u64 pte;
        unsigned offset = offset_in_page(gpa);
        unsigned pte_size;
        unsigned page_offset;
        unsigned misaligned;
        int level;
        int flooded = 0;
+       int npte;
 
        pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes);
        if (gfn == vcpu->last_pt_write_gfn) {
@@ -1144,22 +1162,27 @@ void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes)
                }
                page_offset = offset;
                level = page->role.level;
+               npte = 1;
                if (page->role.glevels == PT32_ROOT_LEVEL) {
-                       page_offset <<= 1;          /* 32->64 */
+                       page_offset <<= 1;      /* 32->64 */
+                       /*
+                        * A 32-bit pde maps 4MB while the shadow pdes map
+                        * only 2MB.  So we need to double the offset again
+                        * and zap two pdes instead of one.
+                        */
+                       if (level == PT32_ROOT_LEVEL) {
+                               page_offset &= ~7; /* kill rounding error */
+                               page_offset <<= 1;
+                               npte = 2;
+                       }
                        page_offset &= ~PAGE_MASK;
                }
                spte = __va(page->page_hpa);
                spte += page_offset / sizeof(*spte);
-               pte = *spte;
-               if (is_present_pte(pte)) {
-                       if (level == PT_PAGE_TABLE_LEVEL)
-                               rmap_remove(vcpu, spte);
-                       else {
-                               child = page_header(pte & PT64_BASE_ADDR_MASK);
-                               mmu_page_remove_parent_pte(vcpu, child, spte);
-                       }
+               while (npte--) {
+                       mmu_pre_write_zap_pte(vcpu, page, spte);
+                       ++spte;
                }
-               *spte = 0;
        }
 }
 
@@ -1337,7 +1360,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 
 static void audit_mappings(struct kvm_vcpu *vcpu)
 {
-       int i;
+       unsigned i;
 
        if (vcpu->mmu.root_level == 4)
                audit_mappings_page(vcpu, vcpu->mmu.root_hpa, 0, 4);