Merge git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/v4l-dvb

[pandora-kernel.git] / arch / x86 / kvm / mmu.c

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ee3f530..b0e4ddc 100644 (file)
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -66,7 +66,8 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {}
 #endif
 
 #if defined(MMU_DEBUG) || defined(AUDIT)
-static int dbg = 1;
+static int dbg = 0;
+module_param(dbg, bool, 0644);
 #endif
 
 #ifndef MMU_DEBUG
@@ -640,6 +641,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
                        rmap_remove(kvm, spte);
                        --kvm->stat.lpages;
                        set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+                       spte = NULL;
                        write_protected = 1;
                }
                spte = rmap_next(kvm, rmapp, spte);
@@ -775,6 +777,15 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
        BUG();
 }
 
+static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu,
+                                   struct kvm_mmu_page *sp)
+{
+       int i;
+
+       for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
+               sp->spt[i] = shadow_trap_nonpresent_pte;
+}
+
 static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
 {
        unsigned index;
@@ -840,7 +851,10 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
        hlist_add_head(&sp->hash_link, bucket);
        if (!metaphysical)
                rmap_write_protect(vcpu->kvm, gfn);
-       vcpu->arch.mmu.prefetch_page(vcpu, sp);
+       if (shadow_trap_nonpresent_pte != shadow_notrap_nonpresent_pte)
+               vcpu->arch.mmu.prefetch_page(vcpu, sp);
+       else
+               nonpaging_prefetch_page(vcpu, sp);
        return sp;
 }
 
@@ -916,14 +930,17 @@ static void kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
        }
        kvm_mmu_page_unlink_children(kvm, sp);
        if (!sp->root_count) {
-               if (!sp->role.metaphysical)
+               if (!sp->role.metaphysical && !sp->role.invalid)
                        unaccount_shadowed(kvm, sp->gfn);
                hlist_del(&sp->hash_link);
                kvm_mmu_free_page(kvm, sp);
        } else {
+               int invalid = sp->role.invalid;
                list_move(&sp->link, &kvm->arch.active_mmu_pages);
                sp->role.invalid = 1;
                kvm_reload_remote_mmus(kvm);
+               if (!sp->role.metaphysical && !invalid)
+                       unaccount_shadowed(kvm, sp->gfn);
        }
        kvm_mmu_reset_last_pte_updated(kvm);
 }
@@ -1082,10 +1099,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
                struct kvm_mmu_page *shadow;
 
                spte |= PT_WRITABLE_MASK;
-               if (user_fault) {
-                       mmu_unshadow(vcpu->kvm, gfn);
-                       goto unshadowed;
-               }
 
                shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
                if (shadow ||
@@ -1102,13 +1115,11 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
                }
        }
 
-unshadowed:
-
        if (pte_access & ACC_WRITE_MASK)
                mark_page_dirty(vcpu->kvm, gfn);
 
        pgprintk("%s: setting spte %llx\n", __func__, spte);
-       pgprintk("instantiating %s PTE (%s) at %d (%llx) addr %llx\n",
+       pgprintk("instantiating %s PTE (%s) at %ld (%llx) addr %p\n",
                 (spte&PT_PAGE_SIZE_MASK)? "2MB" : "4kB",
                 (spte&PT_WRITABLE_MASK)?"RW":"R", gfn, spte, shadow_pte);
        set_shadow_pte(shadow_pte, spte);
@@ -1127,8 +1138,10 @@ unshadowed:
                else
                        kvm_release_pfn_clean(pfn);
        }
-       if (!ptwrite || !*ptwrite)
+       if (speculative) {
                vcpu->arch.last_pte_updated = shadow_pte;
+               vcpu->arch.last_pte_gfn = gfn;
+       }
 }
 
 static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
@@ -1176,9 +1189,10 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
                                return -ENOMEM;
                        }
 
-                       table[index] = __pa(new_table->spt)
-                               | PT_PRESENT_MASK | PT_WRITABLE_MASK
-                               | shadow_user_mask | shadow_x_mask;
+                       set_shadow_pte(&table[index],
+                                      __pa(new_table->spt)
+                                      | PT_PRESENT_MASK | PT_WRITABLE_MASK
+                                      | shadow_user_mask | shadow_x_mask);
                }
                table_addr = table[index] & PT64_BASE_ADDR_MASK;
        }
@@ -1216,15 +1230,6 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
 }
 
 
-static void nonpaging_prefetch_page(struct kvm_vcpu *vcpu,
-                                   struct kvm_mmu_page *sp)
-{
-       int i;
-
-       for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
-               sp->spt[i] = shadow_trap_nonpresent_pte;
-}
-
 static void mmu_free_roots(struct kvm_vcpu *vcpu)
 {
        int i;
@@ -1580,11 +1585,13 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
                                  u64 *spte,
                                  const void *new)
 {
-       if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
-           && !vcpu->arch.update_pte.largepage) {
-               ++vcpu->kvm->stat.mmu_pde_zapped;
-               return;
-       }
+       if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
+               if (!vcpu->arch.update_pte.largepage ||
+                   sp->role.glevels == PT32_ROOT_LEVEL) {
+                       ++vcpu->kvm->stat.mmu_pde_zapped;
+                       return;
+               }
+        }
 
        ++vcpu->kvm->stat.mmu_pte_updated;
        if (sp->role.glevels == PT32_ROOT_LEVEL)
@@ -1674,6 +1681,18 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
        vcpu->arch.update_pte.pfn = pfn;
 }
 
+static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+       u64 *spte = vcpu->arch.last_pte_updated;
+
+       if (spte
+           && vcpu->arch.last_pte_gfn == gfn
+           && shadow_accessed_mask
+           && !(*spte & shadow_accessed_mask)
+           && is_shadow_present_pte(*spte))
+               set_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
+}
+
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
                       const u8 *new, int bytes)
 {
@@ -1697,6 +1716,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
        pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
        mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
        spin_lock(&vcpu->kvm->mmu_lock);
+       kvm_mmu_access_page(vcpu, gfn);
        kvm_mmu_free_some_pages(vcpu);
        ++vcpu->kvm->stat.mmu_pte_write;
        kvm_mmu_audit(vcpu, "pre pte write");
@@ -1951,7 +1971,7 @@ void kvm_mmu_zap_all(struct kvm *kvm)
        kvm_flush_remote_tlbs(kvm);
 }
 
-void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+static void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
 {
        struct kvm_mmu_page *page;
 
@@ -1971,6 +1991,8 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
        list_for_each_entry(kvm, &vm_list, vm_list) {
                int npages;
 
+               if (!down_read_trylock(&kvm->slots_lock))
+                       continue;
                spin_lock(&kvm->mmu_lock);
                npages = kvm->arch.n_alloc_mmu_pages -
                         kvm->arch.n_free_mmu_pages;
@@ -1983,6 +2005,7 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
                nr_to_scan--;
 
                spin_unlock(&kvm->mmu_lock);
+               up_read(&kvm->slots_lock);
        }
        if (kvm_freed)
                list_move_tail(&kvm_freed->vm_list, &vm_list);