Merge branch 'kvm-older-features' into HEAD

[linux-2.6-microblaze.git] / arch / x86 / kvm / mmu / mmu.c

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 51671cb..c623019 100644 (file)
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1866,17 +1866,14 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
          &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)])     \
                if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
 
-static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
                         struct list_head *invalid_list)
 {
        int ret = vcpu->arch.mmu->sync_page(vcpu, sp);
 
-       if (ret < 0) {
+       if (ret < 0)
                kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
-               return false;
-       }
-
-       return !!ret;
+       return ret;
 }
 
 static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
@@ -1998,7 +1995,7 @@ static int mmu_sync_children(struct kvm_vcpu *vcpu,
 
                for_each_sp(pages, sp, parents, i) {
                        kvm_unlink_unsync_page(vcpu->kvm, sp);
-                       flush |= kvm_sync_page(vcpu, sp, &invalid_list);
+                       flush |= kvm_sync_page(vcpu, sp, &invalid_list) > 0;
                        mmu_pages_clear_parents(&parents);
                }
                if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
@@ -2039,6 +2036,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
        struct hlist_head *sp_list;
        unsigned quadrant;
        struct kvm_mmu_page *sp;
+       int ret;
        int collisions = 0;
        LIST_HEAD(invalid_list);
 
@@ -2091,11 +2089,13 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
                         * If the sync fails, the page is zapped.  If so, break
                         * in order to rebuild it.
                         */
-                       if (!kvm_sync_page(vcpu, sp, &invalid_list))
+                       ret = kvm_sync_page(vcpu, sp, &invalid_list);
+                       if (ret < 0)
                                break;
 
                        WARN_ON(!list_empty(&invalid_list));
-                       kvm_flush_remote_tlbs(vcpu->kvm);
+                       if (ret > 0)
+                               kvm_flush_remote_tlbs(vcpu->kvm);
                }
 
                __clear_sp_write_flooding_count(sp);
@@ -2696,8 +2696,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
        if (*sptep == spte) {
                ret = RET_PF_SPURIOUS;
        } else {
-               trace_kvm_mmu_set_spte(level, gfn, sptep);
                flush |= mmu_spte_update(sptep, spte);
+               trace_kvm_mmu_set_spte(level, gfn, sptep);
        }
 
        if (wrprot) {
@@ -3703,7 +3703,7 @@ void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu)
 }
 
 static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-                                 gpa_t vaddr, u32 access,
+                                 gpa_t vaddr, u64 access,
                                  struct x86_exception *exception)
 {
        if (exception)
@@ -4591,11 +4591,11 @@ static void update_permission_bitmask(struct kvm_mmu *mmu, bool ept)
                         *   - X86_CR4_SMAP is set in CR4
                         *   - A user page is accessed
                         *   - The access is not a fetch
-                        *   - Page fault in kernel mode
-                        *   - if CPL = 3 or X86_EFLAGS_AC is clear
+                        *   - The access is supervisor mode
+                        *   - If implicit supervisor access or X86_EFLAGS_AC is clear
                         *
-                        * Here, we cover the first three conditions.
-                        * The fourth is computed dynamically in permission_fault();
+                        * Here, we cover the first four conditions.
+                        * The fifth is computed dynamically in permission_fault();
                         * PFERR_RSVD_MASK bit will be set in PFEC if the access is
                         * *not* subject to SMAP restrictions.
                         */
@@ -5768,17 +5768,24 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
        kvm_mmu_zap_all_fast(kvm);
 }
 
-void kvm_mmu_init_vm(struct kvm *kvm)
+int kvm_mmu_init_vm(struct kvm *kvm)
 {
        struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
+       int r;
 
+       INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+       INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
+       INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
        spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
-       kvm_mmu_init_tdp_mmu(kvm);
+       r = kvm_mmu_init_tdp_mmu(kvm);
+       if (r < 0)
+               return r;
 
        node->track_write = kvm_mmu_pte_write;
        node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot;
        kvm_page_track_register_notifier(kvm, node);
+       return 0;
 }
 
 void kvm_mmu_uninit_vm(struct kvm *kvm)
@@ -5842,8 +5849,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
        if (is_tdp_mmu_enabled(kvm)) {
                for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-                       flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start,
-                                                         gfn_end, flush);
+                       flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
+                                                     gfn_end, true, flush);
        }
 
        if (flush)
@@ -6230,12 +6237,24 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
        return 0;
 }
 
-int kvm_mmu_module_init(void)
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+void kvm_mmu_x86_module_init(void)
 {
-       int ret = -ENOMEM;
-
        if (nx_huge_pages == -1)
                __set_nx_huge_pages(get_nx_auto_mode());
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+       int ret = -ENOMEM;
 
        /*
         * MMU roles use union aliasing which is, generally speaking, an
@@ -6283,7 +6302,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
        mmu_free_memory_caches(vcpu);
 }
 
-void kvm_mmu_module_exit(void)
+void kvm_mmu_vendor_module_exit(void)
 {
        mmu_destroy_caches();
        percpu_counter_destroy(&kvm_total_used_mmu_pages);