1 files changed, 77 insertions, 7 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cbc84c6abc2e..6e838cb6c9e1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1983,14 +1983,35 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp)
 	return true;
 }
 
+static __ro_after_init HLIST_HEAD(empty_page_hash);
+
+static struct hlist_head *kvm_get_mmu_page_hash(struct kvm *kvm, gfn_t gfn)
+{
+	/*
+	 * Ensure the load of the hash table pointer itself is ordered before
+	 * loads to walk the table.  The pointer is set at runtime outside of
+	 * mmu_lock when the TDP MMU is enabled, i.e. when the hash table of
+	 * shadow pages becomes necessary only when KVM needs to shadow L1's
+	 * TDP for an L2 guest.  Pairs with the smp_store_release() in
+	 * kvm_mmu_alloc_page_hash().
+	 */
+	struct hlist_head *page_hash = smp_load_acquire(&kvm->arch.mmu_page_hash);
+
+	lockdep_assert_held(&kvm->mmu_lock);
+
+	if (!page_hash)
+		return &empty_page_hash;
+
+	return &page_hash[kvm_page_table_hashfn(gfn)];
+}
+
 #define for_each_valid_sp(_kvm, _sp, _list)				\
 	hlist_for_each_entry(_sp, _list, hash_link)			\
 		if (is_obsolete_sp((_kvm), (_sp))) {			\
 		} else
 
 #define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn)		\
-	for_each_valid_sp(_kvm, _sp,					\
-	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)])	\
+	for_each_valid_sp(_kvm, _sp, kvm_get_mmu_page_hash(_kvm, _gfn))	\
 		if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else
 
 static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
@@ -2358,6 +2379,12 @@ static struct kvm_mmu_page *__kvm_mmu_get_shadow_page(struct kvm *kvm,
 	struct kvm_mmu_page *sp;
 	bool created = false;
 
+	/*
+	 * No need for memory barriers, unlike in kvm_get_mmu_page_hash(), as
+	 * mmu_page_hash must be set prior to creating the first shadow root,
+	 * i.e. reaching this point is fully serialized by slots_arch_lock.
+	 */
+	BUG_ON(!kvm->arch.mmu_page_hash);
 	sp_list = &kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)];
 
 	sp = kvm_mmu_find_shadow_page(kvm, vcpu, gfn, sp_list, role);
@@ -3882,6 +3909,28 @@ out_unlock:
 	return r;
 }
 
+static int kvm_mmu_alloc_page_hash(struct kvm *kvm)
+{
+	struct hlist_head *h;
+
+	if (kvm->arch.mmu_page_hash)
+		return 0;
+
+	h = kvcalloc(KVM_NUM_MMU_PAGES, sizeof(*h), GFP_KERNEL_ACCOUNT);
+	if (!h)
+		return -ENOMEM;
+
+	/*
+	 * Ensure the hash table pointer is set only after all stores to zero
+	 * the memory are retired.  Pairs with the smp_load_acquire() in
+	 * kvm_get_mmu_page_hash().  Note, mmu_lock must be held for write to
+	 * add (or remove) shadow pages, and so readers are guaranteed to see
+	 * an empty list for their current mmu_lock critical section.
+	 */
+	smp_store_release(&kvm->arch.mmu_page_hash, h);
+	return 0;
+}
+
 static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 {
 	struct kvm_memslots *slots;
@@ -3901,9 +3950,13 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
 	if (kvm_shadow_root_allocated(kvm))
 		goto out_unlock;
 
+	r = kvm_mmu_alloc_page_hash(kvm);
+	if (r)
+		goto out_unlock;
+
 	/*
-	 * Check if anything actually needs to be allocated, e.g. all metadata
-	 * will be allocated upfront if TDP is disabled.
+	 * Check if memslot metadata actually needs to be allocated, e.g. all
+	 * metadata will be allocated upfront if TDP is disabled.
 	 */
 	if (kvm_memslots_have_rmaps(kvm) &&
 	    kvm_page_track_write_tracking_enabled(kvm))
@@ -4896,12 +4949,16 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 {
 	u64 error_code = PFERR_GUEST_FINAL_MASK;
 	u8 level = PG_LEVEL_4K;
+	u64 direct_bits;
 	u64 end;
 	int r;
 
 	if (!vcpu->kvm->arch.pre_fault_allowed)
 		return -EOPNOTSUPP;
 
+	if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa)))
+		return -EINVAL;
+
 	/*
 	 * reload is efficient when called repeatedly, so we can do it on
 	 * every iteration.
@@ -4910,15 +4967,18 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 	if (r)
 		return r;
 
+	direct_bits = 0;
 	if (kvm_arch_has_private_mem(vcpu->kvm) &&
 	    kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
 		error_code |= PFERR_PRIVATE_ACCESS;
+	else
+		direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
 
 	/*
 	 * Shadow paging uses GVA for kvm page fault, so restrict to
 	 * two-dimensional paging.
 	 */
-	r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
+	r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level);
 	if (r < 0)
 		return r;
 
@@ -6675,15 +6735,22 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
 		kvm_tdp_mmu_zap_invalidated_roots(kvm, true);
 }
 
-void kvm_mmu_init_vm(struct kvm *kvm)
+int kvm_mmu_init_vm(struct kvm *kvm)
 {
+	int r;
+
 	kvm->arch.shadow_mmio_value = shadow_mmio_value;
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
 	spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
-	if (tdp_mmu_enabled)
+	if (tdp_mmu_enabled) {
 		kvm_mmu_init_tdp_mmu(kvm);
+	} else {
+		r = kvm_mmu_alloc_page_hash(kvm);
+		if (r)
+			return r;
+	}
 
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
 	kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
@@ -6692,6 +6759,7 @@ void kvm_mmu_init_vm(struct kvm *kvm)
 
 	kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache;
 	kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO;
+	return 0;
 }
 
 static void mmu_free_vm_memory_caches(struct kvm *kvm)
@@ -6703,6 +6771,8 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm)
 
 void kvm_mmu_uninit_vm(struct kvm *kvm)
 {
+	kvfree(kvm->arch.mmu_page_hash);
+
 	if (tdp_mmu_enabled)
 		kvm_mmu_uninit_tdp_mmu(kvm);