Merge branch 'kvm-tdp-fix-flushes' into HEAD

arch/x86/kvm/mmu/mmu.c

@@ -5939,6 +5939,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	struct kvm_mmu_page *sp;
 	unsigned int ratio;
 	LIST_HEAD(invalid_list);
+	bool flush = false;
 	ulong to_zap;
 
 	rcu_idx = srcu_read_lock(&kvm->srcu);
@@ -5960,19 +5961,19 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 				      lpage_disallowed_link);
 		WARN_ON_ONCE(!sp->lpage_disallowed);
 		if (is_tdp_mmu_page(sp)) {
-			kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
-				sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+			flush = kvm_tdp_mmu_zap_sp(kvm, sp);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 			WARN_ON_ONCE(sp->lpage_disallowed);
 		}
 
 		if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
-			kvm_mmu_commit_zap_page(kvm, &invalid_list);
+			kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
 			cond_resched_rwlock_write(&kvm->mmu_lock);
+			flush = false;
 		}
 	}
-	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
 
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, rcu_idx);

arch/x86/kvm/mmu/tdp_mmu.c

@@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 	list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
 
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield);
+			  gfn_t start, gfn_t end, bool can_yield, bool flush);
 
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
@@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 
 	list_del(&root->link);
 
-	zap_gfn_range(kvm, root, 0, max_gfn, false);
+	zap_gfn_range(kvm, root, 0, max_gfn, false, false);
 
 	free_page((unsigned long)root->spt);
 	kmem_cache_free(mmu_page_header_cache, root);
@@ -664,20 +664,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
  * scheduler needs the CPU or there is contention on the MMU lock. If this
  * function cannot yield, it will not release the MMU lock or reschedule and
  * the caller must ensure it does not supply too large a GFN range, or the
- * operation can cause a soft lockup.
+ * operation can cause a soft lockup.  Note, in some use cases a flush may be
+ * required by prior actions.  Ensure the pending flush is performed prior to
+ * yielding.
  */
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield)
+			  gfn_t start, gfn_t end, bool can_yield, bool flush)
 {
 	struct tdp_iter iter;
-	bool flush_needed = false;
 
 	rcu_read_lock();
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 		if (can_yield &&
-		    tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
-			flush_needed = false;
+		    tdp_mmu_iter_cond_resched(kvm, &iter, flush)) {
+			flush = false;
 			continue;
 		}
 
@@ -695,11 +696,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			continue;
 
 		tdp_mmu_set_spte(kvm, &iter, 0);
-		flush_needed = true;
+		flush = true;
 	}
 
 	rcu_read_unlock();
-	return flush_needed;
+	return flush;
 }
 
 /*
@@ -708,13 +709,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
  * SPTEs have been cleared and a TLB flush is needed before releasing the
  * MMU lock.
  */
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield)
 {
 	struct kvm_mmu_page *root;
 	bool flush = false;
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root)
-		flush |= zap_gfn_range(kvm, root, start, end, true);
+		flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
 
 	return flush;
 }
@@ -931,7 +933,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm,
 				     struct kvm_mmu_page *root, gfn_t start,
 				     gfn_t end, unsigned long unused)
 {
-	return zap_gfn_range(kvm, root, start, end, false);
+	return zap_gfn_range(kvm, root, start, end, false, false);
 }
 
 int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,

arch/x86/kvm/mmu/tdp_mmu.h

@@ -8,7 +8,29 @@
 hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root);
 
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end);
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield);
+static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start,
+					     gfn_t end)
+{
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true);
+}
+static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
+
+	/*
+	 * Don't allow yielding, as the caller may have a flush pending.  Note,
+	 * if mmu_lock is held for write, zapping will never yield in this case,
+	 * but explicitly disallow it for safety.  The TDP MMU does not yield
+	 * until it has made forward progress (steps sideways), and when zapping
+	 * a single shadow page that it's guaranteed to see (thus the mmu_lock
+	 * requirement), its "step sideways" will always step beyond the bounds
+	 * of the shadow page's gfn range and stop iterating before yielding.
+	 */
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false);
+}
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,