KVM: X86: Optimize zapping rmap

Using rmap_get_first() and rmap_remove() for zapping a huge rmap list could be
slow.  The easy way is to travers the rmap list, collecting the a/d bits and
free the slots along the way.

Provide a pte_list_destroy() and do exactly that.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20210730220605.26377-1-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/mmu/mmu.c

@@ -1007,6 +1007,34 @@ static void pte_list_remove(struct kvm_rmap_head *rmap_head, u64 *sptep)
 	__pte_list_remove(sptep, rmap_head);
 }
 
+/* Return true if rmap existed, false otherwise */
+static bool pte_list_destroy(struct kvm_rmap_head *rmap_head)
+{
+	struct pte_list_desc *desc, *next;
+	int i;
+
+	if (!rmap_head->val)
+		return false;
+
+	if (!(rmap_head->val & 1)) {
+		mmu_spte_clear_track_bits((u64 *)rmap_head->val);
+		goto out;
+	}
+
+	desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
+
+	for (; desc; desc = next) {
+		for (i = 0; i < desc->spte_count; i++)
+			mmu_spte_clear_track_bits(desc->sptes[i]);
+		next = desc->more;
+		mmu_free_pte_list_desc(desc);
+	}
+out:
+	/* rmap_head is meaningless now, remember to reset it */
+	rmap_head->val = 0;
+	return true;
+}
+
 static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level,
 					   const struct kvm_memory_slot *slot)
 {
@@ -1398,18 +1426,7 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn)
 static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 			  const struct kvm_memory_slot *slot)
 {
-	u64 *sptep;
-	struct rmap_iterator iter;
-	bool flush = false;
-
-	while ((sptep = rmap_get_first(rmap_head, &iter))) {
-		rmap_printk("spte %p %llx.\n", sptep, *sptep);
-
-		pte_list_remove(rmap_head, sptep);
-		flush = true;
-	}
-
-	return flush;
+	return pte_list_destroy(rmap_head);
 }
 
 static bool kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,