diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a91cd99f26e..f2fe6ec0894 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -48,8 +48,8 @@ static int perf_event__exit_del_thread(union perf_event *event,
 		    event->fork.ppid, event->fork.ptid);
 
 	if (thread) {
-		rb_erase(&thread->rb_node, &session->threads);
-		session->last_match = NULL;
+		rb_erase(&thread->rb_node, &session->host_machine.threads);
+		session->host_machine.last_match = NULL;
 		thread__delete(thread);
 	}
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 78284b13e80..316aa0ab712 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -562,6 +562,10 @@ int machine__init(struct machine *self, const char *root_dir, pid_t pid)
 	INIT_LIST_HEAD(&self->user_dsos);
 	INIT_LIST_HEAD(&self->kernel_dsos);
 
+	self->threads = RB_ROOT;
+	INIT_LIST_HEAD(&self->dead_threads);
+	self->last_match = NULL;
+
 	self->kmaps.machine = self;
 	self->pid	    = pid;
 	self->root_dir      = strdup(root_dir);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 890d85545d0..bde6835ee25 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -62,6 +62,9 @@ struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
 	char		  *root_dir;
+	struct rb_root	  threads;
+	struct list_head  dead_threads;
+	struct thread	  *last_match;
 	struct list_head  user_dsos;
 	struct list_head  kernel_dsos;
 	struct map_groups kmaps;
@@ -190,6 +193,12 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       struct map **mapp,
 					       symbol_filter_t filter);
 
+
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
+void machine__remove_thread(struct machine *machine, struct thread *th);
+
+size_t machine__fprintf(struct machine *machine, FILE *fp);
+
 static inline
 struct symbol *machine__find_kernel_symbol(struct machine *self,
 					   enum map_type type, u64 addr,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 85c1e6b76f0..a76666f1776 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -139,9 +139,6 @@ struct perf_session *perf_session__new(const char *filename, int mode,
 		goto out;
 
 	memcpy(self->filename, filename, len);
-	self->threads = RB_ROOT;
-	INIT_LIST_HEAD(&self->dead_threads);
-	self->last_match = NULL;
 	/*
 	 * On 64bit we can mmap the data file in one go. No need for tiny mmap
 	 * slices. On 32bit we use 32MB.
@@ -184,17 +181,22 @@ out_delete:
 	return NULL;
 }
 
-static void perf_session__delete_dead_threads(struct perf_session *self)
+static void machine__delete_dead_threads(struct machine *machine)
 {
 	struct thread *n, *t;
 
-	list_for_each_entry_safe(t, n, &self->dead_threads, node) {
+	list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
 		list_del(&t->node);
 		thread__delete(t);
 	}
 }
 
-static void perf_session__delete_threads(struct perf_session *self)
+static void perf_session__delete_dead_threads(struct perf_session *session)
+{
+	machine__delete_dead_threads(&session->host_machine);
+}
+
+static void machine__delete_threads(struct machine *self)
 {
 	struct rb_node *nd = rb_first(&self->threads);
 
@@ -207,6 +209,11 @@ static void perf_session__delete_threads(struct perf_session *self)
 	}
 }
 
+static void perf_session__delete_threads(struct perf_session *session)
+{
+	machine__delete_threads(&session->host_machine);
+}
+
 void perf_session__delete(struct perf_session *self)
 {
 	perf_session__destroy_kernel_maps(self);
@@ -217,7 +224,7 @@ void perf_session__delete(struct perf_session *self)
 	free(self);
 }
 
-void perf_session__remove_thread(struct perf_session *self, struct thread *th)
+void machine__remove_thread(struct machine *self, struct thread *th)
 {
 	self->last_match = NULL;
 	rb_erase(&th->rb_node, &self->threads);
@@ -884,6 +891,11 @@ void perf_event_header__bswap(struct perf_event_header *self)
 	self->size = bswap_16(self->size);
 }
 
+struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
+{
+	return machine__findnew_thread(&session->host_machine, pid);
+}
+
 static struct thread *perf_session__register_idle_thread(struct perf_session *self)
 {
 	struct thread *thread = perf_session__findnew(self, 0);
@@ -1224,6 +1236,27 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 	return ret;
 }
 
+size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
+{
+	/*
+	 * FIXME: Here we have to actually print all the machines in this
+	 * session, not just the host...
+	 */
+	return machine__fprintf(&session->host_machine, fp);
+}
+
+void perf_session__remove_thread(struct perf_session *session,
+				 struct thread *th)
+{
+	/*
+	 * FIXME: This one makes no sense, we need to remove the thread from
+	 * the machine it belongs to, perf_session can have many machines, so
+	 * doing it always on ->host_machine is wrong.  Fix when auditing all
+	 * the 'perf kvm' code.
+	 */
+	machine__remove_thread(&session->host_machine, th);
+}
+
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					      unsigned int type)
 {
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 6e393c98eb3..76d462d3bef 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -30,9 +30,6 @@ struct perf_session {
 	struct perf_header	header;
 	unsigned long		size;
 	unsigned long		mmap_window;
-	struct rb_root		threads;
-	struct list_head	dead_threads;
-	struct thread		*last_match;
 	struct machine		host_machine;
 	struct rb_root		machines;
 	struct perf_evlist	*evlist;
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index d5d3b22250f..fb4b7ea6752 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -61,7 +61,7 @@ static size_t thread__fprintf(struct thread *self, FILE *fp)
 	       map_groups__fprintf(&self->mg, verbose, fp);
 }
 
-struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
+struct thread *machine__findnew_thread(struct machine *self, pid_t pid)
 {
 	struct rb_node **p = &self->threads.rb_node;
 	struct rb_node *parent = NULL;
@@ -125,12 +125,12 @@ int thread__fork(struct thread *self, struct thread *parent)
 	return 0;
 }
 
-size_t perf_session__fprintf(struct perf_session *self, FILE *fp)
+size_t machine__fprintf(struct machine *machine, FILE *fp)
 {
 	size_t ret = 0;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->threads); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
 		struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
 		ret += thread__fprintf(pos, fp);