diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 8bd960658463..fe1b02c2c95b 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -36,7 +36,7 @@ $(LIBFILE): $(API_IN)
 
 clean:
 	$(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \
-	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o | xargs $(RM)
+	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
 
 FORCE:
 
diff --git a/tools/lib/hweight.c b/tools/lib/hweight.c
new file mode 100644
index 000000000000..0b859b884339
--- /dev/null
+++ b/tools/lib/hweight.c
@@ -0,0 +1,62 @@
+#include <linux/bitops.h>
+#include <asm/types.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int __sw_hweight32(unsigned int w)
+{
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x55555555;
+	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f;
+	return (w * 0x01010101) >> 24;
+#else
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+#endif
+}
+
+unsigned int __sw_hweight16(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x5555);
+	res = (res & 0x3333) + ((res >> 2) & 0x3333);
+	res = (res + (res >> 4)) & 0x0F0F;
+	return (res + (res >> 8)) & 0x00FF;
+}
+
+unsigned int __sw_hweight8(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55);
+	res = (res & 0x33) + ((res >> 2) & 0x33);
+	return (res + (res >> 4)) & 0x0F;
+}
+
+unsigned long __sw_hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return __sw_hweight32((unsigned int)(w >> 32)) +
+	       __sw_hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x5555555555555555ul;
+	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
+	return (w * 0x0101010101010101ul) >> 56;
+#else
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+#endif
+}
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 6daaff652aff..7851df1490e0 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -268,7 +268,7 @@ install: install_lib
 
 clean:
 	$(call QUIET_CLEAN, libtraceevent) \
-		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
 		$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 PHONY += force plugins
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 09dc0aabb515..d01a0aad5a01 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,7 @@ tools/arch/x86/include/asm/atomic.h
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
+tools/lib/hweight.c
 tools/lib/rbtree.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
@@ -57,7 +58,6 @@ include/linux/perf_event.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
-lib/hweight.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 37e301a32f43..d99d850e1444 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -343,7 +343,7 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void read_counters(bool close)
+static void read_counters(bool close_counters)
 {
 	struct perf_evsel *counter;
 
@@ -354,7 +354,7 @@ static void read_counters(bool close)
 		if (process_counter(counter))
 			pr_warning("failed to process counter %s\n", counter->name);
 
-		if (close) {
+		if (close_counters) {
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
 					     thread_map__nr(evsel_list->threads));
 		}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 601d11440596..d2d318c59b37 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -143,6 +143,6 @@ $(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE
+$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e23ded40c79e..0766d98c5da5 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-../../lib/hweight.c
+../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
@@ -19,5 +19,5 @@ util/rblist.c
 util/stat.c
 util/strlist.c
 util/trace-event.c
-../../lib/rbtree.c
+../lib/rbtree.c
 util/string.c
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index da7646d767fe..292ae2c90e06 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -136,8 +136,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		if (grow) {
 			struct thread_map *tmp;
 
-			tmp = realloc(threads, (sizeof(*threads) +
-						max_threads * sizeof(pid_t)));
+			tmp = thread_map__realloc(threads, max_threads);
 			if (tmp == NULL)
 				goto out_free_namelist;
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 4b89118f158d..44d440da15dc 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -236,18 +236,16 @@ static struct dso *__machine__findnew_compat(struct machine *machine,
 	const char *file_name;
 	struct dso *dso;
 
-	pthread_rwlock_wrlock(&machine->dsos.lock);
 	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		goto out_unlock;
+		goto out;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		goto out_unlock;
+		goto out;
 
 	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
-out_unlock:
-	pthread_rwlock_unlock(&machine->dsos.lock);
+out:
 	return dso;
 }