diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 5e8daee7c5c94be6fc48bc7f32e593fb46948557..804a3a6030ca046500e7a092cfa0a854be77796f 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -23,7 +23,7 @@ extern struct static_key rdpmc_always_available;
 
 static inline void load_mm_cr4(struct mm_struct *mm)
 {
-	if (static_key_true(&rdpmc_always_available) ||
+	if (static_key_false(&rdpmc_always_available) ||
 	    atomic_read(&mm->context.perf_rdpmc_allowed))
 		cr4_set_bits(X86_CR4_PCE);
 	else
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 8bd9606584632582f7e893c0a3c01e8f0240678f..fe1b02c2c95bbe1274376f1b20ffebfac7358cc7 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 0000000000000000000000000000000000000000..0b859b8843390fe4ba09b06f388ff31843f13d33
--- /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 6daaff652affdde16240c91330781864aaedfd35..7851df1490e0a81f6a17776bbdb464f564a99894 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 09dc0aabb5154cb0906b6299afed4a3d0fc009c8..d01a0aad5a01b7e2e5c8d0f45d90c72f9e713574 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/Makefile.perf b/tools/perf/Makefile.perf
index 7a4b549214e34715aaf2ff7b834598ef2bae8080..bba34636b7334b334bdb520d3ebd8925f86f84c0 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -109,9 +109,22 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
 	$(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
 	$(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
-CC = $(CROSS_COMPILE)gcc
-LD ?= $(CROSS_COMPILE)ld
-AR = $(CROSS_COMPILE)ar
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 37e301a32f437eb6004ba4f4ccc6b90c73b9aa5c..d99d850e1444c9751cdbf7e0552b314e26597fef 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/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7629bef2fd791b41f64e49da53bc895e62d3dab4..fa67613976a80147e672bd2b960c9f577ff06b74 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -48,7 +48,7 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 
 static bool hist_browser__has_filter(struct hist_browser *hb)
 {
-	return hists__has_filter(hb->hists) || hb->min_pcnt;
+	return hists__has_filter(hb->hists) || hb->min_pcnt || symbol_conf.has_filter;
 }
 
 static int hist_browser__get_folding(struct hist_browser *browser)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 601d11440596dfd2b1d5244f56e972487d3fecff..d2d318c59b379531903f775abd9f842a02e01ca8 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/auxtrace.c b/tools/perf/util/auxtrace.c
index 7e7405c9b9361638f649820ae369bdec64e89c20..83d9dd96fe08ea8c613d1bda4db9b00bf4d04cd9 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -53,11 +53,6 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 {
 	struct perf_event_mmap_page *pc = userpg;
 
-#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
-	pr_err("Cannot use AUX area tracing mmaps\n");
-	return -1;
-#endif
-
 	WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
 
 	mm->userpg = userpg;
@@ -73,6 +68,11 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 		return 0;
 	}
 
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pr_err("Cannot use AUX area tracing mmaps\n");
+	return -1;
+#endif
+
 	pc->aux_offset = mp->offset;
 	pc->aux_size = mp->len;
 
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e23ded40c79e3ecd62642bf2a07a34c5fc7662f8..0766d98c5da59dd1aa44c41aaee1791502ac9a0d 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/symbol.c b/tools/perf/util/symbol.c
index 48b588c6951a9476246d6c71a9ee7b8535a8be37..60f11414bb5c8c6b463980f7b767662654e0331d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1911,6 +1911,8 @@ int setup_list(struct strlist **list, const char *list_str,
 		pr_err("problems parsing %s list\n", list_name);
 		return -1;
 	}
+
+	symbol_conf.has_filter = true;
 	return 0;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index bef47ead1d9bd1efc5e9620f04b13714286ff616..b98ce51af1422f8e22415d6a104b4a19810940cc 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -105,7 +105,8 @@ struct symbol_conf {
 			demangle_kernel,
 			filter_relative,
 			show_hist_headers,
-			branch_callstack;
+			branch_callstack,
+			has_filter;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index da7646d767feba14c4f1ad3ba60f3758d5f89413..292ae2c90e063d958da5f5859787c4c1c70ccab5 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 4b89118f158db458ae29cca6d20b093d81392cf6..44d440da15dcf73f97a81518c97a33be5c32b89b 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;
 }