Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  - Fix "Command" sort_entry's cmp and collapse function (Jiri Olsa)

  - Load map's symtab before 'perf probe' glob matching (Wang Nan)

  - Set vmlinux_path__nr_entries to 0 in vmlinux_path__exit, to fix
    the use case where this code is called multiple times, which wasn't
    that common when it was introduced but seems to be now (Wang Nan).

Infrastructure changes:

  - Protect dso symtab and cache operations with a mutex (Namhyung Kim)

  - Make all refcnt operations use atomic.h (Arnaldo Carvalho de Melo)

  - Install libtraceevent.a into libdir (Wang Nan)

Build fixes:

  - Fix one build failure on RHEL5 by making 'perf bench numa' use the
    __weak sched_getcpu() provided by cloexec.h (Arnaldo Carvalho de Melo)

  - Fix dwarf-aux.c compilation on i386 (Jiri Olsa)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

23 files changed, 263 insertions, 99 deletions

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3a0b0ca2a28c..2975632d51e2 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,7 +27,7 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS =			\
+FEATURE_TESTS ?=			\
 	backtrace			\
 	dwarf				\
 	fortify-source			\
@@ -53,7 +53,7 @@ FEATURE_TESTS =			\
 	zlib				\
 	lzma
 
-FEATURE_DISPLAY =			\
+FEATURE_DISPLAY ?=			\
 	dwarf				\
 	glibc				\
 	gtk2				\
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index 0bdeda66aae5..8ebf6278b2ef 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -64,6 +64,10 @@ typedef struct {
 	int counter;
 } atomic_t;
 
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
 struct list_head {
 	struct list_head *next, *prev;
 };
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index d410da335e3d..84640394ebf9 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -34,9 +34,15 @@ INSTALL = install
 DESTDIR ?=
 DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
 prefix ?= /usr/local
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+libdir = $(prefix)/$(libdir_relative)
 man_dir = $(prefix)/share/man
 man_dir_SQ = '$(subst ','\'',$(man_dir))'
 
@@ -58,7 +64,7 @@ ifeq ($(prefix),$(HOME))
 override plugin_dir = $(HOME)/.traceevent/plugins
 set_plugin_dir := 0
 else
-override plugin_dir = $(prefix)/lib/traceevent/plugins
+override plugin_dir = $(libdir)/traceevent/plugins
 endif
 endif
 
@@ -85,11 +91,11 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-export prefix bindir src obj
+export prefix libdir src obj
 
 # Shell quotes
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 LIB_FILE = libtraceevent.a libtraceevent.so
@@ -240,7 +246,7 @@ endef
 
 install_lib: all_cmd install_plugins
 	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(bindir_SQ))
+		$(call do_install,$(LIB_FILE),$(libdir_SQ))
 
 install_plugins: $(PLUGINS)
 	$(call QUIET_INSTALL, trace_plugins) \
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index e2415f40343a..870b7e665a20 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -8,6 +8,7 @@
 #include "../builtin.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
+#include "../util/cloexec.h"
 
 #include "bench.h"
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 3b884e37ab8b..30e59620179d 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -61,13 +61,13 @@ struct timechart {
 				tasks_only,
 				with_backtrace,
 				topology;
+	bool			force;
 	/* IO related settings */
-	u64			io_events;
 	bool			io_only,
 				skip_eagain;
+	u64			io_events;
 	u64			min_time,
 				merge_dist;
-	bool			force;
 };
 
 struct per_pidcomm;
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index c0ed56f7efc6..01fabb19d746 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -43,7 +43,7 @@ int test__thread_mg_share(void)
 			leader && t1 && t2 && t3 && other);
 
 	mg = leader->mg;
-	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 4);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
 
 	/* test the map groups pointer is shared */
 	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
@@ -71,25 +71,25 @@ int test__thread_mg_share(void)
 	machine__remove_thread(machine, other_leader);
 
 	other_mg = other->mg;
-	TEST_ASSERT_EQUAL("wrong refcnt", other_mg->refcnt, 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
 
 	TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
 
 	/* release thread group */
 	thread__put(leader);
-	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 3);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
 
 	thread__put(t1);
-	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
 
 	thread__put(t2);
-	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
 
 	thread__put(t3);
 
 	/* release other group  */
 	thread__put(other_leader);
-	TEST_ASSERT_EQUAL("wrong refcnt", other_mg->refcnt, 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
 
 	thread__put(other);
 
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 88f7be399432..32e12ecfe9c5 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -115,23 +115,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (cgrp->refcnt == 0)
+	if (atomic_read(&cgrp->refcnt) == 0)
 		free(cgrp);
 
 	return -1;
 found:
-	cgrp->refcnt++;
+	atomic_inc(&cgrp->refcnt);
 	counter->cgrp = cgrp;
 	return 0;
 }
 
 void close_cgroup(struct cgroup_sel *cgrp)
 {
-	if (!cgrp)
-		return;
-
-	/* XXX: not reentrant */
-	if (--cgrp->refcnt == 0) {
+	if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);
 		zfree(&cgrp->name);
 		free(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 89acd6debdc5..b4b8cb42fe5e 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,12 +1,14 @@
 #ifndef __CGROUP_H__
 #define __CGROUP_H__
 
+#include <linux/atomic.h>
+
 struct option;
 
 struct cgroup_sel {
 	char *name;
 	int fd;
-	int refcnt;
+	atomic_t refcnt;
 };
 
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 13d9ae0bd15c..1b96c8d18435 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -265,6 +265,7 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  */
 static LIST_HEAD(dso__data_open);
 static long dso__data_open_cnt;
+static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
 
 static void dso__list_add(struct dso *dso)
 {
@@ -434,7 +435,9 @@ static void check_data_close(void)
  */
 void dso__data_close(struct dso *dso)
 {
+	pthread_mutex_lock(&dso__data_open_lock);
 	close_dso(dso);
+	pthread_mutex_unlock(&dso__data_open_lock);
 }
 
 /**
@@ -457,6 +460,8 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	if (dso->data.status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
+	pthread_mutex_lock(&dso__data_open_lock);
+
 	if (dso->data.fd >= 0)
 		goto out;
 
@@ -479,6 +484,7 @@ out:
 	else
 		dso->data.status = DSO_DATA_STATUS_ERROR;
 
+	pthread_mutex_unlock(&dso__data_open_lock);
 	return dso->data.fd;
 }
 
@@ -495,10 +501,12 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 }
 
 static void
-dso_cache__free(struct rb_root *root)
+dso_cache__free(struct dso *dso)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node *next = rb_first(root);
 
+	pthread_mutex_lock(&dso->lock);
 	while (next) {
 		struct dso_cache *cache;
 
@@ -507,10 +515,12 @@ dso_cache__free(struct rb_root *root)
 		rb_erase(&cache->rb_node, root);
 		free(cache);
 	}
+	pthread_mutex_unlock(&dso->lock);
 }
 
-static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
 {
+	const struct rb_root *root = &dso->data.cache;
 	struct rb_node * const *p = &root->rb_node;
 	const struct rb_node *parent = NULL;
 	struct dso_cache *cache;
@@ -529,17 +539,20 @@ static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
 		else
 			return cache;
 	}
+
 	return NULL;
 }
 
-static void
-dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+static struct dso_cache *
+dso_cache__insert(struct dso *dso, struct dso_cache *new)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct dso_cache *cache;
 	u64 offset = new->offset;
 
+	pthread_mutex_lock(&dso->lock);
 	while (*p != NULL) {
 		u64 end;
 
@@ -551,10 +564,17 @@ dso_cache__insert(struct rb_root *root, struct dso_cache *new)
 			p = &(*p)->rb_left;
 		else if (offset >= end)
 			p = &(*p)->rb_right;
+		else
+			goto out;
 	}
 
 	rb_link_node(&new->rb_node, parent, p);
 	rb_insert_color(&new->rb_node, root);
+
+	cache = NULL;
+out:
+	pthread_mutex_unlock(&dso->lock);
+	return cache;
 }
 
 static ssize_t
@@ -569,19 +589,34 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, struct machine *machine,
+		u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
+	struct dso_cache *old;
 	ssize_t ret;
 
 	do {
 		u64 cache_offset;
 
-		ret = -ENOMEM;
-
 		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
 		if (!cache)
-			break;
+			return -ENOMEM;
+
+		pthread_mutex_lock(&dso__data_open_lock);
+
+		/*
+		 * dso->data.fd might be closed if other thread opened another
+		 * file (dso) due to open file limit (RLIMIT_NOFILE).
+		 */
+		if (dso->data.fd < 0) {
+			dso->data.fd = open_dso(dso, machine);
+			if (dso->data.fd < 0) {
+				ret = -errno;
+				dso->data.status = DSO_DATA_STATUS_ERROR;
+				break;
+			}
+		}
 
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 
@@ -591,11 +626,20 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->data.cache, cache);
+	} while (0);
 
-		ret = dso_cache__memcpy(cache, offset, data, size);
+	pthread_mutex_unlock(&dso__data_open_lock);
 
-	} while (0);
+	if (ret > 0) {
+		old = dso_cache__insert(dso, cache);
+		if (old) {
+			/* we lose the race */
+			free(cache);
+			cache = old;
+		}
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+	}
 
 	if (ret <= 0)
 		free(cache);
@@ -603,16 +647,16 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, u64 offset,
-			      u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->data.cache, offset);
+	cache = dso_cache__find(dso, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, offset, data, size);
+		return dso_cache__read(dso, machine, offset, data, size);
 }
 
 /*
@@ -620,7 +664,8 @@ static ssize_t dso_cache_read(struct dso *dso, u64 offset,
  * in the rb_tree. Any read to already cached data is served
  * by cached data.
  */
-static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+static ssize_t cached_read(struct dso *dso, struct machine *machine,
+			   u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -628,7 +673,7 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, offset, p, size);
+		ret = dso_cache_read(dso, machine, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -648,21 +693,42 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return r;
 }
 
-static int data_file_size(struct dso *dso)
+static int data_file_size(struct dso *dso, struct machine *machine)
 {
+	int ret = 0;
 	struct stat st;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (!dso->data.file_size) {
-		if (fstat(dso->data.fd, &st)) {
-			pr_err("dso mmap failed, fstat: %s\n",
-				strerror_r(errno, sbuf, sizeof(sbuf)));
-			return -1;
+	if (dso->data.file_size)
+		return 0;
+
+	pthread_mutex_lock(&dso__data_open_lock);
+
+	/*
+	 * dso->data.fd might be closed if other thread opened another
+	 * file (dso) due to open file limit (RLIMIT_NOFILE).
+	 */
+	if (dso->data.fd < 0) {
+		dso->data.fd = open_dso(dso, machine);
+		if (dso->data.fd < 0) {
+			ret = -errno;
+			dso->data.status = DSO_DATA_STATUS_ERROR;
+			goto out;
 		}
-		dso->data.file_size = st.st_size;
 	}
 
-	return 0;
+	if (fstat(dso->data.fd, &st) < 0) {
+		ret = -errno;
+		pr_err("dso cache fstat failed: %s\n",
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
+	}
+	dso->data.file_size = st.st_size;
+
+out:
+	pthread_mutex_unlock(&dso__data_open_lock);
+	return ret;
 }
 
 /**
@@ -680,17 +746,17 @@ off_t dso__data_size(struct dso *dso, struct machine *machine)
 	if (fd < 0)
 		return fd;
 
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* For now just estimate dso data size is close to file size */
 	return dso->data.file_size;
 }
 
-static ssize_t data_read_offset(struct dso *dso, u64 offset,
-				u8 *data, ssize_t size)
+static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
+				u64 offset, u8 *data, ssize_t size)
 {
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* Check the offset sanity. */
@@ -700,7 +766,7 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 	if (offset + size < offset)
 		return -1;
 
-	return cached_read(dso, offset, data, size);
+	return cached_read(dso, machine, offset, data, size);
 }
 
 /**
@@ -717,10 +783,10 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size)
 {
-	if (dso__data_fd(dso, machine) < 0)
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
-	return data_read_offset(dso, offset, data, size);
+	return data_read_offset(dso, machine, offset, data, size);
 }
 
 /**
@@ -936,6 +1002,7 @@ struct dso *dso__new(const char *name)
 		RB_CLEAR_NODE(&dso->rb_node);
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
+		pthread_mutex_init(&dso->lock, NULL);
 	}
 
 	return dso;
@@ -963,9 +1030,10 @@ void dso__delete(struct dso *dso)
 
 	dso__data_close(dso);
 	auxtrace_cache__free(dso->auxtrace_cache);
-	dso_cache__free(&dso->data.cache);
+	dso_cache__free(dso);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
+	pthread_mutex_destroy(&dso->lock);
 	free(dso);
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 3d79c749934c..b26ec3ab1336 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -129,6 +129,7 @@ struct dsos {
 struct auxtrace_cache;
 
 struct dso {
+	pthread_mutex_t	 lock;
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index eb47abdcf0ac..57f3ef41c2bc 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -994,11 +994,11 @@ static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
 		end -= entry;
 
 		if (first) {
-			strbuf_addf(buf, "@<%s+[%lu-%lu",
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
 				name, start, end);
 			first = false;
 		} else {
-			strbuf_addf(buf, ",%lu-%lu",
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
 				start, end);
 		}
 	}
@@ -1057,11 +1057,11 @@ int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
 		start -= entry;
 		end -= entry;
 		if (first) {
-			strbuf_addf(buf, "@<%s+[%lu-%lu",
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
 				name, start, end);
 			first = false;
 		} else {
-			strbuf_addf(buf, ",%lu-%lu",
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
 				start, end);
 		}
 	}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7ec1bf93ab28..dc1dc2c181ef 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -700,14 +700,14 @@ static bool perf_mmap__empty(struct perf_mmap *md)
 
 static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
 {
-	++evlist->mmap[idx].refcnt;
+	atomic_inc(&evlist->mmap[idx].refcnt);
 }
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
 {
-	BUG_ON(evlist->mmap[idx].refcnt == 0);
+	BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
 
-	if (--evlist->mmap[idx].refcnt == 0)
+	if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
 		__perf_evlist__munmap(evlist, idx);
 }
 
@@ -721,7 +721,7 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 		perf_mmap__write_tail(md, old);
 	}
 
-	if (md->refcnt == 1 && perf_mmap__empty(md))
+	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
 		perf_evlist__mmap_put(evlist, idx);
 }
 
@@ -758,7 +758,7 @@ static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
-		evlist->mmap[idx].refcnt = 0;
+		atomic_set(&evlist->mmap[idx].refcnt, 0);
 	}
 	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
 }
@@ -807,7 +807,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	evlist->mmap[idx].refcnt = 2;
+	atomic_set(&evlist->mmap[idx].refcnt, 2);
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mp->mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index c07b1a94a724..955bf31b7dd3 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
+#include <linux/atomic.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
 #include <stdio.h>
@@ -27,7 +28,7 @@ struct record_opts;
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
-	int		 refcnt;
+	atomic_t	 refcnt;
 	u64		 prev;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
@@ -39,6 +40,7 @@ struct perf_evlist {
 	int		 nr_entries;
 	int		 nr_groups;
 	int		 nr_mmaps;
+	bool		 overwrite;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -47,7 +49,6 @@ struct perf_evlist {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
-	bool		 overwrite;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
 	struct thread_map *threads;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e486151b0308..21ec08247d47 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -73,7 +73,6 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	bool			snapshot;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
@@ -86,6 +85,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
 	bool			no_aux_samples;
@@ -93,11 +93,11 @@ struct perf_evsel {
 	bool			system_wide;
 	bool			tracking;
 	bool			per_pkg;
-	unsigned long		*per_pkg_mask;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
 	int			sample_read;
+	unsigned long		*per_pkg_mask;
 	struct perf_evsel	*leader;
 	char			*group_name;
 };
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 34bf89f7f4f3..daa55910ff28 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1311,7 +1311,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	if (machine->last_match == th)
 		machine->last_match = NULL;
 
-	BUG_ON(th->refcnt.counter == 0);
+	BUG_ON(atomic_read(&th->refcnt) == 0);
 	if (lock)
 		pthread_rwlock_wrlock(&machine->threads_lock);
 	rb_erase(&th->rb_node, &machine->threads);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index cd0e335008b4..2d20c5ff8653 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -426,7 +426,7 @@ void map_groups__init(struct map_groups *mg, struct machine *machine)
 		INIT_LIST_HEAD(&mg->removed_maps[i]);
 	}
 	mg->machine = machine;
-	mg->refcnt = 1;
+	atomic_set(&mg->refcnt, 1);
 }
 
 static void maps__delete(struct rb_root *maps)
@@ -494,7 +494,7 @@ void map_groups__delete(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg)
 {
-	if (--mg->refcnt == 0)
+	if (mg && atomic_dec_and_test(&mg->refcnt))
 		map_groups__delete(mg);
 }
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 4e0c729841ab..7f39217d29bf 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_MAP_H
 #define __PERF_MAP_H
 
+#include <linux/atomic.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
@@ -61,7 +62,7 @@ struct map_groups {
 	struct rb_root	 maps[MAP__NR_TYPES];
 	struct list_head removed_maps[MAP__NR_TYPES];
 	struct machine	 *machine;
-	int		 refcnt;
+	atomic_t	 refcnt;
 };
 
 struct map_groups *map_groups__new(struct machine *machine);
@@ -70,7 +71,8 @@ bool map_groups__empty(struct map_groups *mg);
 
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
-	++mg->refcnt;
+	if (mg)
+		atomic_inc(&mg->refcnt);
 	return mg;
 }
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2399dc4f6089..1faa1e67398b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2499,6 +2499,9 @@ static int find_probe_functions(struct map *map, char *name)
 	struct symbol *sym;
 	struct rb_node *tmp;
 
+	if (map__load(map, NULL) < 0)
+		return 0;
+
 	map__for_each_symbol(map, sym, tmp) {
 		if (strglobmatch(sym->name, name))
 			found++;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4593f36ecc4c..09d4696fd9a1 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -89,14 +89,14 @@ static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
 sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 45ba48a7acb3..82a31fd0fcf5 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1383,12 +1383,22 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
 	bool kmod;
 
-	dso__set_loaded(dso, map->type);
+	pthread_mutex_lock(&dso->lock);
+
+	/* check again under the dso->lock */
+	if (dso__loaded(dso, map->type)) {
+		ret = 1;
+		goto out;
+	}
+
+	if (dso->kernel) {
+		if (dso->kernel == DSO_TYPE_KERNEL)
+			ret = dso__load_kernel_sym(dso, map, filter);
+		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+			ret = dso__load_guest_kernel_sym(dso, map, filter);
 
-	if (dso->kernel == DSO_TYPE_KERNEL)
-		return dso__load_kernel_sym(dso, map, filter);
-	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		return dso__load_guest_kernel_sym(dso, map, filter);
+		goto out;
+	}
 
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
@@ -1401,18 +1411,18 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		struct stat st;
 
 		if (lstat(dso->name, &st) < 0)
-			return -1;
+			goto out;
 
 		if (st.st_uid && (st.st_uid != geteuid())) {
 			pr_warning("File %s not owned by current user or root, "
 				"ignoring it.\n", dso->name);
-			return -1;
+			goto out;
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
-		return ret;
+		goto out;
 	}
 
 	if (machine)
@@ -1420,7 +1430,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 	name = malloc(PATH_MAX);
 	if (!name)
-		return -1;
+		goto out;
 
 	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
 		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
@@ -1501,7 +1511,11 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 out_free:
 	free(name);
 	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
-		return 0;
+		ret = 0;
+out:
+	dso__set_loaded(dso, map->type);
+	pthread_mutex_unlock(&dso->lock);
+
 	return ret;
 }
 
@@ -1805,6 +1819,7 @@ static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0)
 		zfree(&vmlinux_path[vmlinux_path__nr_entries]);
+	vmlinux_path__nr_entries = 0;
 
 	zfree(&vmlinux_path);
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index f33c48cfdaa0..a0ac0317affb 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -25,9 +25,9 @@ struct thread {
 	atomic_t		refcnt;
 	char			shortname[3];
 	bool			comm_set;
+	int			comm_len;
 	bool			dead; /* if set thread has exited */
 	struct list_head	comm_list;
-	int			comm_len;
 	u64			db_id;
 
 	void			*priv;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 4ee6d0d4c993..0c264bc685ac 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -72,6 +72,49 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
+int rm_rf(char *path)
+{
+	DIR *dir;
+	int ret = 0;
+	struct dirent *d;
+	char namebuf[PATH_MAX];
+
+	dir = opendir(path);
+	if (dir == NULL)
+		return 0;
+
+	while ((d = readdir(dir)) != NULL && !ret) {
+		struct stat statbuf;
+
+		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+			continue;
+
+		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
+			  path, d->d_name);
+
+		ret = stat(namebuf, &statbuf);
+		if (ret < 0) {
+			pr_debug("stat failed: %s\n", namebuf);
+			break;
+		}
+
+		if (S_ISREG(statbuf.st_mode))
+			ret = unlink(namebuf);
+		else if (S_ISDIR(statbuf.st_mode))
+			ret = rm_rf(namebuf);
+		else {
+			pr_debug("unknown file: %s\n", namebuf);
+			ret = -1;
+		}
+	}
+	closedir(dir);
+
+	if (ret < 0)
+		return ret;
+
+	return rmdir(path);
+}
+
 static int slow_copyfile(const char *from, const char *to, mode_t mode)
 {
 	int err = -1;
@@ -102,11 +145,38 @@ out:
 	return err;
 }
 
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+{
+	void *ptr;
+	loff_t pgoff;
+
+	pgoff = off_in & ~(page_size - 1);
+	off_in -= pgoff;
+
+	ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
+	if (ptr == MAP_FAILED)
+		return -1;
+
+	while (size) {
+		ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			break;
+
+		size -= ret;
+		off_in += ret;
+		off_out -= ret;
+	}
+	munmap(ptr, off_in + size);
+
+	return size ? -1 : 0;
+}
+
 int copyfile_mode(const char *from, const char *to, mode_t mode)
 {
 	int fromfd, tofd;
 	struct stat st;
-	void *addr;
 	int err = -1;
 
 	if (stat(from, &st))
@@ -123,15 +193,8 @@ int copyfile_mode(const char *from, const char *to, mode_t mode)
 	if (tofd < 0)
 		goto out_close_from;
 
-	addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
-	if (addr == MAP_FAILED)
-		goto out_close_to;
-
-	if (write(tofd, addr, st.st_size) == st.st_size)
-		err = 0;
+	err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
 
-	munmap(addr, st.st_size);
-out_close_to:
 	close(tofd);
 	if (err)
 		unlink(to);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 3601ffd3d8b4..8bce58b47a82 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -249,8 +249,10 @@ static inline int sane_case(int x, int high)
 }
 
 int mkdir_p(char *path, mode_t mode);
+int rm_rf(char *path);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);