21 files changed, 155 insertions, 74 deletions

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 08278eda31a5..96db5248e995 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -343,7 +343,7 @@ find_next:
                         continue;
                 }
 
-                if (use_browser) {
+                if (use_browser > 0) {
                         key = hist_entry__tui_annotate(he);
                         if (is_exit_key(key))
                                 break;
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 44a47e13bd67..99890728409e 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -43,8 +43,10 @@ static int __cmd_buildid_list(void)
         if (session == NULL)
                 return -1;
 
-        if (with_hits)
+        if (with_hits) {
+                symbol_conf.full_paths = true;
                 perf_session__process_events(session, &build_id__mark_dso_hit_ops);
+        }
 
         perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9bc89050e6f8..711745f56bba 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -193,7 +193,7 @@ static void sig_handler(int sig)
 
 static void sig_atexit(void)
 {
-        if (child_pid != -1)
+        if (child_pid > 0)
                 kill(child_pid, SIGTERM);
 
         if (signr == -1)
@@ -503,7 +503,6 @@ static int __cmd_record(int argc, const char **argv)
 {
         int i, counter;
         struct stat st;
-        pid_t pid = 0;
         int flags;
         int err;
         unsigned long waking = 0;
@@ -572,7 +571,7 @@ static int __cmd_record(int argc, const char **argv)
 
         if (forks) {
                 child_pid = fork();
-                if (pid < 0) {
+                if (child_pid < 0) {
                         perror("failed to fork");
                         exit(-1);
                 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 359205782964..fd7407c7205c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -107,7 +107,7 @@ static int perf_session__add_hist_entry(struct perf_session *self,
                 goto out_free_syms;
         err = 0;
         if (symbol_conf.use_callchain) {
-                err = append_chain(he->callchain, data->callchain, syms);
+                err = append_chain(he->callchain, data->callchain, syms, data->period);
                 if (err)
                         goto out_free_syms;
         }
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f67bce2a83b4..55f3b5dcc731 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1645,6 +1645,7 @@ static struct perf_event_ops event_ops = {
         .sample                 = process_sample_event,
         .comm                   = event__process_comm,
         .lost                   = event__process_lost,
+        .fork                   = event__process_task,
         .ordered_samples        = true,
 };
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 397290a0a76e..a66f4272b994 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1060,7 +1060,7 @@ static void event__process_sample(const event_t *self,
                         pr_err("Can't annotate %s", sym->name);
                         if (sym_filter_entry->map->dso->origin == DSO__ORIG_KERNEL) {
                                 pr_err(": No vmlinux file was found in the path:\n");
-                                vmlinux_path__fprintf(stderr);
+                                machine__fprintf_vmlinux_path(machine, stderr);
                         } else
                                 pr_err(".\n");
                         exit(1);
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
index 964d934395ff..d9f7893e315c 100644
--- a/tools/perf/scripts/python/check-perf-trace.py
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -51,8 +51,7 @@ def kmem__kmalloc(event_name, context, common_cpu,
 
                 flag_str("kmem__kmalloc", "gfp_flags", gfp_flags)),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-                common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     try:
         unhandled[event_name] += 1
     except TypeError:
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 49ece7921914..97d76562a1a0 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -5,17 +5,13 @@ if [ $# -eq 1 ]  ; then
 fi
 
 GVF=${OUTPUT}PERF-VERSION-FILE
-DEF_VER=v0.0.2.PERF
 
 LF='
 '
 
-# First see if there is a version file (included in release tarballs),
-# then try git-describe, then default.
-if test -f version
-then
-        VN=$(cat version) || VN="$DEF_VER"
-elif test -d .git -o -f .git &&
+# First check if there is a .git to get the version from git describe
+# otherwise try to get the version from the kernel makefile
+if test -d ../../.git -o -f ../../.git &&
         VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
         case "$VN" in
         *$LF*) (exit 1) ;;
@@ -27,7 +23,12 @@ elif test -d .git -o -f .git &&
 then
         VN=$(echo "$VN" | sed -e 's/-/./g');
 else
-        VN="$DEF_VER"
+        eval `grep '^VERSION\s*=' ../../Makefile|tr -d ' '`
+        eval `grep '^PATCHLEVEL\s*=' ../../Makefile|tr -d ' '`
+        eval `grep '^SUBLEVEL\s*=' ../../Makefile|tr -d ' '`
+        eval `grep '^EXTRAVERSION\s*=' ../../Makefile|tr -d ' '`
+
+        VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}"
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 62b69ad4aa73..52c777e451ed 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -230,7 +230,7 @@ fill_node(struct callchain_node *node, struct resolved_chain *chain, int start)
 
 static void
 add_child(struct callchain_node *parent, struct resolved_chain *chain,
-          int start)
+          int start, u64 period)
 {
         struct callchain_node *new;
 
@@ -238,7 +238,7 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain,
         fill_node(new, chain, start);
 
         new->children_hit = 0;
-        new->hit = 1;
+        new->hit = period;
 }
 
 /*
@@ -248,7 +248,8 @@ add_child(struct callchain_node *parent, struct resolved_chain *chain,
  */
 static void
 split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
-                struct callchain_list *to_split, int idx_parents, int idx_local)
+                struct callchain_list *to_split, int idx_parents, int idx_local,
+                u64 period)
 {
         struct callchain_node *new;
         struct list_head *old_tail;
@@ -275,41 +276,41 @@ split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
         /* create a new child for the new branch if any */
         if (idx_total < chain->nr) {
                 parent->hit = 0;
-                add_child(parent, chain, idx_total);
-                parent->children_hit++;
+                add_child(parent, chain, idx_total, period);
+                parent->children_hit += period;
         } else {
-                parent->hit = 1;
+                parent->hit = period;
         }
 }
 
 static int
 __append_chain(struct callchain_node *root, struct resolved_chain *chain,
-               unsigned int start);
+               unsigned int start, u64 period);
 
 static void
 __append_chain_children(struct callchain_node *root,
                         struct resolved_chain *chain,
-                        unsigned int start)
+                        unsigned int start, u64 period)
 {
         struct callchain_node *rnode;
 
         /* lookup in childrens */
         chain_for_each_child(rnode, root) {
-                unsigned int ret = __append_chain(rnode, chain, start);
+                unsigned int ret = __append_chain(rnode, chain, start, period);
 
                 if (!ret)
                         goto inc_children_hit;
         }
         /* nothing in children, add to the current node */
-        add_child(root, chain, start);
+        add_child(root, chain, start, period);
 
 inc_children_hit:
-        root->children_hit++;
+        root->children_hit += period;
 }
 
 static int
 __append_chain(struct callchain_node *root, struct resolved_chain *chain,
-               unsigned int start)
+               unsigned int start, u64 period)
 {
         struct callchain_list *cnode;
         unsigned int i = start;
@@ -345,18 +346,18 @@ __append_chain(struct callchain_node *root, struct resolved_chain *chain,
 
         /* we match only a part of the node. Split it and add the new chain */
         if (i - start < root->val_nr) {
-                split_add_child(root, chain, cnode, start, i - start);
+                split_add_child(root, chain, cnode, start, i - start, period);
                 return 0;
         }
 
         /* we match 100% of the path, increment the hit */
         if (i - start == root->val_nr && i == chain->nr) {
-                root->hit++;
+                root->hit += period;
                 return 0;
         }
 
         /* We match the node and still have a part remaining */
-        __append_chain_children(root, chain, i);
+        __append_chain_children(root, chain, i, period);
 
         return 0;
 }
@@ -380,7 +381,7 @@ static void filter_context(struct ip_callchain *old, struct resolved_chain *new,
 
 
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-                 struct map_symbol *syms)
+                 struct map_symbol *syms, u64 period)
 {
         struct resolved_chain *filtered;
 
@@ -397,7 +398,7 @@ int append_chain(struct callchain_node *root, struct ip_callchain *chain,
         if (!filtered->nr)
                 goto end;
 
-        __append_chain_children(root, filtered, 0);
+        __append_chain_children(root, filtered, 0, period);
 end:
         free(filtered);
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1ca73e4a2723..f2e9ee164bd8 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -49,6 +49,9 @@ static inline void callchain_init(struct callchain_node *node)
         INIT_LIST_HEAD(&node->brothers);
         INIT_LIST_HEAD(&node->children);
         INIT_LIST_HEAD(&node->val);
+
+        node->parent = NULL;
+        node->hit = 0;
 }
 
 static inline u64 cumul_hits(struct callchain_node *node)
@@ -58,7 +61,7 @@ static inline u64 cumul_hits(struct callchain_node *node)
 
 int register_callchain_param(struct callchain_param *param);
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-                 struct map_symbol *syms);
+                 struct map_symbol *syms, u64 period);
 
 bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index dd824cf3b628..6cddff2bc970 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -22,7 +22,7 @@ int eprintf(int level, const char *fmt, ...)
 
         if (verbose >= level) {
                 va_start(args, fmt);
-                if (use_browser)
+                if (use_browser > 0)
                         ret = browser__show_help(fmt, args);
                 else
                         ret = vfprintf(stderr, fmt, args);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 50771b5813ee..2fbf6a463c81 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -370,9 +370,9 @@ static int thread__set_comm_adjust(struct thread *self, const char *comm)
 
 int event__process_comm(event_t *self, struct perf_session *session)
 {
-        struct thread *thread = perf_session__findnew(session, self->comm.pid);
+        struct thread *thread = perf_session__findnew(session, self->comm.tid);
 
-        dump_printf(": %s:%d\n", self->comm.comm, self->comm.pid);
+        dump_printf(": %s:%d\n", self->comm.comm, self->comm.tid);
 
         if (thread == NULL || thread__set_comm_adjust(thread, self->comm.comm)) {
                 dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
@@ -532,19 +532,16 @@ out_problem:
 
 int event__process_task(event_t *self, struct perf_session *session)
 {
-        struct thread *thread = perf_session__findnew(session, self->fork.pid);
-        struct thread *parent = perf_session__findnew(session, self->fork.ppid);
+        struct thread *thread = perf_session__findnew(session, self->fork.tid);
+        struct thread *parent = perf_session__findnew(session, self->fork.ptid);
 
         dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
                     self->fork.ppid, self->fork.ptid);
-        /*
-         * A thread clone will have the same PID for both parent and child.
-         */
-        if (thread == parent)
-                return 0;
 
-        if (self->header.type == PERF_RECORD_EXIT)
+        if (self->header.type == PERF_RECORD_EXIT) {
+                perf_session__remove_thread(session, thread);
                 return 0;
+        }
 
         if (thread == NULL || parent == NULL ||
             thread__fork(thread, parent) < 0) {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cbf7eae2ce09..07f89b66b318 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -965,7 +965,7 @@ static int hist_entry__parse_objdump_line(struct hist_entry *self, FILE *file,
                  * Parse hexa addresses followed by ':'
                  */
                 line_ip = strtoull(tmp, &tmp2, 16);
-                if (*tmp2 != ':')
+                if (*tmp2 != ':' || tmp == tmp2)
                         line_ip = -1;
         }
 
diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c
index d54c540f49db..7537ca15900b 100644
--- a/tools/perf/util/newt.c
+++ b/tools/perf/util/newt.c
@@ -43,6 +43,9 @@ struct ui_progress *ui_progress__new(const char *title, u64 total)
 
         if (self != NULL) {
                 int cols;
+
+                if (use_browser <= 0)   
+                        return self;
                 newtGetScreenSize(&cols, NULL);
                 cols -= 4;
                 newtCenteredWindow(cols, 1, title);
@@ -67,14 +70,22 @@ out_free_self:
 
 void ui_progress__update(struct ui_progress *self, u64 curr)
 {
+        /*
+         * FIXME: We should have a per UI backend way of showing progress,
+         * stdio will just show a percentage as NN%, etc.
+         */
+        if (use_browser <= 0)
+                return;
         newtScaleSet(self->scale, curr);
         newtRefresh();
 }
 
 void ui_progress__delete(struct ui_progress *self)
 {
-        newtFormDestroy(self->form);
-        newtPopWindow();
+        if (use_browser > 0) {
+                newtFormDestroy(self->form);
+                newtPopWindow();
+        }
         free(self);
 }
 
@@ -1139,6 +1150,7 @@ void setup_browser(void)
         struct newtPercentTreeColors *c = &defaultPercentTreeColors;
 
         if (!isatty(1) || !use_browser || dump_trace) {
+                use_browser = 0;
                 setup_pager();
                 return;
         }
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 81f39cab3aaa..33a632523743 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -208,7 +208,7 @@ static void python_process_event(int cpu, void *data,
                                  int size __unused,
                                  unsigned long long nsecs, char *comm)
 {
-        PyObject *handler, *retval, *context, *t, *obj;
+        PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
         static char handler_name[256];
         struct format_field *field;
         unsigned long long val;
@@ -232,6 +232,14 @@ static void python_process_event(int cpu, void *data,
 
         sprintf(handler_name, "%s__%s", event->system, event->name);
 
+        handler = PyDict_GetItemString(main_dict, handler_name);
+        if (handler && !PyCallable_Check(handler))
+                handler = NULL;
+        if (!handler) {
+                dict = PyDict_New();
+                if (!dict)
+                        Py_FatalError("couldn't create Python dict");
+        }
         s = nsecs / NSECS_PER_SEC;
         ns = nsecs - s * NSECS_PER_SEC;
 
@@ -242,12 +250,20 @@ static void python_process_event(int cpu, void *data,
         PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
         PyTuple_SetItem(t, n++,
                         PyCObject_FromVoidPtr(scripting_context, NULL));
-        PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
-        PyTuple_SetItem(t, n++, PyInt_FromLong(s));
-        PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
-        PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
-        PyTuple_SetItem(t, n++, PyString_FromString(comm));
 
+        if (handler) {
+                PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
+                PyTuple_SetItem(t, n++, PyInt_FromLong(s));
+                PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
+                PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
+                PyTuple_SetItem(t, n++, PyString_FromString(comm));
+        } else {
+                PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu));
+                PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s));
+                PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns));
+                PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid));
+                PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm));
+        }
         for (field = event->format.fields; field; field = field->next) {
                 if (field->flags & FIELD_IS_STRING) {
                         int offset;
@@ -272,27 +288,31 @@ static void python_process_event(int cpu, void *data,
                                         obj = PyLong_FromUnsignedLongLong(val);
                         }
                 }
-                PyTuple_SetItem(t, n++, obj);
+                if (handler)
+                        PyTuple_SetItem(t, n++, obj);
+                else
+                        PyDict_SetItemString(dict, field->name, obj);
+
         }
+        if (!handler)
+                PyTuple_SetItem(t, n++, dict);
 
         if (_PyTuple_Resize(&t, n) == -1)
                 Py_FatalError("error resizing Python tuple");
 
-        handler = PyDict_GetItemString(main_dict, handler_name);
-        if (handler && PyCallable_Check(handler)) {
+        if (handler) {
                 retval = PyObject_CallObject(handler, t);
                 if (retval == NULL)
                         handler_call_die(handler_name);
         } else {
                 handler = PyDict_GetItemString(main_dict, "trace_unhandled");
                 if (handler && PyCallable_Check(handler)) {
-                        if (_PyTuple_Resize(&t, N_COMMON_FIELDS) == -1)
-                                Py_FatalError("error resizing Python tuple");
 
                         retval = PyObject_CallObject(handler, t);
                         if (retval == NULL)
                                 handler_call_die("trace_unhandled");
                 }
+                Py_DECREF(dict);
         }
 
         Py_DECREF(t);
@@ -548,12 +568,10 @@ static int python_generate_script(const char *outfile)
         }
 
         fprintf(ofp, "def trace_unhandled(event_name, context, "
-                "common_cpu, common_secs, common_nsecs,\n\t\t"
-                "common_pid, common_comm):\n");
+                "event_fields_dict):\n");
 
-        fprintf(ofp, "\t\tprint_header(event_name, common_cpu, "
-                "common_secs, common_nsecs,\n\t\tcommon_pid, "
-                "common_comm)\n\n");
+        fprintf(ofp, "\t\tprint ' '.join(['%%s=%%s'%%(k,str(v))"
+                "for k,v in sorted(event_fields_dict.items())])\n\n");
 
         fprintf(ofp, "def print_header("
                 "event_name, cpu, secs, nsecs, pid, comm):\n"
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8f83a1835766..c422cd676313 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -90,6 +90,7 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 
         memcpy(self->filename, filename, len);
         self->threads = RB_ROOT;
+        INIT_LIST_HEAD(&self->dead_threads);
         self->hists_tree = RB_ROOT;
         self->last_match = NULL;
         self->mmap_window = 32;
@@ -131,6 +132,16 @@ void perf_session__delete(struct perf_session *self)
         free(self);
 }
 
+void perf_session__remove_thread(struct perf_session *self, struct thread *th)
+{
+        rb_erase(&th->rb_node, &self->threads);
+        /*
+         * We may have references to this thread, for instance in some hist_entry
+         * instances, so just move them to a separate list.
+         */
+        list_add_tail(&th->node, &self->dead_threads);
+}
+
 static bool symbol__match_parent_regex(struct symbol *sym)
 {
         if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 55c6881b218d..9fa0fc2a863f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -26,6 +26,7 @@ struct perf_session {
         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;
@@ -99,6 +100,7 @@ int perf_session__create_kernel_maps(struct perf_session *self);
 
 int do_read(int fd, void *buf, size_t size);
 void perf_session__update_sample_type(struct perf_session *self);
+void perf_session__remove_thread(struct perf_session *self, struct thread *th);
 
 static inline
 struct machine *perf_session__find_host_machine(struct perf_session *self)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index aaa51ba147df..b63e5713849f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1695,9 +1695,20 @@ int dso__load_vmlinux_path(struct dso *self, struct map *map,
                            symbol_filter_t filter)
 {
         int i, err = 0;
+        char *filename;
 
         pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-                 vmlinux_path__nr_entries);
+                 vmlinux_path__nr_entries + 1);
+
+        filename = dso__build_id_filename(self, NULL, 0);
+        if (filename != NULL) {
+                err = dso__load_vmlinux(self, map, filename, filter);
+                if (err > 0) {
+                        dso__set_long_name(self, filename);
+                        goto out;
+                }
+                free(filename);
+        }
 
         for (i = 0; i < vmlinux_path__nr_entries; ++i) {
                 err = dso__load_vmlinux(self, map, vmlinux_path[i], filter);
@@ -1706,7 +1717,7 @@ int dso__load_vmlinux_path(struct dso *self, struct map *map,
                         break;
                 }
         }
-
+out:
         return err;
 }
 
@@ -1734,7 +1745,12 @@ static int dso__load_kernel_sym(struct dso *self, struct map *map,
         if (symbol_conf.vmlinux_name != NULL) {
                 err = dso__load_vmlinux(self, map,
                                         symbol_conf.vmlinux_name, filter);
-                goto out_try_fixup;
+                if (err > 0) {
+                        dso__set_long_name(self,
+                                           strdup(symbol_conf.vmlinux_name));
+                        goto out_fixup;
+                }
+                return err;
         }
 
         if (vmlinux_path != NULL) {
@@ -1795,7 +1811,6 @@ do_kallsyms:
                 pr_debug("Using %s for symbols\n", kallsyms_filename);
         free(kallsyms_allocated_filename);
 
-out_try_fixup:
         if (err > 0) {
 out_fixup:
                 if (kallsyms_filename != NULL)
@@ -2102,13 +2117,21 @@ out_fail:
         return -1;
 }
 
-size_t vmlinux_path__fprintf(FILE *fp)
+size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp)
 {
         int i;
         size_t printed = 0;
+        struct dso *kdso = self->vmlinux_maps[MAP__FUNCTION]->dso;
+
+        if (kdso->has_build_id) {
+                char filename[PATH_MAX];
+                if (dso__build_id_filename(kdso, filename, sizeof(filename)))
+                        printed += fprintf(fp, "[0] %s\n", filename);
+        }
 
         for (i = 0; i < vmlinux_path__nr_entries; ++i)
-                printed += fprintf(fp, "[%d] %s\n", i, vmlinux_path[i]);
+                printed += fprintf(fp, "[%d] %s\n",
+                                   i + kdso->has_build_id, vmlinux_path[i]);
 
         return printed;
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5d25b5eb1456..5e02d2c17154 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -216,6 +216,6 @@ int machines__create_guest_kernel_maps(struct rb_root *self);
 int symbol__init(void);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 
-size_t vmlinux_path__fprintf(FILE *fp);
+size_t machine__fprintf_vmlinux_path(struct machine *self, FILE *fp);
 
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1f7ecd47f499..9a448b47400c 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,15 @@
 #include "util.h"
 #include "debug.h"
 
+/* Skip "." and ".." directories */
+static int filter(const struct dirent *dir)
+{
+        if (dir->d_name[0] == '.')
+                return 0;
+        else
+                return 1;
+}
+
 int find_all_tid(int pid, pid_t ** all_tid)
 {
         char name[256];
@@ -16,7 +25,7 @@ int find_all_tid(int pid, pid_t ** all_tid)
         int i;
 
         sprintf(name, "/proc/%d/task", pid);
-        items = scandir(name, &namelist, NULL, NULL);
+        items = scandir(name, &namelist, filter, NULL);
         if (items <= 0)
                 return -ENOENT;
         *all_tid = malloc(sizeof(pid_t) * items);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 1dfd9ff8bdcd..ee6bbcf277ca 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -6,7 +6,10 @@
 #include "symbol.h"
 
 struct thread {
-        struct rb_node          rb_node;
+        union {
+                struct rb_node   rb_node;
+                struct list_head node;
+        };
         struct map_groups       mg;
         pid_t                   pid;
         char                    shortname[3];