18 files changed, 244 insertions, 66 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3d8f31ed771d..d75c28a825f5 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -600,30 +600,32 @@ endif
 
 ifdef NO_DEMANGLE
         BASIC_CFLAGS += -DNO_DEMANGLE
-else ifdef HAVE_CPLUS_DEMANGLE
-        EXTLIBS += -liberty
-        BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
 else
-        has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
-
-        ifeq ($(has_bfd),y)
-                EXTLIBS += -lbfd
+        ifdef HAVE_CPLUS_DEMANGLE
+                EXTLIBS += -liberty
+                BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
         else
-                has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
-                ifeq ($(has_bfd_iberty),y)
-                        EXTLIBS += -lbfd -liberty
+                has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd "$(QUIET_STDERR)" && echo y")
+
+                ifeq ($(has_bfd),y)
+                        EXTLIBS += -lbfd
                 else
-                        has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
-                        ifeq ($(has_bfd_iberty_z),y)
-                                EXTLIBS += -lbfd -liberty -lz
+                        has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty "$(QUIET_STDERR)" && echo y")
+                        ifeq ($(has_bfd_iberty),y)
+                                EXTLIBS += -lbfd -liberty
                         else
-                                has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
-                                ifeq ($(has_cplus_demangle),y)
-                                        EXTLIBS += -liberty
-                                        BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
+                                has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -lbfd -liberty -lz "$(QUIET_STDERR)" && echo y")
+                                ifeq ($(has_bfd_iberty_z),y)
+                                        EXTLIBS += -lbfd -liberty -lz
                                 else
-                                        msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
-                                        BASIC_CFLAGS += -DNO_DEMANGLE
+                                        has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o $(BITBUCKET) $(ALL_LDFLAGS) $(EXTLIBS) -liberty "$(QUIET_STDERR)" && echo y")
+                                        ifeq ($(has_cplus_demangle),y)
+                                                EXTLIBS += -liberty
+                                                BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE
+                                        else
+                                                msg := $(warning No bfd.h/libbfd found, install binutils-dev[el]/zlib-static to gain symbol demangling)
+                                                BASIC_CFLAGS += -DNO_DEMANGLE
+                                        endif
                                 endif
                         endif
                 endif
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
new file mode 100644
index 000000000000..15130b50dfe3
--- /dev/null
+++ b/tools/perf/arch/arm/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
diff --git a/tools/perf/arch/arm/util/dwarf-regs.c b/tools/perf/arch/arm/util/dwarf-regs.c
new file mode 100644
index 000000000000..fff6450c8c99
--- /dev/null
+++ b/tools/perf/arch/arm/util/dwarf-regs.c
@@ -0,0 +1,64 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Will Deacon, ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <libio.h>
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+        const char *name;
+        unsigned int dwarfnum;
+};
+
+#define STR(s) #s
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num) \
+        {.name = STR(%r##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0040a/IHI0040A_aadwarf.pdf
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+        GPR_DWARFNUM_NAME(0),
+        GPR_DWARFNUM_NAME(1),
+        GPR_DWARFNUM_NAME(2),
+        GPR_DWARFNUM_NAME(3),
+        GPR_DWARFNUM_NAME(4),
+        GPR_DWARFNUM_NAME(5),
+        GPR_DWARFNUM_NAME(6),
+        GPR_DWARFNUM_NAME(7),
+        GPR_DWARFNUM_NAME(8),
+        GPR_DWARFNUM_NAME(9),
+        GPR_DWARFNUM_NAME(10),
+        REG_DWARFNUM_NAME("%fp", 11),
+        REG_DWARFNUM_NAME("%ip", 12),
+        REG_DWARFNUM_NAME("%sp", 13),
+        REG_DWARFNUM_NAME("%lr", 14),
+        REG_DWARFNUM_NAME("%pc", 15),
+        REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:  the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+        const struct pt_regs_dwarfnum *roff;
+        for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+                if (roff->dwarfnum == n)
+                        return roff->name;
+        return NULL;
+}
diff --git a/tools/perf/arch/sparc/Makefile b/tools/perf/arch/sparc/Makefile
new file mode 100644
index 000000000000..15130b50dfe3
--- /dev/null
+++ b/tools/perf/arch/sparc/Makefile
@@ -0,0 +1,4 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
diff --git a/tools/perf/arch/sparc/util/dwarf-regs.c b/tools/perf/arch/sparc/util/dwarf-regs.c
new file mode 100644
index 000000000000..0ab88483720c
--- /dev/null
+++ b/tools/perf/arch/sparc/util/dwarf-regs.c
@@ -0,0 +1,43 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 David S. Miller <davem@davemloft.net>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <libio.h>
+#include <dwarf-regs.h>
+
+#define SPARC_MAX_REGS  96
+
+const char *sparc_regs_table[SPARC_MAX_REGS] = {
+        "%g0", "%g1", "%g2", "%g3", "%g4", "%g5", "%g6", "%g7",
+        "%o0", "%o1", "%o2", "%o3", "%o4", "%o5", "%sp", "%o7",
+        "%l0", "%l1", "%l2", "%l3", "%l4", "%l5", "%l6", "%l7",
+        "%i0", "%i1", "%i2", "%i3", "%i4", "%i5", "%fp", "%i7",
+        "%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
+        "%f8", "%f9", "%f10", "%f11", "%f12", "%f13", "%f14", "%f15",
+        "%f16", "%f17", "%f18", "%f19", "%f20", "%f21", "%f22", "%f23",
+        "%f24", "%f25", "%f26", "%f27", "%f28", "%f29", "%f30", "%f31",
+        "%f32", "%f33", "%f34", "%f35", "%f36", "%f37", "%f38", "%f39",
+        "%f40", "%f41", "%f42", "%f43", "%f44", "%f45", "%f46", "%f47",
+        "%f48", "%f49", "%f50", "%f51", "%f52", "%f53", "%f54", "%f55",
+        "%f56", "%f57", "%f58", "%f59", "%f60", "%f61", "%f62", "%f63",
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:  the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+        return (n <= SPARC_MAX_REGS) ? sparc_regs_table[n] : NULL;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dc3435e18bde..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)
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/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/event.c b/tools/perf/util/event.c
index 1f08f008d289..2fbf6a463c81 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -538,8 +538,10 @@ int event__process_task(event_t *self, struct perf_session *session)
         dump_printf("(%d:%d):(%d:%d)\n", self->fork.pid, self->fork.tid,
                     self->fork.ppid, self->fork.ptid);
 
-        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 07f89b66b318..784ee0bdda77 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -631,9 +631,14 @@ int hist_entry__fprintf(struct hist_entry *self, struct hists *pair_hists,
                         u64 session_total)
 {
         char bf[512];
-        hist_entry__snprintf(self, bf, sizeof(bf), pair_hists,
-                             show_displacement, displacement,
-                             true, session_total);
+        int ret;
+
+        ret = hist_entry__snprintf(self, bf, sizeof(bf), pair_hists,
+                                   show_displacement, displacement,
+                                   true, session_total);
+        if (!ret)
+                return 0;
+
         return fprintf(fp, "%s\n", bf);
 }
 
@@ -762,6 +767,7 @@ size_t hists__fprintf(struct hists *self, struct hists *pair,
 print_entries:
         for (nd = rb_first(&self->entries); nd; nd = rb_next(nd)) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+                int cnt;
 
                 if (show_displacement) {
                         if (h->pair != NULL)
@@ -771,8 +777,13 @@ print_entries:
                                 displacement = 0;
                         ++position;
                 }
-                ret += hist_entry__fprintf(h, pair, show_displacement,
-                                           displacement, fp, self->stats.total_period);
+                cnt = hist_entry__fprintf(h, pair, show_displacement,
+                                          displacement, fp, self->stats.total_period);
+                /* Ignore those that didn't match the parent filter */
+                if (!cnt)
+                        continue;
+
+                ret += cnt;
 
                 if (symbol_conf.use_callchain)
                         ret += hist_entry__fprintf_callchain(h, fp, self->stats.total_period);
@@ -965,13 +976,17 @@ 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 != ':' || tmp == tmp2)
+                if (*tmp2 != ':' || tmp == tmp2 || tmp2[1] == '\0')
                         line_ip = -1;
         }
 
         if (line_ip != -1) {
-                u64 start = map__rip_2objdump(self->ms.map, sym->start);
+                u64 start = map__rip_2objdump(self->ms.map, sym->start),
+                    end = map__rip_2objdump(self->ms.map, sym->end);
+
                 offset = line_ip - start;
+                if (offset < 0 || (u64)line_ip > end)
+                        offset = -1;
         }
 
         objdump_line = objdump_line__new(offset, line);
diff --git a/tools/perf/util/newt.c b/tools/perf/util/newt.c
index cf182ca132fe..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);
 }
 
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 b63e5713849f..5b276833e2bf 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1443,6 +1443,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 {
         struct dirent *dent;
         DIR *dir = opendir(dir_name);
+        int ret = 0;
 
         if (!dir) {
                 pr_debug("%s: cannot open %s dir\n", __func__, dir_name);
@@ -1465,8 +1466,9 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
 
                         snprintf(path, sizeof(path), "%s/%s",
                                  dir_name, dent->d_name);
-                        if (map_groups__set_modules_path_dir(self, path) < 0)
-                                goto failure;
+                        ret = map_groups__set_modules_path_dir(self, path);
+                        if (ret < 0)
+                                goto out;
                 } else {
                         char *dot = strrchr(dent->d_name, '.'),
                              dso_name[PATH_MAX];
@@ -1487,17 +1489,18 @@ static int map_groups__set_modules_path_dir(struct map_groups *self,
                                  dir_name, dent->d_name);
 
                         long_name = strdup(path);
-                        if (long_name == NULL)
-                                goto failure;
+                        if (long_name == NULL) {
+                                ret = -1;
+                                goto out;
+                        }
                         dso__set_long_name(map->dso, long_name);
                         dso__kernel_module_get_build_id(map->dso, "");
                 }
         }
 
-        return 0;
-failure:
+out:
         closedir(dir);
-        return -1;
+        return ret;
 }
 
 static char *get_kernel_version(const char *root_dir)
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];