diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index 4592d8438318..ec57d0c1fbc2 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -4,6 +4,19 @@
 #include <endian.h>
 #include "event-parse.h"
 
+/*
+ * From glibc endian.h, for older systems where it is not present, e.g.: RHEL5,
+ * Fedora6.
+ */
+#ifndef le16toh
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+#  define le16toh(x) (x)
+# else
+#  define le16toh(x) __bswap_16 (x)
+# endif
+#endif
+
+
 static unsigned long long
 process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
 {
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 57dd57bcef95..280533ebf9df 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -147,7 +147,8 @@ OPTIONS
 
 -s::
 --stat::
-	Per thread counts.
+	Record per-thread event counts.  Use it with 'perf report -T' to see
+	the values.
 
 -d::
 --data::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 27190ed06f9c..c33b69f3374f 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -34,7 +34,8 @@ OPTIONS
 
 -T::
 --threads::
-	Show per-thread event counters
+	Show per-thread event counters.  The input data file should be recorded
+	with -s option.
 -c::
 --comms=::
 	Only consider symbols in these comms. CSV that understands
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index e0173c7f17b1..254614b10c4a 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -713,7 +713,7 @@ static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
 		.size = sample->raw_size,
 	};
 	struct trace_seq seq;
-	char *str, *pos;
+	char *str, *pos = NULL;
 
 	if (nr_gfps) {
 		struct gfp_flag key = {
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 7fa2c7a1086a..1272559fa22d 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -372,6 +372,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Show accessible variables on PROBEDEF", opt_show_vars),
 	OPT_BOOLEAN('\0', "externs", &probe_conf.show_ext_vars,
 		    "Show external variables too (with --vars only)"),
+	OPT_BOOLEAN('\0', "range", &probe_conf.show_location_range,
+		"Show variables location range in scope (with --vars only)"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_STRING('s', "source", &symbol_conf.source_prefix,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 62b49ca0fc7b..92fca2157e5e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -333,15 +333,14 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	}
 
 	if (sort_order == NULL &&
-	    parent_pattern == default_parent_pattern) {
+	    parent_pattern == default_parent_pattern)
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
-		if (rep->show_threads) {
-			bool style = !strcmp(rep->pretty_printing_style, "raw");
-			perf_read_values_display(stdout, &rep->show_threads_values,
-						 style);
-			perf_read_values_destroy(&rep->show_threads_values);
-		}
+	if (rep->show_threads) {
+		bool style = !strcmp(rep->pretty_printing_style, "raw");
+		perf_read_values_display(stdout, &rep->show_threads_values,
+					 style);
+		perf_read_values_destroy(&rep->show_threads_values);
 	}
 
 	return 0;
@@ -815,8 +814,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto error;
 	}
 
-	/* Force tty output for header output. */
-	if (report.header || report.header_only)
+	/* Force tty output for header output and per-thread stat. */
+	if (report.header || report.header_only || report.show_threads)
 		use_browser = 0;
 
 	if (strcmp(input_name, "-") != 0)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index cbfdb9523868..a05490d06374 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -16,7 +16,6 @@
 
 #include <libaudit.h>
 #include <stdlib.h>
-#include <sys/eventfd.h>
 #include <sys/mman.h>
 #include <linux/futex.h>
 
@@ -41,6 +40,34 @@
 # define EFD_SEMAPHORE		1
 #endif
 
+#ifndef EFD_NONBLOCK
+# define EFD_NONBLOCK		00004000
+#endif
+
+#ifndef EFD_CLOEXEC
+# define EFD_CLOEXEC		02000000
+#endif
+
+#ifndef O_CLOEXEC
+# define O_CLOEXEC		02000000
+#endif
+
+#ifndef SOCK_DCCP
+# define SOCK_DCCP		6
+#endif
+
+#ifndef SOCK_CLOEXEC
+# define SOCK_CLOEXEC		02000000
+#endif
+
+#ifndef SOCK_NONBLOCK
+# define SOCK_NONBLOCK		00004000
+#endif
+
+#ifndef MSG_CMSG_CLOEXEC
+# define MSG_CMSG_CLOEXEC	0x40000000
+#endif
+
 struct tp_field {
 	int offset;
 	union {
@@ -2721,11 +2748,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	signal(SIGFPE, sighandler_dump_stack);
 
 	trace.evlist = perf_evlist__new();
-	if (trace.evlist == NULL)
-		return -ENOMEM;
 
 	if (trace.evlist == NULL) {
 		pr_err("Not enough memory to run!\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 4f4098167112..f42af98a5c16 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -219,7 +219,7 @@ static int run_test(struct test *test)
 	wait(&status);
 
 	if (WIFEXITED(status)) {
-		err = WEXITSTATUS(status);
+		err = (signed char)WEXITSTATUS(status);
 		pr_debug("test child finished with %d\n", err);
 	} else if (WIFSIGNALED(status)) {
 		err = -1;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 52758a33f64c..a10eaf5c4767 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -9,6 +9,15 @@ do {									 \
 	}								 \
 } while (0)
 
+#define TEST_ASSERT_EQUAL(text, val, expected)				 \
+do {									 \
+	if (val != expected) {						 \
+		pr_debug("FAILED %s:%d %s (%d != %d)\n",		 \
+			 __FILE__, __LINE__, text, val, expected);	 \
+		return -1;						 \
+	}								 \
+} while (0)
+
 enum {
 	TEST_OK   =  0,
 	TEST_FAIL = -1,
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index dc05bd62b4a3..c0ed56f7efc6 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_VAL("wrong refcnt", mg->refcnt == 4);
+	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 4);
 
 	/* test the map groups pointer is shared */
 	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
@@ -58,34 +58,41 @@ int test__thread_mg_share(void)
 	other_leader = machine__find_thread(machine, 4, 4);
 	TEST_ASSERT_VAL("failed to find other leader", other_leader);
 
+	/*
+	 * Ok, now that all the rbtree related operations were done,
+	 * lets remove all of them from there so that we can do the
+	 * refcounting tests.
+	 */
+	machine__remove_thread(machine, leader);
+	machine__remove_thread(machine, t1);
+	machine__remove_thread(machine, t2);
+	machine__remove_thread(machine, t3);
+	machine__remove_thread(machine, other);
+	machine__remove_thread(machine, other_leader);
+
 	other_mg = other->mg;
-	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", 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_VAL("wrong refcnt", mg->refcnt == 3);
+	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 3);
 
 	thread__put(t1);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 2);
 
 	thread__put(t2);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", mg->refcnt, 1);
 
 	thread__put(t3);
 
 	/* release other group  */
 	thread__put(other_leader);
-	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+	TEST_ASSERT_EQUAL("wrong refcnt", other_mg->refcnt, 1);
 
 	thread__put(other);
 
-	/*
-	 * Cannot call machine__delete_threads(machine) now,
-	 * because we've already released all the threads.
-	 */
-
 	machines__exit(&machines);
 	return 0;
 }
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index d552203aead0..6966d0743bf7 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -102,19 +102,19 @@ CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="B
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
 
 CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fbcca21d66ab..c861373aaed3 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -30,7 +30,6 @@ extern const char *perf_config_dirname(const char *, const char *);
 
 /* pager.c */
 extern void setup_pager(void);
-extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 16d46e26edac..eb47abdcf0ac 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -433,6 +433,43 @@ struct __addr_die_search_param {
 	Dwarf_Die	*die_mem;
 };
 
+static int __die_search_func_tail_cb(Dwarf_Die *fn_die, void *data)
+{
+	struct __addr_die_search_param *ad = data;
+	Dwarf_Addr addr = 0;
+
+	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+	    !dwarf_highpc(fn_die, &addr) &&
+	    addr == ad->addr) {
+		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+		return DWARF_CB_ABORT;
+	}
+	return DWARF_CB_OK;
+}
+
+/**
+ * die_find_tailfunc - Search for a non-inlined function with tail call at
+ * given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search for a non-inlined function DIE with tail call at @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem)
+{
+	struct __addr_die_search_param ad;
+	ad.addr = addr;
+	ad.die_mem = die_mem;
+	/* dwarf_getscopes can't find subprogram. */
+	if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+		return NULL;
+	else
+		return die_mem;
+}
+
 /* die_find callback for non-inlined function search */
 static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
@@ -848,19 +885,17 @@ Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 /**
  * die_get_typename - Get the name of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for result type name
- * @len: a max-length of @buf
+ * @buf: a strbuf for result type name
  *
- * Get the name of @vr_die and stores it to @buf. Return the actual length
- * of type name if succeeded. Return -E2BIG if @len is not enough long, and
- * Return -ENOENT if failed to find type name.
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
  * Note that the result will stores typedef name if possible, and stores
  * "*(function_type)" if the type is a function pointer.
  */
-int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 {
 	Dwarf_Die type;
-	int tag, ret, ret2;
+	int tag, ret;
 	const char *tmp = "";
 
 	if (__die_get_real_type(vr_die, &type) == NULL)
@@ -871,8 +906,8 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
-		ret = snprintf(buf, len, "(function_type)");
-		return (ret >= len) ? -E2BIG : ret;
+		strbuf_addf(buf, "(function_type)");
+		return 0;
 	} else {
 		if (!dwarf_diename(&type))
 			return -ENOENT;
@@ -883,39 +918,156 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		else if (tag == DW_TAG_enumeration_type)
 			tmp = "enum ";
 		/* Write a base name */
-		ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
-		return (ret >= len) ? -E2BIG : ret;
-	}
-	ret = die_get_typename(&type, buf, len);
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+		strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
+		return 0;
 	}
+	ret = die_get_typename(&type, buf);
+	if (ret == 0)
+		strbuf_addf(buf, "%s", tmp);
+
 	return ret;
 }
 
 /**
  * die_get_varname - Get the name and type of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for type and variable name
- * @len: the max-length of @buf
+ * @buf: a strbuf for type and variable name
  *
  * Get the name and type of @vr_die and stores it in @buf as "type\tname".
  */
-int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 {
-	int ret, ret2;
+	int ret;
 
-	ret = die_get_typename(vr_die, buf, len);
+	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		ret = snprintf(buf, len, "(unknown_type)");
+		strbuf_addf(buf, "(unknown_type)");
 	}
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "\t%s",
-				dwarf_diename(vr_die));
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+
+	strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
+
+	return 0;
+}
+
+/**
+ * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for variable byte offset range
+ *
+ * Get the innermost scope range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+				struct strbuf *buf)
+{
+	Dwarf_Die *scopes;
+	int count;
+	size_t offset = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	int ret;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	count = dwarf_getscopes_die(vr_die, &scopes);
+
+	/* (*SCOPES)[1] is the DIE for the scope containing that scope */
+	if (count <= 1) {
+		ret = -EINVAL;
+		goto out;
 	}
+
+	while ((offset = dwarf_ranges(&scopes[1], offset, &base,
+				&start, &end)) > 0) {
+		start -= entry;
+		end -= entry;
+
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%lu-%lu",
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%lu-%lu",
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+out:
+	free(scopes);
 	return ret;
 }
 
+/**
+ * die_get_var_range - Get byte offset range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for type and variable name and byte offset range
+ *
+ * Get the byte offset range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
+{
+	int ret = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	Dwarf_Op *op;
+	size_t nops;
+	size_t offset = 0;
+	Dwarf_Attribute attr;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+		return -EINVAL;
+
+	while ((offset = dwarf_getlocations(
+				&attr, offset, &base,
+				&start, &end, &op, &nops)) > 0) {
+		if (start == 0) {
+			/* Single Location Descriptions */
+			ret = die_get_var_innermost_scope(sp_die, vr_die, buf);
+			return ret;
+		}
+
+		/* Location Lists */
+		start -= entry;
+		end -= entry;
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%lu-%lu",
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%lu-%lu",
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+	return ret;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 50a3cdc55fd7..c42ec366f2a7 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -85,6 +85,10 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
+/* Search a non-inlined function with tail call at given address */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem);
+
 /* Search the top inlined function including given address */
 extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 					  Dwarf_Die *die_mem);
@@ -117,8 +121,10 @@ extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 				  Dwarf_Die *die_mem);
 
 /* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+			struct strbuf *buf);
 #endif
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
index 275b0ee345f5..7405123692f1 100644
--- a/tools/perf/util/environment.c
+++ b/tools/perf/util/environment.c
@@ -5,5 +5,4 @@
  */
 #include "cache.h"
 
-const char *pager_program;
 int pager_use_color = 1;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8b0b307d91f4..34bf89f7f4f3 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -364,7 +364,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 			return th;
 		}
 
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 	}
 
 	while (*p != NULL) {
@@ -372,7 +372,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			machine->last_match = thread__get(th);
+			machine->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
 			return th;
 		}
@@ -409,7 +409,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		machine->last_match = thread__get(th);
+		machine->last_match = th;
 	}
 
 	return th;
@@ -1309,7 +1309,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
 	if (machine->last_match == th)
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 
 	BUG_ON(th->refcnt.counter == 0);
 	if (lock)
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 31ee02d4e988..53ef006a951c 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -50,11 +50,6 @@ void setup_pager(void)
 
 	if (!isatty(1))
 		return;
-	if (!pager) {
-		if (!pager_program)
-			perf_config(perf_default_config, NULL);
-		pager = pager_program;
-	}
 	if (!pager)
 		pager = getenv("PAGER");
 	if (!(pager || access("/usr/bin/pager", X_OK)))
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 1e2faa3559d2..537eb329c2cf 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -9,6 +9,7 @@
 /* Probe related configurations */
 struct probe_conf {
 	bool	show_ext_vars;
+	bool	show_location_range;
 	bool	force_add;
 	bool	no_inlines;
 	int	max_probes;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 8b9e274f940c..c50da392e256 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -177,7 +177,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	Dwarf_Word offs = 0;
 	bool ref = false;
 	const char *regs;
-	int ret;
+	int ret, ret2 = 0;
 
 	if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
 		goto static_var;
@@ -187,9 +187,19 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 		return -EINVAL;	/* Broken DIE ? */
 	if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
 		ret = dwarf_entrypc(sp_die, &tmp);
-		if (ret || addr != tmp ||
-		    dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
-		    dwarf_highpc(sp_die, &tmp))
+		if (ret)
+			return -ENOENT;
+
+		if (probe_conf.show_location_range &&
+			(dwarf_tag(vr_die) == DW_TAG_variable)) {
+			ret2 = -ERANGE;
+		} else if (addr != tmp ||
+			dwarf_tag(vr_die) != DW_TAG_formal_parameter) {
+			return -ENOENT;
+		}
+
+		ret = dwarf_highpc(sp_die, &tmp);
+		if (ret)
 			return -ENOENT;
 		/*
 		 * This is fuzzed by fentry mcount. We try to find the
@@ -210,7 +220,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	if (op->atom == DW_OP_addr) {
 static_var:
 		if (!tvar)
-			return 0;
+			return ret2;
 		/* Static variables on memory (not stack), make @varname */
 		ret = strlen(dwarf_diename(vr_die));
 		tvar->value = zalloc(ret + 2);
@@ -220,7 +230,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 		tvar->ref = alloc_trace_arg_ref((long)offs);
 		if (tvar->ref == NULL)
 			return -ENOMEM;
-		return 0;
+		return ret2;
 	}
 
 	/* If this is based on frame buffer, set the offset */
@@ -250,14 +260,14 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	}
 
 	if (!tvar)
-		return 0;
+		return ret2;
 
 	regs = get_arch_regstr(regn);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
 		pr_warning("Mapping for the register number %u "
 			   "missing on this architecture.\n", regn);
-		return -ERANGE;
+		return -ENOTSUP;
 	}
 
 	tvar->value = strdup(regs);
@@ -269,7 +279,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 		if (tvar->ref == NULL)
 			return -ENOMEM;
 	}
-	return 0;
+	return ret2;
 }
 
 #define BYTES_TO_BITS(nb)	((nb) * BITS_PER_LONG / sizeof(long))
@@ -517,10 +527,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
 					&pf->sp_die, pf->tvar);
-	if (ret == -ENOENT || ret == -EINVAL)
-		pr_err("Failed to find the location of %s at this address.\n"
-		       " Perhaps, it has been optimized out.\n", pf->pvar->var);
-	else if (ret == -ENOTSUP)
+	if (ret == -ENOENT || ret == -EINVAL) {
+		pr_err("Failed to find the location of the '%s' variable at this address.\n"
+		       " Perhaps it has been optimized out.\n"
+		       " Use -V with the --range option to show '%s' location range.\n",
+		       pf->pvar->var, pf->pvar->var);
+	} else if (ret == -ENOTSUP)
 		pr_err("Sorry, we don't support this variable location yet.\n");
 	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
@@ -662,9 +674,15 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* If not a real subprogram, find a real one */
 	if (!die_is_func_def(sc_die)) {
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
-			pr_warning("Failed to find probe point in any "
-				   "functions.\n");
-			return -ENOENT;
+			if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
+				pr_warning("Ignoring tail call from %s\n",
+						dwarf_diename(&pf->sp_die));
+				return 0;
+			} else {
+				pr_warning("Failed to find probe point in any "
+					   "functions.\n");
+				return -ENOENT;
+			}
 		}
 	} else
 		memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
@@ -1255,14 +1273,11 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	return (ret < 0) ? ret : tf.ntevs;
 }
 
-#define MAX_VAR_LEN 64
-
 /* Collect available variables in this scope */
 static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 {
 	struct available_var_finder *af = data;
 	struct variable_list *vl;
-	char buf[MAX_VAR_LEN];
 	int tag, ret;
 
 	vl = &af->vls[af->nvls - 1];
@@ -1273,11 +1288,38 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 		ret = convert_variable_location(die_mem, af->pf.addr,
 						af->pf.fb_ops, &af->pf.sp_die,
 						NULL);
-		if (ret == 0) {
-			ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
-			pr_debug2("Add new var: %s\n", buf);
-			if (ret > 0)
-				strlist__add(vl->vars, buf);
+		if (ret == 0 || ret == -ERANGE) {
+			int ret2;
+			bool externs = !af->child;
+			struct strbuf buf;
+
+			strbuf_init(&buf, 64);
+
+			if (probe_conf.show_location_range) {
+				if (!externs) {
+					if (ret)
+						strbuf_addf(&buf, "[INV]\t");
+					else
+						strbuf_addf(&buf, "[VAL]\t");
+				} else
+					strbuf_addf(&buf, "[EXT]\t");
+			}
+
+			ret2 = die_get_varname(die_mem, &buf);
+
+			if (!ret2 && probe_conf.show_location_range &&
+				!externs) {
+				strbuf_addf(&buf, "\t");
+				ret2 = die_get_var_range(&af->pf.sp_die,
+							die_mem, &buf);
+			}
+
+			pr_debug("Add new var: %s\n", buf.buf);
+			if (ret2 == 0) {
+				strlist__add(vl->vars,
+					strbuf_detach(&buf, NULL));
+			}
+			strbuf_release(&buf);
 		}
 	}