diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 04412b4770a2230ec83296cb179eb397ebb42e94..7af26acf06d9d573e42c1326757af673ce780c50 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -375,7 +375,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('x', "exec", NULL, "executable|path",
 			"target executable name or path", opt_set_target),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
-		    "Disable symbol demangling"),
+		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
 	OPT_END()
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 937e4324ad94ed601bb43a2d12489c2f90eb841b..a3b13d7dc1d43f3caf301b4d9f941c60d88ed37c 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -13,7 +13,7 @@
 #define wmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 336
 #endif
@@ -30,7 +30,7 @@
 #define wmb()		asm volatile("sfence" ::: "memory")
 #define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
 # define __NR_perf_event_open 298
 #endif
@@ -47,14 +47,14 @@
 #define mb()		asm volatile ("sync" ::: "memory")
 #define wmb()		asm volatile ("sync" ::: "memory")
 #define rmb()		asm volatile ("sync" ::: "memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __s390__
 #define mb()		asm volatile("bcr 15,0" ::: "memory")
 #define wmb()		asm volatile("bcr 15,0" ::: "memory")
 #define rmb()		asm volatile("bcr 15,0" ::: "memory")
-#define CPUINFO_PROC	"vendor_id"
+#define CPUINFO_PROC	{"vendor_id"}
 #endif
 
 #ifdef __sh__
@@ -67,14 +67,14 @@
 # define wmb()		asm volatile("" ::: "memory")
 # define rmb()		asm volatile("" ::: "memory")
 #endif
-#define CPUINFO_PROC	"cpu type"
+#define CPUINFO_PROC	{"cpu type"}
 #endif
 
 #ifdef __hppa__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __sparc__
@@ -87,14 +87,14 @@
 #endif
 #define wmb()		asm volatile("":::"memory")
 #define rmb()		asm volatile("":::"memory")
-#define CPUINFO_PROC	"cpu"
+#define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __alpha__
 #define mb()		asm volatile("mb" ::: "memory")
 #define wmb()		asm volatile("wmb" ::: "memory")
 #define rmb()		asm volatile("mb" ::: "memory")
-#define CPUINFO_PROC	"cpu model"
+#define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __ia64__
@@ -102,7 +102,7 @@
 #define wmb()		asm volatile ("mf" ::: "memory")
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
-#define CPUINFO_PROC	"model name"
+#define CPUINFO_PROC	{"model name"}
 #endif
 
 #ifdef __arm__
@@ -113,7 +113,7 @@
 #define mb()		((void(*)(void))0xffff0fa0)()
 #define wmb()		((void(*)(void))0xffff0fa0)()
 #define rmb()		((void(*)(void))0xffff0fa0)()
-#define CPUINFO_PROC	"Processor"
+#define CPUINFO_PROC	{"model name", "Processor"}
 #endif
 
 #ifdef __aarch64__
@@ -133,28 +133,28 @@
 				: "memory")
 #define wmb()	mb()
 #define rmb()	mb()
-#define CPUINFO_PROC	"cpu model"
+#define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __arc__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"Processor"
+#define CPUINFO_PROC	{"Processor"}
 #endif
 
 #ifdef __metag__
 #define mb()		asm volatile("" ::: "memory")
 #define wmb()		asm volatile("" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"CPU"
+#define CPUINFO_PROC	{"CPU"}
 #endif
 
 #ifdef __xtensa__
 #define mb()		asm volatile("memw" ::: "memory")
 #define wmb()		asm volatile("memw" ::: "memory")
 #define rmb()		asm volatile("" ::: "memory")
-#define CPUINFO_PROC	"core ID"
+#define CPUINFO_PROC	{"core ID"}
 #endif
 
 #ifdef __tile__
@@ -162,7 +162,7 @@
 #define wmb()		asm volatile ("mf" ::: "memory")
 #define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("mfspr zero, PASS" ::: "memory")
-#define CPUINFO_PROC    "model name"
+#define CPUINFO_PROC    {"model name"}
 #endif
 
 #define barrier() asm volatile ("" ::: "memory")
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ce0de00399da381accf00472f66c6064cdcee20a..26f5b2fe5dc89832c44eb8c20b5deb6db1c72d3e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -579,16 +579,12 @@ static int write_version(int fd, struct perf_header *h __maybe_unused,
 	return do_write_string(fd, perf_version_string);
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
-		       struct perf_evlist *evlist __maybe_unused)
+static int __write_cpudesc(int fd, const char *cpuinfo_proc)
 {
-#ifndef CPUINFO_PROC
-#define CPUINFO_PROC NULL
-#endif
 	FILE *file;
 	char *buf = NULL;
 	char *s, *p;
-	const char *search = CPUINFO_PROC;
+	const char *search = cpuinfo_proc;
 	size_t len = 0;
 	int ret = -1;
 
@@ -638,6 +634,25 @@ static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
 	return ret;
 }
 
+static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+		       struct perf_evlist *evlist __maybe_unused)
+{
+#ifndef CPUINFO_PROC
+#define CPUINFO_PROC {"model name", }
+#endif
+	const char *cpuinfo_procs[] = CPUINFO_PROC;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(cpuinfo_procs); i++) {
+		int ret;
+		ret = __write_cpudesc(fd, cpuinfo_procs[i]);
+		if (ret >= 0)
+			return ret;
+	}
+	return -1;
+}
+
+
 static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
 			struct perf_evlist *evlist __maybe_unused)
 {
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4906cd81cb56a852843b38e85a1d2f5b82417654..9402885a77f383674e40d54e1a543da111dc6725 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -373,6 +373,9 @@ struct sort_entry sort_cpu = {
 static int64_t
 sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return _sort__dso_cmp(left->branch_info->from.map,
 			      right->branch_info->from.map);
 }
@@ -380,13 +383,19 @@ sort__dso_from_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return _hist_entry__dso_snprintf(he->branch_info->from.map,
-					 bf, size, width);
+	if (he->branch_info)
+		return _hist_entry__dso_snprintf(he->branch_info->from.map,
+						 bf, size, width);
+	else
+		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return _sort__dso_cmp(left->branch_info->to.map,
 			      right->branch_info->to.map);
 }
@@ -394,8 +403,11 @@ sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	return _hist_entry__dso_snprintf(he->branch_info->to.map,
-					 bf, size, width);
+	if (he->branch_info)
+		return _hist_entry__dso_snprintf(he->branch_info->to.map,
+						 bf, size, width);
+	else
+		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int64_t
@@ -404,6 +416,12 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 	struct addr_map_symbol *from_l = &left->branch_info->from;
 	struct addr_map_symbol *from_r = &right->branch_info->from;
 
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	from_l = &left->branch_info->from;
+	from_r = &right->branch_info->from;
+
 	if (!from_l->sym && !from_r->sym)
 		return _sort__addr_cmp(from_l->addr, from_r->addr);
 
@@ -413,8 +431,13 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 static int64_t
 sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	struct addr_map_symbol *to_l = &left->branch_info->to;
-	struct addr_map_symbol *to_r = &right->branch_info->to;
+	struct addr_map_symbol *to_l, *to_r;
+
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
+	to_l = &left->branch_info->to;
+	to_r = &right->branch_info->to;
 
 	if (!to_l->sym && !to_r->sym)
 		return _sort__addr_cmp(to_l->addr, to_r->addr);
@@ -425,19 +448,27 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf,
 					 size_t size, unsigned int width)
 {
-	struct addr_map_symbol *from = &he->branch_info->from;
-	return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
-					 he->level, bf, size, width);
+	if (he->branch_info) {
+		struct addr_map_symbol *from = &he->branch_info->from;
 
+		return _hist_entry__sym_snprintf(from->map, from->sym, from->addr,
+						 he->level, bf, size, width);
+	}
+
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	struct addr_map_symbol *to = &he->branch_info->to;
-	return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
-					 he->level, bf, size, width);
+	if (he->branch_info) {
+		struct addr_map_symbol *to = &he->branch_info->to;
 
+		return _hist_entry__sym_snprintf(to->map, to->sym, to->addr,
+						 he->level, bf, size, width);
+	}
+
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
 struct sort_entry sort_dso_from = {
@@ -471,11 +502,13 @@ struct sort_entry sort_sym_to = {
 static int64_t
 sort__mispredict_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	const unsigned char mp = left->branch_info->flags.mispred !=
-					right->branch_info->flags.mispred;
-	const unsigned char p = left->branch_info->flags.predicted !=
-					right->branch_info->flags.predicted;
+	unsigned char mp, p;
+
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
 
+	mp = left->branch_info->flags.mispred != right->branch_info->flags.mispred;
+	p  = left->branch_info->flags.predicted != right->branch_info->flags.predicted;
 	return mp || p;
 }
 
@@ -483,10 +516,12 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width){
 	static const char *out = "N/A";
 
-	if (he->branch_info->flags.predicted)
-		out = "N";
-	else if (he->branch_info->flags.mispred)
-		out = "Y";
+	if (he->branch_info) {
+		if (he->branch_info->flags.predicted)
+			out = "N";
+		else if (he->branch_info->flags.mispred)
+			out = "Y";
+	}
 
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }
@@ -989,6 +1024,9 @@ struct sort_entry sort_mem_dcacheline = {
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.abort !=
 		right->branch_info->flags.abort;
 }
@@ -996,10 +1034,15 @@ sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__abort_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	static const char *out = ".";
+	static const char *out = "N/A";
+
+	if (he->branch_info) {
+		if (he->branch_info->flags.abort)
+			out = "A";
+		else
+			out = ".";
+	}
 
-	if (he->branch_info->flags.abort)
-		out = "A";
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -1013,6 +1056,9 @@ struct sort_entry sort_abort = {
 static int64_t
 sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 {
+	if (!left->branch_info || !right->branch_info)
+		return cmp_null(left->branch_info, right->branch_info);
+
 	return left->branch_info->flags.in_tx !=
 		right->branch_info->flags.in_tx;
 }
@@ -1020,10 +1066,14 @@ sort__in_tx_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__in_tx_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	static const char *out = ".";
+	static const char *out = "N/A";
 
-	if (he->branch_info->flags.in_tx)
-		out = "T";
+	if (he->branch_info) {
+		if (he->branch_info->flags.in_tx)
+			out = "T";
+		else
+			out = ".";
+	}
 
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2b7b2d91c016b211f48a9823f9837033615b1136..c41411726c7a1052a704f75d829e433f3abdb6b8 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -117,6 +117,9 @@ int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
 		if (!new)
 			return -ENOMEM;
 		list_add(&new->list, &thread->comm_list);
+
+		if (exec)
+			unwind__flush_access(thread);
 	}
 
 	thread->comm_set = true;
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index e060386165c5fad82372123e99252f577eb7eac4..4d45c0dfe34347ef57527dd90f132e9067eb57e9 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -539,11 +539,23 @@ int unwind__prepare_access(struct thread *thread)
 		return -ENOMEM;
 	}
 
+	unw_set_caching_policy(addr_space, UNW_CACHE_GLOBAL);
 	thread__set_priv(thread, addr_space);
 
 	return 0;
 }
 
+void unwind__flush_access(struct thread *thread)
+{
+	unw_addr_space_t addr_space;
+
+	if (callchain_param.record_mode != CALLCHAIN_DWARF)
+		return;
+
+	addr_space = thread__priv(thread);
+	unw_flush_cache(addr_space, 0, 0);
+}
+
 void unwind__finish_access(struct thread *thread)
 {
 	unw_addr_space_t addr_space;
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index c17c4855bdbc3e4bcf8423246c92b8f7bc750494..f50b737235eb82eaabb44778c33cb4646f091459 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -23,6 +23,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 #ifdef HAVE_LIBUNWIND_SUPPORT
 int libunwind__arch_reg_id(int regnum);
 int unwind__prepare_access(struct thread *thread);
+void unwind__flush_access(struct thread *thread);
 void unwind__finish_access(struct thread *thread);
 #else
 static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
@@ -30,6 +31,7 @@ static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
 	return 0;
 }
 
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
 static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif
 #else
@@ -49,6 +51,7 @@ static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
 	return 0;
 }
 
+static inline void unwind__flush_access(struct thread *thread __maybe_unused) {}
 static inline void unwind__finish_access(struct thread *thread __maybe_unused) {}
 #endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */