perf callchain: Use global caching provided by libunwind

The libunwind provides two caching policy which are global and
per-thread.  As perf unwinds callchains in a single thread, it'd
sufficient to use global caching.

This speeds up my perf report from 14s to 7s on a ~260MB data file.
Although the output sometimes contains a slight difference (~0.01% in
terms of number of lines printed) on callchains which were not resolved.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jean Pihet <jean.pihet@linaro.org>
Cc: Arun Sharma <asharma@fb.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1412556363-26229-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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;

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;

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 */