perf hist: Don't fprintf the callgraph unconditionally

[root@doppio ~]# perf report -i newt.data | head -10
  # Samples: 11999679868
  #
  # Overhead  Command                  Shared Object  Symbol
  # ........  .......  .............................  ......
  #
      63.61%     perf  libslang.so.2.1.4              [.] SLsmg_write_chars
       6.30%     perf  perf                           [.] symbols__find
       2.19%     perf  libnewt.so.0.52.10             [.] newtListboxAppendEntry
       2.08%     perf  libslang.so.2.1.4              [.] SLsmg_write_chars@plt
       1.99%     perf  libc-2.10.2.so                 [.] _IO_vfprintf_internal
  [root@doppio ~]#

Not good, the newt form for report works, but slang has to eat
the cost of the additional callgraph lines everytime it prints a
line, and the callgraph doesn't appear on the screen, so move
the callgraph printing to a separate function and don't use it
in newt.c.

Newt tree widgets are being investigated to properly support
callgraphs, but till that gets merged, lets remove this huge
overhead and show at least the symbol overheads for a callgraph
rich perf.data with good performance.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frédéric Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <1268408808-13595-2-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

tools/perf/util/hist.c

@@ -532,23 +532,23 @@ size_t hist_entry__fprintf(struct hist_entry *self,
 		ret += se->print(fp, self, se->width ? *se->width : 0);
 	}
 
-	ret += fprintf(fp, "\n");
-
-	if (symbol_conf.use_callchain) {
-		int left_margin = 0;
+	return ret + fprintf(fp, "\n");
+}
 
-		if (sort__first_dimension == SORT_COMM) {
-			se = list_first_entry(&hist_entry__sort_list, typeof(*se),
-						list);
-			left_margin = se->width ? *se->width : 0;
-			left_margin -= thread__comm_len(self->thread);
-		}
+static size_t hist_entry__fprintf_callchain(struct hist_entry *self, FILE *fp,
+					    u64 session_total)
+{
+	int left_margin = 0;
 
-		ret += hist_entry_callchain__fprintf(fp, self, session_total,
-						     left_margin);
+	if (sort__first_dimension == SORT_COMM) {
+		struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
+							 typeof(*se), list);
+		left_margin = se->width ? *se->width : 0;
+		left_margin -= thread__comm_len(self->thread);
 	}
 
-	return ret;
+	return hist_entry_callchain__fprintf(fp, self, session_total,
+					     left_margin);
 }
 
 size_t perf_session__fprintf_hists(struct rb_root *hists,
@@ -655,6 +655,10 @@ print_entries:
 		}
 		ret += hist_entry__fprintf(h, pair, show_displacement,
 					   displacement, fp, session_total);
+
+		if (symbol_conf.use_callchain)
+			ret += hist_entry__fprintf_callchain(h, fp, session_total);
+
 		if (h->map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(&h->thread->mg,
 						   MAP__FUNCTION, fp);