perf report: Enable sorting by srcline as key

Often it is interesting to know how costly a given source line is in
total. Previously, one had to build these sums manually based on all
addresses that pointed to the same source line. This patch introduces
srcline as a sort key, which will do the aggregation for us.

Paired with the recent addition of showing inline frames, this makes
perf report much more useful for many C++ work loads.

The following shows the new feature in action. First, let's show the
status quo output when we sort by address. The result contains many hist
entries that generate the same output:

  ~~~~~~~~~~~~~~~~
  $ perf report --stdio --inline -g address
  # Children      Self  Command       Shared Object        Symbol
  # ........  ........  ............  ...................  .........................................
  #
      99.89%    35.34%  cpp-inlining  cpp-inlining         [.] main
            |
            |--64.55%--main complex:655
            |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
            |          /usr/include/c++/6.3.1/complex:664 (inline)
            |          |
            |          |--60.31%--hypot +20
            |          |          |
            |          |          |--8.52%--__hypot_finite +273
            |          |          |
            |          |          |--7.32%--__hypot_finite +411
...
             --35.34%--_start +4194346
                       __libc_start_main +241
                       |
                       |--6.65%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
                       |
                       |--2.70%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
                       |
                       |--1.69%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
  ...
  ~~~~~~~~~~~~~~~~

With this patch and `-g srcline` we instead get the following output:

  ~~~~~~~~~~~~~~~~
  $ perf report --stdio --inline -g srcline
  # Children      Self  Command       Shared Object        Symbol
  # ........  ........  ............  ...................  .........................................
  #
      99.89%    35.34%  cpp-inlining  cpp-inlining         [.] main
            |
            |--64.55%--main complex:655
            |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
            |          /usr/include/c++/6.3.1/complex:664 (inline)
            |          |
            |          |--64.02%--hypot
            |          |          |
            |          |           --59.81%--__hypot_finite
            |          |
            |           --0.53%--cabs
            |
             --35.34%--_start
                       __libc_start_main
                       |
                       |--12.48%--main random.tcc:3326
                       |          /home/milian/projects/kdab/rnd/hotspot/tests/test-clients/cpp-inlining/main.cpp:39 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1809 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:1818 (inline)
                       |          /usr/include/c++/6.3.1/bits/random.h:185 (inline)
  ...
  ~~~~~~~~~~~~~~~~

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/20170318214928.9047-1-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 47 insertions, 5 deletions

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index aba953421a03..d78776a20e80 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -80,6 +80,10 @@ static int parse_callchain_sort_key(const char *value)
 		callchain_param.key = CCKEY_ADDRESS;
 		return 0;
 	}
+	if (!strncmp(value, "srcline", strlen(value))) {
+		callchain_param.key = CCKEY_SRCLINE;
+		return 0;
+	}
 	if (!strncmp(value, "branch", strlen(value))) {
 		callchain_param.branch_callstack = 1;
 		return 0;
@@ -510,14 +514,51 @@ enum match_result {
 	MATCH_GT,
 };
 
+static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
+					     struct callchain_list *cnode)
+{
+	char *left = get_srcline(cnode->ms.map->dso,
+				 map__rip_2objdump(cnode->ms.map, cnode->ip),
+				 cnode->ms.sym, true, false);
+	char *right = get_srcline(node->map->dso,
+				  map__rip_2objdump(node->map, node->ip),
+				  node->sym, true, false);
+	enum match_result ret = MATCH_EQ;
+	int cmp;
+
+	if (left && right)
+		cmp = strcmp(left, right);
+	else if (!left && right)
+		cmp = 1;
+	else if (left && !right)
+		cmp = -1;
+	else if (cnode->ip == node->ip)
+		cmp = 0;
+	else
+		cmp = (cnode->ip < node->ip) ? -1 : 1;
+
+	if (cmp != 0)
+		ret = cmp < 0 ? MATCH_LT : MATCH_GT;
+
+	free_srcline(left);
+	free_srcline(right);
+	return ret;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
 				     struct callchain_list *cnode)
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
 
-	if (cnode->ms.sym && sym &&
-	    callchain_param.key == CCKEY_FUNCTION) {
+	if (callchain_param.key == CCKEY_SRCLINE) {
+		enum match_result match = match_chain_srcline(node, cnode);
+
+		if (match != MATCH_ERROR)
+			return match;
+	}
+
+	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
 	} else {
@@ -911,15 +952,16 @@ out:
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso)
 {
+	bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+	bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE;
 	int printed;
 
 	if (cl->ms.sym) {
-		if (callchain_param.key == CCKEY_ADDRESS &&
-		    cl->ms.map && !cl->srcline)
+		if (show_srcline && cl->ms.map && !cl->srcline)
 			cl->srcline = get_srcline(cl->ms.map->dso,
 						  map__rip_2objdump(cl->ms.map,
 								    cl->ip),
-						  cl->ms.sym, false);
+						  cl->ms.sym, false, show_addr);
 		if (cl->srcline)
 			printed = scnprintf(bf, bfsize, "%s %s",
 					cl->ms.sym->name, cl->srcline);