[PATCH 02/13] perf symbols: Fix symbols searching for module in buildid-cache

[Arnaldo Carvalho de Melo]

From: Wang Nan <wangnan0@xxxxxxxxxx>

Before this patch, if a sample is triggered inside a module not in
/lib/modules/`uname -r`/, even if the module is in buildid-cache, 'perf
report' will still be unable to find the correct symbol.  For example:

  # rm -rf ~/.debug/
  # perf buildid-cache -a ./mymodule.ko
  # perf probe -m ./mymodule.ko -a get_mymodule_val
  Added new event:
    probe:get_mymodule_val (on get_mymodule_val in mymodule)

  You can now use it in all perf tools, such as:

 	perf record -e probe:get_mymodule_val -aR sleep 1

  # perf record -e probe:get_mymodule_val cat /proc/mymodule
  mymodule:3
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.011 MB perf.data (1 samples) ]

  # perf report --stdio
  [SNIP]
  #
  # Overhead  Command  Shared Object     Symbol
  # ........  .......  ................  ......................
  #
    100.00%  cat      [mymodule]        [k] 0x0000000000000001

  # perf report -vvvv --stdio
  dso__load_sym: adjusting symbol: st_value: 0 sh_addr: 0 sh_offset: 0x70
  symbol__new: get_mymodule_val 0x70-0x8a
  [SNIP]

This is caused by dso__load() -> dso__load_sym(). In dso__load(), kmod
is true only when its file is found in some well know directories. All
files loaded from buildid-cache are treated as user programs. Following
dso__load_sym() set map->pgoff incorrectly.

This patch gives kernel modules in buildid-cache a chance to adjust
value of kmod. After dso__load() get the type of symbols, if it is
buildid, check the last 3 chars of original filename against '.ko', and
adjust the value of kmod if the file is a kernel module.

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Cc: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Brendan Gregg <brendan.d.gregg@xxxxxxxxx>
Cc: Cody P Schafer <dev@xxxxxxxxxx>
Cc: He Kuang <hekuang@xxxxxxxxxx>
Cc: Jeremie Galarneau <jeremie.galarneau@xxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kirill Smelkov <kirr@xxxxxxxxxx>
Cc: Li Zefan <lizefan@xxxxxxxxxx>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: pi3orama@xxxxxxx
Link: http://lkml.kernel.org/r/1454680939-24963-3-git-send-email-wangnan0@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/build-id.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/build-id.h |  1 +
 tools/perf/util/symbol.c   |  4 ++++
 3 files changed, 49 insertions(+)

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index b28100ee1732..f1479eeef7da 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -166,6 +166,50 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 	return build_id__filename(build_id_hex, bf, size);
 }
 
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
+{
+	char *id_name, *ch;
+	struct stat sb;
+
+	id_name = dso__build_id_filename(dso, bf, size);
+	if (!id_name)
+		goto err;
+	if (access(id_name, F_OK))
+		goto err;
+	if (lstat(id_name, &sb) == -1)
+		goto err;
+	if ((size_t)sb.st_size > size - 1)
+		goto err;
+	if (readlink(id_name, bf, size - 1) < 0)
+		goto err;
+
+	bf[sb.st_size] = '\0';
+
+	/*
+	 * link should be:
+	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
+	 */
+	ch = strrchr(bf, '/');
+	if (!ch)
+		goto err;
+	if (ch - 3 < bf)
+		goto err;
+
+	return strncmp(".ko", ch - 3, 3) == 0;
+err:
+	/*
+	 * If dso__build_id_filename work, get id_name again,
+	 * because id_name points to bf and is broken.
+	 */
+	if (id_name)
+		id_name = dso__build_id_filename(dso, bf, size);
+	pr_err("Invalid build id: %s\n", id_name ? :
+					 dso->long_name ? :
+					 dso->short_name ? :
+					 "[unknown]");
+	return false;
+}
+
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 27a14a8a945b..64af3e20610d 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -16,6 +16,7 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 90cedfa30e43..e7588dc91518 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1529,6 +1529,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
+	if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
+		if (dso__build_id_is_kmod(dso, name, PATH_MAX))
+			kmod = true;
+
 	if (syms_ss)
 		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
 	else
-- 
2.5.0