Merge tag 'perf-core-for-mingo-20160411' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements from Arnaldo Carvalho de Melo:

User visible changes:

- Automagically create a 'bpf-output' event, easing the setup of BPF
  C "scripts" that produce output via the perf ring buffer. Now it is
  just a matter of calling any perf tool, such as 'trace', with a C
  source file that references the __bpf_stdout__ output channel and
  that channel will be created and connected to the script:

  # trace -e nanosleep --event test_bpf_stdout.c usleep 1
    0.013 ( 0.013 ms): usleep/2818 nanosleep(rqtp: 0x7ffcead45f40                                        ) ...
    0.013 (         ): __bpf_stdout__:Raise a BPF event!..)
    0.015 (         ): perf_bpf_probe:func_begin:(ffffffff81112460))
    0.261 (         ): __bpf_stdout__:Raise a BPF event!..)
    0.262 (         ): perf_bpf_probe:func_end:(ffffffff81112460 <- ffffffff81003d92))
    0.264 ( 0.264 ms): usleep/2818  ... [continued]: nanosleep()) = 0
  #

  Further work is needed to reduce the number of lines in a perf bpf C source
  file, this being the part where we greatly reduce the command line setup (Wang Nan)

- 'perf trace' now supports callchains, with 'trace --call-graph dwarf' using
  libunwind, just like 'perf top', to ask the kernel for stack dumps for CFI
  processing. This reduces the overhead by asking just for userspace callchains
  and also only for the syscall exit tracepoint (raw_syscalls:sys_exit)
  (Milian Wolff, Arnaldo Carvalho de Melo)

  Try it with, for instance:

     # perf trace --call dwarf ping 127.0.0.1

  An excerpt of a system wide 'perf trace --call dwarf" session is at:

   https://fedorapeople.org/~acme/perf/perf-trace--call-graph-dwarf--all-cpus.txt

  You may need to bump the number of mmap pages, using -m/--mmap-pages,
  but on a Broadwell machine the defaults allowed system wide tracing to
  work without losing that many records, experiment with just some
  syscalls, like:

    # perf trace --call dwarf -e nanosleep,futex

  All the targets available for 'perf record', 'perf top' (--pid, --tid, --cpu,
  etc) should work. Also --duration may be interesting to try.

  To get filenames from in various syscalls pointer args (open, ettc), add this
  to the mix:

  # perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'

  Making this work is next in line:

     # trace --call dwarf --ev sched:sched_switch/call-graph=fp/ usleep 1

  I.e. honouring per-tracepoint callchains in 'perf trace' in addition to
  in raw_syscalls:sys_exit.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 38 insertions, 40 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 59009aa7e2ca..ddd5b79e94c2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -579,8 +579,8 @@ static void print_sample_bts(struct perf_sample *sample,
 				print_opts &= ~PRINT_IP_OPT_SRCLINE;
 			}
 		}
-		perf_evsel__print_ip(evsel, sample, al, print_opts,
-				     scripting_max_stack);
+		perf_evsel__fprintf_sym(evsel, sample, al, 0, print_opts,
+					scripting_max_stack, stdout);
 	}
 
 	/* print branch_to information */
@@ -788,9 +788,9 @@ static void process_event(struct perf_script *script,
 		else
 			printf("\n");
 
-		perf_evsel__print_ip(evsel, sample, al,
-				     output[attr->type].print_ip_opts,
-				     scripting_max_stack);
+		perf_evsel__fprintf_sym(evsel, sample, al, 0,
+					output[attr->type].print_ip_opts,
+					scripting_max_stack, stdout);
 	}
 
 	if (PRINT_FIELD(IREGS))
@@ -1415,21 +1415,19 @@ static int is_directory(const char *base_path, const struct dirent *dent)
 	return S_ISDIR(st.st_mode);
 }
 
-#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\
-	while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&	\
-	       lang_next)						\
-		if ((lang_dirent.d_type == DT_DIR ||			\
-		     (lang_dirent.d_type == DT_UNKNOWN &&		\
-		      is_directory(scripts_path, &lang_dirent))) &&	\
-		    (strcmp(lang_dirent.d_name, ".")) &&		\
-		    (strcmp(lang_dirent.d_name, "..")))
+#define for_each_lang(scripts_path, scripts_dir, lang_dirent)		\
+	while ((lang_dirent = readdir(scripts_dir)) != NULL)		\
+		if ((lang_dirent->d_type == DT_DIR ||			\
+		     (lang_dirent->d_type == DT_UNKNOWN &&		\
+		      is_directory(scripts_path, lang_dirent))) &&	\
+		    (strcmp(lang_dirent->d_name, ".")) &&		\
+		    (strcmp(lang_dirent->d_name, "..")))
 
-#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\
-	while (!readdir_r(lang_dir, &script_dirent, &script_next) &&	\
-	       script_next)						\
-		if (script_dirent.d_type != DT_DIR &&			\
-		    (script_dirent.d_type != DT_UNKNOWN ||		\
-		     !is_directory(lang_path, &script_dirent)))
+#define for_each_script(lang_path, lang_dir, script_dirent)		\
+	while ((script_dirent = readdir(lang_dir)) != NULL)		\
+		if (script_dirent->d_type != DT_DIR &&			\
+		    (script_dirent->d_type != DT_UNKNOWN ||		\
+		     !is_directory(lang_path, script_dirent)))
 
 
 #define RECORD_SUFFIX			"-record"
@@ -1575,7 +1573,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 				  const char *s __maybe_unused,
 				  int unset __maybe_unused)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	char script_path[MAXPATHLEN];
@@ -1590,19 +1588,19 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	if (!scripts_dir)
 		return -1;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			script_root = get_script_root(&script_dirent, REPORT_SUFFIX);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			script_root = get_script_root(script_dirent, REPORT_SUFFIX);
 			if (script_root) {
 				desc = script_desc__findnew(script_root);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				read_script_info(desc, script_path);
 				free(script_root);
 			}
@@ -1690,7 +1688,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
  */
 int find_scripts(char **scripts_array, char **scripts_path_array)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN], lang_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
 	struct perf_session *session;
@@ -1713,9 +1711,9 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		return -1;
 	}
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 #ifdef NO_LIBPERL
 		if (strstr(lang_path, "perl"))
 			continue;
@@ -1729,16 +1727,16 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
+		for_each_script(lang_path, lang_dir, script_dirent) {
 			/* Skip those real time scripts: xxxtop.p[yl] */
-			if (strstr(script_dirent.d_name, "top."))
+			if (strstr(script_dirent->d_name, "top."))
 				continue;
 			sprintf(scripts_path_array[i], "%s/%s", lang_path,
-				script_dirent.d_name);
-			temp = strchr(script_dirent.d_name, '.');
+				script_dirent->d_name);
+			temp = strchr(script_dirent->d_name, '.');
 			snprintf(scripts_array[i],
-				(temp - script_dirent.d_name) + 1,
-				"%s", script_dirent.d_name);
+				(temp - script_dirent->d_name) + 1,
+				"%s", script_dirent->d_name);
 
 			if (check_ev_match(lang_path,
 					scripts_array[i], session))
@@ -1756,7 +1754,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 
 static char *get_script_path(const char *script_root, const char *suffix)
 {
-	struct dirent *script_next, *lang_next, script_dirent, lang_dirent;
+	struct dirent *script_dirent, *lang_dirent;
 	char scripts_path[MAXPATHLEN];
 	char script_path[MAXPATHLEN];
 	DIR *scripts_dir, *lang_dir;
@@ -1769,21 +1767,21 @@ static char *get_script_path(const char *script_root, const char *suffix)
 	if (!scripts_dir)
 		return NULL;
 
-	for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
+	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
 		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent.d_name);
+			 lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
 
-		for_each_script(lang_path, lang_dir, script_dirent, script_next) {
-			__script_root = get_script_root(&script_dirent, suffix);
+		for_each_script(lang_path, lang_dir, script_dirent) {
+			__script_root = get_script_root(script_dirent, suffix);
 			if (__script_root && !strcmp(script_root, __script_root)) {
 				free(__script_root);
 				closedir(lang_dir);
 				closedir(scripts_dir);
 				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent.d_name);
+					 lang_path, script_dirent->d_name);
 				return strdup(script_path);
 			}
 			free(__script_root);