Merge tag 'perf-core-for-mingo-20160415' 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:

- Wire the callchain unwinding "max-stack" now to 'perf script --max-stack',
  allowing to limit the depth of callchains, possibly reducing processing
  time (Arnaldo Carvalho de Melo)

- Ditto for 'perf trace --max-stack' (Arnaldo Carvalho de Melo)

- Introduce a --min-stack filter for 'perf trace', to show syscalls that
  had a userspace callchain leading to it at least min-stack deep (Arnaldo Carvalho de Melo)

- Make 'perf trace' work with multiple threads and the --duration filter,
  i.e. do not print the start of an interrupted syscall followed by ...
  to print interrupts from other threads, as we need to wait the sys_exit
  syscall tracepoint to calculate the duration, duh. (Arnaldo Carvalho de Melo)

  System wide --duration now works as expected:

   [root@jouet ~]# trace --duration 100
     152.393 (145.147 ms): Timer/24358 futex(uaddr: 0x7f5ed98e56cc, op: WAIT_BITSET|PRIV|CLKRT, val: 7055125, utime: 0x7f5ecdbfec30, val3: 4294967295) = -1 ETIMEDOUT Connection timed out
     152.438 (145.040 ms): firefox/24321 poll(ufds: 0x7f5ec388b460, nfds: 6, timeout_msecs: 4294967295) = 1
     358.580 (158.279 ms): Xorg/2025 select(n: 512, inp: 0x83a8e0, tvp: 0x7ffdcbb63610) = 0 Timeout
     358.687 (148.285 ms): gnome-terminal/2711 poll(ufds: 0x55b7e6811ad0, nfds: 15, timeout_msecs: 249) = 1
     370.150 (169.569 ms): gnome-shell/2287 poll(ufds: 0x55e623d65490, nfds: 86, timeout_msecs: 4294967295) = 1

- Now 'perf trace's --max-stack and --min-stack will automatically set
  "--call-graph dwarf", if --call-graph is not present on the command line:

   [root@jouet ~]# perf trace -e nanosleep --max-stack 3 usleep 1
     0.299 ( 0.057 ms): usleep/29658 nanosleep(rqtp: 0x7fff80f3b230) = 0
                                       __nanosleep+0x10 (/usr/lib64/libc-2.22.so)
                                       usleep+0x34 (/usr/lib64/libc-2.22.so)
                                       main+0x1eb (/usr/bin/usleep)
   [root@jouet ~]#

- Bump 'perf trace --mmap-pages' for root when using callchains and not
  specifying --mmap-pages explicitely (Arnaldo Carvalho de Melo)

Build fixes:

- The python binding object had missing symbols, to some refactoring
  to fix that (Arnaldo Carvalho de Melo)

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

1 files changed, 25 insertions, 14 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 838c0bc38105..0e93282b405e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -22,6 +22,7 @@
 #include "util/thread_map.h"
 #include "util/stat.h"
 #include <linux/bitmap.h>
+#include <linux/stringify.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
 
@@ -569,18 +570,23 @@ static void print_sample_bts(struct perf_sample *sample,
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
 		unsigned int print_opts = output[attr->type].print_ip_opts;
+		struct callchain_cursor *cursor = NULL, cursor_callchain;
 
-		if (symbol_conf.use_callchain && sample->callchain) {
-			printf("\n");
-		} else {
-			printf(" ");
+		if (symbol_conf.use_callchain && sample->callchain &&
+		    thread__resolve_callchain(al->thread, &cursor_callchain, evsel,
+					      sample, NULL, NULL, scripting_max_stack) == 0)
+			cursor = &cursor_callchain;
+
+		if (cursor == NULL) {
+			putchar(' ');
 			if (print_opts & EVSEL__PRINT_SRCLINE) {
 				print_srcline_last = true;
 				print_opts &= ~EVSEL__PRINT_SRCLINE;
 			}
-		}
-		perf_evsel__fprintf_sym(evsel, sample, al, 0, print_opts,
-					scripting_max_stack, stdout);
+		} else
+			putchar('\n');
+
+		sample__fprintf_sym(sample, al, 0, print_opts, cursor, stdout);
 	}
 
 	/* print branch_to information */
@@ -783,14 +789,15 @@ static void process_event(struct perf_script *script,
 		printf("%16" PRIu64, sample->weight);
 
 	if (PRINT_FIELD(IP)) {
-		if (!symbol_conf.use_callchain)
-			printf(" ");
-		else
-			printf("\n");
+		struct callchain_cursor *cursor = NULL, cursor_callchain;
+
+		if (symbol_conf.use_callchain &&
+		    thread__resolve_callchain(al->thread, &cursor_callchain, evsel,
+					      sample, NULL, NULL, scripting_max_stack) == 0)
+			cursor = &cursor_callchain;
 
-		perf_evsel__fprintf_sym(evsel, sample, al, 0,
-					output[attr->type].print_ip_opts,
-					scripting_max_stack, stdout);
+		putchar(cursor ? '\n' : ' ');
+		sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout);
 	}
 
 	if (PRINT_FIELD(IREGS))
@@ -2021,6 +2028,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "only consider symbols in these pids"),
 	OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
 		   "only consider symbols in these tids"),
+	OPT_UINTEGER(0, "max-stack", &scripting_max_stack,
+		     "Set the maximum stack depth when parsing the callchain, "
+		     "anything beyond the specified depth will be ignored. "
+		     "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
 	OPT_BOOLEAN('I', "show-info", &show_full_info,
 		    "display extended information from perf.data file"),
 	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,