Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "This tree includes an x86 PMU scheduling fix, but most changes are
  late breaking tooling fixes and updates:

  User visible fixes:

   - Create config.detected into OUTPUT directory, fixing parallel
     builds sharing the same source directory (Aaro Kiskinen)

   - Allow to specify custom linker command, fixing some MIPS64 builds.
     (Aaro Kiskinen)

   - Fix to show proper convergence stats in 'perf bench numa' (Srikar
     Dronamraju)

  User visible changes:

   - Validate syscall list passed via -e argument to 'perf trace'.
     (Arnaldo Carvalho de Melo)

   - Introduce 'perf stat --per-thread' (Jiri Olsa)

   - Check access permission for --kallsyms and --vmlinux (Li Zhang)

   - Move toggling event logic from 'perf top' and into hists browser,
     allowing freeze/unfreeze with event lists with more than one entry
     (Namhyung Kim)

   - Add missing newlines when dumping PERF_RECORD_FINISHED_ROUND and
     showing the Aggregated stats in 'perf report -D' (Adrian Hunter)

  Infrastructure fixes:

   - Add missing break for PERF_RECORD_ITRACE_START, which caused those
     events samples to be parsed as well as PERF_RECORD_LOST_SAMPLES.
     ITRACE_START only appears when Intel PT or BTS are present, so..
     (Jiri Olsa)

   - Call the perf_session destructor when bailing out in the inject,
     kmem, report, kvm and mem tools (Taeung Song)

  Infrastructure changes:

   - Move stuff out of 'perf stat' and into the lib for further use
     (Jiri Olsa)

   - Reference count the cpu_map and thread_map classes (Jiri Olsa)

   - Set evsel->{cpus,threads} from the evlist, if not set, allowing the
     generalization of some 'perf stat' functions that previously were
     accessing private static evlist variable (Jiri Olsa)

   - Delete an unnecessary check before the calling free_event_desc()
     (Markus Elfring)

   - Allow auxtrace data alignment (Adrian Hunter)

   - Allow events with dot (Andi Kleen)

   - Fix failure to 'perf probe' events on arm (He Kuang)

   - Add testing for Makefile.perf (Jiri Olsa)

   - Add test for make install with prefix (Jiri Olsa)

   - Fix single target build dependency check (Jiri Olsa)

   - Access thread_map entries via accessors, prep patch to hold more
     info per entry, for ongoing 'perf stat --per-thread' work (Jiri
     Olsa)

   - Use __weak definition from compiler.h (Sukadev Bhattiprolu)

   - Split perf_pmu__new_alias() (Sukadev Bhattiprolu)"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  perf tools: Allow to specify custom linker command
  perf tools: Create config.detected into OUTPUT directory
  perf mem: Fill in the missing session freeing after an error occurs
  perf kvm: Fill in the missing session freeing after an error occurs
  perf report: Fill in the missing session freeing after an error occurs
  perf kmem: Fill in the missing session freeing after an error occurs
  perf inject: Fill in the missing session freeing after an error occurs
  perf tools: Add missing break for PERF_RECORD_ITRACE_START
  perf/x86: Fix 'active_events' imbalance
  perf symbols: Check access permission when reading symbol files
  perf stat: Introduce --per-thread option
  perf stat: Introduce print_counters function
  perf stat: Using init_stats instead of memset
  perf stat: Rename print_interval to process_interval
  perf stat: Remove perf_evsel__read_cb function
  perf stat: Move perf_stat initialization counter process code
  perf stat: Move zero_per_pkg into counter process code
  perf stat: Separate counters reading and processing
  perf stat: Introduce read_counters function
  perf stat: Introduce perf_evsel__read function
  ...

1 files changed, 117 insertions, 15 deletions

diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f4822bd03709..da7646d767fe 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -8,8 +8,11 @@
 #include <unistd.h>
 #include "strlist.h"
 #include <string.h>
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 #include "thread_map.h"
 #include "util.h"
+#include "debug.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -20,11 +23,26 @@ static int filter(const struct dirent *dir)
 		return 1;
 }
 
+static void thread_map__reset(struct thread_map *map, int start, int nr)
+{
+	size_t size = (nr - start) * sizeof(map->map[0]);
+
+	memset(&map->map[start], 0, size);
+}
+
 static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
 {
-	size_t size = sizeof(*map) + sizeof(pid_t) * nr;
+	size_t size = sizeof(*map) + sizeof(map->map[0]) * nr;
+	int start = map ? map->nr : 0;
+
+	map = realloc(map, size);
+	/*
+	 * We only realloc to add more items, let's reset new items.
+	 */
+	if (map)
+		thread_map__reset(map, start, nr);
 
-	return realloc(map, size);
+	return map;
 }
 
 #define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
@@ -45,8 +63,9 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
-			threads->map[i] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
 		threads->nr = items;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -61,8 +80,9 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0] = tid;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, tid);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -84,6 +104,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		goto out_free_threads;
 
 	threads->nr = 0;
+	atomic_set(&threads->refcnt, 1);
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -123,8 +144,10 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 			threads = tmp;
 		}
 
-		for (i = 0; i < items; i++)
-			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
+		for (i = 0; i < items; i++) {
+			thread_map__set_pid(threads, threads->nr + i,
+					    atoi(namelist[i]->d_name));
+		}
 
 		for (i = 0; i < items; i++)
 			zfree(&namelist[i]);
@@ -201,7 +224,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 		threads = nt;
 
 		for (i = 0; i < items; i++) {
-			threads->map[j++] = atoi(namelist[i]->d_name);
+			thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
 			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
@@ -210,6 +233,8 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
 out:
 	strlist__delete(slist);
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -227,8 +252,9 @@ struct thread_map *thread_map__new_dummy(void)
 	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
-		threads->map[0]	= -1;
-		threads->nr	= 1;
+		thread_map__set_pid(threads, 0, -1);
+		threads->nr = 1;
+		atomic_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -267,10 +293,12 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 			goto out_free_threads;
 
 		threads = nt;
-		threads->map[ntasks - 1] = tid;
-		threads->nr		 = ntasks;
+		thread_map__set_pid(threads, ntasks - 1, tid);
+		threads->nr = ntasks;
 	}
 out:
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -290,9 +318,30 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	return thread_map__new_by_tid_str(tid);
 }
 
-void thread_map__delete(struct thread_map *threads)
+static void thread_map__delete(struct thread_map *threads)
 {
-	free(threads);
+	if (threads) {
+		int i;
+
+		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+			  "thread map refcnt unbalanced\n");
+		for (i = 0; i < threads->nr; i++)
+			free(thread_map__comm(threads, i));
+		free(threads);
+	}
+}
+
+struct thread_map *thread_map__get(struct thread_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void thread_map__put(struct thread_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		thread_map__delete(map);
 }
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
@@ -301,7 +350,60 @@ size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
 	size_t printed = fprintf(fp, "%d thread%s: ",
 				 threads->nr, threads->nr > 1 ? "s" : "");
 	for (i = 0; i < threads->nr; ++i)
-		printed += fprintf(fp, "%s%d", i ? ", " : "", threads->map[i]);
+		printed += fprintf(fp, "%s%d", i ? ", " : "", thread_map__pid(threads, i));
 
 	return printed + fprintf(fp, "\n");
 }
+
+static int get_comm(char **comm, pid_t pid)
+{
+	char *path;
+	size_t size;
+	int err;
+
+	if (asprintf(&path, "%s/%d/comm", procfs__mountpoint(), pid) == -1)
+		return -ENOMEM;
+
+	err = filename__read_str(path, comm, &size);
+	if (!err) {
+		/*
+		 * We're reading 16 bytes, while filename__read_str
+		 * allocates data per BUFSIZ bytes, so we can safely
+		 * mark the end of the string.
+		 */
+		(*comm)[size] = 0;
+		rtrim(*comm);
+	}
+
+	free(path);
+	return err;
+}
+
+static void comm_init(struct thread_map *map, int i)
+{
+	pid_t pid = thread_map__pid(map, i);
+	char *comm = NULL;
+
+	/* dummy pid comm initialization */
+	if (pid == -1) {
+		map->map[i].comm = strdup("dummy");
+		return;
+	}
+
+	/*
+	 * The comm name is like extra bonus ;-),
+	 * so just warn if we fail for any reason.
+	 */
+	if (get_comm(&comm, pid))
+		pr_warning("Couldn't resolve comm name for pid %d\n", pid);
+
+	map->map[i].comm = comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads)
+{
+	int i;
+
+	for (i = 0; i < threads->nr; ++i)
+		comm_init(threads, i);
+}