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

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  * Add --repeat global option to 'perf bench' to be used in benchmarks
    such as the existing 'futex' one, that was modified to use it instead
    of a local option. (Davidlohr Bueso)

  * Fix fd -> pathname resolution in 'trace', be it using /proc or
    a vfs_getname probe point. (Arnaldo Carvalho de Melo)

  * Add suggestion of how to set perf_event_paranoid sysctl, to help
    non-root users trying tools like 'trace' to get a working environment.
    (Arnaldo Carvalho de Melo)

Fixes:

  * Fix memory leak in the 'sched-messaging' perf bench test. (Davidlohr Bueso)

  * The -o and -n 'perf bench mem' options are mutually exclusive, emit error
    when both are specified. (Davidlohr Bueso)

  * Fix scrollbar refresh row index in the ui browser, problem exposed now
    that headers will be added and will be allowed to be switched on/off.
    (Jiri Olsa)

Cleanups:

  * Remove needless reassignments in 'trace' (Arnaldo Carvalho de Melo)

  * Cache the is_exit syscall test in 'trace) (Arnaldo Carvalho de Melo)

  * No need to reimplement err() in 'perf bench sched-messaging', drop barf().
    (Davidlohr Bueso).

  * Remove ev_name argument from perf_evsel__hists_browse, can be obtained
    from the other parameters. (Jiri Olsa)

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

12 files changed, 67 insertions, 68 deletions

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 4464ad770d51..f6480cbf309b 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -16,6 +16,10 @@ This 'perf bench' command is a general framework for benchmark suites.
 
 COMMON OPTIONS
 --------------
+-r::
+--repeat=::
+Specify amount of times to repeat the run (default 10).
+
 -f::
 --format=::
 Specify format style.
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index eba46709b279..3c4dd44d45cb 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -43,5 +43,6 @@ extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 #define BENCH_FORMAT_UNKNOWN            -1
 
 extern int bench_format;
+extern unsigned int bench_repeat;
 
 #endif
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index a16255876f1d..732403bfd31a 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -29,13 +29,6 @@ static u_int32_t futex1 = 0, futex2 = 0;
  */
 static unsigned int nrequeue = 1;
 
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
 static pthread_t *worker;
 static bool done = 0, silent = 0;
 static pthread_mutex_t thread_lock;
@@ -46,7 +39,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0;
 static const struct option options[] = {
         OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
         OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
-        OPT_UINTEGER('r', "repeat",   &repeat,   "Specify amount of times to repeat the run"),
         OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
         OPT_END()
 };
@@ -146,7 +138,7 @@ int bench_futex_requeue(int argc, const char **argv,
         pthread_cond_init(&thread_parent, NULL);
         pthread_cond_init(&thread_worker, NULL);
 
-        for (j = 0; j < repeat && !done; j++) {
+        for (j = 0; j < bench_repeat && !done; j++) {
                 unsigned int nrequeued = 0;
                 struct timeval start, end, runtime;
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index d096169b161e..50022cbce87e 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -30,15 +30,8 @@ static u_int32_t futex1 = 0;
  */
 static unsigned int nwakes = 1;
 
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
 pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
@@ -47,7 +40,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0;
 static const struct option options[] = {
         OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
         OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
-        OPT_UINTEGER('r', "repeat",  &repeat,   "Specify amount of times to repeat the run"),
         OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
         OPT_END()
 };
@@ -149,7 +141,7 @@ int bench_futex_wake(int argc, const char **argv,
         pthread_cond_init(&thread_parent, NULL);
         pthread_cond_init(&thread_worker, NULL);
 
-        for (j = 0; j < repeat && !done; j++) {
+        for (j = 0; j < bench_repeat && !done; j++) {
                 unsigned int nwoken = 0;
                 struct timeval start, end, runtime;
 
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 5ce71d3b72cf..e622c3e96efc 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -189,6 +189,11 @@ int bench_mem_memcpy(int argc, const char **argv,
         argc = parse_options(argc, argv, options,
                              bench_mem_memcpy_usage, 0);
 
+        if (no_prefault && only_prefault) {
+                fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+                return 1;
+        }
+
         if (use_cycle)
                 init_cycle();
 
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 9af79d2b18e5..2a65468619f0 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -181,6 +181,11 @@ int bench_mem_memset(int argc, const char **argv,
         argc = parse_options(argc, argv, options,
                              bench_mem_memset_usage, 0);
 
+        if (no_prefault && only_prefault) {
+                fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+                return 1;
+        }
+
         if (use_cycle)
                 init_cycle();
 
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index cc1190a0849b..52a56599a543 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -28,6 +28,7 @@
 #include <sys/time.h>
 #include <sys/poll.h>
 #include <limits.h>
+#include <err.h>
 
 #define DATASIZE 100
 
@@ -50,12 +51,6 @@ struct receiver_context {
         int wakefd;
 };
 
-static void barf(const char *msg)
-{
-        fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno));
-        exit(1);
-}
-
 static void fdpair(int fds[2])
 {
         if (use_pipes) {
@@ -66,7 +61,7 @@ static void fdpair(int fds[2])
                         return;
         }
 
-        barf(use_pipes ? "pipe()" : "socketpair()");
+        err(EXIT_FAILURE, use_pipes ? "pipe()" : "socketpair()");
 }
 
 /* Block until we're ready to go */
@@ -77,11 +72,11 @@ static void ready(int ready_out, int wakefd)
 
         /* Tell them we're ready. */
         if (write(ready_out, &dummy, 1) != 1)
-                barf("CLIENT: ready write");
+                err(EXIT_FAILURE, "CLIENT: ready write");
 
         /* Wait for "GO" signal */
         if (poll(&pollfd, 1, -1) != 1)
-                barf("poll");
+                err(EXIT_FAILURE, "poll");
 }
 
 /* Sender sprays loops messages down each file descriptor */
@@ -101,7 +96,7 @@ again:
                         ret = write(ctx->out_fds[j], data + done,
                                     sizeof(data)-done);
                         if (ret < 0)
-                                barf("SENDER: write");
+                                err(EXIT_FAILURE, "SENDER: write");
                         done += ret;
                         if (done < DATASIZE)
                                 goto again;
@@ -131,7 +126,7 @@ static void *receiver(struct receiver_context* ctx)
 again:
                 ret = read(ctx->in_fds[0], data + done, DATASIZE - done);
                 if (ret < 0)
-                        barf("SERVER: read");
+                        err(EXIT_FAILURE, "SERVER: read");
                 done += ret;
                 if (done < DATASIZE)
                         goto again;
@@ -144,14 +139,14 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
 {
         pthread_attr_t attr;
         pthread_t childid;
-        int err;
+        int ret;
 
         if (!thread_mode) {
                 /* process mode */
                 /* Fork the receiver. */
                 switch (fork()) {
                 case -1:
-                        barf("fork()");
+                        err(EXIT_FAILURE, "fork()");
                         break;
                 case 0:
                         (*func) (ctx);
@@ -165,19 +160,17 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
         }
 
         if (pthread_attr_init(&attr) != 0)
-                barf("pthread_attr_init:");
+                err(EXIT_FAILURE, "pthread_attr_init:");
 
 #ifndef __ia64__
         if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0)
-                barf("pthread_attr_setstacksize");
+                err(EXIT_FAILURE, "pthread_attr_setstacksize");
 #endif
 
-        err = pthread_create(&childid, &attr, func, ctx);
-        if (err != 0) {
-                fprintf(stderr, "pthread_create failed: %s (%d)\n",
-                        strerror(err), err);
-                exit(-1);
-        }
+        ret = pthread_create(&childid, &attr, func, ctx);
+        if (ret != 0)
+                err(EXIT_FAILURE, "pthread_create failed");
+
         return childid;
 }
 
@@ -207,14 +200,14 @@ static unsigned int group(pthread_t *pth,
                         + num_fds * sizeof(int));
 
         if (!snd_ctx)
-                barf("malloc()");
+                err(EXIT_FAILURE, "malloc()");
 
         for (i = 0; i < num_fds; i++) {
                 int fds[2];
                 struct receiver_context *ctx = malloc(sizeof(*ctx));
 
                 if (!ctx)
-                        barf("malloc()");
+                        err(EXIT_FAILURE, "malloc()");
 
 
                 /* Create the pipe between client and server */
@@ -281,7 +274,7 @@ int bench_sched_messaging(int argc, const char **argv,
 
         pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t));
         if (!pth_tab)
-                barf("main:malloc()");
+                err(EXIT_FAILURE, "main:malloc()");
 
         fdpair(readyfds);
         fdpair(wakefds);
@@ -294,13 +287,13 @@ int bench_sched_messaging(int argc, const char **argv,
         /* Wait for everyone to be ready */
         for (i = 0; i < total_children; i++)
                 if (read(readyfds[0], &dummy, 1) != 1)
-                        barf("Reading for readyfds");
+                        err(EXIT_FAILURE, "Reading for readyfds");
 
         gettimeofday(&start, NULL);
 
         /* Kick them off */
         if (write(wakefds[1], &dummy, 1) != 1)
-                barf("Writing to start them");
+                err(EXIT_FAILURE, "Writing to start them");
 
         /* Reap them all */
         for (i = 0; i < total_children; i++)
@@ -332,5 +325,7 @@ int bench_sched_messaging(int argc, const char **argv,
                 break;
         }
 
+        free(pth_tab);
+
         return 0;
 }
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 1e6e77710545..b9a56fa83330 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -104,9 +104,11 @@ static const char *bench_format_str;
 
 /* Output/formatting style, exported to benchmark modules: */
 int bench_format = BENCH_FORMAT_DEFAULT;
+unsigned int bench_repeat = 10; /* default number of times to repeat the run */
 
 static const struct option bench_options[] = {
         OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
+        OPT_UINTEGER('r', "repeat",  &bench_repeat,   "Specify amount of times to repeat the run"),
         OPT_END()
 };
 
@@ -226,6 +228,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
                 goto end;
         }
 
+        if (bench_repeat == 0) {
+                printf("Invalid repeat option: Must specify a positive value\n");
+                goto end;
+        }
+
         if (argc < 1) {
                 print_usage();
                 goto end;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f954c26de231..5549cee61680 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1108,6 +1108,7 @@ struct syscall {
         struct event_format *tp_format;
         const char          *name;
         bool                filtered;
+        bool                is_exit;
         struct syscall_fmt  *fmt;
         size_t              (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
         void                **arg_parm;
@@ -1276,11 +1277,11 @@ static const char *thread__fd_path(struct thread *thread, int fd,
         if (fd < 0)
                 return NULL;
 
-        if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
+        if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) {
                 if (!trace->live)
                         return NULL;
                 ++trace->stats.proc_getname;
-                if (thread__read_fd_path(thread, fd)) {
+                if (thread__read_fd_path(thread, fd))
                         return NULL;
         }
 
@@ -1473,6 +1474,8 @@ static int trace__read_syscall_info(struct trace *trace, int id)
         if (sc->tp_format == NULL)
                 return -1;
 
+        sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
+
         return syscall__set_arg_fmts(sc);
 }
 
@@ -1629,7 +1632,6 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
                 return -1;
 
         args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-        ttrace = thread->priv;
 
         if (ttrace->entry_str == NULL) {
                 ttrace->entry_str = malloc(1024);
@@ -1644,7 +1646,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
         printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
                                            args, trace, thread);
 
-        if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
+        if (sc->is_exit) {
                 if (!trace->duration_filter && !trace->summary_only) {
                         trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
                         fprintf(trace->output, "%-70s\n", ttrace->entry_str);
@@ -1687,8 +1689,6 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
                 ++trace->stats.vfs_getname;
         }
 
-        ttrace = thread->priv;
-
         ttrace->exit_time = sample->time;
 
         if (ttrace->entry_time) {
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 3ccf6e14f89b..9d2294efc00c 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -279,7 +279,7 @@ static void ui_browser__scrollbar_set(struct ui_browser *browser)
 {
         int height = browser->height, h = 0, pct = 0,
             col = browser->width,
-            row = browser->y - 1;
+            row = 0;
 
         if (browser->nr_entries > 1) {
                 pct = ((browser->index * (browser->height - 1)) /
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 04a229aa5c0f..2185091c5227 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -33,8 +33,7 @@ struct hist_browser {
 
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
-                                const char *ev_name);
+static int hists__browser_title(struct hists *hists, char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -346,7 +345,7 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
                 "Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
+static int hist_browser__run(struct hist_browser *browser,
                              struct hist_browser_timer *hbt)
 {
         int key;
@@ -357,7 +356,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
         browser->b.nr_entries = hist_browser__nr_entries(browser);
 
         hist_browser__refresh_dimensions(browser);
-        hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+        hists__browser_title(browser->hists, title, sizeof(title));
 
         if (ui_browser__show(&browser->b, title,
                              "Press '?' for help on key bindings") < 0)
@@ -384,7 +383,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
                                 ui_browser__warn_lost_events(&browser->b);
                         }
 
-                        hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+                        hists__browser_title(browser->hists, title, sizeof(title));
                         ui_browser__show_title(&browser->b, title);
                         continue;
                 }
@@ -1213,8 +1212,7 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
         return browser->he_selection->thread;
 }
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
-                                const char *ev_name)
+static int hists__browser_title(struct hists *hists, char *bf, size_t size)
 {
         char unit;
         int printed;
@@ -1223,6 +1221,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
         unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
         u64 nr_events = hists->stats.total_period;
         struct perf_evsel *evsel = hists_to_evsel(hists);
+        const char *ev_name = perf_evsel__name(evsel);
         char buf[512];
         size_t buflen = sizeof(buf);
 
@@ -1390,7 +1389,7 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
-                                    const char *helpline, const char *ev_name,
+                                    const char *helpline,
                                     bool left_exits,
                                     struct hist_browser_timer *hbt,
                                     float min_pcnt,
@@ -1465,7 +1464,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
                 nr_options = 0;
 
-                key = hist_browser__run(browser, ev_name, hbt);
+                key = hist_browser__run(browser, hbt);
 
                 if (browser->he_selection != NULL) {
                         thread = hist_browser__selected_thread(browser);
@@ -1843,7 +1842,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 {
         struct perf_evlist *evlist = menu->b.priv;
         struct perf_evsel *pos;
-        const char *ev_name, *title = "Available samples";
+        const char *title = "Available samples";
         int delay_secs = hbt ? hbt->refresh : 0;
         int key;
 
@@ -1876,9 +1875,8 @@ browse_hists:
                          */
                         if (hbt)
                                 hbt->timer(hbt->arg);
-                        ev_name = perf_evsel__name(pos);
                         key = perf_evsel__hists_browse(pos, nr_events, help,
-                                                       ev_name, true, hbt,
+                                                       true, hbt,
                                                        menu->min_pcnt,
                                                        menu->env);
                         ui_browser__show_title(&menu->b, title);
@@ -1982,10 +1980,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 single_entry:
         if (nr_entries == 1) {
                 struct perf_evsel *first = perf_evlist__first(evlist);
-                const char *ev_name = perf_evsel__name(first);
 
                 return perf_evsel__hists_browse(first, nr_entries, help,
-                                                ev_name, false, hbt, min_pcnt,
+                                                false, hbt, min_pcnt,
                                                 env);
         }
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 59ef2802fcf6..c51223ac25f4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1214,10 +1214,11 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
                                              "For your workloads it needs to be <= 1\nHint:\t");
                 }
                 printed += scnprintf(buf + printed, size - printed,
-                                     "For system wide tracing it needs to be set to -1");
+                                     "For system wide tracing it needs to be set to -1.\n");
 
                 printed += scnprintf(buf + printed, size - printed,
-                                    ".\nHint:\tThe current value is %d.", value);
+                                    "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
+                                    "Hint:\tThe current value is %d.", value);
                 break;
         default:
                 scnprintf(buf, size, "%s", emsg);