perf report: Add --tasks option to display monitored tasks

Add --tasks option to display monitored tasks stored in perf.data.
Displaying pid/tid/ppid plus the command string aligned to distinguish
parent and child tasks.

  $ perf record -a
  ...
  $ perf report --tasks
  #     pid     tid    ppid  comm
          0       0      -1 |swapper
          2       2       0 | kthreadd
      14080   14080       2 |  kworker/u17:1
          4       4       2 |  kworker/0:0H
          6       6       2 |  mm_percpu_wq
  ...
          1       1       0 | systemd
      23242   23242       1 |  firefox
      23242   23298   23242 |   Cache2 I/O
      23242   23304   23242 |   GMPThread
  ...
       1195    1195       1 |  login
       1611    1611    1195 |   bash
       1639    1639    1611 |    startx
       1663    1663    1639 |     xinit
       1673    1673    1663 |      xmonad-x86_64-l
      23939   23939    1673 |       xterm
      23941   23941   23939 |        bash
      23963   23963   23941 |         mutt
      24954   24954   23963 |          offlineimap

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180107160356.28203-13-jolsa@kernel.org
[ Make it --tasks, plural, --task works as well, as its unambiguous ]
[ Use machine__find_thread(), not findnew(), as pointed out by Namhyung ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 138 insertions, 2 deletions

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index a7d11ef2fe25..856c3c7e94fa 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -461,6 +461,10 @@ include::itrace.txt[]
         Display overall events statistics without any further processing.
         (like the one at the end of the perf report -D command)
 
+--tasks::
+        Display monitored tasks stored in perf data. Displaying pid/tid/ppid
+        plus the command string aligned to distinguish parent and child tasks.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8e67a8c25ab1..2c7bd85651dc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -15,6 +15,7 @@
 #include "util/color.h"
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <linux/err.h>
 #include "util/symbol.h"
 #include "util/callchain.h"
 #include "util/values.h"
@@ -63,6 +64,7 @@ struct report {
         bool                    inverted_callchain;
         bool                    mem_mode;
         bool                    stats_mode;
+        bool                    tasks_mode;
         bool                    header;
         bool                    header_only;
         bool                    nonany_branch_mode;
@@ -603,6 +605,124 @@ static int stats_print(struct report *rep)
         return 0;
 }
 
+static void tasks_setup(struct report *rep)
+{
+        memset(&rep->tool, 0, sizeof(rep->tool));
+        rep->tool.comm = perf_event__process_comm;
+        rep->tool.exit = perf_event__process_exit;
+        rep->tool.fork = perf_event__process_fork;
+        rep->tool.no_warn = true;
+}
+
+struct task {
+        struct thread           *thread;
+        struct list_head         list;
+        struct list_head         children;
+};
+
+static struct task *tasks_list(struct task *task, struct machine *machine)
+{
+        struct thread *parent_thread, *thread = task->thread;
+        struct task   *parent_task;
+
+        /* Already listed. */
+        if (!list_empty(&task->list))
+                return NULL;
+
+        /* Last one in the chain. */
+        if (thread->ppid == -1)
+                return task;
+
+        parent_thread = machine__find_thread(machine, -1, thread->ppid);
+        if (!parent_thread)
+                return ERR_PTR(-ENOENT);
+
+        parent_task = thread__priv(parent_thread);
+        list_add_tail(&task->list, &parent_task->children);
+        return tasks_list(parent_task, machine);
+}
+
+static void task__print_level(struct task *task, FILE *fp, int level)
+{
+        struct thread *thread = task->thread;
+        struct task *child;
+
+        fprintf(fp, "  %8d %8d %8d |%*s%s\n",
+                thread->pid_, thread->tid, thread->ppid,
+                level, "", thread__comm_str(thread));
+
+        if (!list_empty(&task->children)) {
+                list_for_each_entry(child, &task->children, list)
+                        task__print_level(child, fp, level + 1);
+        }
+}
+
+static int tasks_print(struct report *rep, FILE *fp)
+{
+        struct perf_session *session = rep->session;
+        struct machine      *machine = &session->machines.host;
+        struct task *tasks, *task;
+        unsigned int nr = 0, itask = 0, i;
+        struct rb_node *nd;
+        LIST_HEAD(list);
+
+        /*
+         * No locking needed while accessing machine->threads,
+         * because --tasks is single threaded command.
+         */
+
+        /* Count all the threads. */
+        for (i = 0; i < THREADS__TABLE_SIZE; i++)
+                nr += machine->threads[i].nr;
+
+        tasks = malloc(sizeof(*tasks) * nr);
+        if (!tasks)
+                return -ENOMEM;
+
+        for (i = 0; i < THREADS__TABLE_SIZE; i++) {
+                struct threads *threads = &machine->threads[i];
+
+                for (nd = rb_first(&threads->entries); nd; nd = rb_next(nd)) {
+                        task = tasks + itask++;
+
+                        task->thread = rb_entry(nd, struct thread, rb_node);
+                        INIT_LIST_HEAD(&task->children);
+                        INIT_LIST_HEAD(&task->list);
+                        thread__set_priv(task->thread, task);
+                }
+        }
+
+        /*
+         * Iterate every task down to the unprocessed parent
+         * and link all in task children list. Task with no
+         * parent is added into 'list'.
+         */
+        for (itask = 0; itask < nr; itask++) {
+                task = tasks + itask;
+
+                if (!list_empty(&task->list))
+                        continue;
+
+                task = tasks_list(task, machine);
+                if (IS_ERR(task)) {
+                        pr_err("Error: failed to process tasks\n");
+                        free(tasks);
+                        return PTR_ERR(task);
+                }
+
+                if (task)
+                        list_add_tail(&task->list, &list);
+        }
+
+        fprintf(fp, "# %8s %8s %8s  %s\n", "pid", "tid", "ppid", "comm");
+
+        list_for_each_entry(task, &list, list)
+                task__print_level(task, fp, 0);
+
+        free(tasks);
+        return 0;
+}
+
 static int __cmd_report(struct report *rep)
 {
         int ret;
@@ -637,6 +757,9 @@ static int __cmd_report(struct report *rep)
         if (rep->stats_mode)
                 stats_setup(rep);
 
+        if (rep->tasks_mode)
+                tasks_setup(rep);
+
         ret = perf_session__process_events(session);
         if (ret) {
                 ui__error("failed to process sample\n");
@@ -646,6 +769,9 @@ static int __cmd_report(struct report *rep)
         if (rep->stats_mode)
                 return stats_print(rep);
 
+        if (rep->tasks_mode)
+                return tasks_print(rep, stdout);
+
         report__warn_kptr_restrict(rep);
 
         evlist__for_each_entry(session->evlist, pos)
@@ -803,6 +929,7 @@ int cmd_report(int argc, const char **argv)
         OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                     "dump raw trace in ASCII"),
         OPT_BOOLEAN(0, "stats", &report.stats_mode, "Display event stats"),
+        OPT_BOOLEAN(0, "tasks", &report.tasks_mode, "Display recorded tasks"),
         OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
                    "file", "vmlinux pathname"),
         OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
@@ -1064,8 +1191,12 @@ repeat:
                 report.tool.show_feat_hdr = SHOW_FEAT_HEADER;
         if (report.show_full_info)
                 report.tool.show_feat_hdr = SHOW_FEAT_HEADER_FULL_INFO;
-        if (report.stats_mode)
+        if (report.stats_mode || report.tasks_mode)
                 use_browser = 0;
+        if (report.stats_mode && report.tasks_mode) {
+                pr_err("Error: --tasks and --stats options cannot be used together\n");
+                goto error;
+        }
 
         if (strcmp(input_name, "-") != 0)
                 setup_browser(true);
@@ -1088,7 +1219,8 @@ repeat:
                         ret = 0;
                         goto error;
                 }
-        } else if (use_browser == 0 && !quiet && !report.stats_mode) {
+        } else if (use_browser == 0 && !quiet &&
+                   !report.stats_mode && !report.tasks_mode) {
                 fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
                       stdout);
         }