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:

New features:

- Allow using trace events fields as sort order keys, making 'perf evlist --trace_fields'
  show those, and then the user can select a subset and use like:

    perf top -e sched:sched_switch -s prev_comm,next_comm

  That works as well in 'perf report' when handling files containing
  tracepoints.

  The default when just tracepoint events are found in a perf.data file is to
  format it like ftrace, using the libtraceevent formatters, plugins, etc (Namhyung Kim)

- Add support in 'perf script' to process 'perf stat record' generated files,
  culminating in a python perf script that calculates CPI (Cycles per
  Instruction) (Jiri Olsa)

- Show random perf tool tips in the 'perf report' bottom line (Namhyung Kim)

- perf report now defaults to --group if the perf.data file has grouped events, try it with:

  # perf record -e '{cycles,instructions}' -a sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ]
  # perf report
  # Samples: 1K of event 'anon group { cycles, instructions }'
  # Event count (approx.): 1955219195
  #
  #       Overhead  Command     Shared Object      Symbol

     2.86%   0.22%  swapper     [kernel.kallsyms]  [k] intel_idle
     1.05%   0.33%  firefox     libxul.so          [.] js::SetObjectElement
     1.05%   0.00%  kworker/0:3 [kernel.kallsyms]  [k] gen6_ring_get_seqno
     0.88%   0.17%  chrome      chrome             [.] 0x0000000000ee27ab
     0.65%   0.86%  firefox     libxul.so          [.] js::ValueToId<(js::AllowGC)1>
     0.64%   0.23%  JS Helper   libxul.so          [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay
     0.62%   1.27%  firefox     libxul.so          [.] js::GetIterator
     0.61%   1.74%  firefox     libxul.so          [.] js::NativeSetProperty
     0.61%   0.31%  firefox     libxul.so          [.] js::SetPropertyByDefining

User visible fixes:

- Coect data mmaps so that the DWARF unwinder can handle usecases needing them,
  like softice (Jiri Olsa)

- Decay callchains in fractal mode, fixing up cases where 'perf top -g' would
  show entries with more than 100% (Namhyung Kim)

Infrastructure changes:

- Sync tools/lib with the lib/ in the kernel sources for find_bit.c and
  move bitmap.[ch] from tools/perf/util/ to tools/lib/ (Arnaldo Carvalho de Melo)

- No need to set attr.sample_freq in some 'perf test' entries that only
  want to deal with PERF_RECORD_ meta-events, improve a bit error output
  for CQM test (Arnaldo Carvalho de Melo)

- Fix python binding build, adding some missing object files now required
  due to cpumap using find_bit stuff (Arnaldo Carvalho de Melo)

- tools/build improvemnts (Jiri Olsa)

- Add more files to cscope/ctags databases (Jiri Olsa)

- Do not show 'trace' in 'perf help' if it is not compiled in (Jiri Olsa)

- Make perf_evlist__open() open evsels with their cpus and threads,
  like perf record does, making them consistent (Adrian Hunter)

- Fix pmu snapshot initialization bug (Stephane Eranian)

- Add missing headers in perf's MANIFEST (Wang Nan)

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

1 files changed, 109 insertions, 6 deletions

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index a8e825fca42a..d72fafc1c800 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -41,6 +41,9 @@
 #include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "stat.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
@@ -859,6 +862,104 @@ static void python_process_event(union perf_event *event,
         }
 }
 
+static void get_handler_name(char *str, size_t size,
+                             struct perf_evsel *evsel)
+{
+        char *p = str;
+
+        scnprintf(str, size, "stat__%s", perf_evsel__name(evsel));
+
+        while ((p = strchr(p, ':'))) {
+                *p = '_';
+                p++;
+        }
+}
+
+static void
+process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp,
+             struct perf_counts_values *count)
+{
+        PyObject *handler, *t;
+        static char handler_name[256];
+        int n = 0;
+
+        t = PyTuple_New(MAX_FIELDS);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+        get_handler_name(handler_name, sizeof(handler_name),
+                         counter);
+
+        handler = get_handler(handler_name);
+        if (!handler) {
+                pr_debug("can't find python handler %s\n", handler_name);
+                return;
+        }
+
+        PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
+        PyTuple_SetItem(t, n++, PyInt_FromLong(thread));
+
+        tuple_set_u64(t, n++, tstamp);
+        tuple_set_u64(t, n++, count->val);
+        tuple_set_u64(t, n++, count->ena);
+        tuple_set_u64(t, n++, count->run);
+
+        if (_PyTuple_Resize(&t, n) == -1)
+                Py_FatalError("error resizing Python tuple");
+
+        call_object(handler, t, handler_name);
+
+        Py_DECREF(t);
+}
+
+static void python_process_stat(struct perf_stat_config *config,
+                                struct perf_evsel *counter, u64 tstamp)
+{
+        struct thread_map *threads = counter->threads;
+        struct cpu_map *cpus = counter->cpus;
+        int cpu, thread;
+
+        if (config->aggr_mode == AGGR_GLOBAL) {
+                process_stat(counter, -1, -1, tstamp,
+                             &counter->counts->aggr);
+                return;
+        }
+
+        for (thread = 0; thread < threads->nr; thread++) {
+                for (cpu = 0; cpu < cpus->nr; cpu++) {
+                        process_stat(counter, cpus->map[cpu],
+                                     thread_map__pid(threads, thread), tstamp,
+                                     perf_counts(counter->counts, cpu, thread));
+                }
+        }
+}
+
+static void python_process_stat_interval(u64 tstamp)
+{
+        PyObject *handler, *t;
+        static const char handler_name[] = "stat__interval";
+        int n = 0;
+
+        t = PyTuple_New(MAX_FIELDS);
+        if (!t)
+                Py_FatalError("couldn't create Python tuple");
+
+        handler = get_handler(handler_name);
+        if (!handler) {
+                pr_debug("can't find python handler %s\n", handler_name);
+                return;
+        }
+
+        tuple_set_u64(t, n++, tstamp);
+
+        if (_PyTuple_Resize(&t, n) == -1)
+                Py_FatalError("error resizing Python tuple");
+
+        call_object(handler, t, handler_name);
+
+        Py_DECREF(t);
+}
+
 static int run_start_sub(void)
 {
         main_module = PyImport_AddModule("__main__");
@@ -1201,10 +1302,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 }
 
 struct scripting_ops python_scripting_ops = {
-        .name = "Python",
-        .start_script = python_start_script,
-        .flush_script = python_flush_script,
-        .stop_script = python_stop_script,
-        .process_event = python_process_event,
-        .generate_script = python_generate_script,
+        .name                   = "Python",
+        .start_script           = python_start_script,
+        .flush_script           = python_flush_script,
+        .stop_script            = python_stop_script,
+        .process_event          = python_process_event,
+        .process_stat           = python_process_stat,
+        .process_stat_interval  = python_process_stat_interval,
+        .generate_script        = python_generate_script,
 };