perf inject: Add jitdump mmap injection support

This patch adds a --jit/-j option to perf inject.

This options injects MMAP records into the perf.data file to cover the
jitted code mmaps. It also emits ELF images for each function in the
jidump file.  Those images are created where the jitdump file is.  The
MMAP records point to that location as well.

Typical flow:

  $ perf record -k mono -- java -agentpath:libpjvmti.so java_class
  $ perf inject --jit -i perf.data -o perf.data.jitted
  $ perf report -i perf.data.jitted

Note that jitdump.h support is not limited to Java, it works with any
jitted environment modified to emit the jitdump file format, include
those where code can be jitted multiple times and moved around.

The jitdump.h format is adapted from the Oprofile project.

The genelf.c (ELF binary generation) depends on MD5 hash encoding for
the buildid. To enable this, libssl-dev must be installed. If not, then
genelf.c defaults to using urandom to generate the buildid, which is not
ideal.  The Makefile auto-detects the presence on libssl-dev.

This version mmaps the jitdump file to create a marker MMAP record in
the perf.data file. The marker is used to detect jitdump and cause perf
inject to inject the jitted mmaps and generate ELF images for jitted
functions.

In V8, the following fixes and changes were made among other things:

  -  the jidump header format include a new flags field to be used
     to carry information about the configuration of the runtime agent.
     Contributed by: Adrian Hunter <adrian.hunter@intel.com>

  - Fix mmap pgoff: MMAP event pgoff must be the offset within the ELF file
    at which the code resides.
    Contributed by: Adrian Hunter <adrian.hunter@intel.com>

  - Fix ELF virtual addresses: perf tools expect the ELF virtual addresses of dynamic
    objects to match the file offset.
    Contributed by: Adrian Hunter <adrian.hunter@intel.com>

  - JIT MMAP injection does not obey finished_round semantics. JIT MMAP injection injects all
    MMAP events in one go, so it does not obey finished_round semantics, so drop the
    finished_round events from the output perf.data file.
    Contributed by: Adrian Hunter <adrian.hunter@intel.com>

Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Carl Love <cel@us.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John McCutchan <johnmccutchan@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pawel Moll <pawel.moll@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sonny Rao <sonnyrao@chromium.org>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1448874143-7269-3-git-send-email-eranian@google.com
[ Moved inject.build_ids ordering bits to a separate patch, fixed the NO_LIBELF=1 build ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 95 insertions, 3 deletions

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6567baedd92a..b38445f08c2f 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -17,6 +17,7 @@
 #include "util/build-id.h"
 #include "util/data.h"
 #include "util/auxtrace.h"
+#include "util/jit.h"
 
 #include <subcmd/parse-options.h>
 
@@ -29,6 +30,7 @@ struct perf_inject {
         bool                    sched_stat;
         bool                    have_auxtrace;
         bool                    strip;
+        bool                    jit_mode;
         const char              *input_name;
         struct perf_data_file   output;
         u64                     bytes_written;
@@ -71,6 +73,15 @@ static int perf_event__repipe_oe_synth(struct perf_tool *tool,
         return perf_event__repipe_synth(tool, event);
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
+static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused,
+                               union perf_event *event __maybe_unused,
+                               struct ordered_events *oe __maybe_unused)
+{
+        return 0;
+}
+#endif
+
 static int perf_event__repipe_op2_synth(struct perf_tool *tool,
                                         union perf_event *event,
                                         struct perf_session *session
@@ -234,6 +245,27 @@ static int perf_event__repipe_mmap(struct perf_tool *tool,
         return err;
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
+static int perf_event__jit_repipe_mmap(struct perf_tool *tool,
+                                       union perf_event *event,
+                                       struct perf_sample *sample,
+                                       struct machine *machine)
+{
+        struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+        u64 n = 0;
+
+        /*
+         * if jit marker, then inject jit mmaps and generate ELF images
+         */
+        if (!jit_process(inject->session, &inject->output, machine,
+                         event->mmap.filename, sample->pid, &n)) {
+                inject->bytes_written += n;
+                return 0;
+        }
+        return perf_event__repipe_mmap(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_mmap2(struct perf_tool *tool,
                                    union perf_event *event,
                                    struct perf_sample *sample,
@@ -247,6 +279,27 @@ static int perf_event__repipe_mmap2(struct perf_tool *tool,
         return err;
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
+static int perf_event__jit_repipe_mmap2(struct perf_tool *tool,
+                                        union perf_event *event,
+                                        struct perf_sample *sample,
+                                        struct machine *machine)
+{
+        struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+        u64 n = 0;
+
+        /*
+         * if jit marker, then inject jit mmaps and generate ELF images
+         */
+        if (!jit_process(inject->session, &inject->output, machine,
+                          event->mmap2.filename, sample->pid, &n)) {
+                inject->bytes_written += n;
+                return 0;
+        }
+        return perf_event__repipe_mmap2(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
                                    union perf_event *event,
                                    struct perf_sample *sample,
@@ -664,6 +717,23 @@ static int __cmd_inject(struct perf_inject *inject)
         return ret;
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
+static int
+jit_validate_events(struct perf_session *session)
+{
+        struct perf_evsel *evsel;
+
+        /*
+         * check that all events use CLOCK_MONOTONIC
+         */
+        evlist__for_each(session->evlist, evsel) {
+                if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
+                        return -1;
+        }
+        return 0;
+}
+#endif
+
 int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         struct perf_inject inject = {
@@ -703,7 +773,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
         };
         int ret;
 
-        const struct option options[] = {
+        struct option options[] = {
                 OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
                             "Inject build-ids into the output stream"),
                 OPT_STRING('i', "input", &inject.input_name, "file",
@@ -713,6 +783,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
                             "Merge sched-stat and sched-switch for getting events "
                             "where and how long tasks slept"),
+                OPT_BOOLEAN('j', "jit", &inject.jit_mode, "merge jitdump files into perf.data file"),
                 OPT_INCR('v', "verbose", &verbose,
                          "be more verbose (show build ids, etc)"),
                 OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
@@ -729,7 +800,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 "perf inject [<options>]",
                 NULL
         };
-
+#ifndef HAVE_LIBELF_SUPPORT
+        set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true);
+#endif
         argc = parse_options(argc, argv, options, inject_usage, 0);
 
         /*
@@ -765,7 +838,26 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 inject.tool.ordered_events = true;
                 inject.tool.ordering_requires_timestamps = true;
         }
-
+#ifdef HAVE_LIBELF_SUPPORT
+        if (inject.jit_mode) {
+                /*
+                 * validate event is using the correct clockid
+                 */
+                if (jit_validate_events(inject.session)) {
+                        fprintf(stderr, "error, jitted code must be sampled with perf record -k 1\n");
+                        return -1;
+                }
+                inject.tool.mmap2          = perf_event__jit_repipe_mmap2;
+                inject.tool.mmap           = perf_event__jit_repipe_mmap;
+                inject.tool.ordered_events = true;
+                inject.tool.ordering_requires_timestamps = true;
+                /*
+                 * JIT MMAP injection injects all MMAP events in one go, so it
+                 * does not obey finished_round semantics.
+                 */
+                inject.tool.finished_round = perf_event__drop_oe;
+        }
+#endif
         ret = symbol__init(&inject.session->header.env);
         if (ret < 0)
                 goto out_delete;