[PATCH V4 00/15] perf tools: some fixes and tweaks

[PATCH V4 00/15] perf tools: some fixes and tweaks

[Adrian Hunter]

Hi

Here are some fixes and tweaks to perf tools (version 4).

I have added kernel support for matching sample types via
PERF_SAMPLE_IDENTIFIER.  perf tools support for that required
first fixing some other things.

Changes in V4:
	perf tools: fix parse_events_terms() freeing local variable on error path
		Dropped - covered by David Ahern
	perf tools: struct thread has a tid not a pid
		Added ack by David Ahern
	perf tools: add pid to struct thread
		Remove unused function
	perf tools: fix missing increment in sample parsing
		New patch
	perf tools: tidy up sample parsing overflow checking
		New patch
	perf tools: remove unnecessary callchain validation
		New patch
	perf tools: remove references to struct ip_event
		New patch
	perf tools: move struct ip_event
		New patch
	perf: make events stream always parsable
		New patch
	perf tools: add support for PERF_SAMPLE_IDENTFIER
		New patch

Changes in V3:
	perf tools: add pid to struct thread
		Split into 2 patches
	perf tools: fix ppid in thread__fork()
		Dropped for now

Changes in V2:
	perf tools: fix missing tool parameter
		Fixed one extra occurrence
	perf tools: fix parse_events_terms() freeing local variable on error path
		Made "freeing" code into a new function
	perf tools: validate perf event header size
		Corrected byte-swapping
	perf tools: allow non-matching sample types
		Added comments
		Fixed id_pos calculation
		id_pos/is_pos updated whenever sample_type changes
		Removed perf_evlist__sample_type()
		Added __perf_evlist__combined_sample_type()
		Added perf_evlist__combined_sample_type()
		Added perf_evlist__make_sample_types_compatible()
	Added ack's to patches acked by Jiri Olsa


Adrian Hunter (21):
      perf tools: remove unused parameter
      perf tools: fix missing tool parameter
      perf tools: fix missing 'finished_round'
      perf tools: fix parse_events_terms() segfault on error path
      perf tools: fix new_term() missing free on error path
      perf tools: add const specifier to perf_pmu__find name parameter
      perf tools: tidy duplicated munmap code
      perf tools: validate perf event header size
      perf tools: add debug prints
      perf tools: fix symbol_conf.nr_events
      perf tools: allow non-matching sample types
      perf tools: struct thread has a tid not a pid
      perf tools: add pid to struct thread
      perf tools: change "machine" functions to set thread pid
      perf tools: fix missing increment in sample parsing
      perf tools: tidy up sample parsing overflow checking
      perf tools: remove unnecessary callchain validation
      perf tools: remove references to struct ip_event
      perf tools: move struct ip_event
      perf: make events stream always parsable
      perf tools: add support for PERF_SAMPLE_IDENTFIER

 include/uapi/linux/perf_event.h |   3 +-
 kernel/events/core.c            |  11 +-
 tools/perf/builtin-inject.c     |  44 ++++---
 tools/perf/builtin-kmem.c       |   4 +-
 tools/perf/builtin-mem.c        |   2 +-
 tools/perf/builtin-report.c     |   2 +-
 tools/perf/builtin-sched.c      |  12 +-
 tools/perf/builtin-script.c     |   2 +-
 tools/perf/builtin-top.c        |  10 +-
 tools/perf/builtin-trace.c      |   4 +-
 tools/perf/tests/hists_link.c   |  27 ++++-
 tools/perf/tests/mmap-basic.c   |   2 +-
 tools/perf/ui/browsers/hists.c  |   6 +-
 tools/perf/util/build-id.c      |   6 +-
 tools/perf/util/callchain.c     |   8 --
 tools/perf/util/callchain.h     |   5 -
 tools/perf/util/event.c         |   6 +-
 tools/perf/util/event.h         |  30 +++--
 tools/perf/util/evlist.c        | 251 +++++++++++++++++++++++++++++++++++----
 tools/perf/util/evlist.h        |   9 +-
 tools/perf/util/evsel.c         | 256 +++++++++++++++++++++++++++++++++-------
 tools/perf/util/evsel.h         |  13 +-
 tools/perf/util/header.c        |   8 +-
 tools/perf/util/header.h        |   6 +-
 tools/perf/util/machine.c       |  47 +++++---
 tools/perf/util/machine.h       |   6 +-
 tools/perf/util/parse-events.c  |   4 +-
 tools/perf/util/pmu.c           |  14 +--
 tools/perf/util/pmu.h           |   2 +-
 tools/perf/util/session.c       |  58 ++++-----
 tools/perf/util/sort.c          |   6 +-
 tools/perf/util/thread.c        |  11 +-
 tools/perf/util/thread.h        |   5 +-
 tools/perf/util/tool.h          |   9 +-
 34 files changed, 658 insertions(+), 231 deletions(-)


Regards
Adrian

[PATCH V4 01/21] perf tools: remove unused parameter

[Adrian Hunter]

'machine' is unused in 'perf_event__repipe_synth()' and some
callers pass NULL anyway.  So remove it.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/builtin-inject.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 84ad6ab..f299ddf 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -38,8 +38,7 @@ struct event_entry {
 };
 
 static int perf_event__repipe_synth(struct perf_tool *tool,
-				    union perf_event *event,
-				    struct machine *machine __maybe_unused)
+				    union perf_event *event)
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	uint32_t size;
@@ -65,20 +64,20 @@ static int perf_event__repipe_op2_synth(struct perf_tool *tool,
 					struct perf_session *session
 					__maybe_unused)
 {
-	return perf_event__repipe_synth(tool, event, NULL);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
 					       union perf_event *event)
 {
-	return perf_event__repipe_synth(tool, event, NULL);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_tracing_data_synth(union perf_event *event,
 						 struct perf_session *session
 						 __maybe_unused)
 {
-	return perf_event__repipe_synth(NULL, event, NULL);
+	return perf_event__repipe_synth(NULL, event);
 }
 
 static int perf_event__repipe_attr(union perf_event *event,
@@ -89,15 +88,15 @@ static int perf_event__repipe_attr(union perf_event *event,
 	if (ret)
 		return ret;
 
-	return perf_event__repipe_synth(NULL, event, NULL);
+	return perf_event__repipe_synth(NULL, event);
 }
 
 static int perf_event__repipe(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
-			      struct machine *machine)
+			      struct machine *machine __maybe_unused)
 {
-	return perf_event__repipe_synth(tool, event, machine);
+	return perf_event__repipe_synth(tool, event);
 }
 
 typedef int (*inject_handler)(struct perf_tool *tool,
@@ -119,7 +118,7 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
 
 	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 
-	return perf_event__repipe_synth(tool, event, machine);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_mmap(struct perf_tool *tool,
@@ -153,7 +152,7 @@ static int perf_event__repipe_tracing_data(union perf_event *event,
 {
 	int err;
 
-	perf_event__repipe_synth(NULL, event, NULL);
+	perf_event__repipe_synth(NULL, event);
 	err = perf_event__process_tracing_data(event, session);
 
 	return err;
-- 
1.7.11.7

[PATCH V4 02/21] perf tools: fix missing tool parameter

[Adrian Hunter]

perf inject expects to get a reference to 'struct perf_inject'
from its 'tool' member.  For that to work, 'tool' needs to be
a parameter of all tool callbacks.  Make it so.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/builtin-inject.c | 26 +++++++++++---------------
 tools/perf/util/header.c    |  6 ++++--
 tools/perf/util/header.h    |  6 ++++--
 tools/perf/util/session.c   | 11 +++++++----
 tools/perf/util/tool.h      |  9 ++++-----
 5 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index f299ddf..c943513 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -73,22 +73,17 @@ static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event);
 }
 
-static int perf_event__repipe_tracing_data_synth(union perf_event *event,
-						 struct perf_session *session
-						 __maybe_unused)
-{
-	return perf_event__repipe_synth(NULL, event);
-}
-
-static int perf_event__repipe_attr(union perf_event *event,
-				   struct perf_evlist **pevlist __maybe_unused)
+static int perf_event__repipe_attr(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_evlist **pevlist)
 {
 	int ret;
-	ret = perf_event__process_attr(event, pevlist);
+
+	ret = perf_event__process_attr(tool, event, pevlist);
 	if (ret)
 		return ret;
 
-	return perf_event__repipe_synth(NULL, event);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe(struct perf_tool *tool,
@@ -147,13 +142,14 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
 	return err;
 }
 
-static int perf_event__repipe_tracing_data(union perf_event *event,
+static int perf_event__repipe_tracing_data(struct perf_tool *tool,
+					   union perf_event *event,
 					   struct perf_session *session)
 {
 	int err;
 
-	perf_event__repipe_synth(NULL, event);
-	err = perf_event__process_tracing_data(event, session);
+	perf_event__repipe_synth(tool, event);
+	err = perf_event__process_tracing_data(tool, event, session);
 
 	return err;
 }
@@ -407,7 +403,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.unthrottle	= perf_event__repipe,
 			.attr		= perf_event__repipe_attr,
 			.event_type	= perf_event__repipe_event_type_synth,
-			.tracing_data	= perf_event__repipe_tracing_data_synth,
+			.tracing_data	= perf_event__repipe_op2_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 93dd315..855f056 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2922,7 +2922,8 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_attr(union perf_event *event,
+int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
 			     struct perf_evlist **pevlist)
 {
 	u32 i, ids, n_ids;
@@ -3063,7 +3064,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	return aligned_size;
 }
 
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
 				     struct perf_session *session)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 16a3e83..2d1ca7d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -130,7 +130,8 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 int perf_event__synthesize_attrs(struct perf_tool *tool,
 				 struct perf_session *session,
 				 perf_event__handler_t process);
-int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist);
+int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
+			     struct perf_evlist **pevlist);
 
 int perf_event__synthesize_event_type(struct perf_tool *tool,
 				      u64 event_id, char *name,
@@ -145,7 +146,8 @@ int perf_event__process_event_type(struct perf_tool *tool,
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
 					perf_event__handler_t process);
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool,
+				     union perf_event *event,
 				     struct perf_session *session);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ad47fb9..6b71b88 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -193,7 +193,9 @@ void perf_session__delete(struct perf_session *self)
 	vdso__exit();
 }
 
-static int process_event_synth_tracing_data_stub(union perf_event *event
+static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+						 __maybe_unused,
+						 union perf_event *event
 						 __maybe_unused,
 						 struct perf_session *session
 						__maybe_unused)
@@ -202,7 +204,8 @@ static int process_event_synth_tracing_data_stub(union perf_event *event
 	return 0;
 }
 
-static int process_event_synth_attr_stub(union perf_event *event __maybe_unused,
+static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
+					 union perf_event *event __maybe_unused,
 					 struct perf_evlist **pevlist
 					 __maybe_unused)
 {
@@ -921,7 +924,7 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	/* These events are processed right away */
 	switch (event->header.type) {
 	case PERF_RECORD_HEADER_ATTR:
-		err = tool->attr(event, &session->evlist);
+		err = tool->attr(tool, event, &session->evlist);
 		if (err == 0)
 			perf_session__set_id_hdr_size(session);
 		return err;
@@ -930,7 +933,7 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(session->fd, file_offset, SEEK_SET);
-		return tool->tracing_data(event, session);
+		return tool->tracing_data(tool, event, session);
 	case PERF_RECORD_HEADER_BUILD_ID:
 		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index b0e1aad..88f8cbd 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -18,12 +18,11 @@ typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event,
 typedef int (*event_op)(struct perf_tool *tool, union perf_event *event,
 			struct perf_sample *sample, struct machine *machine);
 
-typedef int (*event_attr_op)(union perf_event *event,
+typedef int (*event_attr_op)(struct perf_tool *tool,
+			     union perf_event *event,
 			     struct perf_evlist **pevlist);
-typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event);
 
-typedef int (*event_synth_op)(union perf_event *event,
-			      struct perf_session *session);
+typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event);
 
 typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
 			 struct perf_session *session);
@@ -39,7 +38,7 @@ struct perf_tool {
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
-	event_synth_op	tracing_data;
+	event_op2	tracing_data;
 	event_simple_op	event_type;
 	event_op2	finished_round,
 			build_id;
-- 
1.7.11.7

[PATCH V4 03/21] perf tools: fix missing 'finished_round'

[Adrian Hunter]

By default, perf inject should "repipe" all events
including 'finished_round'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/builtin-inject.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c943513..ad1296c 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -404,6 +404,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		= perf_event__repipe_attr,
 			.event_type	= perf_event__repipe_event_type_synth,
 			.tracing_data	= perf_event__repipe_op2_synth,
+			.finished_round	= perf_event__repipe_op2_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",
-- 
1.7.11.7

[PATCH V4 04/21] perf tools: fix parse_events_terms() segfault on error path

[Adrian Hunter]

On the error path, 'data.terms' may not have been
initialised.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/parse-events.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1ae166c..8fcd872 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -883,7 +883,8 @@ int parse_events_terms(struct list_head *terms, const char *str)
 		return 0;
 	}
 
-	parse_events__free_terms(data.terms);
+	if (data.terms)
+		parse_events__free_terms(data.terms);
 	return ret;
 }
 
-- 
1.7.11.7

[PATCH V4 05/21] perf tools: fix new_term() missing free on error path

[Adrian Hunter]

On the error path, newly allocated 'term' must be freed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/parse-events.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 8fcd872..ef72e98 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1207,6 +1207,7 @@ static int new_term(struct parse_events_term **_term, int type_val,
 		term->val.str = str;
 		break;
 	default:
+		free(term);
 		return -EINVAL;
 	}
 
-- 
1.7.11.7

[PATCH V4 06/21] perf tools: add const specifier to perf_pmu__find name parameter

[Adrian Hunter]

The name parameter is constant, declare it so.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/pmu.c | 14 +++++++-------
 tools/perf/util/pmu.h |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 4c6f9c4..1d1862d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -73,7 +73,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head)
  * located at:
  * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
  */
-static int pmu_format(char *name, struct list_head *format)
+static int pmu_format(const char *name, struct list_head *format)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -162,7 +162,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
  * Reading the pmu event aliases definition, which should be located at:
  * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
  */
-static int pmu_aliases(char *name, struct list_head *head)
+static int pmu_aliases(const char *name, struct list_head *head)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -208,7 +208,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
  * located at:
  * /sys/bus/event_source/devices/<dev>/type as sysfs attribute.
  */
-static int pmu_type(char *name, __u32 *type)
+static int pmu_type(const char *name, __u32 *type)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -266,7 +266,7 @@ static void pmu_read_sysfs(void)
 	closedir(dir);
 }
 
-static struct cpu_map *pmu_cpumask(char *name)
+static struct cpu_map *pmu_cpumask(const char *name)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -293,7 +293,7 @@ static struct cpu_map *pmu_cpumask(char *name)
 	return cpus;
 }
 
-static struct perf_pmu *pmu_lookup(char *name)
+static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
 	LIST_HEAD(format);
@@ -330,7 +330,7 @@ static struct perf_pmu *pmu_lookup(char *name)
 	return pmu;
 }
 
-static struct perf_pmu *pmu_find(char *name)
+static struct perf_pmu *pmu_find(const char *name)
 {
 	struct perf_pmu *pmu;
 
@@ -356,7 +356,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
 	return NULL;
 }
 
-struct perf_pmu *perf_pmu__find(char *name)
+struct perf_pmu *perf_pmu__find(const char *name)
 {
 	struct perf_pmu *pmu;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 32fe55b..d17b565 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -21,7 +21,7 @@ struct perf_pmu {
 	struct list_head list;
 };
 
-struct perf_pmu *perf_pmu__find(char *name);
+struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,
-- 
1.7.11.7

[PATCH V4 07/21] perf tools: tidy duplicated munmap code

[Adrian Hunter]

The same lines of code are used in three places.
Make it a new function '__perf_evlist__munmap()'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/evlist.c | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4a901be..160036e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -403,16 +403,20 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	return event;
 }
 
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+{
+	if (evlist->mmap[idx].base != NULL) {
+		munmap(evlist->mmap[idx].base, evlist->mmap_len);
+		evlist->mmap[idx].base = NULL;
+	}
+}
+
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
 	int i;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
-		if (evlist->mmap[i].base != NULL) {
-			munmap(evlist->mmap[i].base, evlist->mmap_len);
-			evlist->mmap[i].base = NULL;
-		}
-	}
+	for (i = 0; i < evlist->nr_mmaps; i++)
+		__perf_evlist__munmap(evlist, i);
 
 	free(evlist->mmap);
 	evlist->mmap = NULL;
@@ -477,12 +481,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
-		}
-	}
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		__perf_evlist__munmap(evlist, cpu);
 	return -1;
 }
 
@@ -517,12 +517,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < nr_threads; thread++) {
-		if (evlist->mmap[thread].base != NULL) {
-			munmap(evlist->mmap[thread].base, evlist->mmap_len);
-			evlist->mmap[thread].base = NULL;
-		}
-	}
+	for (thread = 0; thread < nr_threads; thread++)
+		__perf_evlist__munmap(evlist, thread);
 	return -1;
 }
 
-- 
1.7.11.7

[PATCH V4 08/21] perf tools: validate perf event header size

[Adrian Hunter]

'size' includes the header so must be at least
'sizeof(struct perf_event_header)'.  Error out
immediately if that is not the case.  Also
don't byte-swap the header until it is actually
"fetched" from the mmap region.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/session.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6b71b88..951a1cf 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1094,8 +1094,10 @@ more:
 		perf_event_header__bswap(&event->header);
 
 	size = event->header.size;
-	if (size == 0)
-		size = 8;
+	if (size < sizeof(struct perf_event_header)) {
+		pr_err("bad event header size\n");
+		goto out_err;
+	}
 
 	if (size > cur_size) {
 		void *new = realloc(buf, size);
@@ -1164,8 +1166,12 @@ fetch_mmaped_event(struct perf_session *session,
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (head + event->header.size > mmap_size)
+	if (head + event->header.size > mmap_size) {
+		/* We're not fetching the event so swap back again */
+		if (session->header.needs_swap)
+			perf_event_header__bswap(&event->header);
 		return NULL;
+	}
 
 	return event;
 }
@@ -1245,7 +1251,7 @@ more:
 
 	size = event->header.size;
 
-	if (size == 0 ||
+	if (size < sizeof(struct perf_event_header) ||
 	    perf_session__process_event(session, event, tool, file_pos) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       file_offset + head, event->header.size,
-- 
1.7.11.7

[PATCH V4 09/21] perf tools: add debug prints

[Adrian Hunter]

It is useful to see the arguments to perf_event_open
and whether the perf events ring buffer was mmapped
per-cpu or per-thread.  That information will now be
displayed when verbose is 2 i.e option -vv

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
---
 tools/perf/util/evlist.c |  3 +++
 tools/perf/util/evsel.c  | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 160036e..dfc267b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -14,6 +14,7 @@
 #include "target.h"
 #include "evlist.h"
 #include "evsel.h"
+#include "debug.h"
 #include <unistd.h>
 
 #include "parse-events.h"
@@ -454,6 +455,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 	int nr_threads = thread_map__nr(evlist->threads);
 
+	pr_debug2("perf event ring buffer mmapped per cpu\n");
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 
@@ -492,6 +494,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	int thread;
 	int nr_threads = thread_map__nr(evlist->threads);
 
+	pr_debug2("perf event ring buffer mmapped per thread\n");
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dea0684..8978213 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -21,6 +21,7 @@
 #include "thread_map.h"
 #include "target.h"
 #include "perf_regs.h"
+#include "debug.h"
 
 static struct {
 	bool sample_id_all;
@@ -817,6 +818,54 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
 	return fd;
 }
 
+static void show_attr(struct perf_event_attr *attr)
+{
+	pr_debug2("------------------------------------------------------------\n");
+	pr_debug2("perf_event_attr:\n");
+	pr_debug2("  type                %u\n", attr->type);
+	pr_debug2("  size                %u\n", attr->size);
+	pr_debug2("  config              %#"PRIx64"\n", (uint64_t)attr->config);
+	pr_debug2("  sample_period       %"PRIu64"\n", (uint64_t)attr->sample_period);
+	pr_debug2("  sample_freq         %"PRIu64"\n", (uint64_t)attr->sample_freq);
+	pr_debug2("  sample_type         %#"PRIx64"\n", (uint64_t)attr->sample_type);
+	pr_debug2("  read_format         %#"PRIx64"\n", (uint64_t)attr->read_format);
+
+	pr_debug2("  disabled            %u    ", attr->disabled);
+	pr_debug2("inherit             %u\n", attr->inherit);
+	pr_debug2("  pinned              %u    ", attr->pinned);
+	pr_debug2("exclusive           %u\n", attr->exclusive);
+	pr_debug2("  exclude_user        %u    ", attr->exclude_user);
+	pr_debug2("exclude_kernel      %u\n", attr->exclude_kernel);
+	pr_debug2("  exclude_hv          %u    ", attr->exclude_hv);
+	pr_debug2("exclude_idle        %u\n", attr->exclude_idle);
+	pr_debug2("  mmap                %u    ", attr->mmap);
+	pr_debug2("comm                %u\n", attr->comm);
+	pr_debug2("  freq                %u    ", attr->freq);
+	pr_debug2("inherit_stat        %u\n", attr->inherit_stat);
+	pr_debug2("  enable_on_exec      %u    ", attr->enable_on_exec);
+	pr_debug2("task                %u\n", attr->task);
+	pr_debug2("  watermark           %u    ", attr->watermark);
+	pr_debug2("precise_ip          %u\n", attr->precise_ip);
+	pr_debug2("  mmap_data           %u    ", attr->mmap_data);
+	pr_debug2("sample_id_all       %u\n", attr->sample_id_all);
+	pr_debug2("  exclude_host        %u    ", attr->exclude_host);
+	pr_debug2("exclude_guest       %u\n", attr->exclude_guest);
+	pr_debug2("  excl.callchain.kern %u    ", attr->exclude_callchain_kernel);
+	pr_debug2("excl.callchain.user %u\n", attr->exclude_callchain_user);
+
+	pr_debug2("  wakeup_events       %u\n", attr->wakeup_events);
+	pr_debug2("  wakeup_watermark    %u\n", attr->wakeup_watermark);
+	pr_debug2("  bp_type             %#x\n", attr->bp_type);
+	pr_debug2("  bp_addr             %#"PRIx64"\n", (uint64_t)attr->bp_addr);
+	pr_debug2("  config1             %#"PRIx64"\n", (uint64_t)attr->config1);
+	pr_debug2("  bp_len              %"PRIu64"\n", (uint64_t)attr->bp_len);
+	pr_debug2("  config2             %#"PRIx64"\n", (uint64_t)attr->config2);
+	pr_debug2("  branch_sample_type  %#"PRIx64"\n", (uint64_t)attr->branch_sample_type);
+	pr_debug2("  sample_regs_user    %#"PRIx64"\n", (uint64_t)attr->sample_regs_user);
+	pr_debug2("  sample_stack_user   %u\n", attr->sample_stack_user);
+	pr_debug2("------------------------------------------------------------\n");
+}
+
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
@@ -840,6 +889,7 @@ retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
 
+	show_attr(&evsel->attr);
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
 		for (thread = 0; thread < threads->nr; thread++) {
@@ -850,6 +900,8 @@ retry_sample_id:
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 
+			pr_debug2("perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
+				  pid, cpus->map[cpu], group_fd, flags);
 			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
 								     pid,
 								     cpus->map[cpu],
-- 
1.7.11.7

[PATCH V4 10/21] perf tools: fix symbol_conf.nr_events

[Adrian Hunter]

symbol_conf.nr_events must be updated when processing
attribute events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/header.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 855f056..d12d79c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2957,6 +2957,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
 		perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]);
 	}
 
+	symbol_conf.nr_events = evlist->nr_entries;
+
 	return 0;
 }
 
-- 
1.7.11.7

[PATCH V4 11/21] perf tools: allow non-matching sample types

[Adrian Hunter]

Sample types need not be identical to determine
the sample id from the event.  Only the position
of the sample id needs to be the same.

Compatible sample types are ones in which the bits
defined by PERF_COMPAT_MASK are the same.
'perf_evlist__config()' forces sample types to be
compatible on that basis.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/builtin-report.c |   2 +-
 tools/perf/util/event.h     |  14 +++++
 tools/perf/util/evlist.c    | 135 ++++++++++++++++++++++++++++++++++++++++++--
 tools/perf/util/evlist.h    |   8 ++-
 tools/perf/util/evsel.c     |  64 ++++++++++++++++++++-
 tools/perf/util/evsel.h     |  10 ++++
 tools/perf/util/session.c   |   8 ++-
 7 files changed, 230 insertions(+), 11 deletions(-)

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ee2ca3e..c8810ba 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -367,7 +367,7 @@ static int process_read_event(struct perf_tool *tool,
 static int perf_report__setup_sample_type(struct perf_report *rep)
 {
 	struct perf_session *self = rep->session;
-	u64 sample_type = perf_evlist__sample_type(self->evlist);
+	u64 sample_type = perf_evlist__combined_sample_type(self->evlist);
 
 	if (!self->fd_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
 		if (sort__has_parent) {
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 1813895..3aef78c 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -65,6 +65,20 @@ struct read_event {
 	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
 	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
 
+/*
+ * Events have compatible sample types if the following bits all have the same
+ * value.  This is because the order of sample members is fixed.  For sample
+ * events the order is: PERF_SAMPLE_IP, PERF_SAMPLE_TID, PERF_SAMPLE_TIME,
+ * PERF_SAMPLE_ADDR, PERF_SAMPLE_ID.  For non-sample events the sample members
+ * are accessed in reverse order.  The order is: PERF_SAMPLE_ID,
+ * PERF_SAMPLE_STREAM_ID, PERF_SAMPLE_CPU.
+ */
+#define PERF_COMPAT_MASK				\
+	(PERF_SAMPLE_IP   | PERF_SAMPLE_TID       |	\
+	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR      |	\
+	 PERF_SAMPLE_ID   | PERF_SAMPLE_STREAM_ID |	\
+	 PERF_SAMPLE_CPU)
+
 struct sample_event {
 	struct perf_event_header        header;
 	u64 array[];
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index dfc267b..d9cffc4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -49,6 +49,45 @@ struct perf_evlist *perf_evlist__new(void)
 	return evlist;
 }
 
+/**
+ * perf_evlist__set_id_pos - set the positions of event ids.
+ * @evlist: selected event list
+ *
+ * Events with compatible sample types all have the same id_pos
+ * and is_pos.  For convenience, put a copy on evlist.
+ */
+static void perf_evlist__set_id_pos(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist);
+
+	evlist->id_pos = first->id_pos;
+	evlist->is_pos = first->is_pos;
+}
+
+/**
+ * perf_evlist__make_sample_types_compatible - make sample types compatible.
+ * @evlist: selected event list
+ *
+ * Events with compatible sample types all have the same id_pos and is_pos.
+ * This can be achieved by matching the bits of PERF_COMPAT_MASK.
+ */
+void perf_evlist__make_sample_types_compatible(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	u64 compat = 0;
+
+	list_for_each_entry(evsel, &evlist->entries, node)
+		compat |= evsel->attr.sample_type & PERF_COMPAT_MASK;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		evsel->attr.sample_type |= compat;
+		evsel->sample_size = __perf_evsel__sample_size(evsel->attr.sample_type);
+		perf_evsel__calc_id_pos(evsel);
+	}
+
+	perf_evlist__set_id_pos(evlist);
+}
+
 void perf_evlist__config(struct perf_evlist *evlist,
 			struct perf_record_opts *opts)
 {
@@ -69,6 +108,8 @@ void perf_evlist__config(struct perf_evlist *evlist,
 		if (evlist->nr_entries > 1)
 			perf_evsel__set_sample_id(evsel);
 	}
+
+	perf_evlist__make_sample_types_compatible(evlist);
 }
 
 static void perf_evlist__purge(struct perf_evlist *evlist)
@@ -102,6 +143,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	list_add_tail(&entry->node, &evlist->entries);
 	++evlist->nr_entries;
+	perf_evlist__set_id_pos(evlist);
 }
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
@@ -110,6 +152,7 @@ void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
 {
 	list_splice_tail(list, &evlist->entries);
 	evlist->nr_entries += nr_entries;
+	perf_evlist__set_id_pos(evlist);
 }
 
 void __perf_evlist__set_leader(struct list_head *list)
@@ -339,6 +382,55 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
 	return NULL;
 }
 
+static int perf_evlist__event2id(struct perf_evlist *evlist,
+				 union perf_event *event, u64 *id)
+{
+	const u64 *array = event->sample.array;
+	ssize_t n;
+
+	n = (event->header.size - sizeof(event->header)) >> 3;
+
+	if (event->header.type == PERF_RECORD_SAMPLE) {
+		if (evlist->id_pos >= n)
+			return -1;
+		*id = array[evlist->id_pos];
+	} else {
+		if (evlist->is_pos >= n)
+			return -1;
+		n -= evlist->is_pos;
+		*id = array[n];
+	}
+	return 0;
+}
+
+static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
+						   union perf_event *event)
+{
+	struct hlist_head *head;
+	struct perf_sample_id *sid;
+	int hash;
+	u64 id;
+
+	if (evlist->nr_entries == 1 || evlist->matching_sample_types)
+		return perf_evlist__first(evlist);
+
+	if (perf_evlist__event2id(evlist, event, &id))
+		return NULL;
+
+	/* Synthesized events have an id of zero */
+	if (!id)
+		return perf_evlist__first(evlist);
+
+	hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
+	head = &evlist->heads[hash];
+
+	hlist_for_each_entry(sid, head, node) {
+		if (sid->id == id)
+			return sid->evsel;
+	}
+	return NULL;
+}
+
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
@@ -650,19 +742,49 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
+	bool ok = true;
 
 	list_for_each_entry_continue(pos, &evlist->entries, node) {
-		if (first->attr.sample_type != pos->attr.sample_type)
+		if (first->attr.sample_type != pos->attr.sample_type) {
+			ok = false;
+			break;
+		}
+	}
+
+	if (ok) {
+		evlist->matching_sample_types = true;
+		return true;
+	}
+
+	if (evlist->id_pos < 0 || evlist->is_pos < 0)
+		return false;
+
+	list_for_each_entry(pos, &evlist->entries, node) {
+		if (pos->id_pos != evlist->id_pos ||
+		    pos->is_pos != evlist->is_pos)
 			return false;
 	}
 
 	return true;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
 {
-	struct perf_evsel *first = perf_evlist__first(evlist);
-	return first->attr.sample_type;
+	struct perf_evsel *evsel;
+
+	if (evlist->combined_sample_type)
+		return evlist->combined_sample_type;
+
+	list_for_each_entry(evsel, &evlist->entries, node)
+		evlist->combined_sample_type |= evsel->attr.sample_type;
+
+	return evlist->combined_sample_type;
+}
+
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist)
+{
+	evlist->combined_sample_type = 0;
+	return __perf_evlist__combined_sample_type(evlist);
 }
 
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
@@ -856,7 +978,10 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
 			      struct perf_sample *sample)
 {
-	struct perf_evsel *evsel = perf_evlist__first(evlist);
+	struct perf_evsel *evsel = perf_evlist__event2evsel(evlist, event);
+
+	if (!evsel)
+		return -EFAULT;
 	return perf_evsel__parse_sample(evsel, event, sample);
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0583d36..b1be475 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -32,11 +32,15 @@ struct perf_evlist {
 	int		 nr_fds;
 	int		 nr_mmaps;
 	int		 mmap_len;
+	int		 id_pos;
+	int		 is_pos;
+	u64		 combined_sample_type;
 	struct {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
 	bool		 overwrite;
+	bool		 matching_sample_types;
 	struct perf_mmap *mmap;
 	struct pollfd	 *pollfd;
 	struct thread_map *threads;
@@ -83,6 +87,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
+void perf_evlist__make_sample_types_compatible(struct perf_evlist *evlist);
 void perf_evlist__config(struct perf_evlist *evlist,
 			 struct perf_record_opts *opts);
 
@@ -118,7 +123,8 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist);
 void __perf_evlist__set_leader(struct list_head *list);
 void perf_evlist__set_leader(struct perf_evlist *evlist);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
+u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8978213..86628fe 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -30,7 +30,7 @@ static struct {
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
-static int __perf_evsel__sample_size(u64 sample_type)
+int __perf_evsel__sample_size(u64 sample_type)
 {
 	u64 mask = sample_type & PERF_SAMPLE_MASK;
 	int size = 0;
@@ -46,6 +46,65 @@ static int __perf_evsel__sample_size(u64 sample_type)
 	return size;
 }
 
+/**
+ * __perf_evsel__calc_id_pos - calculate id_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position of the event id (PERF_SAMPLE_ID) in a
+ * sample event i.e. in the array of struct sample_event.
+ */
+static int __perf_evsel__calc_id_pos(u64 sample_type)
+{
+	int idx = 0;
+
+	if (!(sample_type & PERF_SAMPLE_ID))
+		return -1;
+
+	if (sample_type & PERF_SAMPLE_IP)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_TID)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_TIME)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_ADDR)
+		idx += 1;
+
+	return idx;
+}
+
+/**
+ * __perf_evsel__calc_is_pos - calculate is_pos.
+ * @sample_type: sample type
+ *
+ * This function returns the position (counting backwards) of the event id
+ * (PERF_SAMPLE_ID) in a non-sample event i.e. if sample_id_all is used there is
+ * an id sample appended to non-sample events.
+ */
+static int __perf_evsel__calc_is_pos(u64 sample_type)
+{
+	int idx = 1;
+
+	if (!(sample_type & PERF_SAMPLE_ID))
+		return -1;
+
+	if (sample_type & PERF_SAMPLE_CPU)
+		idx += 1;
+
+	if (sample_type & PERF_SAMPLE_STREAM_ID)
+		idx += 1;
+
+	return idx;
+}
+
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
+{
+	evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type);
+	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
+}
+
 void hists__init(struct hists *hists)
 {
 	memset(hists, 0, sizeof(*hists));
@@ -62,6 +121,7 @@ void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
 	if (!(evsel->attr.sample_type & bit)) {
 		evsel->attr.sample_type |= bit;
 		evsel->sample_size += sizeof(u64);
+		perf_evsel__calc_id_pos(evsel);
 	}
 }
 
@@ -71,6 +131,7 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
 	if (evsel->attr.sample_type & bit) {
 		evsel->attr.sample_type &= ~bit;
 		evsel->sample_size -= sizeof(u64);
+		perf_evsel__calc_id_pos(evsel);
 	}
 }
 
@@ -89,6 +150,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
+	perf_evsel__calc_id_pos(evsel);
 }
 
 struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3f156cc..c6d616c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -45,6 +45,11 @@ struct perf_sample_id {
  * @name - Can be set to retain the original event name passed by the user,
  *         so that when showing results in tools such as 'perf stat', we
  *         show the name used, not some alias.
+ * @id_pos: the position of the event id (PERF_SAMPLE_ID) in a sample event
+ *          i.e. in the array of struct sample_event
+ * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID)
+ *          in a non-sample event i.e. if sample_id_all is used there is an id
+ *          sample appended to non-sample events
  */
 struct perf_evsel {
 	struct list_head	node;
@@ -71,6 +76,8 @@ struct perf_evsel {
 	} handler;
 	struct cpu_map		*cpus;
 	unsigned int		sample_size;
+	int			id_pos;
+	int			is_pos;
 	bool 			supported;
 	bool 			needs_swap;
 	/* parse modifier helper */
@@ -100,6 +107,9 @@ void perf_evsel__delete(struct perf_evsel *evsel);
 void perf_evsel__config(struct perf_evsel *evsel,
 			struct perf_record_opts *opts);
 
+int __perf_evsel__sample_size(u64 sample_type);
+void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
+
 bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
 
 #define PERF_EVSEL__MAX_ALIASES 8
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 951a1cf..66e6dc9 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -743,7 +743,7 @@ static void perf_session__print_tstamp(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_sample *sample)
 {
-	u64 sample_type = perf_evlist__sample_type(session->evlist);
+	u64 sample_type = __perf_evlist__combined_sample_type(session->evlist);
 
 	if (event->header.type != PERF_RECORD_SAMPLE &&
 	    !perf_evlist__sample_id_all(session->evlist)) {
@@ -902,7 +902,7 @@ static int perf_session__preprocess_sample(struct perf_session *session,
 					   union perf_event *event, struct perf_sample *sample)
 {
 	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_CALLCHAIN))
+	    !sample->callchain)
 		return 0;
 
 	if (!ip_callchain__valid(sample->callchain, event)) {
@@ -1304,7 +1304,9 @@ int perf_session__process_events(struct perf_session *self,
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
-	if (!(perf_evlist__sample_type(session->evlist) & PERF_SAMPLE_RAW)) {
+	u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
+
+	if (!(sample_type & PERF_SAMPLE_RAW)) {
 		pr_err("No trace sample to read. Did you call 'perf %s'?\n", msg);
 		return false;
 	}
-- 
1.7.11.7

[PATCH V4 12/21] perf tools: struct thread has a tid not a pid

[Adrian Hunter]

As evident from 'machine__process_fork_event()' and
'machine__process_exit_event()' the 'pid' member of
struct thread is actually the tid.

Rename 'pid' to 'tid' in struct thread accordingly.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: David Ahern <dsahern@gmail.com>
---
 tools/perf/builtin-kmem.c      |  2 +-
 tools/perf/builtin-sched.c     | 12 ++++++------
 tools/perf/builtin-trace.c     |  4 ++--
 tools/perf/ui/browsers/hists.c |  6 +++---
 tools/perf/util/event.c        |  2 +-
 tools/perf/util/machine.c      | 20 ++++++++++----------
 tools/perf/util/machine.h      |  4 ++--
 tools/perf/util/sort.c         |  6 +++---
 tools/perf/util/thread.c       | 10 +++++-----
 tools/perf/util/thread.h       |  4 ++--
 10 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 0259502..b49f5c5 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -313,7 +313,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
 
 	if (evsel->handler.func != NULL) {
 		tracepoint_handler f = evsel->handler.func;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index fed9ae4..32f21c2 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1075,7 +1075,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
 			return -1;
-		register_pid(sched, migrant->pid, migrant->comm);
+		register_pid(sched, migrant->tid, migrant->comm);
 		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("migration-event: Internal tree error");
@@ -1115,7 +1115,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->pid);
+	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
@@ -1131,9 +1131,9 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 {
-	if (l->thread->pid < r->thread->pid)
+	if (l->thread->tid < r->thread->tid)
 		return -1;
-	if (l->thread->pid > r->thread->pid)
+	if (l->thread->tid > r->thread->tid)
 		return 1;
 
 	return 0;
@@ -1321,7 +1321,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 			printf("*");
 
 		if (sched->curr_thread[cpu]) {
-			if (sched->curr_thread[cpu]->pid)
+			if (sched->curr_thread[cpu]->tid)
 				printf("%2s ", sched->curr_thread[cpu]->shortname);
 			else
 				printf(".  ");
@@ -1332,7 +1332,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	printf("  %12.6f secs ", (double)timestamp/1e9);
 	if (new_shortname) {
 		printf("%s => %s:%d\n",
-			sched_in->shortname, sched_in->comm, sched_in->pid);
+			sched_in->shortname, sched_in->comm, sched_in->tid);
 	} else {
 		printf("\n");
 	}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 87fc7d0..0e4b67f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -142,7 +142,7 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 	printed += fprintf_duration(duration, fp);
 
 	if (trace->multiple_threads)
-		printed += fprintf(fp, "%d ", thread->pid);
+		printed += fprintf(fp, "%d ", thread->tid);
 
 	return printed;
 }
@@ -593,7 +593,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 			color = PERF_COLOR_YELLOW;
 
 		printed += color_fprintf(fp, color, "%20s", thread->comm);
-		printed += fprintf(fp, " - %-5d :%11lu   [", thread->pid, ttrace->nr_events);
+		printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
 		printed += color_fprintf(fp, color, "%5.1f%%", ratio);
 		printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
 	}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fc0bd38..06e892f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1256,7 +1256,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 		printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
 				    (thread->comm_set ? thread->comm : ""),
-				    thread->pid);
+				    thread->tid);
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
@@ -1579,7 +1579,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
 			     (browser->hists->thread_filter ? "out of" : "into"),
 			     (thread->comm_set ? thread->comm : ""),
-			     thread->pid) > 0)
+			     thread->tid) > 0)
 			zoom_thread = nr_options++;
 
 		if (dso != NULL &&
@@ -1702,7 +1702,7 @@ zoom_out_thread:
 			} else {
 				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
 						   thread->comm_set ? thread->comm : "",
-						   thread->pid);
+						   thread->tid);
 				browser->hists->thread_filter = thread;
 				sort_thread.elide = true;
 				pstack__push(fstack, &browser->hists->thread_filter);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 5cd13d7..9541270 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -686,7 +686,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	    !strlist__has_entry(symbol_conf.comm_list, thread->comm))
 		goto out_filtered;
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
 	 *
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 93527af..5dd5026 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -233,7 +233,7 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 	return;
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid,
+static struct thread *__machine__findnew_thread(struct machine *machine, pid_t tid,
 						bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;
@@ -241,23 +241,23 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	struct thread *th;
 
 	/*
-	 * Font-end cache - PID lookups come in blocks,
+	 * Front-end cache - TID lookups come in blocks,
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	if (machine->last_match && machine->last_match->pid == pid)
+	if (machine->last_match && machine->last_match->tid == tid)
 		return machine->last_match;
 
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
 
-		if (th->pid == pid) {
+		if (th->tid == tid) {
 			machine->last_match = th;
 			return th;
 		}
 
-		if (pid < th->pid)
+		if (tid < th->tid)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -266,7 +266,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	if (!create)
 		return NULL;
 
-	th = thread__new(pid);
+	th = thread__new(tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
 		rb_insert_color(&th->rb_node, &machine->threads);
@@ -276,14 +276,14 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, true);
+	return __machine__findnew_thread(machine, tid, true);
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid)
+struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, false);
+	return __machine__findnew_thread(machine, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 7794068..e49ba01 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -36,7 +36,7 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 	return machine->vmlinux_maps[type];
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid);
+struct thread *machine__find_thread(struct machine *machine, pid_t tid);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event);
 int machine__process_exit_event(struct machine *machine, union perf_event *event);
@@ -99,7 +99,7 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t tid);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 313a5a7..8deee19 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -55,14 +55,14 @@ static int64_t cmp_null(void *l, void *r)
 static int64_t
 sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return right->thread->pid - left->thread->pid;
+	return right->thread->tid - left->thread->tid;
 }
 
 static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
 				       size_t size, unsigned int width)
 {
 	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-			      self->thread->comm ?: "", self->thread->pid);
+			      self->thread->comm ?: "", self->thread->tid);
 }
 
 struct sort_entry sort_thread = {
@@ -77,7 +77,7 @@ struct sort_entry sort_thread = {
 static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return right->thread->pid - left->thread->pid;
+	return right->thread->tid - left->thread->tid;
 }
 
 static int64_t
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 40399cb..6feeb88 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,17 +7,17 @@
 #include "util.h"
 #include "debug.h"
 
-struct thread *thread__new(pid_t pid)
+struct thread *thread__new(pid_t tid)
 {
 	struct thread *self = zalloc(sizeof(*self));
 
 	if (self != NULL) {
 		map_groups__init(&self->mg);
-		self->pid = pid;
+		self->tid = tid;
 		self->ppid = -1;
 		self->comm = malloc(32);
 		if (self->comm)
-			snprintf(self->comm, 32, ":%d", self->pid);
+			snprintf(self->comm, 32, ":%d", self->tid);
 	}
 
 	return self;
@@ -57,7 +57,7 @@ int thread__comm_len(struct thread *self)
 
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
-	return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) +
+	return fprintf(fp, "Thread %d %s\n", thread->tid, thread->comm) +
 	       map_groups__fprintf(&thread->mg, verbose, fp);
 }
 
@@ -84,7 +84,7 @@ int thread__fork(struct thread *self, struct thread *parent)
 		if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
 			return -ENOMEM;
 
-	self->ppid = parent->pid;
+	self->ppid = parent->tid;
 
 	return 0;
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 5e7ba35..0fe1f9c 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -12,7 +12,7 @@ struct thread {
 		struct list_head node;
 	};
 	struct map_groups	mg;
-	pid_t			pid;
+	pid_t			tid;
 	pid_t			ppid;
 	char			shortname[3];
 	bool			comm_set;
@@ -24,7 +24,7 @@ struct thread {
 
 struct machine;
 
-struct thread *thread__new(pid_t pid);
+struct thread *thread__new(pid_t tid);
 void thread__delete(struct thread *self);
 
 int thread__set_comm(struct thread *self, const char *comm);
-- 
1.7.11.7

[PATCH V4 13/21] perf tools: add pid to struct thread

[Adrian Hunter]

Record pid on struct thread.  The member is named 'pid_'
to avoid confusion with the 'tid' member which was previously
named 'pid'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/machine.c | 16 +++++++++++-----
 tools/perf/util/thread.c  |  3 ++-
 tools/perf/util/thread.h  |  3 ++-
 3 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5dd5026..fe5d9db 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -233,7 +233,8 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 	return;
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine, pid_t tid,
+static struct thread *__machine__findnew_thread(struct machine *machine,
+						pid_t pid, pid_t tid,
 						bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;
@@ -245,8 +246,11 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	if (machine->last_match && machine->last_match->tid == tid)
+	if (machine->last_match && machine->last_match->tid == tid) {
+		if (pid && !machine->last_match->pid_)
+			machine->last_match->pid_ = pid;
 		return machine->last_match;
+	}
 
 	while (*p != NULL) {
 		parent = *p;
@@ -254,6 +258,8 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 
 		if (th->tid == tid) {
 			machine->last_match = th;
+			if (pid && !th->pid_)
+				th->pid_ = pid;
 			return th;
 		}
 
@@ -266,7 +272,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 	if (!create)
 		return NULL;
 
-	th = thread__new(tid);
+	th = thread__new(pid, tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
 		rb_insert_color(&th->rb_node, &machine->threads);
@@ -278,12 +284,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t t
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, tid, true);
+	return __machine__findnew_thread(machine, 0, tid, true);
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, tid, false);
+	return __machine__findnew_thread(machine, 0, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 6feeb88..e3d4a55 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,12 +7,13 @@
 #include "util.h"
 #include "debug.h"
 
-struct thread *thread__new(pid_t tid)
+struct thread *thread__new(pid_t pid, pid_t tid)
 {
 	struct thread *self = zalloc(sizeof(*self));
 
 	if (self != NULL) {
 		map_groups__init(&self->mg);
+		self->pid_ = pid;
 		self->tid = tid;
 		self->ppid = -1;
 		self->comm = malloc(32);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 0fe1f9c..fc464bc 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -12,6 +12,7 @@ struct thread {
 		struct list_head node;
 	};
 	struct map_groups	mg;
+	pid_t			pid_; /* Not all tools update this */
 	pid_t			tid;
 	pid_t			ppid;
 	char			shortname[3];
@@ -24,7 +25,7 @@ struct thread {
 
 struct machine;
 
-struct thread *thread__new(pid_t tid);
+struct thread *thread__new(pid_t pid, pid_t tid);
 void thread__delete(struct thread *self);
 
 int thread__set_comm(struct thread *self, const char *comm);
-- 
1.7.11.7

[PATCH V4 14/21] perf tools: change "machine" functions to set thread pid

[Adrian Hunter]

Typically tracking events such as mmap events, comm events,
fork events and exit events, are processed by "machine"
functions.  Change these functions to put pid in the new
pid_ member of struct thread.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/machine.c | 21 +++++++++++++++++----
 tools/perf/util/machine.h |  2 ++
 2 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fe5d9db..a7ed350 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -287,6 +287,12 @@ struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
 	return __machine__findnew_thread(machine, 0, tid, true);
 }
 
+struct thread *machine__findnew_thread_ex(struct machine *machine, pid_t pid,
+					  pid_t tid)
+{
+	return __machine__findnew_thread(machine, pid, tid, true);
+}
+
 struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 {
 	return __machine__findnew_thread(machine, 0, tid, false);
@@ -294,7 +300,9 @@ struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
+	struct thread *thread = machine__findnew_thread_ex(machine,
+							   event->comm.pid,
+							   event->comm.tid);
 
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
@@ -975,7 +983,8 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 		return 0;
 	}
 
-	thread = machine__findnew_thread(machine, event->mmap.pid);
+	thread = machine__findnew_thread_ex(machine, event->mmap.pid,
+					    event->mmap.pid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1002,8 +1011,12 @@ out_problem:
 
 int machine__process_fork_event(struct machine *machine, union perf_event *event)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
-	struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
+	struct thread *thread = machine__findnew_thread_ex(machine,
+							   event->fork.pid,
+							   event->fork.tid);
+	struct thread *parent = machine__findnew_thread_ex(machine,
+							   event->fork.ppid,
+							   event->fork.ptid);
 
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e49ba01..d986ecf 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -100,6 +100,8 @@ static inline bool machine__is_host(struct machine *machine)
 }
 
 struct thread *machine__findnew_thread(struct machine *machine, pid_t tid);
+struct thread *machine__findnew_thread_ex(struct machine *machine, pid_t pid,
+					  pid_t tid);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
-- 
1.7.11.7

[PATCH V4 15/21] perf tools: fix missing increment in sample parsing

[Adrian Hunter]

The final sample format bit used to be PERF_SAMPLE_STACK_USER
which neglected to do a final increment of the array pointer.
The result is that the following parsing might start at the
wrong place.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/evsel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 86628fe..10ccf38 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1284,7 +1284,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		} else {
 			data->user_stack.data = (char *)array;
 			array += size / sizeof(*array);
-			data->user_stack.size = *array;
+			data->user_stack.size = *array++;
 		}
 	}
 
-- 
1.7.11.7

[PATCH V4 16/21] perf tools: tidy up sample parsing overflow checking

[Adrian Hunter]

The size of data retrieved from a sample event must be
validated to ensure it does not go past the end of the
event.  That was being done sporadically and without
considering integer overflows.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/evsel.c | 101 ++++++++++++++++++++++++++++++------------------
 1 file changed, 63 insertions(+), 38 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 10ccf38..16b5d5f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1108,24 +1108,38 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
 	return 0;
 }
 
-static bool sample_overlap(const union perf_event *event,
-			   const void *offset, u64 size)
+static inline bool overflow_one(const void *endp, const void *offset)
 {
-	const void *base = event;
-
-	if (offset + size > base + event->header.size)
-		return true;
+	return offset + sizeof(u64) > endp;
+}
 
-	return false;
+static inline bool overflow(const void *endp, u16 max_size, const void *offset,
+			    u64 size)
+{
+	return size > max_size || offset + size > endp;
 }
 
+#define OVERFLOW_CHECK_ONE(offset)				\
+	do {							\
+		if (overflow_one(endp, (offset)))		\
+			return -EFAULT;				\
+	} while (0)
+
+#define OVERFLOW_CHECK(offset, size)				\
+	do {							\
+		if (overflow(endp, max_size, (offset), (size)))	\
+			return -EFAULT;				\
+	} while (0)
+
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *data)
 {
 	u64 type = evsel->attr.sample_type;
-	u64 regs_user = evsel->attr.sample_regs_user;
 	bool swapped = evsel->needs_swap;
 	const u64 *array;
+	u16 max_size = event->header.size;
+	const void *endp = (void *)event + max_size;
+	u64 sz;
 
 	/*
 	 * used for cross-endian analysis. See git commit 65014ab3
@@ -1147,6 +1161,11 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	array = event->sample.array;
 
+	/*
+	 * sample_size is based on PERF_SAMPLE_MASK which includes up to
+	 * PERF_SAMPLE_PERIOD.  After that overflow_one() or overflow() must be
+	 * used to check the format does not go past the end of the event.
+	 */
 	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 
@@ -1215,20 +1234,19 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	}
 
 	if (type & PERF_SAMPLE_CALLCHAIN) {
-		if (sample_overlap(event, array, sizeof(data->callchain->nr)))
-			return -EFAULT;
-
-		data->callchain = (struct ip_callchain *)array;
+		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
 
-		if (sample_overlap(event, array, data->callchain->nr))
+		OVERFLOW_CHECK_ONE(array);
+		data->callchain = (struct ip_callchain *)array++;
+		if (data->callchain->nr > max_callchain_nr)
 			return -EFAULT;
-
-		array += 1 + data->callchain->nr;
+		sz = data->callchain->nr * sizeof(u64);
+		OVERFLOW_CHECK(array, sz);
+		array = (void*)array + sz;
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
-		const u64 *pdata;
-
+		OVERFLOW_CHECK_ONE(array);
 		u.val64 = *array;
 		if (WARN_ONCE(swapped,
 			      "Endianness of raw data not corrected!\n")) {
@@ -1237,65 +1255,72 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			u.val32[0] = bswap_32(u.val32[0]);
 			u.val32[1] = bswap_32(u.val32[1]);
 		}
-
-		if (sample_overlap(event, array, sizeof(u32)))
-			return -EFAULT;
-
 		data->raw_size = u.val32[0];
-		pdata = (void *) array + sizeof(u32);
+		array = (void *)array + sizeof(u32);
 
-		if (sample_overlap(event, pdata, data->raw_size))
-			return -EFAULT;
-
-		data->raw_data = (void *) pdata;
-
-		array = (void *)array + data->raw_size + sizeof(u32);
+		OVERFLOW_CHECK(array, data->raw_size);
+		data->raw_data = (void *)array;
+		array = (void *)array + data->raw_size;
 	}
 
 	if (type & PERF_SAMPLE_BRANCH_STACK) {
-		u64 sz;
+		const u64 max_branch_nr = UINT64_MAX / sizeof(struct branch_entry);
 
-		data->branch_stack = (struct branch_stack *)array;
-		array++; /* nr */
+		OVERFLOW_CHECK_ONE(array);
+		data->branch_stack = (struct branch_stack *)array++;
 
+		if (data->branch_stack->nr > max_branch_nr)
+			return -EFAULT;
 		sz = data->branch_stack->nr * sizeof(struct branch_entry);
-		sz /= sizeof(u64);
-		array += sz;
+		OVERFLOW_CHECK(array, sz);
+		array = (void *)array + sz;
 	}
 
 	if (type & PERF_SAMPLE_REGS_USER) {
+		u64 avail;
+
 		/* First u64 tells us if we have any regs in sample. */
-		u64 avail = *array++;
+		OVERFLOW_CHECK_ONE(array);
+		avail = *array++;
 
 		if (avail) {
+			u64 regs_user = evsel->attr.sample_regs_user;
+
+			sz = hweight_long(regs_user) * sizeof(u64);
+			OVERFLOW_CHECK(array, sz);
 			data->user_regs.regs = (u64 *)array;
-			array += hweight_long(regs_user);
+			array = (void *)array + sz;
 		}
 	}
 
 	if (type & PERF_SAMPLE_STACK_USER) {
-		u64 size = *array++;
+		OVERFLOW_CHECK_ONE(array);
+		sz = *array++;
 
 		data->user_stack.offset = ((char *)(array - 1)
 					  - (char *) event);
 
-		if (!size) {
+		if (!sz) {
 			data->user_stack.size = 0;
 		} else {
+			OVERFLOW_CHECK(array, sz);
 			data->user_stack.data = (char *)array;
-			array += size / sizeof(*array);
+			array = (void *)array + sz;
+			OVERFLOW_CHECK_ONE(array);
 			data->user_stack.size = *array++;
 		}
 	}
 
 	data->weight = 0;
 	if (type & PERF_SAMPLE_WEIGHT) {
+		OVERFLOW_CHECK_ONE(array);
 		data->weight = *array;
 		array++;
 	}
 
 	data->data_src = PERF_MEM_DATA_SRC_NONE;
 	if (type & PERF_SAMPLE_DATA_SRC) {
+		OVERFLOW_CHECK_ONE(array);
 		data->data_src = *array;
 		array++;
 	}
-- 
1.7.11.7

[PATCH V4 17/21] perf tools: remove unnecessary callchain validation

[Adrian Hunter]

Now that the sample parsing correctly checks data sizes
there is no reason for it to be done again for callchains.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/util/callchain.c |  8 --------
 tools/perf/util/callchain.h |  5 -----
 tools/perf/util/session.c   | 20 --------------------
 3 files changed, 33 deletions(-)

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 42b6a63..024162a 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -20,14 +20,6 @@
 
 __thread struct callchain_cursor callchain_cursor;
 
-bool ip_callchain__valid(struct ip_callchain *chain,
-			 const union perf_event *event)
-{
-	unsigned int chain_size = event->header.size;
-	chain_size -= (unsigned long)&event->ip.__more_data - (unsigned long)event;
-	return chain->nr * sizeof(u64) <= chain_size;
-}
-
 #define chain_for_each_child(child, parent)	\
 	list_for_each_entry(child, &parent->children, siblings)
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 3ee9f67..988c1aa 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -103,11 +103,6 @@ int callchain_append(struct callchain_root *root,
 int callchain_merge(struct callchain_cursor *cursor,
 		    struct callchain_root *dst, struct callchain_root *src);
 
-struct ip_callchain;
-union perf_event;
-
-bool ip_callchain__valid(struct ip_callchain *chain,
-			 const union perf_event *event);
 /*
  * Initialize a cursor before adding entries inside, but keep
  * the previously allocated entries as a cache.
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 66e6dc9..e8d5521 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -898,22 +898,6 @@ static int perf_session_deliver_event(struct perf_session *session,
 	}
 }
 
-static int perf_session__preprocess_sample(struct perf_session *session,
-					   union perf_event *event, struct perf_sample *sample)
-{
-	if (event->header.type != PERF_RECORD_SAMPLE ||
-	    !sample->callchain)
-		return 0;
-
-	if (!ip_callchain__valid(sample->callchain, event)) {
-		pr_debug("call-chain problem with event, skipping it.\n");
-		++session->stats.nr_invalid_chains;
-		session->stats.total_invalid_chains += sample->period;
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
 					    struct perf_tool *tool, u64 file_offset)
 {
@@ -978,10 +962,6 @@ static int perf_session__process_event(struct perf_session *session,
 	if (ret)
 		return ret;
 
-	/* Preprocess sample records - precheck callchains */
-	if (perf_session__preprocess_sample(session, event, &sample))
-		return 0;
-
 	if (tool->ordered_samples) {
 		ret = perf_session_queue_event(session, event, &sample,
 					       file_offset);
-- 
1.7.11.7

[PATCH V4 18/21] perf tools: remove references to struct ip_event

[Adrian Hunter]

struct ip_event assumes fixeed positions for ip, pid
and tid.  That is no longer true with the addition of
PERF_SAMPLE_IDENTIFIER.  The information is anyway in
struct sample, so use that instead.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/builtin-inject.c   |  4 ++--
 tools/perf/builtin-kmem.c     |  2 +-
 tools/perf/builtin-mem.c      |  2 +-
 tools/perf/builtin-script.c   |  2 +-
 tools/perf/builtin-top.c      | 10 +++++-----
 tools/perf/tests/hists_link.c |  4 ++++
 tools/perf/util/build-id.c    |  6 +++---
 tools/perf/util/event.c       |  4 ++--
 tools/perf/util/evsel.c       |  4 ++--
 tools/perf/util/session.c     |  7 ++++---
 10 files changed, 25 insertions(+), 20 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index ad1296c..6bb6522 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -204,7 +204,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread = machine__findnew_thread(machine, event->ip.pid);
+	thread = machine__findnew_thread(machine, sample->pid);
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
 		       event->header.type);
@@ -212,7 +212,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 	}
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index b49f5c5..401ead7 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -305,7 +305,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index a8ff6d2..4274680 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -96,7 +96,7 @@ dump_raw_samples(struct perf_tool *tool,
 		symbol_conf.field_sep,
 		sample->tid,
 		symbol_conf.field_sep,
-		event->ip.ip,
+		sample->ip,
 		symbol_conf.field_sep,
 		sample->addr,
 		symbol_conf.field_sep,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 92d4658..6425e09 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -479,7 +479,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct machine *machine)
 {
 	struct addr_location al;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
+	struct thread *thread = machine__findnew_thread(machine, sample->tid);
 
 	if (thread == NULL) {
 		pr_debug("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a237059..daa698e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -690,7 +690,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 {
 	struct perf_top *top = container_of(tool, struct perf_top, tool);
 	struct symbol *parent = NULL;
-	u64 ip = event->ip.ip;
+	u64 ip = sample->ip;
 	struct addr_location al;
 	int err;
 
@@ -700,10 +700,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		if (!seen)
 			seen = intlist__new(NULL);
 
-		if (!intlist__has_entry(seen, event->ip.pid)) {
+		if (!intlist__has_entry(seen, sample->pid)) {
 			pr_err("Can't find guest [%d]'s kernel information\n",
-				event->ip.pid);
-			intlist__add(seen, event->ip.pid);
+				sample->pid);
+			intlist__add(seen, sample->pid);
 		}
 		return;
 	}
@@ -839,7 +839,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 			break;
 		case PERF_RECORD_MISC_GUEST_KERNEL:
 			++top->guest_kernel_samples;
-			machine = perf_session__find_machine(session, event->ip.pid);
+			machine = perf_session__find_machine(session, sample.pid);
 			break;
 		case PERF_RECORD_MISC_GUEST_USER:
 			++top->guest_us_samples;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 89085a9..6fa9aa6 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -219,6 +219,8 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				},
 			};
 
+			sample.pid = ip_event.ip.pid;
+			sample.ip = ip_event.ip.ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;
@@ -243,6 +245,8 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				},
 			};
 
+			sample.pid = ip_event.ip.pid;
+			sample.ip = ip_event.ip.ip;
 			if (perf_event__preprocess_sample(&event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 5295625..e45da29 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -18,13 +18,13 @@
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   union perf_event *event,
-			   struct perf_sample *sample __maybe_unused,
+			   struct perf_sample *sample,
 			   struct perf_evsel *evsel __maybe_unused,
 			   struct machine *machine)
 {
 	struct addr_location al;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid);
 
 	if (thread == NULL) {
 		pr_err("problem processing %d event, skipping it.\n",
@@ -33,7 +33,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 	}
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, &al);
+			      sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9541270..227c1a4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -677,7 +677,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  symbol_filter_t filter)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
+	struct thread *thread = machine__findnew_thread(machine, sample->pid);
 
 	if (thread == NULL)
 		return -1;
@@ -699,7 +699,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 		machine__create_kernel_maps(machine);
 
 	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      event->ip.ip, al);
+			      sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 16b5d5f..fa806db 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1170,7 +1170,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		return -EFAULT;
 
 	if (type & PERF_SAMPLE_IP) {
-		data->ip = event->ip.ip;
+		data->ip = *array;
 		array++;
 	}
 
@@ -1343,7 +1343,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	array = event->sample.array;
 
 	if (type & PERF_SAMPLE_IP) {
-		event->ip.ip = sample->ip;
+		*array = sample->ip;
 		array++;
 	}
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index e8d5521..0ae80bb 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -811,7 +811,8 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
 static struct machine *
 	perf_session__find_machine_for_cpumode(struct perf_session *session,
-					       union perf_event *event)
+					       union perf_event *event,
+					       struct perf_sample *sample)
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
@@ -823,7 +824,7 @@ static struct machine *
 		if (event->header.type == PERF_RECORD_MMAP)
 			pid = event->mmap.pid;
 		else
-			pid = event->ip.pid;
+			pid = sample->pid;
 
 		return perf_session__findnew_machine(session, pid);
 	}
@@ -860,7 +861,7 @@ static int perf_session_deliver_event(struct perf_session *session,
 		hists__inc_nr_events(&evsel->hists, event->header.type);
 	}
 
-	machine = perf_session__find_machine_for_cpumode(session, event);
+	machine = perf_session__find_machine_for_cpumode(session, event, sample);
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-- 
1.7.11.7

[PATCH V4 19/21] perf tools: move struct ip_event

[Adrian Hunter]

struct ip_event assumes fixed positions for ip, pid
and tid.  That is no longer true with the addition of
PERF_SAMPLE_IDENTIFIER.

struct ip_event is no longer used except by hists_link.c.
Move it there.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/tests/hists_link.c | 23 +++++++++++++++++++----
 tools/perf/util/event.h       | 11 -----------
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 6fa9aa6..5bcbeb3 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -194,6 +194,19 @@ static struct sample fake_samples[][5] = {
 	},
 };
 
+/* PERF_SAMPLE_IP | PERF_SAMPLE_TID | * but not PERF_SAMPLE_IDENTIFIER */
+struct ip_event {
+	struct perf_event_header header;
+	u64 ip;
+	u32 pid, tid;
+	unsigned char __more_data[];
+};
+
+union perf_ip_event {
+	struct ip_event ip;
+	union perf_event event;
+};
+
 static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 {
 	struct perf_evsel *evsel;
@@ -209,7 +222,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	 */
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
-			const union perf_event event = {
+			const union perf_ip_event ip_event = {
 				.ip = {
 					.header = {
 						.misc = PERF_RECORD_MISC_USER,
@@ -218,10 +231,11 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.ip  = fake_common_samples[k].ip,
 				},
 			};
+			const union perf_event *event = &ip_event.event;
 
 			sample.pid = ip_event.ip.pid;
 			sample.ip = ip_event.ip.ip;
-			if (perf_event__preprocess_sample(&event, machine, &al,
+			if (perf_event__preprocess_sample(event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;
 
@@ -235,7 +249,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 		}
 
 		for (k = 0; k < ARRAY_SIZE(fake_samples[i]); k++) {
-			const union perf_event event = {
+			const union perf_ip_event ip_event = {
 				.ip = {
 					.header = {
 						.misc = PERF_RECORD_MISC_USER,
@@ -244,10 +258,11 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.ip  = fake_samples[i][k].ip,
 				},
 			};
+			const union perf_event *event = &ip_event.event;
 
 			sample.pid = ip_event.ip.pid;
 			sample.ip = ip_event.ip.ip;
-			if (perf_event__preprocess_sample(&event, machine, &al,
+			if (perf_event__preprocess_sample(event, machine, &al,
 							  &sample, 0) < 0)
 				goto out;
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 3aef78c..a7b2245 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -8,16 +8,6 @@
 #include "map.h"
 #include "build-id.h"
 
-/*
- * PERF_SAMPLE_IP | PERF_SAMPLE_TID | *
- */
-struct ip_event {
-	struct perf_event_header header;
-	u64 ip;
-	u32 pid, tid;
-	unsigned char __more_data[];
-};
-
 struct mmap_event {
 	struct perf_event_header header;
 	u32 pid, tid;
@@ -162,7 +152,6 @@ struct tracing_data_event {
 
 union perf_event {
 	struct perf_event_header	header;
-	struct ip_event			ip;
 	struct mmap_event		mmap;
 	struct comm_event		comm;
 	struct fork_event		fork;
-- 
1.7.11.7

[PATCH V4 20/21] perf: make events stream always parsable

[Adrian Hunter]

The event stream is not always parsable because the format of a sample
is dependent on the sample_type of the selected event.  When there
is more than one selected event and the sample_types are not the
same then parsing becomes problematic.  A sample can be matched to its
selected event using the ID that is allocated when the event is opened.
Unfortunately, to get the ID from the sample means first parsing it.

This patch adds a new sample format bit PERF_SAMPLE_IDENTIFER that puts
the ID at a fixed position so that the ID can be retrieved without
parsing the sample.  For sample events, that is the first position
immediately after the header.  For non-sample events, that is the last
position.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 include/uapi/linux/perf_event.h |  3 ++-
 kernel/events/core.c            | 11 ++++++++++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 0b1df41..6bb217e 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -134,8 +134,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
 	PERF_SAMPLE_WEIGHT			= 1U << 14,
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 
-	PERF_SAMPLE_MAX = 1U << 16,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
 };
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1db3af9..ca532f2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1203,6 +1203,9 @@ static void perf_event__id_header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_TIME)
 		size += sizeof(data->time);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
+
 	if (sample_type & PERF_SAMPLE_ID)
 		size += sizeof(data->id);
 
@@ -4229,7 +4232,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_TIME)
 		data->time = perf_clock();
 
-	if (sample_type & PERF_SAMPLE_ID)
+	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
 		data->id = primary_event_id(event);
 
 	if (sample_type & PERF_SAMPLE_STREAM_ID)
@@ -4268,6 +4271,9 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle,
 
 	if (sample_type & PERF_SAMPLE_CPU)
 		perf_output_put(handle, data->cpu_entry);
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
 }
 
 void perf_event__output_id_sample(struct perf_event *event,
@@ -4380,6 +4386,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 
 	perf_output_put(handle, *header);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
+
 	if (sample_type & PERF_SAMPLE_IP)
 		perf_output_put(handle, data->ip);
 
-- 
1.7.11.7

[PATCH V4 21/21] perf tools: add support for PERF_SAMPLE_IDENTFIER

[Adrian Hunter]

Enable parsing of samples with sample format bit
PERF_SAMPLE_IDENTFIER.  In addition, if the kernel supports
it, prefer it to selecting PERF_SAMPLE_ID thereby avoiding
the need to force compatible sample types.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/tests/mmap-basic.c |  2 +-
 tools/perf/util/event.h       |  9 +++--
 tools/perf/util/evlist.c      | 83 +++++++++++++++++++++++++++++++++++++++++--
 tools/perf/util/evlist.h      |  1 +
 tools/perf/util/evsel.c       | 41 +++++++++++++++++----
 tools/perf/util/evsel.h       |  3 +-
 6 files changed, 125 insertions(+), 14 deletions(-)

diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5b1b5ab..c4185b9 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -72,7 +72,7 @@ int test__basic_mmap(void)
 		}
 
 		evsels[i]->attr.wakeup_events = 1;
-		perf_evsel__set_sample_id(evsels[i]);
+		perf_evsel__set_sample_id(evsels[i], false);
 
 		perf_evlist__add(evlist, evsels[i]);
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a7b2245..ce2a92c 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -53,7 +53,8 @@ struct read_event {
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
 	PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID |	\
-	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+	 PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD |		\
+	 PERF_SAMPLE_IDENTIFIER)
 
 /*
  * Events have compatible sample types if the following bits all have the same
@@ -61,13 +62,15 @@ struct read_event {
  * events the order is: PERF_SAMPLE_IP, PERF_SAMPLE_TID, PERF_SAMPLE_TIME,
  * PERF_SAMPLE_ADDR, PERF_SAMPLE_ID.  For non-sample events the sample members
  * are accessed in reverse order.  The order is: PERF_SAMPLE_ID,
- * PERF_SAMPLE_STREAM_ID, PERF_SAMPLE_CPU.
+ * PERF_SAMPLE_STREAM_ID, PERF_SAMPLE_CPU.  PERF_SAMPLE_IDENTIFIER is added for
+ * completeness but it should not be used with PERF_SAMPLE_ID.  Sample types
+ * that include PERF_SAMPLE_IDENTIFIER are always compatible.
  */
 #define PERF_COMPAT_MASK				\
 	(PERF_SAMPLE_IP   | PERF_SAMPLE_TID       |	\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR      |	\
 	 PERF_SAMPLE_ID   | PERF_SAMPLE_STREAM_ID |	\
-	 PERF_SAMPLE_CPU)
+	 PERF_SAMPLE_CPU  | PERF_SAMPLE_IDENTIFIER)
 
 struct sample_event {
 	struct perf_event_header        header;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d9cffc4..752c35e 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -88,10 +88,83 @@ void perf_evlist__make_sample_types_compatible(struct perf_evlist *evlist)
 	perf_evlist__set_id_pos(evlist);
 }
 
+typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
+
+static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+{
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	int err = -EAGAIN, fd;
+
+	evlist = perf_evlist__new();
+	if (!evlist)
+		return -ENOMEM;
+
+	if (parse_events(evlist, str))
+		goto out_delete;
+
+	evsel = perf_evlist__first(evlist);
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd < 0)
+		goto out_delete;
+	close(fd);
+
+	fn(evsel);
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd < 0) {
+		if (errno == EINVAL)
+			err = -EINVAL;
+		goto out_delete;
+	}
+	close(fd);
+	err = 0;
+
+out_delete:
+	perf_evlist__delete(evlist);
+	return err;
+}
+
+static bool perf_probe_api(setup_probe_fn_t fn)
+{
+	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+	struct cpu_map *cpus;
+	int cpu, ret, i = 0;
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus)
+		return false;
+	cpu = cpus->map[0];
+	cpu_map__delete(cpus);
+
+	do {
+		ret = perf_do_probe_api(fn, cpu, try[i++]);
+		if (!ret)
+			return true;
+	} while (ret == -EAGAIN && try[i]);
+
+	return false;
+}
+
+static void perf_probe_sample_identifier(struct perf_evsel *evsel)
+{
+	evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
+}
+
+bool perf_can_sample_identifier(void)
+{
+	return perf_probe_api(perf_probe_sample_identifier);
+}
+
 void perf_evlist__config(struct perf_evlist *evlist,
 			struct perf_record_opts *opts)
 {
 	struct perf_evsel *evsel;
+	bool can_sample_identifier;
+
+	can_sample_identifier = perf_can_sample_identifier();
+
 	/*
 	 * Set the evsel leader links before we configure attributes,
 	 * since some might depend on this info.
@@ -106,10 +179,13 @@ void perf_evlist__config(struct perf_evlist *evlist,
 		perf_evsel__config(evsel, opts);
 
 		if (evlist->nr_entries > 1)
-			perf_evsel__set_sample_id(evsel);
+			perf_evsel__set_sample_id(evsel, can_sample_identifier);
 	}
 
-	perf_evlist__make_sample_types_compatible(evlist);
+	if (can_sample_identifier)
+		perf_evlist__set_id_pos(evlist);
+	else
+		perf_evlist__make_sample_types_compatible(evlist);
 }
 
 static void perf_evlist__purge(struct perf_evlist *evlist)
@@ -813,6 +889,9 @@ u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
 
 	if (sample_type & PERF_SAMPLE_CPU)
 		size += sizeof(data->cpu) * 2;
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
 out:
 	return size;
 }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b1be475..9b767e6 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -88,6 +88,7 @@ int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__make_sample_types_compatible(struct perf_evlist *evlist);
+bool perf_can_sample_identifier(void);
 void perf_evlist__config(struct perf_evlist *evlist,
 			 struct perf_record_opts *opts);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index fa806db..bcae21c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -50,13 +50,17 @@ int __perf_evsel__sample_size(u64 sample_type)
  * __perf_evsel__calc_id_pos - calculate id_pos.
  * @sample_type: sample type
  *
- * This function returns the position of the event id (PERF_SAMPLE_ID) in a
- * sample event i.e. in the array of struct sample_event.
+ * This function returns the position of the event id (PERF_SAMPLE_ID or
+ * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
+ * sample_event.
  */
 static int __perf_evsel__calc_id_pos(u64 sample_type)
 {
 	int idx = 0;
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		return 0;
+
 	if (!(sample_type & PERF_SAMPLE_ID))
 		return -1;
 
@@ -80,13 +84,16 @@ static int __perf_evsel__calc_id_pos(u64 sample_type)
  * @sample_type: sample type
  *
  * This function returns the position (counting backwards) of the event id
- * (PERF_SAMPLE_ID) in a non-sample event i.e. if sample_id_all is used there is
- * an id sample appended to non-sample events.
+ * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if
+ * sample_id_all is used there is an id sample appended to non-sample events.
  */
 static int __perf_evsel__calc_is_pos(u64 sample_type)
 {
 	int idx = 1;
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		return 1;
+
 	if (!(sample_type & PERF_SAMPLE_ID))
 		return -1;
 
@@ -135,9 +142,13 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
 	}
 }
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel)
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+			       bool can_sample_identifier)
 {
-	perf_evsel__set_sample_bit(evsel, ID);
+	if (can_sample_identifier)
+		perf_evsel__set_sample_bit(evsel, IDENTIFIER);
+	else
+		perf_evsel__set_sample_bit(evsel, ID);
 	evsel->attr.read_format |= PERF_FORMAT_ID;
 }
 
@@ -1065,6 +1076,11 @@ static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
 	array += ((event->header.size -
 		   sizeof(event->header)) / sizeof(u64)) - 1;
 
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		sample->id = *array;
+		array--;
+	}
+
 	if (type & PERF_SAMPLE_CPU) {
 		u.val64 = *array;
 		if (swapped) {
@@ -1169,6 +1185,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (evsel->sample_size + sizeof(event->header) > event->header.size)
 		return -EFAULT;
 
+	data->id = -1ULL;
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		data->id = *array;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_IP) {
 		data->ip = *array;
 		array++;
@@ -1199,7 +1221,6 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 	}
 
-	data->id = -1ULL;
 	if (type & PERF_SAMPLE_ID) {
 		data->id = *array;
 		array++;
@@ -1342,6 +1363,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 
 	array = event->sample.array;
 
+	if (type & PERF_SAMPLE_IDENTIFIER) {
+		*array = sample->id;
+		array++;
+	}
+
 	if (type & PERF_SAMPLE_IP) {
 		*array = sample->ip;
 		array++;
@@ -1530,6 +1556,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
 		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
 		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
+		bit_name(IDENTIFIER),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c6d616c..bca8e5f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -148,7 +148,8 @@ void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
 #define perf_evsel__reset_sample_bit(evsel, bit) \
 	__perf_evsel__reset_sample_bit(evsel, PERF_SAMPLE_##bit)
 
-void perf_evsel__set_sample_id(struct perf_evsel *evsel);
+void perf_evsel__set_sample_id(struct perf_evsel *evsel,
+			       bool use_sample_identifier);
 
 int perf_evsel__set_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			   const char *filter);
-- 
1.7.11.7

Re: [PATCH V4 20/21] perf: make events stream always parsable

[Namhyung Kim]

Hi Adrian,

On Thu, Jul 4, 2013 at 10:20 PM, Adrian Hunter <adrian.hunter@intel.com> wrote:
> The event stream is not always parsable because the format of a sample
> is dependent on the sample_type of the selected event.  When there
> is more than one selected event and the sample_types are not the
> same then parsing becomes problematic.  A sample can be matched to its
> selected event using the ID that is allocated when the event is opened.
> Unfortunately, to get the ID from the sample means first parsing it.
>
> This patch adds a new sample format bit PERF_SAMPLE_IDENTIFER that puts
> the ID at a fixed position so that the ID can be retrieved without
> parsing the sample.  For sample events, that is the first position
> immediately after the header.  For non-sample events, that is the last
> position.

Why do we have to keep another ID again?
If all we need is the sample_type, why not just saving it directly?

And for the implementation, I guess it'll break old perf tools
by parsing invalid position of data. IOW if it's recorded on a newer
kernel/tool and then reported on an older perf tool (maybe on a
different machine).  In this case the old tool cannot recognize the
PERF_SAMPLE_IDENTIFIER and try to parse it as a different
type of data, right?

So I suggest put the data at the end of sample data like other new
sample types added.  Older tools would simply ignore that part, and
newer tools can access it directly by checking event.header.size
and/or evsel->sample_size.

Thanks,
Namhyung

>
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> ---
>  include/uapi/linux/perf_event.h |  3 ++-
>  kernel/events/core.c            | 11 ++++++++++-
>  2 files changed, 12 insertions(+), 2 deletions(-)
>
> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
> index 0b1df41..6bb217e 100644
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -134,8 +134,9 @@ enum perf_event_sample_format {
>         PERF_SAMPLE_STACK_USER                  = 1U << 13,
>         PERF_SAMPLE_WEIGHT                      = 1U << 14,
>         PERF_SAMPLE_DATA_SRC                    = 1U << 15,
> +       PERF_SAMPLE_IDENTIFIER                  = 1U << 16,
>
> -       PERF_SAMPLE_MAX = 1U << 16,             /* non-ABI */
> +       PERF_SAMPLE_MAX = 1U << 17,             /* non-ABI */
>  };
>
>  /*
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 1db3af9..ca532f2 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -1203,6 +1203,9 @@ static void perf_event__id_header_size(struct perf_event *event)
>         if (sample_type & PERF_SAMPLE_TIME)
>                 size += sizeof(data->time);
>
> +       if (sample_type & PERF_SAMPLE_IDENTIFIER)
> +               size += sizeof(data->id);
> +
>         if (sample_type & PERF_SAMPLE_ID)
>                 size += sizeof(data->id);
>
> @@ -4229,7 +4232,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
>         if (sample_type & PERF_SAMPLE_TIME)
>                 data->time = perf_clock();
>
> -       if (sample_type & PERF_SAMPLE_ID)
> +       if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
>                 data->id = primary_event_id(event);
>
>         if (sample_type & PERF_SAMPLE_STREAM_ID)
> @@ -4268,6 +4271,9 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle,
>
>         if (sample_type & PERF_SAMPLE_CPU)
>                 perf_output_put(handle, data->cpu_entry);
> +
> +       if (sample_type & PERF_SAMPLE_IDENTIFIER)
> +               perf_output_put(handle, data->id);
>  }
>
>  void perf_event__output_id_sample(struct perf_event *event,
> @@ -4380,6 +4386,9 @@ void perf_output_sample(struct perf_output_handle *handle,
>
>         perf_output_put(handle, *header);
>
> +       if (sample_type & PERF_SAMPLE_IDENTIFIER)
> +               perf_output_put(handle, data->id);
> +
>         if (sample_type & PERF_SAMPLE_IP)
>                 perf_output_put(handle, data->ip);
>
> --
> 1.7.11.7
>

Re: [PATCH V4 09/21] perf tools: add debug prints

[Arnaldo Carvalho de Melo]

Em Thu, Jul 04, 2013 at 04:20:28PM +0300, Adrian Hunter escreveu:
> It is useful to see the arguments to perf_event_open
> and whether the perf events ring buffer was mmapped
> per-cpu or per-thread.  That information will now be
> displayed when verbose is 2 i.e option -vv
> 
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> Acked-by: Jiri Olsa <jolsa@redhat.com>
> ---
>  tools/perf/util/evlist.c |  3 +++
>  tools/perf/util/evsel.c  | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 55 insertions(+)
> 
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index 160036e..dfc267b 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -14,6 +14,7 @@
>  #include "target.h"
>  #include "evlist.h"
>  #include "evsel.h"
> +#include "debug.h"
>  #include <unistd.h>
>  
>  #include "parse-events.h"
> @@ -454,6 +455,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
>  	int nr_cpus = cpu_map__nr(evlist->cpus);
>  	int nr_threads = thread_map__nr(evlist->threads);
>  
> +	pr_debug2("perf event ring buffer mmapped per cpu\n");
>  	for (cpu = 0; cpu < nr_cpus; cpu++) {
>  		int output = -1;
>  
> @@ -492,6 +494,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
>  	int thread;
>  	int nr_threads = thread_map__nr(evlist->threads);
>  
> +	pr_debug2("perf event ring buffer mmapped per thread\n");
>  	for (thread = 0; thread < nr_threads; thread++) {
>  		int output = -1;
>  
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index dea0684..8978213 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -21,6 +21,7 @@
>  #include "thread_map.h"
>  #include "target.h"
>  #include "perf_regs.h"
> +#include "debug.h"
>  
>  static struct {
>  	bool sample_id_all;
> @@ -817,6 +818,54 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
>  	return fd;
>  }
>  
> +static void show_attr(struct perf_event_attr *attr)
> +{

These things have been done usually as:

	size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)

Take a look at dso__fprintf() for instance, and grep for __fprintf on
tools/perf for other examples.

And then you can do just one test of (verbose >= 2) to call this
function.

> +	pr_debug2("------------------------------------------------------------\n");
> +	pr_debug2("perf_event_attr:\n");
> +	pr_debug2("  type                %u\n", attr->type);
> +	pr_debug2("  size                %u\n", attr->size);
> +	pr_debug2("  config              %#"PRIx64"\n", (uint64_t)attr->config);
> +	pr_debug2("  sample_period       %"PRIu64"\n", (uint64_t)attr->sample_period);
> +	pr_debug2("  sample_freq         %"PRIu64"\n", (uint64_t)attr->sample_freq);
> +	pr_debug2("  sample_type         %#"PRIx64"\n", (uint64_t)attr->sample_type);
> +	pr_debug2("  read_format         %#"PRIx64"\n", (uint64_t)attr->read_format);
> +
> +	pr_debug2("  disabled            %u    ", attr->disabled);
> +	pr_debug2("inherit             %u\n", attr->inherit);
> +	pr_debug2("  pinned              %u    ", attr->pinned);
> +	pr_debug2("exclusive           %u\n", attr->exclusive);
> +	pr_debug2("  exclude_user        %u    ", attr->exclude_user);
> +	pr_debug2("exclude_kernel      %u\n", attr->exclude_kernel);
> +	pr_debug2("  exclude_hv          %u    ", attr->exclude_hv);
> +	pr_debug2("exclude_idle        %u\n", attr->exclude_idle);
> +	pr_debug2("  mmap                %u    ", attr->mmap);
> +	pr_debug2("comm                %u\n", attr->comm);
> +	pr_debug2("  freq                %u    ", attr->freq);
> +	pr_debug2("inherit_stat        %u\n", attr->inherit_stat);
> +	pr_debug2("  enable_on_exec      %u    ", attr->enable_on_exec);
> +	pr_debug2("task                %u\n", attr->task);
> +	pr_debug2("  watermark           %u    ", attr->watermark);
> +	pr_debug2("precise_ip          %u\n", attr->precise_ip);
> +	pr_debug2("  mmap_data           %u    ", attr->mmap_data);
> +	pr_debug2("sample_id_all       %u\n", attr->sample_id_all);
> +	pr_debug2("  exclude_host        %u    ", attr->exclude_host);
> +	pr_debug2("exclude_guest       %u\n", attr->exclude_guest);
> +	pr_debug2("  excl.callchain.kern %u    ", attr->exclude_callchain_kernel);
> +	pr_debug2("excl.callchain.user %u\n", attr->exclude_callchain_user);
> +
> +	pr_debug2("  wakeup_events       %u\n", attr->wakeup_events);
> +	pr_debug2("  wakeup_watermark    %u\n", attr->wakeup_watermark);
> +	pr_debug2("  bp_type             %#x\n", attr->bp_type);
> +	pr_debug2("  bp_addr             %#"PRIx64"\n", (uint64_t)attr->bp_addr);
> +	pr_debug2("  config1             %#"PRIx64"\n", (uint64_t)attr->config1);
> +	pr_debug2("  bp_len              %"PRIu64"\n", (uint64_t)attr->bp_len);
> +	pr_debug2("  config2             %#"PRIx64"\n", (uint64_t)attr->config2);
> +	pr_debug2("  branch_sample_type  %#"PRIx64"\n", (uint64_t)attr->branch_sample_type);
> +	pr_debug2("  sample_regs_user    %#"PRIx64"\n", (uint64_t)attr->sample_regs_user);
> +	pr_debug2("  sample_stack_user   %u\n", attr->sample_stack_user);
> +	pr_debug2("------------------------------------------------------------\n");
> +}
> +
>  static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
>  			      struct thread_map *threads)
>  {
> @@ -840,6 +889,7 @@ retry_sample_id:
>  	if (perf_missing_features.sample_id_all)
>  		evsel->attr.sample_id_all = 0;
>  
> +	show_attr(&evsel->attr);
>  	for (cpu = 0; cpu < cpus->nr; cpu++) {
>  
>  		for (thread = 0; thread < threads->nr; thread++) {
> @@ -850,6 +900,8 @@ retry_sample_id:
>  
>  			group_fd = get_group_fd(evsel, cpu, thread);
>  
> +			pr_debug2("perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
> +				  pid, cpus->map[cpu], group_fd, flags);
>  			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
>  								     pid,
>  								     cpus->map[cpu],
> -- 
> 1.7.11.7

Re: [PATCH V4 15/21] perf tools: fix missing increment in sample parsing

[Arnaldo Carvalho de Melo]

Em Thu, Jul 04, 2013 at 04:20:34PM +0300, Adrian Hunter escreveu:
> The final sample format bit used to be PERF_SAMPLE_STACK_USER
> which neglected to do a final increment of the array pointer.
> The result is that the following parsing might start at the
> wrong place.

One 'perf test' entry that would ask for these features and then check
that the result obtained is what is expected would come in handy here
:-\

- Arnaldo
 
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> ---
>  tools/perf/util/evsel.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 86628fe..10ccf38 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1284,7 +1284,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
>  		} else {
>  			data->user_stack.data = (char *)array;
>  			array += size / sizeof(*array);
> -			data->user_stack.size = *array;
> +			data->user_stack.size = *array++;
>  		}
>  	}
>  
> -- 
> 1.7.11.7

Re: [PATCH V4 14/21] perf tools: change "machine" functions to set thread pid

[David Ahern]

On 7/4/13 7:20 AM, Adrian Hunter wrote:
> Typically tracking events such as mmap events, comm events,
> fork events and exit events, are processed by "machine"
> functions.  Change these functions to put pid in the new
> pid_ member of struct thread.
>
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> ---
>   tools/perf/util/machine.c | 21 +++++++++++++++++----
>   tools/perf/util/machine.h |  2 ++
>   2 files changed, 19 insertions(+), 4 deletions(-)
>

---8<---

> diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
> index e49ba01..d986ecf 100644
> --- a/tools/perf/util/machine.h
> +++ b/tools/perf/util/machine.h
> @@ -100,6 +100,8 @@ static inline bool machine__is_host(struct machine *machine)
>   }
>
>   struct thread *machine__findnew_thread(struct machine *machine, pid_t tid);
> +struct thread *machine__findnew_thread_ex(struct machine *machine, pid_t pid,
> +					  pid_t tid);
>
>   size_t machine__fprintf(struct machine *machine, FILE *fp);
>
>


Why do you want to add a new API for this? Why not just fix 
findnew_thread and find_thread to take the pid argument? We don't need 2 
apis that do the same thing.

David

Re: [PATCH V4 20/21] perf: make events stream always parsable

[Adrian Hunter]

On 05/07/13 16:24, Namhyung Kim wrote:
> Hi Adrian,
> 
> On Thu, Jul 4, 2013 at 10:20 PM, Adrian Hunter <adrian.hunter@intel.com> wrote:
>> The event stream is not always parsable because the format of a sample
>> is dependent on the sample_type of the selected event.  When there
>> is more than one selected event and the sample_types are not the
>> same then parsing becomes problematic.  A sample can be matched to its
>> selected event using the ID that is allocated when the event is opened.
>> Unfortunately, to get the ID from the sample means first parsing it.
>>
>> This patch adds a new sample format bit PERF_SAMPLE_IDENTIFER that puts
>> the ID at a fixed position so that the ID can be retrieved without
>> parsing the sample.  For sample events, that is the first position
>> immediately after the header.  For non-sample events, that is the last
>> position.
> 
> Why do we have to keep another ID again?

It is a different place for the ID not another ID.

> If all we need is the sample_type, why not just saving it directly?

We really want to associate the event with the attribute so the ID is
needed, not just the sample type.

> 
> And for the implementation, I guess it'll break old perf tools
> by parsing invalid position of data. IOW if it's recorded on a newer
> kernel/tool and then reported on an older perf tool (maybe on a
> different machine).  In this case the old tool cannot recognize the
> PERF_SAMPLE_IDENTIFIER and try to parse it as a different
> type of data, right?

I have changed the code so that PERF_SAMPLE_IDENTIFIER is only used for
non-matching sample types.  Since in those cases the data was anyway not
parsable, the scenario you outline cannot happen.

> 
> So I suggest put the data at the end of sample data like other new
> sample types added.  Older tools would simply ignore that part, and
> newer tools can access it directly by checking event.header.size
> and/or evsel->sample_size.

The ID will be on the end of non-sample (e.g. mmap, comm, task) events, so
if tools are parsing those events backwards (as perf tools does) then they
will anyway fail if they are not expecting PERF_SAMPLE_IDENTIFIER.  However
that scenario only happens when the data is anyway not parsable as I
mentioned above.

> 
> Thanks,
> Namhyung
> 
>>
>> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
>> ---
>>  include/uapi/linux/perf_event.h |  3 ++-
>>  kernel/events/core.c            | 11 ++++++++++-
>>  2 files changed, 12 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
>> index 0b1df41..6bb217e 100644
>> --- a/include/uapi/linux/perf_event.h
>> +++ b/include/uapi/linux/perf_event.h
>> @@ -134,8 +134,9 @@ enum perf_event_sample_format {
>>         PERF_SAMPLE_STACK_USER                  = 1U << 13,
>>         PERF_SAMPLE_WEIGHT                      = 1U << 14,
>>         PERF_SAMPLE_DATA_SRC                    = 1U << 15,
>> +       PERF_SAMPLE_IDENTIFIER                  = 1U << 16,
>>
>> -       PERF_SAMPLE_MAX = 1U << 16,             /* non-ABI */
>> +       PERF_SAMPLE_MAX = 1U << 17,             /* non-ABI */
>>  };
>>
>>  /*
>> diff --git a/kernel/events/core.c b/kernel/events/core.c
>> index 1db3af9..ca532f2 100644
>> --- a/kernel/events/core.c
>> +++ b/kernel/events/core.c
>> @@ -1203,6 +1203,9 @@ static void perf_event__id_header_size(struct perf_event *event)
>>         if (sample_type & PERF_SAMPLE_TIME)
>>                 size += sizeof(data->time);
>>
>> +       if (sample_type & PERF_SAMPLE_IDENTIFIER)
>> +               size += sizeof(data->id);
>> +
>>         if (sample_type & PERF_SAMPLE_ID)
>>                 size += sizeof(data->id);
>>
>> @@ -4229,7 +4232,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
>>         if (sample_type & PERF_SAMPLE_TIME)
>>                 data->time = perf_clock();
>>
>> -       if (sample_type & PERF_SAMPLE_ID)
>> +       if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
>>                 data->id = primary_event_id(event);
>>
>>         if (sample_type & PERF_SAMPLE_STREAM_ID)
>> @@ -4268,6 +4271,9 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle,
>>
>>         if (sample_type & PERF_SAMPLE_CPU)
>>                 perf_output_put(handle, data->cpu_entry);
>> +
>> +       if (sample_type & PERF_SAMPLE_IDENTIFIER)
>> +               perf_output_put(handle, data->id);
>>  }
>>
>>  void perf_event__output_id_sample(struct perf_event *event,
>> @@ -4380,6 +4386,9 @@ void perf_output_sample(struct perf_output_handle *handle,
>>
>>         perf_output_put(handle, *header);
>>
>> +       if (sample_type & PERF_SAMPLE_IDENTIFIER)
>> +               perf_output_put(handle, data->id);
>> +
>>         if (sample_type & PERF_SAMPLE_IP)
>>                 perf_output_put(handle, data->ip);
>>
>> --
>> 1.7.11.7
>>
> 
> 

[tip:perf/urgent] perf tools: Fix parse_events_terms() segfault on error path

[tip-bot for Adrian Hunter]

Commit-ID:  b2c34fde048f3c85ef0716a8cdabbe46ac67d1e6
Gitweb:     http://git.kernel.org/tip/b2c34fde048f3c85ef0716a8cdabbe46ac67d1e6
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:23 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 8 Jul 2013 17:45:41 -0300

perf tools: Fix parse_events_terms() segfault on error path

On the error path, 'data.terms' may not have been initialised.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6c8bb0f..d8dcb8d 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -860,7 +860,8 @@ int parse_events_terms(struct list_head *terms, const char *str)
 		return 0;
 	}
 
-	parse_events__free_terms(data.terms);
+	if (data.terms)
+		parse_events__free_terms(data.terms);
 	return ret;
 }
 

[tip:perf/urgent] perf tools: Fix new_term() missing free on error path

[tip-bot for Adrian Hunter]

Commit-ID:  4be8be6b430611def94bcd583b7b302d197a9520
Gitweb:     http://git.kernel.org/tip/4be8be6b430611def94bcd583b7b302d197a9520
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:24 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 8 Jul 2013 17:45:56 -0300

perf tools: Fix new_term() missing free on error path

On the error path, newly allocated 'term' must be freed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-6-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/parse-events.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d8dcb8d..995fc25 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1184,6 +1184,7 @@ static int new_term(struct parse_events_term **_term, int type_val,
 		term->val.str = str;
 		break;
 	default:
+		free(term);
 		return -EINVAL;
 	}
 

[tip:perf/urgent] perf tools: Update symbol_conf.nr_events when processing attribute events

[tip-bot for Adrian Hunter]

Commit-ID:  7e0d6fc90fc6f9faea63a2b67233ae767903573c
Gitweb:     http://git.kernel.org/tip/7e0d6fc90fc6f9faea63a2b67233ae767903573c
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:29 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 8 Jul 2013 17:46:39 -0300

perf tools: Update symbol_conf.nr_events when processing attribute events

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-11-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 93dd315..a4dafbe 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2956,6 +2956,8 @@ int perf_event__process_attr(union perf_event *event,
 		perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]);
 	}
 
+	symbol_conf.nr_events = evlist->nr_entries;
+
 	return 0;
 }
 

[tip:perf/urgent] perf evsel: Fix missing increment in sample parsing

[tip-bot for Adrian Hunter]

Commit-ID:  54bd269205c188967d565f1f5552b13d08ca1be0
Gitweb:     http://git.kernel.org/tip/54bd269205c188967d565f1f5552b13d08ca1be0
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:34 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 8 Jul 2013 17:47:13 -0300

perf evsel: Fix missing increment in sample parsing

The final sample format bit used to be PERF_SAMPLE_STACK_USER which
neglected to do a final increment of the array pointer.  The result is
that the following parsing might start at the wrong place.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-16-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index df99ebe..c9c7494 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1170,7 +1170,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		} else {
 			data->user_stack.data = (char *)array;
 			array += size / sizeof(*array);
-			data->user_stack.size = *array;
+			data->user_stack.size = *array++;
 		}
 	}
 

[tip:perf/core] perf inject: Remove unused parameter

[tip-bot for Adrian Hunter]

Commit-ID:  63c2c9f8f24378ebf46d4a9d542863bb733ef05c
Gitweb:     http://git.kernel.org/tip/63c2c9f8f24378ebf46d4a9d542863bb733ef05c
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:20 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 12 Jul 2013 13:52:47 -0300

perf inject: Remove unused parameter

The 'machine' parameter is unused in 'perf_event__repipe_synth()' and
some callers pass NULL anyway.  So remove it.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 84ad6ab..f299ddf 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -38,8 +38,7 @@ struct event_entry {
 };
 
 static int perf_event__repipe_synth(struct perf_tool *tool,
-				    union perf_event *event,
-				    struct machine *machine __maybe_unused)
+				    union perf_event *event)
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	uint32_t size;
@@ -65,20 +64,20 @@ static int perf_event__repipe_op2_synth(struct perf_tool *tool,
 					struct perf_session *session
 					__maybe_unused)
 {
-	return perf_event__repipe_synth(tool, event, NULL);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
 					       union perf_event *event)
 {
-	return perf_event__repipe_synth(tool, event, NULL);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_tracing_data_synth(union perf_event *event,
 						 struct perf_session *session
 						 __maybe_unused)
 {
-	return perf_event__repipe_synth(NULL, event, NULL);
+	return perf_event__repipe_synth(NULL, event);
 }
 
 static int perf_event__repipe_attr(union perf_event *event,
@@ -89,15 +88,15 @@ static int perf_event__repipe_attr(union perf_event *event,
 	if (ret)
 		return ret;
 
-	return perf_event__repipe_synth(NULL, event, NULL);
+	return perf_event__repipe_synth(NULL, event);
 }
 
 static int perf_event__repipe(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
-			      struct machine *machine)
+			      struct machine *machine __maybe_unused)
 {
-	return perf_event__repipe_synth(tool, event, machine);
+	return perf_event__repipe_synth(tool, event);
 }
 
 typedef int (*inject_handler)(struct perf_tool *tool,
@@ -119,7 +118,7 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
 
 	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 
-	return perf_event__repipe_synth(tool, event, machine);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_mmap(struct perf_tool *tool,
@@ -153,7 +152,7 @@ static int perf_event__repipe_tracing_data(union perf_event *event,
 {
 	int err;
 
-	perf_event__repipe_synth(NULL, event, NULL);
+	perf_event__repipe_synth(NULL, event);
 	err = perf_event__process_tracing_data(event, session);
 
 	return err;

[tip:perf/core] perf tools: Fix missing tool parameter

[tip-bot for Adrian Hunter]

Commit-ID:  47c3d1091cb68e727b840efd6fa3709d5b1ddfc2
Gitweb:     http://git.kernel.org/tip/47c3d1091cb68e727b840efd6fa3709d5b1ddfc2
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:21 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 12 Jul 2013 13:52:49 -0300

perf tools: Fix missing tool parameter

The 'inject' command expects to get a reference to 'struct perf_inject'
from its 'tool' member.  For that to work, 'tool' needs to be a
parameter of all tool callbacks.  Make it so.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c | 26 +++++++++++---------------
 tools/perf/util/header.c    |  6 ++++--
 tools/perf/util/header.h    |  6 ++++--
 tools/perf/util/session.c   | 11 +++++++----
 tools/perf/util/tool.h      |  9 ++++-----
 5 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index f299ddf..c943513 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -73,22 +73,17 @@ static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event);
 }
 
-static int perf_event__repipe_tracing_data_synth(union perf_event *event,
-						 struct perf_session *session
-						 __maybe_unused)
-{
-	return perf_event__repipe_synth(NULL, event);
-}
-
-static int perf_event__repipe_attr(union perf_event *event,
-				   struct perf_evlist **pevlist __maybe_unused)
+static int perf_event__repipe_attr(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_evlist **pevlist)
 {
 	int ret;
-	ret = perf_event__process_attr(event, pevlist);
+
+	ret = perf_event__process_attr(tool, event, pevlist);
 	if (ret)
 		return ret;
 
-	return perf_event__repipe_synth(NULL, event);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe(struct perf_tool *tool,
@@ -147,13 +142,14 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
 	return err;
 }
 
-static int perf_event__repipe_tracing_data(union perf_event *event,
+static int perf_event__repipe_tracing_data(struct perf_tool *tool,
+					   union perf_event *event,
 					   struct perf_session *session)
 {
 	int err;
 
-	perf_event__repipe_synth(NULL, event);
-	err = perf_event__process_tracing_data(event, session);
+	perf_event__repipe_synth(tool, event);
+	err = perf_event__process_tracing_data(tool, event, session);
 
 	return err;
 }
@@ -407,7 +403,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.unthrottle	= perf_event__repipe,
 			.attr		= perf_event__repipe_attr,
 			.event_type	= perf_event__repipe_event_type_synth,
-			.tracing_data	= perf_event__repipe_tracing_data_synth,
+			.tracing_data	= perf_event__repipe_op2_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a4dafbe..d12d79c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2922,7 +2922,8 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_attr(union perf_event *event,
+int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
 			     struct perf_evlist **pevlist)
 {
 	u32 i, ids, n_ids;
@@ -3065,7 +3066,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	return aligned_size;
 }
 
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
 				     struct perf_session *session)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 16a3e83..2d1ca7d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -130,7 +130,8 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 int perf_event__synthesize_attrs(struct perf_tool *tool,
 				 struct perf_session *session,
 				 perf_event__handler_t process);
-int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist);
+int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
+			     struct perf_evlist **pevlist);
 
 int perf_event__synthesize_event_type(struct perf_tool *tool,
 				      u64 event_id, char *name,
@@ -145,7 +146,8 @@ int perf_event__process_event_type(struct perf_tool *tool,
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
 					perf_event__handler_t process);
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool,
+				     union perf_event *event,
 				     struct perf_session *session);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ad47fb9..6b71b88 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -193,7 +193,9 @@ void perf_session__delete(struct perf_session *self)
 	vdso__exit();
 }
 
-static int process_event_synth_tracing_data_stub(union perf_event *event
+static int process_event_synth_tracing_data_stub(struct perf_tool *tool
+						 __maybe_unused,
+						 union perf_event *event
 						 __maybe_unused,
 						 struct perf_session *session
 						__maybe_unused)
@@ -202,7 +204,8 @@ static int process_event_synth_tracing_data_stub(union perf_event *event
 	return 0;
 }
 
-static int process_event_synth_attr_stub(union perf_event *event __maybe_unused,
+static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused,
+					 union perf_event *event __maybe_unused,
 					 struct perf_evlist **pevlist
 					 __maybe_unused)
 {
@@ -921,7 +924,7 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	/* These events are processed right away */
 	switch (event->header.type) {
 	case PERF_RECORD_HEADER_ATTR:
-		err = tool->attr(event, &session->evlist);
+		err = tool->attr(tool, event, &session->evlist);
 		if (err == 0)
 			perf_session__set_id_hdr_size(session);
 		return err;
@@ -930,7 +933,7 @@ static int perf_session__process_user_event(struct perf_session *session, union
 	case PERF_RECORD_HEADER_TRACING_DATA:
 		/* setup for reading amidst mmap */
 		lseek(session->fd, file_offset, SEEK_SET);
-		return tool->tracing_data(event, session);
+		return tool->tracing_data(tool, event, session);
 	case PERF_RECORD_HEADER_BUILD_ID:
 		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index b0e1aad..88f8cbd 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -18,12 +18,11 @@ typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event,
 typedef int (*event_op)(struct perf_tool *tool, union perf_event *event,
 			struct perf_sample *sample, struct machine *machine);
 
-typedef int (*event_attr_op)(union perf_event *event,
+typedef int (*event_attr_op)(struct perf_tool *tool,
+			     union perf_event *event,
 			     struct perf_evlist **pevlist);
-typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event);
 
-typedef int (*event_synth_op)(union perf_event *event,
-			      struct perf_session *session);
+typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event);
 
 typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
 			 struct perf_session *session);
@@ -39,7 +38,7 @@ struct perf_tool {
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
-	event_synth_op	tracing_data;
+	event_op2	tracing_data;
 	event_simple_op	event_type;
 	event_op2	finished_round,
 			build_id;

[tip:perf/core] perf inject: Add missing 'finished_round'

[tip-bot for Adrian Hunter]

Commit-ID:  a609bda78203a21fb0e78b9d5b4ab911678e4ebb
Gitweb:     http://git.kernel.org/tip/a609bda78203a21fb0e78b9d5b4ab911678e4ebb
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:22 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 12 Jul 2013 13:52:50 -0300

perf inject: Add missing 'finished_round'

By default, perf inject should "repipe" all events including
'finished_round'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-inject.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c943513..ad1296c 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -404,6 +404,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		= perf_event__repipe_attr,
 			.event_type	= perf_event__repipe_event_type_synth,
 			.tracing_data	= perf_event__repipe_op2_synth,
+			.finished_round	= perf_event__repipe_op2_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",

[tip:perf/core] perf tools: Add const specifier to perf_pmu__find name parameter

[tip-bot for Adrian Hunter]

Commit-ID:  b6b96fb48f75d62858b39baf13c83c4504642f15
Gitweb:     http://git.kernel.org/tip/b6b96fb48f75d62858b39baf13c83c4504642f15
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:25 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 12 Jul 2013 13:52:52 -0300

perf tools: Add const specifier to perf_pmu__find name parameter

The name parameter is constant, declare it so.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-7-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 14 +++++++-------
 tools/perf/util/pmu.h |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 4c6f9c4..1d1862d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -73,7 +73,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head)
  * located at:
  * /sys/bus/event_source/devices/<dev>/format as sysfs group attributes.
  */
-static int pmu_format(char *name, struct list_head *format)
+static int pmu_format(const char *name, struct list_head *format)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -162,7 +162,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
  * Reading the pmu event aliases definition, which should be located at:
  * /sys/bus/event_source/devices/<dev>/events as sysfs group attributes.
  */
-static int pmu_aliases(char *name, struct list_head *head)
+static int pmu_aliases(const char *name, struct list_head *head)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -208,7 +208,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
  * located at:
  * /sys/bus/event_source/devices/<dev>/type as sysfs attribute.
  */
-static int pmu_type(char *name, __u32 *type)
+static int pmu_type(const char *name, __u32 *type)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -266,7 +266,7 @@ static void pmu_read_sysfs(void)
 	closedir(dir);
 }
 
-static struct cpu_map *pmu_cpumask(char *name)
+static struct cpu_map *pmu_cpumask(const char *name)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -293,7 +293,7 @@ static struct cpu_map *pmu_cpumask(char *name)
 	return cpus;
 }
 
-static struct perf_pmu *pmu_lookup(char *name)
+static struct perf_pmu *pmu_lookup(const char *name)
 {
 	struct perf_pmu *pmu;
 	LIST_HEAD(format);
@@ -330,7 +330,7 @@ static struct perf_pmu *pmu_lookup(char *name)
 	return pmu;
 }
 
-static struct perf_pmu *pmu_find(char *name)
+static struct perf_pmu *pmu_find(const char *name)
 {
 	struct perf_pmu *pmu;
 
@@ -356,7 +356,7 @@ struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
 	return NULL;
 }
 
-struct perf_pmu *perf_pmu__find(char *name)
+struct perf_pmu *perf_pmu__find(const char *name)
 {
 	struct perf_pmu *pmu;
 
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 32fe55b..d17b565 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -21,7 +21,7 @@ struct perf_pmu {
 	struct list_head list;
 };
 
-struct perf_pmu *perf_pmu__find(char *name);
+struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 		     struct list_head *head_terms);
 int perf_pmu__config_terms(struct list_head *formats,

[tip:perf/core] perf evlist: Tidy duplicated munmap code

[tip-bot for Adrian Hunter]

Commit-ID:  93edcbd91d888c7530c7fc749176fc935b8e2287
Gitweb:     http://git.kernel.org/tip/93edcbd91d888c7530c7fc749176fc935b8e2287
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:26 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 12 Jul 2013 13:52:54 -0300

perf evlist: Tidy duplicated munmap code

The same lines of code are used in three places.  Make it a new function
'__perf_evlist__munmap()'.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evlist.c | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d8f34e0..42ea4e9 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -403,16 +403,20 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	return event;
 }
 
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+{
+	if (evlist->mmap[idx].base != NULL) {
+		munmap(evlist->mmap[idx].base, evlist->mmap_len);
+		evlist->mmap[idx].base = NULL;
+	}
+}
+
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
 	int i;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
-		if (evlist->mmap[i].base != NULL) {
-			munmap(evlist->mmap[i].base, evlist->mmap_len);
-			evlist->mmap[i].base = NULL;
-		}
-	}
+	for (i = 0; i < evlist->nr_mmaps; i++)
+		__perf_evlist__munmap(evlist, i);
 
 	free(evlist->mmap);
 	evlist->mmap = NULL;
@@ -477,12 +481,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
-		}
-	}
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		__perf_evlist__munmap(evlist, cpu);
 	return -1;
 }
 
@@ -517,12 +517,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < nr_threads; thread++) {
-		if (evlist->mmap[thread].base != NULL) {
-			munmap(evlist->mmap[thread].base, evlist->mmap_len);
-			evlist->mmap[thread].base = NULL;
-		}
-	}
+	for (thread = 0; thread < nr_threads; thread++)
+		__perf_evlist__munmap(evlist, thread);
 	return -1;
 }
 

[tip:perf/core] perf tools: Validate perf event header size

[tip-bot for Adrian Hunter]

Commit-ID:  27389d7823f573be8eaff32fb4abe564e181eb71
Gitweb:     http://git.kernel.org/tip/27389d7823f573be8eaff32fb4abe564e181eb71
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:27 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 12 Jul 2013 13:53:48 -0300

perf tools: Validate perf event header size

The 'size' variable includes the header so must be at least
'sizeof(struct perf_event_header)'.  Error out immediately if that is
not the case.  Also don't byte-swap the header until it is actually
"fetched" from the mmap region.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-9-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/session.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6b71b88..951a1cf 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1094,8 +1094,10 @@ more:
 		perf_event_header__bswap(&event->header);
 
 	size = event->header.size;
-	if (size == 0)
-		size = 8;
+	if (size < sizeof(struct perf_event_header)) {
+		pr_err("bad event header size\n");
+		goto out_err;
+	}
 
 	if (size > cur_size) {
 		void *new = realloc(buf, size);
@@ -1164,8 +1166,12 @@ fetch_mmaped_event(struct perf_session *session,
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (head + event->header.size > mmap_size)
+	if (head + event->header.size > mmap_size) {
+		/* We're not fetching the event so swap back again */
+		if (session->header.needs_swap)
+			perf_event_header__bswap(&event->header);
 		return NULL;
+	}
 
 	return event;
 }
@@ -1245,7 +1251,7 @@ more:
 
 	size = event->header.size;
 
-	if (size == 0 ||
+	if (size < sizeof(struct perf_event_header) ||
 	    perf_session__process_event(session, event, tool, file_pos) < 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       file_offset + head, event->header.size,

[tip:perf/core] perf tools: struct thread has a tid not a pid

[tip-bot for Adrian Hunter]

Commit-ID:  380512345e13c3af64e59627f1b993c4faa94a84
Gitweb:     http://git.kernel.org/tip/380512345e13c3af64e59627f1b993c4faa94a84
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 4 Jul 2013 16:20:31 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Fri, 12 Jul 2013 13:53:50 -0300

perf tools: struct thread has a tid not a pid

As evident from 'machine__process_fork_event()' and
'machine__process_exit_event()' the 'pid' member of struct thread is
actually the tid.

Rename 'pid' to 'tid' in struct thread accordingly.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1372944040-32690-13-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-kmem.c      |  2 +-
 tools/perf/builtin-sched.c     | 12 ++++++------
 tools/perf/builtin-trace.c     |  4 ++--
 tools/perf/ui/browsers/hists.c |  6 +++---
 tools/perf/util/event.c        |  2 +-
 tools/perf/util/machine.c      | 20 ++++++++++----------
 tools/perf/util/machine.h      |  4 ++--
 tools/perf/util/sort.c         |  6 +++---
 tools/perf/util/thread.c       | 10 +++++-----
 tools/perf/util/thread.h       |  4 ++--
 10 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 0259502..b49f5c5 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -313,7 +313,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
 
 	if (evsel->handler.func != NULL) {
 		tracepoint_handler f = evsel->handler.func;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index fba4a94..948183a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1075,7 +1075,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
 			return -1;
-		register_pid(sched, migrant->pid, migrant->comm);
+		register_pid(sched, migrant->tid, migrant->comm);
 		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("migration-event: Internal tree error");
@@ -1115,7 +1115,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->pid);
+	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
@@ -1131,9 +1131,9 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 {
-	if (l->thread->pid < r->thread->pid)
+	if (l->thread->tid < r->thread->tid)
 		return -1;
-	if (l->thread->pid > r->thread->pid)
+	if (l->thread->tid > r->thread->tid)
 		return 1;
 
 	return 0;
@@ -1321,7 +1321,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 			printf("*");
 
 		if (sched->curr_thread[cpu]) {
-			if (sched->curr_thread[cpu]->pid)
+			if (sched->curr_thread[cpu]->tid)
 				printf("%2s ", sched->curr_thread[cpu]->shortname);
 			else
 				printf(".  ");
@@ -1332,7 +1332,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	printf("  %12.6f secs ", (double)timestamp/1e9);
 	if (new_shortname) {
 		printf("%s => %s:%d\n",
-			sched_in->shortname, sched_in->comm, sched_in->pid);
+			sched_in->shortname, sched_in->comm, sched_in->tid);
 	} else {
 		printf("\n");
 	}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 87fc7d0..0e4b67f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -142,7 +142,7 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 	printed += fprintf_duration(duration, fp);
 
 	if (trace->multiple_threads)
-		printed += fprintf(fp, "%d ", thread->pid);
+		printed += fprintf(fp, "%d ", thread->tid);
 
 	return printed;
 }
@@ -593,7 +593,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 			color = PERF_COLOR_YELLOW;
 
 		printed += color_fprintf(fp, color, "%20s", thread->comm);
-		printed += fprintf(fp, " - %-5d :%11lu   [", thread->pid, ttrace->nr_events);
+		printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
 		printed += color_fprintf(fp, color, "%5.1f%%", ratio);
 		printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
 	}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fc0bd38..06e892f 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1256,7 +1256,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 		printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
 				    (thread->comm_set ? thread->comm : ""),
-				    thread->pid);
+				    thread->tid);
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
@@ -1579,7 +1579,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
 			     (browser->hists->thread_filter ? "out of" : "into"),
 			     (thread->comm_set ? thread->comm : ""),
-			     thread->pid) > 0)
+			     thread->tid) > 0)
 			zoom_thread = nr_options++;
 
 		if (dso != NULL &&
@@ -1702,7 +1702,7 @@ zoom_out_thread:
 			} else {
 				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
 						   thread->comm_set ? thread->comm : "",
-						   thread->pid);
+						   thread->tid);
 				browser->hists->thread_filter = thread;
 				sort_thread.elide = true;
 				pstack__push(fstack, &browser->hists->thread_filter);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 5cd13d7..9541270 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -686,7 +686,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	    !strlist__has_entry(symbol_conf.comm_list, thread->comm))
 		goto out_filtered;
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
 	 *
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 93527af..5dd5026 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -233,7 +233,7 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 	return;
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid,
+static struct thread *__machine__findnew_thread(struct machine *machine, pid_t tid,
 						bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;
@@ -241,23 +241,23 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	struct thread *th;
 
 	/*
-	 * Font-end cache - PID lookups come in blocks,
+	 * Front-end cache - TID lookups come in blocks,
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	if (machine->last_match && machine->last_match->pid == pid)
+	if (machine->last_match && machine->last_match->tid == tid)
 		return machine->last_match;
 
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
 
-		if (th->pid == pid) {
+		if (th->tid == tid) {
 			machine->last_match = th;
 			return th;
 		}
 
-		if (pid < th->pid)
+		if (tid < th->tid)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -266,7 +266,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	if (!create)
 		return NULL;
 
-	th = thread__new(pid);
+	th = thread__new(tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
 		rb_insert_color(&th->rb_node, &machine->threads);
@@ -276,14 +276,14 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, true);
+	return __machine__findnew_thread(machine, tid, true);
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid)
+struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, false);
+	return __machine__findnew_thread(machine, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 7794068..e49ba01 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -36,7 +36,7 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 	return machine->vmlinux_maps[type];
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid);
+struct thread *machine__find_thread(struct machine *machine, pid_t tid);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event);
 int machine__process_exit_event(struct machine *machine, union perf_event *event);
@@ -99,7 +99,7 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t tid);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 313a5a7..8deee19 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -55,14 +55,14 @@ static int64_t cmp_null(void *l, void *r)
 static int64_t
 sort__thread_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return right->thread->pid - left->thread->pid;
+	return right->thread->tid - left->thread->tid;
 }
 
 static int hist_entry__thread_snprintf(struct hist_entry *self, char *bf,
 				       size_t size, unsigned int width)
 {
 	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-			      self->thread->comm ?: "", self->thread->pid);
+			      self->thread->comm ?: "", self->thread->tid);
 }
 
 struct sort_entry sort_thread = {
@@ -77,7 +77,7 @@ struct sort_entry sort_thread = {
 static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	return right->thread->pid - left->thread->pid;
+	return right->thread->tid - left->thread->tid;
 }
 
 static int64_t
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 40399cb..6feeb88 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,17 +7,17 @@
 #include "util.h"
 #include "debug.h"
 
-struct thread *thread__new(pid_t pid)
+struct thread *thread__new(pid_t tid)
 {
 	struct thread *self = zalloc(sizeof(*self));
 
 	if (self != NULL) {
 		map_groups__init(&self->mg);
-		self->pid = pid;
+		self->tid = tid;
 		self->ppid = -1;
 		self->comm = malloc(32);
 		if (self->comm)
-			snprintf(self->comm, 32, ":%d", self->pid);
+			snprintf(self->comm, 32, ":%d", self->tid);
 	}
 
 	return self;
@@ -57,7 +57,7 @@ int thread__comm_len(struct thread *self)
 
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
-	return fprintf(fp, "Thread %d %s\n", thread->pid, thread->comm) +
+	return fprintf(fp, "Thread %d %s\n", thread->tid, thread->comm) +
 	       map_groups__fprintf(&thread->mg, verbose, fp);
 }
 
@@ -84,7 +84,7 @@ int thread__fork(struct thread *self, struct thread *parent)
 		if (map_groups__clone(&self->mg, &parent->mg, i) < 0)
 			return -ENOMEM;
 
-	self->ppid = parent->pid;
+	self->ppid = parent->tid;
 
 	return 0;
 }
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 5e7ba35..0fe1f9c 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -12,7 +12,7 @@ struct thread {
 		struct list_head node;
 	};
 	struct map_groups	mg;
-	pid_t			pid;
+	pid_t			tid;
 	pid_t			ppid;
 	char			shortname[3];
 	bool			comm_set;
@@ -24,7 +24,7 @@ struct thread {
 
 struct machine;
 
-struct thread *thread__new(pid_t pid);
+struct thread *thread__new(pid_t tid);
 void thread__delete(struct thread *self);
 
 int thread__set_comm(struct thread *self, const char *comm);