All of lore.kernel.org
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org, Jiri Olsa <jolsa@kernel.org>,
	David Ahern <dsahern@gmail.com>, He Kuang <hekuang@huawei.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: [PATCH 11/16] perf unwind: Call unwind__prepare_access for forked thread
Date: Mon,  4 Jul 2016 21:38:30 -0300	[thread overview]
Message-ID: <1467679115-20496-12-git-send-email-acme@kernel.org> (raw)
In-Reply-To: <1467679115-20496-1-git-send-email-acme@kernel.org>

From: Jiri Olsa <jolsa@kernel.org>

Currently we call unwind__prepare_access for map event.  In case we
report fork event the thread inherits its parent's maps and
unwind__prepare_access is never called for the thread.

This causes unwind__get_entries seeing uninitialized
unwind_libunwind_ops and thus returning no callchain.

Adding unwind__prepare_access calls for fork even processing.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1467634583-29147-5-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/map.c    |  9 ++++++++-
 tools/perf/util/map.h    |  2 +-
 tools/perf/util/thread.c | 37 +++++++++++++++++++++++++++++++++++--
 3 files changed, 44 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b19bcd3b7128..b39b12a1208d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -15,6 +15,7 @@
 #include "debug.h"
 #include "machine.h"
 #include <linux/string.h>
+#include "unwind.h"
 
 static void __maps__insert(struct maps *maps, struct map *map);
 
@@ -744,9 +745,10 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct map_groups *mg,
+int map_groups__clone(struct thread *thread,
 		      struct map_groups *parent, enum map_type type)
 {
+	struct map_groups *mg = thread->mg;
 	int err = -ENOMEM;
 	struct map *map;
 	struct maps *maps = &parent->maps[type];
@@ -757,6 +759,11 @@ int map_groups__clone(struct map_groups *mg,
 		struct map *new = map__clone(map);
 		if (new == NULL)
 			goto out_unlock;
+
+		err = unwind__prepare_access(thread, new, NULL);
+		if (err)
+			goto out_unlock;
+
 		map_groups__insert(mg, new);
 		map__put(new);
 	}
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 7309d64ce39e..d83396ceecba 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -194,7 +194,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
                                          struct map **mapp, symbol_filter_t filter);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
-int map_groups__clone(struct map_groups *mg,
+int map_groups__clone(struct thread *thread,
 		      struct map_groups *parent, enum map_type type);
 size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2439b122a4e4..8b10a55410a2 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -212,6 +212,39 @@ int thread__insert_map(struct thread *thread, struct map *map)
 	return 0;
 }
 
+static int __thread__prepare_access(struct thread *thread)
+{
+	bool initialized = false;
+	int i, err = 0;
+
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		struct maps *maps = &thread->mg->maps[i];
+		struct map *map;
+
+		pthread_rwlock_rdlock(&maps->lock);
+
+		for (map = maps__first(maps); map; map = map__next(map)) {
+			err = unwind__prepare_access(thread, map, &initialized);
+			if (err || initialized)
+				break;
+		}
+
+		pthread_rwlock_unlock(&maps->lock);
+	}
+
+	return err;
+}
+
+static int thread__prepare_access(struct thread *thread)
+{
+	int err = 0;
+
+	if (symbol_conf.use_callchain)
+		err = __thread__prepare_access(thread);
+
+	return err;
+}
+
 static int thread__clone_map_groups(struct thread *thread,
 				    struct thread *parent)
 {
@@ -219,7 +252,7 @@ static int thread__clone_map_groups(struct thread *thread,
 
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
-		return 0;
+		return thread__prepare_access(thread);
 
 	if (thread->mg == parent->mg) {
 		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
@@ -229,7 +262,7 @@ static int thread__clone_map_groups(struct thread *thread,
 
 	/* But this one is new process, copy maps. */
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		if (map_groups__clone(thread->mg, parent->mg, i) < 0)
+		if (map_groups__clone(thread, parent->mg, i) < 0)
 			return -ENOMEM;
 
 	return 0;
-- 
2.7.4

  parent reply	other threads:[~2016-07-05  0:39 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-05  0:38 [GIT PULL 00/16] perf/core improvements and fixes Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 01/16] perf probe: Use cache entry if possible Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 02/16] perf probe: Show all cached probes Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 03/16] perf probe: Remove caches when --cache is given Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 04/16] perf build: Add feature detection for libelf's elf_getshdrstrndx() Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 05/16] perf sdt: ELF support for SDT Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 06/16] perf probe: Add group name support Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 07/16] perf buildid-cache: Scan and import user SDT events to probe cache Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 08/16] perf header: Transform nodes string info to struct Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 09/16] perf tests: Fix hist accumulation test Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 10/16] perf unwind: Add initialized arg into unwind__prepare_access Arnaldo Carvalho de Melo
2016-07-05  0:38 ` Arnaldo Carvalho de Melo [this message]
2016-07-05  0:38 ` [PATCH 12/16] tools lib bpf: Add license header Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 13/16] tools lib api: Respect WERROR=0 for build Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 14/16] tools lib subcmd: " Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 15/16] perf tools: Update android build documentation Arnaldo Carvalho de Melo
2016-07-05  0:38 ` [PATCH 16/16] perf tools: Sync copy of syscall_64.tbl with the kernel Arnaldo Carvalho de Melo
2016-07-05 10:14 ` [GIT PULL 00/16] perf/core improvements and fixes Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1467679115-20496-12-git-send-email-acme@kernel.org \
    --to=acme@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@redhat.com \
    --cc=dsahern@gmail.com \
    --cc=hekuang@huawei.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.