Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1416563
| From | Arnaldo Carvalho de Melo <acme@kernel.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH 20/24] perf unwind: Check the target platform before assigning unwind methods |
| Date | 2016-06-07 22:10 +0200 |
| Message-ID | <rHvu3-7bR-59@gated-at.bofh.it> (permalink) |
| References | <rHvu1-7bR-3@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
From: He Kuang <hekuang@huawei.com>
Currently, 'perf script' uses host unwind methods to parse perf.data
callchain info without taking the target architecture into account, i.e.
assuming the perf.data file was generated on the same machine where the
analysis is being performed. So we get wrong result without any warnings
when unwinding callchains of x86(32-bit) on x86(64-bit) machine.
This patch adds an extra step that checks the target platform before
assigning unwind methods. In later patches in this series, we can use
this info to assign the right unwind methods for supported platforms.
Committer note:
After fixing it to register the local unwinder for live mode tools
('perf trace', 'perf top'), i.e. tools that don't use a perf.data file,
it works as intended and passes the 'perf test unwind' test:
# perf trace -e nanosleep --call dwarf usleep 1
0.328 ( 0.058 ms): usleep/11115 nanosleep(rqtp: 0x7fff083fa480) = 0
__nanosleep_nocancel+0x7 (/usr/lib64/libc-2.22.so)
usleep+0x34 (/usr/lib64/libc-2.22.so)
main+0x1eb (/usr/bin/usleep)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
_start+0x29 (/usr/bin/usleep)
# perf test 48
48: Test dwarf unwind : Ok
#
Signed-off-by: He Kuang <hekuang@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ekaterina Tumanova <tumanova@linux.vnet.ibm.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1464924803-22214-11-git-send-email-hekuang@huawei.com
[ Fixed exit path for 'live' mode tools, where we need to default to local unwinding ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/thread.c | 2 +-
tools/perf/util/unwind-libunwind.c | 25 ++++++++++++++++++++++++-
tools/perf/util/unwind.h | 8 +++++---
3 files changed, 30 insertions(+), 5 deletions(-)
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0bf552560a41..f30f9566fddc 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -202,7 +202,7 @@ int thread__insert_map(struct thread *thread, struct map *map)
{
int ret;
- ret = unwind__prepare_access(thread);
+ ret = unwind__prepare_access(thread, map);
if (ret)
return ret;
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index f86f903ae8a8..0086726e00e0 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -1,5 +1,8 @@
#include "unwind.h"
#include "thread.h"
+#include "session.h"
+#include "debug.h"
+#include "arch/common.h"
struct unwind_libunwind_ops __weak *local_unwind_libunwind_ops;
@@ -9,8 +12,28 @@ static void unwind__register_ops(struct thread *thread,
thread->unwind_libunwind_ops = ops;
}
-int unwind__prepare_access(struct thread *thread)
+int unwind__prepare_access(struct thread *thread, struct map *map)
{
+ const char *arch;
+ enum dso_type dso_type;
+
+ if (thread->addr_space) {
+ pr_debug("unwind: thread map already set, dso=%s\n",
+ map->dso->name);
+ return 0;
+ }
+
+ /* env->arch is NULL for live-mode (i.e. perf top) */
+ if (!thread->mg->machine->env || !thread->mg->machine->env->arch)
+ goto out_register;
+
+ dso_type = dso__type(map->dso, thread->mg->machine);
+ if (dso_type == DSO__TYPE_UNKNOWN)
+ return 0;
+
+ arch = normalize_arch(thread->mg->machine->env->arch);
+ pr_debug("unwind: target platform=%s\n", arch);
+out_register:
unwind__register_ops(thread, local_unwind_libunwind_ops);
return thread->unwind_libunwind_ops->prepare_access(thread);
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index bbd73d9bea45..bf9f5937caee 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -30,11 +30,12 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
/* libunwind specific */
#ifdef HAVE_LIBUNWIND_SUPPORT
int libunwind__arch_reg_id(int regnum);
-int unwind__prepare_access(struct thread *thread);
+int unwind__prepare_access(struct thread *thread, struct map *map);
void unwind__flush_access(struct thread *thread);
void unwind__finish_access(struct thread *thread);
#else
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+ struct map *map __maybe_unused)
{
return 0;
}
@@ -53,7 +54,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
return 0;
}
-static inline int unwind__prepare_access(struct thread *thread __maybe_unused)
+static inline int unwind__prepare_access(struct thread *thread __maybe_unused,
+ struct map *map __maybe_unused)
{
return 0;
}
--
2.5.5
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[GIT PULL 00/24] perf/core improvements and fixes Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:10 +0200
[PATCH 08/24] perf tools: Fix crash in build_id_cache__kallsyms_path() Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:10 +0200
[PATCH 02/24] tools lib bpf: Rename bpf_map__get_name() to bpf_map__name() Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:10 +0200
[PATCH 20/24] perf unwind: Check the target platform before assigning unwind methods Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:10 +0200
[PATCH 17/24] perf unwind: Rename unwind-libunwind.c to unwind-libunwind-local.c Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:10 +0200
[PATCH 19/24] perf tools: Export normalize_arch() function Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 22/24] perf unwind: Introduce flag to separate local/remote unwind compilation Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 10/24] perf config: Use new perf_config_set__init() to initialize config set Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 06/24] tools lib bpf: Make bpf_program__get_private() use IS_ERR() Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 09/24] perf config: Constructor should free its allocated memory when failing Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 15/24] perf unwind: Don't mix LIBUNWIND_LIBS into LIBUNWIND_LDFLAGS Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 11/24] perf unwind: Use LIBUNWIND_DIR for remote libunwind feature check Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 12/24] perf unwind: Decouple thread->address_space on libunwind Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 13/24] perf unwind: Introduce 'struct unwind_libunwind_ops' for local unwind Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
[PATCH 01/24] tools lib bpf: Use IS_ERR() reporting macros with bpf_map__get_private() Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-07 22:20 +0200
Re: [GIT PULL 00/24] perf/core improvements and fixes Taeung Song <treeze.taeung@gmail.com> - 2016-06-08 01:20 +0200
Re: [GIT PULL 00/24] perf/core improvements and fixes Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-06-08 15:20 +0200
Re: [GIT PULL 00/24] perf/core improvements and fixes Ingo Molnar <mingo@kernel.org> - 2016-06-08 09:50 +0200
csiph-web