[PATCH 4/4] perf tools: Back [vdso] DSO with real data

From: Jiri Olsa
Date: Mon Sep 10 2012 - 12:51:26 EST


Storing data for VDSO shared object, because we need it for the post
unwind processing.

The VDSO shared object is same for all process on a running system,
so it makes no difference when we store it inside the tracer - perf.

When [vdso] map memory is hit, we retrieve [vdso] DSO image and store
it into temporary file.

During the build-id processing phase, the [vdso] DSO image is stored
in build-id db, and build-id reference is made inside perf.data. The
build-id vdso file object is called '[vdso]'. We don't use temporary
file name which gets removed when record is finished.

During report phase the vdso build-id object is treated as any other
build-id DSO object.

Adding following API for vdso object:

bool is_vdso_map(const char *filename)
- returns true if the filename matches vdso map name

struct dso *vdso__dso_findnew(struct list_head *head)
- find/create proper vdso DSO object

vdso__exit(void)
- removes temporary VDSO image if there's any

This change makes backtrace dwarf post unwind possible from [vdso] maps.

Following output is current report of [vdso] sample dwarf backtrace:

# Overhead Command Shared Object Symbol
# ........ ....... ................. .............................
#
99.52% ex [vdso] [.] 0x00007fff3ace89af
|
--- 0x7fff3ace89af

Following output is new report of [vdso] sample dwarf backtrace:

# Overhead Command Shared Object Symbol
# ........ ....... ................. .............................
#
99.52% ex [vdso] [.] 0x00000000000009af
|
--- 0x7fff3ace89af
main
__libc_start_main
_start

Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
---
tools/perf/Makefile | 2 +
tools/perf/builtin-buildid-cache.c | 3 +-
tools/perf/util/header.c | 70 ++++++++++++++++-------
tools/perf/util/header.h | 2 +-
tools/perf/util/map.c | 12 +++-
tools/perf/util/session.c | 2 +
tools/perf/util/vdso.c | 111 +++++++++++++++++++++++++++++++++++++
tools/perf/util/vdso.h | 18 ++++++
8 files changed, 194 insertions(+), 26 deletions(-)
create mode 100644 tools/perf/util/vdso.c
create mode 100644 tools/perf/util/vdso.h

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index e4b2e8f..7b53478 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -336,6 +336,7 @@ LIB_H += util/intlist.h
LIB_H += util/perf_regs.h
LIB_H += util/unwind.h
LIB_H += ui/helpline.h
+LIB_H += util/vdso.h

LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -403,6 +404,7 @@ LIB_OBJS += $(OUTPUT)util/cgroup.o
LIB_OBJS += $(OUTPUT)util/target.o
LIB_OBJS += $(OUTPUT)util/rblist.o
LIB_OBJS += $(OUTPUT)util/intlist.o
+LIB_OBJS += $(OUTPUT)util/vdso.o

LIB_OBJS += $(OUTPUT)ui/helpline.o
LIB_OBJS += $(OUTPUT)ui/hist.o
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 29ad20e..995368e 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -43,7 +43,8 @@ static int build_id_cache__add_file(const char *filename, const char *debugdir)
}

build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
- err = build_id_cache__add_s(sbuild_id, debugdir, filename, false);
+ err = build_id_cache__add_s(sbuild_id, debugdir, filename,
+ false, false);
if (verbose)
pr_info("Adding %s %s: %s\n", sbuild_id, filename,
err ? "FAIL" : "Ok");
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d07bc13..2438580 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -21,6 +21,7 @@
#include "debug.h"
#include "cpumap.h"
#include "pmu.h"
+#include "vdso.h"

static bool no_buildid_cache = false;

@@ -207,6 +208,29 @@ perf_header__set_cmdline(int argc, const char **argv)
continue; \
else

+static int write_buildid(char *name, size_t name_len, u8 *build_id,
+ pid_t pid, u16 misc, int fd)
+{
+ int err;
+ struct build_id_event b;
+ size_t len;
+
+ len = name_len + 1;
+ len = ALIGN(len, NAME_ALIGN);
+
+ memset(&b, 0, sizeof(b));
+ memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+ b.pid = pid;
+ b.header.misc = misc;
+ b.header.size = sizeof(b) + len;
+
+ err = do_write(fd, &b, sizeof(b));
+ if (err < 0)
+ return err;
+
+ return write_padded(fd, name, name_len + 1, len);
+}
+
static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
u16 misc, int fd)
{
@@ -214,24 +238,23 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,

dsos__for_each_with_build_id(pos, head) {
int err;
- struct build_id_event b;
- size_t len;
+ char *name;
+ size_t name_len;

if (!pos->hit)
continue;
- len = pos->long_name_len + 1;
- len = ALIGN(len, NAME_ALIGN);
- memset(&b, 0, sizeof(b));
- memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
- b.pid = pid;
- b.header.misc = misc;
- b.header.size = sizeof(b) + len;
- err = do_write(fd, &b, sizeof(b));
- if (err < 0)
- return err;
- err = write_padded(fd, pos->long_name,
- pos->long_name_len + 1, len);
- if (err < 0)
+
+ if (is_vdso_map(pos->short_name)) {
+ name = (char *) VDSO__MAP_NAME;
+ name_len = sizeof(VDSO__MAP_NAME) + 1;
+ } else {
+ name = pos->long_name;
+ name_len = pos->long_name_len + 1;
+ }
+
+ err = write_buildid(name, name_len, pos->build_id,
+ pid, misc, fd);
+ if (err)
return err;
}

@@ -277,19 +300,20 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd)
}

int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
- const char *name, bool is_kallsyms)
+ const char *name, bool is_kallsyms, bool is_vdso)
{
const size_t size = PATH_MAX;
char *realname, *filename = zalloc(size),
*linkname = zalloc(size), *targetname;
int len, err = -1;
+ bool slash = is_kallsyms || is_vdso;

if (is_kallsyms) {
if (symbol_conf.kptr_restrict) {
pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
return 0;
}
- realname = (char *)name;
+ realname = (char *) name;
} else
realname = realpath(name, NULL);

@@ -297,7 +321,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
goto out_free;

len = scnprintf(filename, size, "%s%s%s",
- debugdir, is_kallsyms ? "/" : "", realname);
+ debugdir, slash ? "/" : "",
+ is_vdso ? VDSO__MAP_NAME : realname);
if (mkdir_p(filename, 0755))
goto out_free;

@@ -333,13 +358,14 @@ out_free:

static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
const char *name, const char *debugdir,
- bool is_kallsyms)
+ bool is_kallsyms, bool is_vdso)
{
char sbuild_id[BUILD_ID_SIZE * 2 + 1];

build_id__sprintf(build_id, build_id_size, sbuild_id);

- return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms);
+ return build_id_cache__add_s(sbuild_id, debugdir, name,
+ is_kallsyms, is_vdso);
}

int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
@@ -383,9 +409,11 @@ out_free:
static int dso__cache_build_id(struct dso *dso, const char *debugdir)
{
bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+ bool is_vdso = is_vdso_map(dso->short_name);

return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
- dso->long_name, debugdir, is_kallsyms);
+ dso->long_name, debugdir,
+ is_kallsyms, is_vdso);
}

static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 9d5eedc..209dad4 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -96,7 +96,7 @@ int perf_header__process_sections(struct perf_header *header, int fd,
int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);

int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
- const char *name, bool is_kallsyms);
+ const char *name, bool is_kallsyms, bool is_vdso);
int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);

int perf_event__synthesize_attr(struct perf_tool *tool,
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 7d37159..b442ee4 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -9,6 +9,7 @@
#include "map.h"
#include "thread.h"
#include "strlist.h"
+#include "vdso.h"

const char *map_type__name[MAP__NR_TYPES] = {
[MAP__FUNCTION] = "Functions",
@@ -23,7 +24,6 @@ static inline int is_anon_memory(const char *filename)
static inline int is_no_dso_memory(const char *filename)
{
return !strcmp(filename, "[stack]") ||
- !strcmp(filename, "[vdso]") ||
!strcmp(filename, "[heap]");
}

@@ -52,9 +52,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
if (self != NULL) {
char newfilename[PATH_MAX];
struct dso *dso;
- int anon, no_dso;
+ int anon, no_dso, vdso;

anon = is_anon_memory(filename);
+ vdso = is_vdso_map(filename);
no_dso = is_no_dso_memory(filename);

if (anon) {
@@ -62,7 +63,12 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
filename = newfilename;
}

- dso = __dsos__findnew(dsos__list, filename);
+ if (vdso) {
+ pgoff = 0;
+ dso = vdso__dso_findnew(dsos__list);
+ } else
+ dso = __dsos__findnew(dsos__list, filename);
+
if (dso == NULL)
goto out_delete;

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 90278ee..bbaf36d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -17,6 +17,7 @@
#include "event-parse.h"
#include "perf_regs.h"
#include "unwind.h"
+#include "vdso.h"

static int perf_session__open(struct perf_session *self, bool force)
{
@@ -211,6 +212,7 @@ void perf_session__delete(struct perf_session *self)
machine__exit(&self->host_machine);
close(self->fd);
free(self);
+ vdso__exit();
}

void machine__remove_thread(struct machine *self, struct thread *th)
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
new file mode 100644
index 0000000..e60951f
--- /dev/null
+++ b/tools/perf/util/vdso.c
@@ -0,0 +1,111 @@
+
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <linux/kernel.h>
+
+#include "vdso.h"
+#include "util.h"
+#include "symbol.h"
+#include "linux/string.h"
+
+static bool vdso_found;
+static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";
+
+static int find_vdso_map(void **start, void **end)
+{
+ FILE *maps;
+ char line[128];
+ int found = 0;
+
+ maps = fopen("/proc/self/maps", "r");
+ if (!maps) {
+ pr_err("vdso: cannot open maps\n");
+ return -1;
+ }
+
+ while (!found && fgets(line, sizeof(line), maps)) {
+ int m = -1;
+
+ /* We care only about private r-x mappings. */
+ if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+ start, end, &m))
+ continue;
+ if (m < 0)
+ continue;
+
+ if (!strncmp(&line[m], VDSO__MAP_NAME,
+ sizeof(VDSO__MAP_NAME) - 1))
+ found = 1;
+ }
+
+ fclose(maps);
+ return !found;
+}
+
+static char *get_file(void)
+{
+ char *vdso = NULL;
+ char *buf = NULL;
+ void *start, *end;
+ size_t size;
+ int fd;
+
+ if (vdso_found)
+ return vdso_file;
+
+ if (find_vdso_map(&start, &end))
+ return NULL;
+
+ size = end - start;
+
+ buf = memdup(start, size);
+ if (!buf)
+ return NULL;
+
+ fd = mkstemp(vdso_file);
+ if (fd < 0)
+ goto out;
+
+ if (size == (size_t) write(fd, buf, size))
+ vdso = vdso_file;
+
+ close(fd);
+
+ out:
+ free(buf);
+
+ vdso_found = (vdso != NULL);
+ return vdso;
+}
+
+void vdso__exit(void)
+{
+ if (vdso_found)
+ unlink(vdso_file);
+}
+
+struct dso *vdso__dso_findnew(struct list_head *head)
+{
+ struct dso *dso = dsos__find(head, VDSO__MAP_NAME);
+
+ if (!dso) {
+ char *file;
+
+ file = get_file();
+ if (!file)
+ return NULL;
+
+ dso = dso__new(VDSO__MAP_NAME);
+ if (dso != NULL) {
+ dsos__add(head, dso);
+ dso__set_long_name(dso, file);
+ }
+ }
+
+ return dso;
+}
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
new file mode 100644
index 0000000..0f76e7c
--- /dev/null
+++ b/tools/perf/util/vdso.h
@@ -0,0 +1,18 @@
+#ifndef __PERF_VDSO__
+#define __PERF_VDSO__
+
+#include <linux/types.h>
+#include <string.h>
+#include <stdbool.h>
+
+#define VDSO__MAP_NAME "[vdso]"
+
+static inline bool is_vdso_map(const char *filename)
+{
+ return !strcmp(filename, VDSO__MAP_NAME);
+}
+
+struct dso *vdso__dso_findnew(struct list_head *head);
+void vdso__exit(void);
+
+#endif /* __PERF_VDSO__ */
--
1.7.11.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/