perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
/*
|
|
|
|
* This program is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License, version 2, as
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*
|
|
|
|
* Copyright (C) 2017 Hari Bathini, IBM Corporation
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "namespaces.h"
|
|
|
|
#include "util.h"
|
|
|
|
#include "event.h"
|
2017-07-06 09:48:08 +08:00
|
|
|
#include <sys/types.h>
|
|
|
|
#include <sys/stat.h>
|
2017-09-11 21:50:26 +08:00
|
|
|
#include <fcntl.h>
|
2017-07-06 09:48:10 +08:00
|
|
|
#include <limits.h>
|
2017-07-06 09:48:08 +08:00
|
|
|
#include <sched.h>
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
#include <stdlib.h>
|
|
|
|
#include <stdio.h>
|
2017-04-20 06:06:30 +08:00
|
|
|
#include <string.h>
|
2017-07-06 09:48:08 +08:00
|
|
|
#include <unistd.h>
|
2018-11-02 01:00:01 +08:00
|
|
|
#include <asm/bug.h>
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
|
|
|
|
|
|
|
struct namespaces *namespaces__new(struct namespaces_event *event)
|
|
|
|
{
|
|
|
|
struct namespaces *namespaces;
|
|
|
|
u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) *
|
|
|
|
sizeof(struct perf_ns_link_info));
|
|
|
|
|
|
|
|
namespaces = zalloc(sizeof(struct namespaces) + link_info_size);
|
|
|
|
if (!namespaces)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
namespaces->end_time = -1;
|
|
|
|
|
|
|
|
if (event)
|
|
|
|
memcpy(namespaces->link_info, event->link_info, link_info_size);
|
|
|
|
|
|
|
|
return namespaces;
|
|
|
|
}
|
|
|
|
|
|
|
|
void namespaces__free(struct namespaces *namespaces)
|
|
|
|
{
|
|
|
|
free(namespaces);
|
|
|
|
}
|
2017-07-06 09:48:08 +08:00
|
|
|
|
2017-07-06 09:48:09 +08:00
|
|
|
int nsinfo__init(struct nsinfo *nsi)
|
2017-07-06 09:48:08 +08:00
|
|
|
{
|
|
|
|
char oldns[PATH_MAX];
|
2017-07-06 09:48:09 +08:00
|
|
|
char spath[PATH_MAX];
|
2017-07-06 09:48:08 +08:00
|
|
|
char *newns = NULL;
|
2017-07-06 09:48:09 +08:00
|
|
|
char *statln = NULL;
|
2017-07-06 09:48:08 +08:00
|
|
|
struct stat old_stat;
|
|
|
|
struct stat new_stat;
|
2017-07-06 09:48:09 +08:00
|
|
|
FILE *f = NULL;
|
|
|
|
size_t linesz = 0;
|
|
|
|
int rv = -1;
|
2017-07-06 09:48:08 +08:00
|
|
|
|
|
|
|
if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
|
2017-07-06 09:48:09 +08:00
|
|
|
return rv;
|
2017-07-06 09:48:08 +08:00
|
|
|
|
|
|
|
if (asprintf(&newns, "/proc/%d/ns/mnt", nsi->pid) == -1)
|
2017-07-06 09:48:09 +08:00
|
|
|
return rv;
|
2017-07-06 09:48:08 +08:00
|
|
|
|
|
|
|
if (stat(oldns, &old_stat) < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (stat(newns, &new_stat) < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* Check if the mount namespaces differ, if so then indicate that we
|
|
|
|
* want to switch as part of looking up dso/map data.
|
|
|
|
*/
|
|
|
|
if (old_stat.st_ino != new_stat.st_ino) {
|
|
|
|
nsi->need_setns = true;
|
|
|
|
nsi->mntns_path = newns;
|
|
|
|
newns = NULL;
|
|
|
|
}
|
|
|
|
|
2017-07-06 09:48:09 +08:00
|
|
|
/* If we're dealing with a process that is in a different PID namespace,
|
|
|
|
* attempt to work out the innermost tgid for the process.
|
|
|
|
*/
|
|
|
|
if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
f = fopen(spath, "r");
|
|
|
|
if (f == NULL)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
while (getline(&statln, &linesz, f) != -1) {
|
|
|
|
/* Use tgid if CONFIG_PID_NS is not defined. */
|
|
|
|
if (strstr(statln, "Tgid:") != NULL) {
|
|
|
|
nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
|
|
|
|
NULL, 10);
|
|
|
|
nsi->nstgid = nsi->tgid;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (strstr(statln, "NStgid:") != NULL) {
|
|
|
|
nsi->nstgid = (pid_t)strtol(strrchr(statln, '\t'),
|
|
|
|
NULL, 10);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
rv = 0;
|
|
|
|
|
2017-07-06 09:48:08 +08:00
|
|
|
out:
|
2017-07-06 09:48:09 +08:00
|
|
|
if (f != NULL)
|
|
|
|
(void) fclose(f);
|
|
|
|
free(statln);
|
2017-07-06 09:48:08 +08:00
|
|
|
free(newns);
|
2017-07-06 09:48:09 +08:00
|
|
|
return rv;
|
2017-07-06 09:48:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
struct nsinfo *nsinfo__new(pid_t pid)
|
|
|
|
{
|
2017-07-06 09:48:09 +08:00
|
|
|
struct nsinfo *nsi;
|
2017-07-06 09:48:08 +08:00
|
|
|
|
2017-07-06 09:48:09 +08:00
|
|
|
if (pid == 0)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
nsi = calloc(1, sizeof(*nsi));
|
2017-07-06 09:48:08 +08:00
|
|
|
if (nsi != NULL) {
|
|
|
|
nsi->pid = pid;
|
2017-07-06 09:48:09 +08:00
|
|
|
nsi->tgid = pid;
|
|
|
|
nsi->nstgid = pid;
|
2017-07-06 09:48:08 +08:00
|
|
|
nsi->need_setns = false;
|
2017-07-06 09:48:09 +08:00
|
|
|
/* Init may fail if the process exits while we're trying to look
|
|
|
|
* at its proc information. In that case, save the pid but
|
|
|
|
* don't try to enter the namespace.
|
|
|
|
*/
|
|
|
|
if (nsinfo__init(nsi) == -1)
|
|
|
|
nsi->need_setns = false;
|
|
|
|
|
2017-07-06 09:48:08 +08:00
|
|
|
refcount_set(&nsi->refcnt, 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
return nsi;
|
|
|
|
}
|
|
|
|
|
2017-07-06 09:48:09 +08:00
|
|
|
struct nsinfo *nsinfo__copy(struct nsinfo *nsi)
|
|
|
|
{
|
|
|
|
struct nsinfo *nnsi;
|
|
|
|
|
2018-08-10 21:36:13 +08:00
|
|
|
if (nsi == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
2017-07-06 09:48:09 +08:00
|
|
|
nnsi = calloc(1, sizeof(*nnsi));
|
|
|
|
if (nnsi != NULL) {
|
|
|
|
nnsi->pid = nsi->pid;
|
|
|
|
nnsi->tgid = nsi->tgid;
|
|
|
|
nnsi->nstgid = nsi->nstgid;
|
|
|
|
nnsi->need_setns = nsi->need_setns;
|
|
|
|
if (nsi->mntns_path) {
|
|
|
|
nnsi->mntns_path = strdup(nsi->mntns_path);
|
|
|
|
if (!nnsi->mntns_path) {
|
|
|
|
free(nnsi);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
refcount_set(&nnsi->refcnt, 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
return nnsi;
|
|
|
|
}
|
|
|
|
|
2017-07-06 09:48:08 +08:00
|
|
|
void nsinfo__delete(struct nsinfo *nsi)
|
|
|
|
{
|
|
|
|
zfree(&nsi->mntns_path);
|
|
|
|
free(nsi);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct nsinfo *nsinfo__get(struct nsinfo *nsi)
|
|
|
|
{
|
|
|
|
if (nsi)
|
|
|
|
refcount_inc(&nsi->refcnt);
|
|
|
|
return nsi;
|
|
|
|
}
|
|
|
|
|
|
|
|
void nsinfo__put(struct nsinfo *nsi)
|
|
|
|
{
|
|
|
|
if (nsi && refcount_dec_and_test(&nsi->refcnt))
|
|
|
|
nsinfo__delete(nsi);
|
|
|
|
}
|
|
|
|
|
2017-07-06 09:48:09 +08:00
|
|
|
void nsinfo__mountns_enter(struct nsinfo *nsi,
|
|
|
|
struct nscookie *nc)
|
2017-07-06 09:48:08 +08:00
|
|
|
{
|
|
|
|
char curpath[PATH_MAX];
|
|
|
|
int oldns = -1;
|
|
|
|
int newns = -1;
|
2018-11-02 01:00:01 +08:00
|
|
|
char *oldcwd = NULL;
|
2017-07-06 09:48:08 +08:00
|
|
|
|
|
|
|
if (nc == NULL)
|
|
|
|
return;
|
|
|
|
|
|
|
|
nc->oldns = -1;
|
|
|
|
nc->newns = -1;
|
|
|
|
|
|
|
|
if (!nsi || !nsi->need_setns)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
|
|
|
|
return;
|
|
|
|
|
2018-11-02 01:00:01 +08:00
|
|
|
oldcwd = get_current_dir_name();
|
|
|
|
if (!oldcwd)
|
|
|
|
return;
|
|
|
|
|
2017-07-06 09:48:08 +08:00
|
|
|
oldns = open(curpath, O_RDONLY);
|
|
|
|
if (oldns < 0)
|
2018-11-02 01:00:01 +08:00
|
|
|
goto errout;
|
2017-07-06 09:48:08 +08:00
|
|
|
|
|
|
|
newns = open(nsi->mntns_path, O_RDONLY);
|
|
|
|
if (newns < 0)
|
|
|
|
goto errout;
|
|
|
|
|
|
|
|
if (setns(newns, CLONE_NEWNS) < 0)
|
|
|
|
goto errout;
|
|
|
|
|
2018-11-02 01:00:01 +08:00
|
|
|
nc->oldcwd = oldcwd;
|
2017-07-06 09:48:08 +08:00
|
|
|
nc->oldns = oldns;
|
|
|
|
nc->newns = newns;
|
|
|
|
return;
|
|
|
|
|
|
|
|
errout:
|
2018-11-02 01:00:01 +08:00
|
|
|
free(oldcwd);
|
2017-07-06 09:48:08 +08:00
|
|
|
if (oldns > -1)
|
|
|
|
close(oldns);
|
|
|
|
if (newns > -1)
|
|
|
|
close(newns);
|
|
|
|
}
|
|
|
|
|
|
|
|
void nsinfo__mountns_exit(struct nscookie *nc)
|
|
|
|
{
|
2018-11-02 01:00:01 +08:00
|
|
|
if (nc == NULL || nc->oldns == -1 || nc->newns == -1 || !nc->oldcwd)
|
2017-07-06 09:48:08 +08:00
|
|
|
return;
|
|
|
|
|
|
|
|
setns(nc->oldns, CLONE_NEWNS);
|
|
|
|
|
2018-11-02 01:00:01 +08:00
|
|
|
if (nc->oldcwd) {
|
|
|
|
WARN_ON_ONCE(chdir(nc->oldcwd));
|
|
|
|
zfree(&nc->oldcwd);
|
|
|
|
}
|
|
|
|
|
2017-07-06 09:48:08 +08:00
|
|
|
if (nc->oldns > -1) {
|
|
|
|
close(nc->oldns);
|
|
|
|
nc->oldns = -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (nc->newns > -1) {
|
|
|
|
close(nc->newns);
|
|
|
|
nc->newns = -1;
|
|
|
|
}
|
|
|
|
}
|
2017-07-06 09:48:10 +08:00
|
|
|
|
|
|
|
char *nsinfo__realpath(const char *path, struct nsinfo *nsi)
|
|
|
|
{
|
|
|
|
char *rpath;
|
|
|
|
struct nscookie nsc;
|
|
|
|
|
|
|
|
nsinfo__mountns_enter(nsi, &nsc);
|
|
|
|
rpath = realpath(path, NULL);
|
|
|
|
nsinfo__mountns_exit(&nsc);
|
|
|
|
|
|
|
|
return rpath;
|
|
|
|
}
|